summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/.gitignore2
-rw-r--r--arch/x86/Kconfig103
-rw-r--r--arch/x86/Makefile15
-rw-r--r--arch/x86/boot/Makefile8
-rw-r--r--arch/x86/boot/compressed/Makefile34
-rw-r--r--arch/x86/boot/compressed/aslr.c5
-rw-r--r--arch/x86/boot/compressed/early_serial_console.c4
-rw-r--r--arch/x86/boot/compressed/eboot.c40
-rw-r--r--arch/x86/boot/compressed/eboot.h16
-rw-r--r--arch/x86/boot/compressed/head_32.S5
-rw-r--r--arch/x86/boot/compressed/head_64.S5
-rw-r--r--arch/x86/boot/compressed/misc.c27
-rw-r--r--arch/x86/boot/compressed/mkpiggy.c9
-rw-r--r--arch/x86/boot/cpu.c68
-rw-r--r--arch/x86/boot/mkcpustr.c1
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/tiny.config1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/crypto/Makefile1
-rw-r--r--arch/x86/crypto/aes_ctrby8_avx-x86_64.S66
-rw-r--r--arch/x86/crypto/aes_glue.c4
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c14
-rw-r--r--arch/x86/crypto/blowfish_glue.c4
-rw-r--r--arch/x86/crypto/camellia_aesni_avx2_glue.c4
-rw-r--r--arch/x86/crypto/camellia_aesni_avx_glue.c4
-rw-r--r--arch/x86/crypto/camellia_glue.c4
-rw-r--r--arch/x86/crypto/cast5_avx_glue.c2
-rw-r--r--arch/x86/crypto/cast6_avx_glue.c2
-rw-r--r--arch/x86/crypto/crc32-pclmul_glue.c4
-rw-r--r--arch/x86/crypto/crc32c-intel_glue.c4
-rw-r--r--arch/x86/crypto/crct10dif-pclmul_glue.c4
-rw-r--r--arch/x86/crypto/des3_ede_glue.c8
-rw-r--r--arch/x86/crypto/fpu.c3
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_glue.c2
-rw-r--r--arch/x86/crypto/salsa20_glue.c4
-rw-r--r--arch/x86/crypto/serpent_avx2_glue.c4
-rw-r--r--arch/x86/crypto/serpent_avx_glue.c2
-rw-r--r--arch/x86/crypto/serpent_sse2_glue.c2
-rw-r--r--arch/x86/crypto/sha-mb/Makefile11
-rw-r--r--arch/x86/crypto/sha-mb/sha1_mb.c934
-rw-r--r--arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S287
-rw-r--r--arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S327
-rw-r--r--arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c64
-rw-r--r--arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S228
-rw-r--r--arch/x86/crypto/sha-mb/sha1_x8_avx2.S472
-rw-r--r--arch/x86/crypto/sha-mb/sha_mb_ctx.h136
-rw-r--r--arch/x86/crypto/sha-mb/sha_mb_mgr.h110
-rw-r--r--arch/x86/crypto/sha1_ssse3_glue.c2
-rw-r--r--arch/x86/crypto/sha256_ssse3_glue.c6
-rw-r--r--arch/x86/crypto/sha512_ssse3_glue.c6
-rw-r--r--arch/x86/crypto/twofish_avx_glue.c2
-rw-r--r--arch/x86/crypto/twofish_glue.c4
-rw-r--r--arch/x86/crypto/twofish_glue_3way.c4
-rw-r--r--arch/x86/ia32/audit.c1
-rw-r--r--arch/x86/ia32/ia32_aout.c29
-rw-r--r--arch/x86/ia32/ia32entry.S31
-rw-r--r--arch/x86/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/atomic.h17
-rw-r--r--arch/x86/include/asm/atomic64_64.h2
-rw-r--r--arch/x86/include/asm/barrier.h70
-rw-r--r--arch/x86/include/asm/cacheflush.h59
-rw-r--r--arch/x86/include/asm/calling.h6
-rw-r--r--arch/x86/include/asm/cpufeature.h65
-rw-r--r--arch/x86/include/asm/debugreg.h4
-rw-r--r--arch/x86/include/asm/disabled-features.h45
-rw-r--r--arch/x86/include/asm/dma-contiguous.h12
-rw-r--r--arch/x86/include/asm/dma.h2
-rw-r--r--arch/x86/include/asm/efi.h55
-rw-r--r--arch/x86/include/asm/elf.h5
-rw-r--r--arch/x86/include/asm/fb.h6
-rw-r--r--arch/x86/include/asm/fixmap.h4
-rw-r--r--arch/x86/include/asm/fpu-internal.h2
-rw-r--r--arch/x86/include/asm/ftrace.h33
-rw-r--r--arch/x86/include/asm/hash.h7
-rw-r--r--arch/x86/include/asm/highmem.h25
-rw-r--r--arch/x86/include/asm/hw_irq.h84
-rw-r--r--arch/x86/include/asm/insn.h10
-rw-r--r--arch/x86/include/asm/io.h10
-rw-r--r--arch/x86/include/asm/io_apic.h35
-rw-r--r--arch/x86/include/asm/irq_vectors.h6
-rw-r--r--arch/x86/include/asm/irq_work.h11
-rw-r--r--arch/x86/include/asm/kprobes.h1
-rw-r--r--arch/x86/include/asm/kvm_host.h85
-rw-r--r--arch/x86/include/asm/kvm_para.h10
-rw-r--r--arch/x86/include/asm/mce.h5
-rw-r--r--arch/x86/include/asm/microcode.h2
-rw-r--r--arch/x86/include/asm/microcode_amd.h4
-rw-r--r--arch/x86/include/asm/microcode_intel.h4
-rw-r--r--arch/x86/include/asm/mmu_context.h37
-rw-r--r--arch/x86/include/asm/mpx.h103
-rw-r--r--arch/x86/include/asm/numa.h1
-rw-r--r--arch/x86/include/asm/page_32_types.h1
-rw-r--r--arch/x86/include/asm/page_64.h4
-rw-r--r--arch/x86/include/asm/page_64_types.h11
-rw-r--r--arch/x86/include/asm/paravirt.h16
-rw-r--r--arch/x86/include/asm/pat.h7
-rw-r--r--arch/x86/include/asm/pci.h3
-rw-r--r--arch/x86/include/asm/pci_x86.h2
-rw-r--r--arch/x86/include/asm/percpu.h61
-rw-r--r--arch/x86/include/asm/perf_event.h11
-rw-r--r--arch/x86/include/asm/perf_event_p4.h2
-rw-r--r--arch/x86/include/asm/pgtable.h24
-rw-r--r--arch/x86/include/asm/pgtable_32.h3
-rw-r--r--arch/x86/include/asm/pgtable_32_types.h2
-rw-r--r--arch/x86/include/asm/pgtable_64.h3
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h2
-rw-r--r--arch/x86/include/asm/pgtable_types.h118
-rw-r--r--arch/x86/include/asm/platform_sst_audio.h62
-rw-r--r--arch/x86/include/asm/preempt.h4
-rw-r--r--arch/x86/include/asm/processor.h45
-rw-r--r--arch/x86/include/asm/ptrace.h5
-rw-r--r--arch/x86/include/asm/rwlock.h49
-rw-r--r--arch/x86/include/asm/segment.h30
-rw-r--r--arch/x86/include/asm/serial.h24
-rw-r--r--arch/x86/include/asm/smp.h1
-rw-r--r--arch/x86/include/asm/spinlock.h103
-rw-r--r--arch/x86/include/asm/spinlock_types.h4
-rw-r--r--arch/x86/include/asm/switch_to.h12
-rw-r--r--arch/x86/include/asm/thread_info.h2
-rw-r--r--arch/x86/include/asm/traps.h1
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h4
-rw-r--r--arch/x86/include/asm/uv/uv_hub.h12
-rw-r--r--arch/x86/include/asm/vgtod.h21
-rw-r--r--arch/x86/include/asm/vmx.h3
-rw-r--r--arch/x86/include/asm/vsyscall.h33
-rw-r--r--arch/x86/include/asm/vvar.h2
-rw-r--r--arch/x86/include/asm/x86_init.h3
-rw-r--r--arch/x86/include/asm/xen/cpuid.h91
-rw-r--r--arch/x86/include/asm/xen/page-coherent.h4
-rw-r--r--arch/x86/include/asm/xen/page.h71
-rw-r--r--arch/x86/include/asm/xsave.h1
-rw-r--r--arch/x86/include/uapi/asm/e820.h5
-rw-r--r--arch/x86/include/uapi/asm/ldt.h7
-rw-r--r--arch/x86/include/uapi/asm/msr-index.h42
-rw-r--r--arch/x86/include/uapi/asm/vmx.h8
-rw-r--r--arch/x86/kernel/Makefile5
-rw-r--r--arch/x86/kernel/acpi/boot.c122
-rw-r--r--arch/x86/kernel/amd_nb.c2
-rw-r--r--arch/x86/kernel/apb_timer.c6
-rw-r--r--arch/x86/kernel/apic/Makefile4
-rw-r--r--arch/x86/kernel/apic/apic.c30
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c28
-rw-r--r--arch/x86/kernel/apic/htirq.c107
-rw-r--r--arch/x86/kernel/apic/hw_nmi.c91
-rw-r--r--arch/x86/kernel/apic/io_apic.c1353
-rw-r--r--arch/x86/kernel/apic/msi.c286
-rw-r--r--arch/x86/kernel/apic/vector.c719
-rw-r--r--arch/x86/kernel/apic/x2apic_cluster.c2
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/apm_32.c1
-rw-r--r--arch/x86/kernel/asm-offsets_32.c4
-rw-r--r--arch/x86/kernel/asm-offsets_64.c5
-rw-r--r--arch/x86/kernel/audit_64.c1
-rw-r--r--arch/x86/kernel/cpu/Makefile15
-rw-r--r--arch/x86/kernel/cpu/amd.c30
-rw-r--r--arch/x86/kernel/cpu/common.c59
-rw-r--r--arch/x86/kernel/cpu/intel.c37
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c6
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h4
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c23
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c118
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_amd.c54
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c22
-rw-r--r--arch/x86/kernel/cpu/mcheck/therm_throt.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c8
-rw-r--r--arch/x86/kernel/cpu/microcode/amd_early.c55
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/core_early.c23
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_early.c52
-rw-r--r--arch/x86/kernel/cpu/mkcapflags.sh2
-rw-r--r--arch/x86/kernel/cpu/mtrr/main.c6
-rw-r--r--arch/x86/kernel/cpu/perf_event.c28
-rw-r--r--arch/x86/kernel/cpu/perf_event.h52
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c4
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c15
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_iommu.c5
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_uncore.c6
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c74
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c301
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c45
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_rapl.c18
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c3203
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h441
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c1221
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c636
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c2324
-rw-r--r--arch/x86/kernel/cpu/perf_event_knc.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c6
-rw-r--r--arch/x86/kernel/cpu/proc.c10
-rw-r--r--arch/x86/kernel/cpu/scattered.c5
-rw-r--r--arch/x86/kernel/cpuid.c2
-rw-r--r--arch/x86/kernel/crash.c11
-rw-r--r--arch/x86/kernel/dumpstack_64.c1
-rw-r--r--arch/x86/kernel/e820.c11
-rw-r--r--arch/x86/kernel/early-quirks.c23
-rw-r--r--arch/x86/kernel/entry_32.S26
-rw-r--r--arch/x86/kernel/entry_64.S164
-rw-r--r--arch/x86/kernel/espfix_64.c3
-rw-r--r--arch/x86/kernel/ftrace.c288
-rw-r--r--arch/x86/kernel/hw_breakpoint.c8
-rw-r--r--arch/x86/kernel/i8259.c3
-rw-r--r--arch/x86/kernel/iosf_mbi.c91
-rw-r--r--arch/x86/kernel/irq.c30
-rw-r--r--arch/x86/kernel/irq_64.c6
-rw-r--r--arch/x86/kernel/irq_work.c2
-rw-r--r--arch/x86/kernel/irqinit.c38
-rw-r--r--arch/x86/kernel/kexec-bzimage64.c15
-rw-r--r--arch/x86/kernel/kprobes/core.c8
-rw-r--r--arch/x86/kernel/kprobes/ftrace.c9
-rw-r--r--arch/x86/kernel/kprobes/opt.c4
-rw-r--r--arch/x86/kernel/kvm.c39
-rw-r--r--arch/x86/kernel/kvmclock.c20
-rw-r--r--arch/x86/kernel/machine_kexec_32.c4
-rw-r--r--arch/x86/kernel/machine_kexec_64.c1
-rw-r--r--arch/x86/kernel/mcount_64.S224
-rw-r--r--arch/x86/kernel/msr.c11
-rw-r--r--arch/x86/kernel/perf_regs.c90
-rw-r--r--arch/x86/kernel/pmc_atom.c11
-rw-r--r--arch/x86/kernel/preempt.S25
-rw-r--r--arch/x86/kernel/process.c16
-rw-r--r--arch/x86/kernel/process_32.c6
-rw-r--r--arch/x86/kernel/process_64.c104
-rw-r--r--arch/x86/kernel/ptrace.c165
-rw-r--r--arch/x86/kernel/quirks.c18
-rw-r--r--arch/x86/kernel/reboot.c1
-rw-r--r--arch/x86/kernel/setup.c15
-rw-r--r--arch/x86/kernel/setup_percpu.c2
-rw-r--r--arch/x86/kernel/signal.c5
-rw-r--r--arch/x86/kernel/smpboot.c193
-rw-r--r--arch/x86/kernel/sysfb.c2
-rw-r--r--arch/x86/kernel/sysfb_simplefb.c5
-rw-r--r--arch/x86/kernel/time.c2
-rw-r--r--arch/x86/kernel/tls.c39
-rw-r--r--arch/x86/kernel/traps.c159
-rw-r--r--arch/x86/kernel/tsc.c5
-rw-r--r--arch/x86/kernel/uprobes.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S2
-rw-r--r--arch/x86/kernel/vsyscall_64.c149
-rw-r--r--arch/x86/kernel/x86_init.c10
-rw-r--r--arch/x86/kernel/xsave.c8
-rw-r--r--arch/x86/kvm/Makefile7
-rw-r--r--arch/x86/kvm/assigned-dev.c1052
-rw-r--r--arch/x86/kvm/assigned-dev.h32
-rw-r--r--arch/x86/kvm/cpuid.c84
-rw-r--r--arch/x86/kvm/cpuid.h10
-rw-r--r--arch/x86/kvm/emulate.c660
-rw-r--r--arch/x86/kvm/i8254.c2
-rw-r--r--arch/x86/kvm/ioapic.c675
-rw-r--r--arch/x86/kvm/ioapic.h119
-rw-r--r--arch/x86/kvm/iommu.c353
-rw-r--r--arch/x86/kvm/irq_comm.c332
-rw-r--r--arch/x86/kvm/lapic.c232
-rw-r--r--arch/x86/kvm/lapic.h14
-rw-r--r--arch/x86/kvm/mmu.c156
-rw-r--r--arch/x86/kvm/mmu.h5
-rw-r--r--arch/x86/kvm/mmutrace.h4
-rw-r--r--arch/x86/kvm/paging_tmpl.h22
-rw-r--r--arch/x86/kvm/pmu.c24
-rw-r--r--arch/x86/kvm/svm.c78
-rw-r--r--arch/x86/kvm/trace.h78
-rw-r--r--arch/x86/kvm/vmx.c1017
-rw-r--r--arch/x86/kvm/x86.c414
-rw-r--r--arch/x86/kvm/x86.h25
-rw-r--r--arch/x86/lguest/boot.c2
-rw-r--r--arch/x86/lib/Makefile5
-rw-r--r--arch/x86/lib/cmpxchg16b_emu.S32
-rw-r--r--arch/x86/lib/cmpxchg8b_emu.S20
-rw-r--r--arch/x86/lib/csum-wrappers_64.c5
-rw-r--r--arch/x86/lib/hash.c92
-rw-r--r--arch/x86/lib/insn.c5
-rw-r--r--arch/x86/lib/rwlock.S44
-rw-r--r--arch/x86/lib/thunk_32.S41
-rw-r--r--arch/x86/lib/thunk_64.S7
-rw-r--r--arch/x86/mm/Makefile2
-rw-r--r--arch/x86/mm/dump_pagetables.c27
-rw-r--r--arch/x86/mm/fault.c93
-rw-r--r--arch/x86/mm/gup.c2
-rw-r--r--arch/x86/mm/init.c78
-rw-r--r--arch/x86/mm/init_32.c2
-rw-r--r--arch/x86/mm/init_64.c114
-rw-r--r--arch/x86/mm/iomap_32.c12
-rw-r--r--arch/x86/mm/ioremap.c87
-rw-r--r--arch/x86/mm/kmemcheck/kmemcheck.c14
-rw-r--r--arch/x86/mm/mm_internal.h2
-rw-r--r--arch/x86/mm/mpx.c928
-rw-r--r--arch/x86/mm/numa.c123
-rw-r--r--arch/x86/mm/pageattr.c108
-rw-r--r--arch/x86/mm/pat.c247
-rw-r--r--arch/x86/mm/pat_internal.h22
-rw-r--r--arch/x86/mm/pat_rbtree.c8
-rw-r--r--arch/x86/mm/pgtable_32.c35
-rw-r--r--arch/x86/net/bpf_jit_comp.c188
-rw-r--r--arch/x86/oprofile/nmi_int.c8
-rw-r--r--arch/x86/oprofile/op_model_p4.c2
-rw-r--r--arch/x86/pci/common.c20
-rw-r--r--arch/x86/pci/i386.c6
-rw-r--r--arch/x86/pci/intel_mid_pci.c10
-rw-r--r--arch/x86/pci/irq.c25
-rw-r--r--arch/x86/pci/mmconfig-shared.c40
-rw-r--r--arch/x86/pci/numachip.c2
-rw-r--r--arch/x86/pci/pcbios.c8
-rw-r--r--arch/x86/pci/xen.c50
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c36
-rw-r--r--arch/x86/platform/efi/efi.c52
-rw-r--r--arch/x86/platform/efi/efi_32.c12
-rw-r--r--arch/x86/platform/efi/efi_64.c9
-rw-r--r--arch/x86/platform/efi/efi_stub_32.S4
-rw-r--r--arch/x86/platform/intel-mid/intel_mid_weak_decls.h7
-rw-r--r--arch/x86/platform/intel-mid/sfi.c2
-rw-r--r--arch/x86/platform/iris/iris.c1
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-pm.c2
-rw-r--r--arch/x86/platform/uv/tlb_uv.c30
-rw-r--r--arch/x86/platform/uv/uv_irq.c6
-rw-r--r--arch/x86/platform/uv/uv_nmi.c40
-rw-r--r--arch/x86/platform/uv/uv_time.c2
-rw-r--r--arch/x86/power/hibernate_32.c4
-rw-r--r--arch/x86/power/hibernate_64.c4
-rw-r--r--arch/x86/purgatory/Makefile4
-rw-r--r--arch/x86/syscalls/syscall_32.tbl2
-rw-r--r--arch/x86/syscalls/syscall_64.tbl3
-rw-r--r--arch/x86/tools/calc_run_size.pl39
-rw-r--r--arch/x86/tools/insn_sanity.c2
-rw-r--r--arch/x86/tools/relocs.c38
-rw-r--r--arch/x86/tools/test_get_len.c2
-rw-r--r--arch/x86/um/asm/barrier.h20
-rw-r--r--arch/x86/um/asm/ptrace.h4
-rw-r--r--arch/x86/um/asm/syscall.h15
-rw-r--r--arch/x86/um/checksum_32.S239
-rw-r--r--arch/x86/um/sys_call_table_32.c2
-rw-r--r--arch/x86/um/sys_call_table_64.c3
-rw-r--r--arch/x86/vdso/vdso2c.h12
-rw-r--r--arch/x86/vdso/vgetcpu.c2
-rw-r--r--arch/x86/vdso/vma.c128
-rw-r--r--arch/x86/xen/efi.c2
-rw-r--r--arch/x86/xen/enlighten.c49
-rw-r--r--arch/x86/xen/mmu.c142
-rw-r--r--arch/x86/xen/multicalls.c8
-rw-r--r--arch/x86/xen/p2m.c1228
-rw-r--r--arch/x86/xen/p2m.h15
-rw-r--r--arch/x86/xen/setup.c504
-rw-r--r--arch/x86/xen/smp.c34
-rw-r--r--arch/x86/xen/smp.h8
-rw-r--r--arch/x86/xen/spinlock.c2
-rw-r--r--arch/x86/xen/time.c10
-rw-r--r--arch/x86/xen/xen-head.S36
-rw-r--r--arch/x86/xen/xen-ops.h7
347 files changed, 19628 insertions, 9708 deletions
diff --git a/arch/x86/.gitignore b/arch/x86/.gitignore
index 7cab8c08e6d1..aff152c87cf4 100644
--- a/arch/x86/.gitignore
+++ b/arch/x86/.gitignore
@@ -1,4 +1,6 @@
boot/compressed/vmlinux
tools/test_get_len
tools/insn_sanity
+purgatory/kexec-purgatory.c
+purgatory/purgatory.ro
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 36327438caf0..ba397bde7948 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,13 +24,13 @@ config X86
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
select ARCH_HAS_FAST_MULTIPLIER
+ select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_MIGHT_HAVE_PC_PARPORT
select ARCH_MIGHT_HAVE_PC_SERIO
select HAVE_AOUT if X86_32
select HAVE_UNSTABLE_SCHED_CLOCK
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
select ARCH_SUPPORTS_INT128 if X86_64
- select ARCH_WANTS_PROT_NUMA_PROT_NONE
select HAVE_IDE
select HAVE_OPROFILE
select HAVE_PCSPKR_PLATFORM
@@ -137,11 +137,16 @@ config X86
select HAVE_ACPI_APEI if ACPI
select HAVE_ACPI_APEI_NMI if ACPI
select ACPI_LEGACY_TABLES_LOOKUP if ACPI
+ select X86_FEATURE_NAMES if PROC_FS
config INSTRUCTION_DECODER
def_bool y
depends on KPROBES || PERF_EVENTS || UPROBES
+config PERF_EVENTS_INTEL_UNCORE
+ def_bool y
+ depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+
config OUTPUT_FORMAT
string
default "elf32-i386" if X86_32
@@ -314,6 +319,17 @@ config SMP
If you don't know what to do here, say N.
+config X86_FEATURE_NAMES
+ bool "Processor feature human-readable names" if EMBEDDED
+ default y
+ ---help---
+ This option compiles in a table of x86 feature bits and corresponding
+ names. This is required to support /proc/cpuinfo and a few kernel
+ messages. You can disable this to save space, at the expense of
+ making those few kernel messages show numeric feature bits instead.
+
+ If in doubt, say Y.
+
config X86_X2APIC
bool "Support x2apic"
depends on X86_LOCAL_APIC && X86_64 && IRQ_REMAP
@@ -480,6 +496,36 @@ config X86_INTEL_LPSS
things like clock tree (common clock framework) and pincontrol
which are needed by the LPSS peripheral drivers.
+config IOSF_MBI
+ tristate "Intel SoC IOSF Sideband support for SoC platforms"
+ depends on PCI
+ ---help---
+ This option enables sideband register access support for Intel SoC
+ platforms. On these platforms the IOSF sideband is used in lieu of
+ MSR's for some register accesses, mostly but not limited to thermal
+ and power. Drivers may query the availability of this device to
+ determine if they need the sideband in order to work on these
+ platforms. The sideband is available on the following SoC products.
+ This list is not meant to be exclusive.
+ - BayTrail
+ - Braswell
+ - Quark
+
+ You should say Y if you are running a kernel on one of these SoC's.
+
+config IOSF_MBI_DEBUG
+ bool "Enable IOSF sideband access through debugfs"
+ depends on IOSF_MBI && DEBUG_FS
+ ---help---
+ Select this option to expose the IOSF sideband access registers (MCR,
+ MDR, MCRX) through debugfs to write and read register information from
+ different units on the SoC. This is most useful for obtaining device
+ state information for debug and analysis. As this is a general access
+ mechanism, users of this option would have specific knowledge of the
+ device they want to access.
+
+ If you don't require the option or are in doubt, say N.
+
config X86_RDC321X
bool "RDC R-321x SoC"
depends on X86_32
@@ -837,11 +883,11 @@ config X86_UP_IOAPIC
config X86_LOCAL_APIC
def_bool y
depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
+ select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
config X86_IO_APIC
- def_bool y
- depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
- select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
+ def_bool X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
+ depends on X86_LOCAL_APIC
select IRQ_DOMAIN
config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
@@ -943,6 +989,24 @@ config X86_ESPFIX64
def_bool y
depends on X86_16BIT && X86_64
+config X86_VSYSCALL_EMULATION
+ bool "Enable vsyscall emulation" if EXPERT
+ default y
+ depends on X86_64
+ ---help---
+ This enables emulation of the legacy vsyscall page. Disabling
+ it is roughly equivalent to booting with vsyscall=none, except
+ that it will also disable the helpful warning if a program
+ tries to use a vsyscall. With this option set to N, offending
+ programs will just segfault, citing addresses of the form
+ 0xffffffffff600?00.
+
+ This option is required by many programs built before 2013, and
+ care should be used even with newer programs if set to N.
+
+ Disabling this option saves about 7K of kernel size and
+ possibly 4K of additional runtime pagetable memory.
+
config TOSHIBA
tristate "Toshiba Laptop support"
depends on X86_32
@@ -1526,6 +1590,32 @@ config X86_SMAP
If unsure, say Y.
+config X86_INTEL_MPX
+ prompt "Intel MPX (Memory Protection Extensions)"
+ def_bool n
+ depends on CPU_SUP_INTEL
+ ---help---
+ MPX provides hardware features that can be used in
+ conjunction with compiler-instrumented code to check
+ memory references. It is designed to detect buffer
+ overflow or underflow bugs.
+
+ This option enables running applications which are
+ instrumented or otherwise use MPX. It does not use MPX
+ itself inside the kernel or to protect the kernel
+ against bad memory references.
+
+ Enabling this option will make the kernel larger:
+ ~8k of kernel text and 36 bytes of data on a 64-bit
+ defconfig. It adds a long to the 'mm_struct' which
+ will increase the kernel memory overhead of each
+ process and adds some branches to paths used during
+ exec() and munmap().
+
+ For details, see Documentation/x86/intel_mpx.txt
+
+ If unsure, say N.
+
config EFI
bool "EFI runtime service support"
depends on ACPI
@@ -2443,11 +2533,6 @@ config X86_DMA_REMAP
bool
depends on STA2X11
-config IOSF_MBI
- tristate
- default m
- depends on PCI
-
config PMC_ATOM
def_bool y
depends on PCI
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 60087ca37679..920e6160c535 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -50,9 +50,6 @@ ifeq ($(CONFIG_X86_32),y)
KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
- # Don't autogenerate MMX or SSE instructions
- KBUILD_CFLAGS += -mno-mmx -mno-sse
-
# Never want PIC in a 32-bit kernel, prevent breakage with GCC built
# with nonstandard options
KBUILD_CFLAGS += -fno-pic
@@ -80,8 +77,7 @@ else
KBUILD_AFLAGS += -m64
KBUILD_CFLAGS += -m64
- # Don't autogenerate traditional x87, MMX or SSE instructions
- KBUILD_CFLAGS += -mno-mmx -mno-sse
+ # Don't autogenerate traditional x87 instructions
KBUILD_CFLAGS += $(call cc-option,-mno-80387)
KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
@@ -168,7 +164,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
#
KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
# prevent gcc from generating any FP code by mistake
-KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
KBUILD_CFLAGS += $(mflags-y)
@@ -253,12 +249,6 @@ archclean:
$(Q)$(MAKE) $(clean)=arch/x86/tools
$(Q)$(MAKE) $(clean)=arch/x86/purgatory
-PHONY += kvmconfig
-kvmconfig:
- $(if $(wildcard $(objtree)/.config),, $(error You need an existing .config for this target))
- $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m -O $(objtree) $(objtree)/.config $(srctree)/arch/x86/configs/kvm_guest.config
- $(Q)yes "" | $(MAKE) -f $(srctree)/Makefile oldconfig
-
define archhelp
echo '* bzImage - Compressed kernel image (arch/x86/boot/bzImage)'
echo ' install - Install kernel using'
@@ -272,5 +262,4 @@ define archhelp
echo ' bzdisk/fdimage*/isoimage also accept:'
echo ' FDARGS="..." arguments for the booted kernel'
echo ' FDINITRD=file initrd for the booted kernel'
- echo ' kvmconfig - Enable additional options for guest kernel support'
endef
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index dbe8dd2fe247..3db07f30636f 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -35,19 +35,23 @@ setup-y += video-vesa.o
setup-y += video-bios.o
targets += $(setup-y)
-hostprogs-y := mkcpustr tools/build
+hostprogs-y := tools/build
+hostprogs-$(CONFIG_X86_FEATURE_NAMES) += mkcpustr
HOST_EXTRACFLAGS += -I$(srctree)/tools/include \
-include include/generated/autoconf.h \
-D__EXPORTED_HEADERS__
+ifdef CONFIG_X86_FEATURE_NAMES
$(obj)/cpu.o: $(obj)/cpustr.h
quiet_cmd_cpustr = CPUSTR $@
cmd_cpustr = $(obj)/mkcpustr > $@
-targets += cpustr.h
+targets += cpustr.h
$(obj)/cpustr.h: $(obj)/mkcpustr FORCE
$(call if_changed,cpustr)
+endif
+clean-files += cpustr.h
# ---------------------------------------------------------------------------
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 0fcd9133790c..d999398928bc 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -3,6 +3,18 @@
#
# create a compressed vmlinux image from the original vmlinux
#
+# vmlinuz is:
+# decompression code (*.o)
+# asm globals (piggy.S), including:
+# vmlinux.bin.(gz|bz2|lzma|...)
+#
+# vmlinux.bin is:
+# vmlinux stripped of debugging and comments
+# vmlinux.bin.all is:
+# vmlinux.bin + vmlinux.relocs
+# vmlinux.bin.(gz|bz2|lzma|...) is:
+# (see scripts/Makefile.lib size_append)
+# compressed vmlinux.bin.all + u32 size of vmlinux.bin.all
targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
@@ -26,17 +38,19 @@ LDFLAGS_vmlinux := -T
hostprogs-y := mkpiggy
HOST_EXTRACFLAGS += -I$(srctree)/tools/include
-VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
- $(obj)/string.o $(obj)/cmdline.o $(obj)/early_serial_console.o \
- $(obj)/piggy.o $(obj)/cpuflags.o $(obj)/aslr.o
+vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
+ $(obj)/string.o $(obj)/cmdline.o \
+ $(obj)/piggy.o $(obj)/cpuflags.o
+
+vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o
+vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/aslr.o
$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
-ifeq ($(CONFIG_EFI_STUB), y)
- VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
-endif
+vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
+ $(objtree)/drivers/firmware/efi/libstub/lib.a
-$(obj)/vmlinux: $(VMLINUX_OBJS) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
$(call if_changed,ld)
@:
@@ -44,7 +58,7 @@ OBJCOPYFLAGS_vmlinux.bin := -R .comment -S
$(obj)/vmlinux.bin: vmlinux FORCE
$(call if_changed,objcopy)
-targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs
+targets += $(patsubst $(obj)/%,%,$(vmlinux-objs-y)) vmlinux.bin.all vmlinux.relocs
CMD_RELOCS = arch/x86/tools/relocs
quiet_cmd_relocs = RELOCS $@
@@ -75,8 +89,10 @@ suffix-$(CONFIG_KERNEL_XZ) := xz
suffix-$(CONFIG_KERNEL_LZO) := lzo
suffix-$(CONFIG_KERNEL_LZ4) := lz4
+RUN_SIZE = $(shell $(OBJDUMP) -h vmlinux | \
+ perl $(srctree)/arch/x86/tools/calc_run_size.pl)
quiet_cmd_mkpiggy = MKPIGGY $@
- cmd_mkpiggy = $(obj)/mkpiggy $< > $@ || ( rm -f $@ ; false )
+ cmd_mkpiggy = $(obj)/mkpiggy $< $(RUN_SIZE) > $@ || ( rm -f $@ ; false )
targets += piggy.S
$(obj)/piggy.S: $(obj)/vmlinux.bin.$(suffix-y) $(obj)/mkpiggy FORCE
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index d39189ba7f8e..bb1376381985 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -1,6 +1,5 @@
#include "misc.h"
-#ifdef CONFIG_RANDOMIZE_BASE
#include <asm/msr.h>
#include <asm/archrandom.h>
#include <asm/e820.h>
@@ -195,7 +194,7 @@ static bool mem_avoid_overlap(struct mem_vector *img)
while (ptr) {
struct mem_vector avoid;
- avoid.start = (u64)ptr;
+ avoid.start = (unsigned long)ptr;
avoid.size = sizeof(*ptr) + ptr->len;
if (mem_overlaps(img, &avoid))
@@ -335,5 +334,3 @@ unsigned char *choose_kernel_location(unsigned char *input,
out:
return (unsigned char *)choice;
}
-
-#endif /* CONFIG_RANDOMIZE_BASE */
diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c
index d3d003cb5481..261e81fb9582 100644
--- a/arch/x86/boot/compressed/early_serial_console.c
+++ b/arch/x86/boot/compressed/early_serial_console.c
@@ -1,9 +1,5 @@
#include "misc.h"
-#ifdef CONFIG_EARLY_PRINTK
-
int early_serial_base;
#include "../early_serial_console.c"
-
-#endif
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index de8eebd6f67c..92b9a5f2aed6 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -21,8 +21,10 @@ static efi_system_table_t *sys_table;
static struct efi_config *efi_early;
-#define efi_call_early(f, ...) \
- efi_early->call(efi_early->f, __VA_ARGS__);
+__pure const struct efi_config *__efi_early(void)
+{
+ return efi_early;
+}
#define BOOT_SERVICES(bits) \
static void setup_boot_services##bits(struct efi_config *c) \
@@ -285,8 +287,6 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
}
}
-#include "../../../../drivers/firmware/efi/libstub/efi-stub-helper.c"
-
static void find_bits(unsigned long mask, u8 *pos, u8 *size)
{
u8 first, len;
@@ -330,8 +330,10 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
size = pci->romsize + sizeof(*rom);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to alloc mem for rom\n");
return status;
+ }
memset(rom, 0, sizeof(*rom));
@@ -344,14 +346,18 @@ __setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
PCI_VENDOR_ID, 1, &(rom->vendor));
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to read rom->vendor\n");
goto free_struct;
+ }
status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
PCI_DEVICE_ID, 1, &(rom->devid));
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to read rom->devid\n");
goto free_struct;
+ }
status = efi_early->call(pci->get_location, pci, &(rom->segment),
&(rom->bus), &(rom->device), &(rom->function));
@@ -432,8 +438,10 @@ __setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
size = pci->romsize + sizeof(*rom);
status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to alloc mem for rom\n");
return status;
+ }
rom->data.type = SETUP_PCI;
rom->data.len = size - sizeof(struct setup_data);
@@ -444,14 +452,18 @@ __setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
PCI_VENDOR_ID, 1, &(rom->vendor));
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to read rom->vendor\n");
goto free_struct;
+ }
status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
PCI_DEVICE_ID, 1, &(rom->devid));
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to read rom->devid\n");
goto free_struct;
+ }
status = efi_early->call(pci->get_location, pci, &(rom->segment),
&(rom->bus), &(rom->device), &(rom->function));
@@ -538,8 +550,10 @@ static void setup_efi_pci(struct boot_params *params)
EFI_LOADER_DATA,
size, (void **)&pci_handle);
- if (status != EFI_SUCCESS)
+ if (status != EFI_SUCCESS) {
+ efi_printk(sys_table, "Failed to alloc mem for pci_handle\n");
return;
+ }
status = efi_call_early(locate_handle,
EFI_LOCATE_BY_PROTOCOL, &pci_proto,
@@ -1105,6 +1119,10 @@ struct boot_params *make_boot_params(struct efi_config *c)
memset(sdt, 0, sizeof(*sdt));
+ status = efi_parse_options(cmdline_ptr);
+ if (status != EFI_SUCCESS)
+ goto fail2;
+
status = handle_cmdline_files(sys_table, image,
(char *)(unsigned long)hdr->cmd_line_ptr,
"initrd=", hdr->initrd_addr_max,
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index c88c31ecad12..d487e727f1ec 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -103,20 +103,4 @@ struct efi_uga_draw_protocol {
void *blt;
};
-struct efi_config {
- u64 image_handle;
- u64 table;
- u64 allocate_pool;
- u64 allocate_pages;
- u64 get_memory_map;
- u64 free_pool;
- u64 free_pages;
- u64 locate_handle;
- u64 handle_protocol;
- u64 exit_boot_services;
- u64 text_output;
- efi_status_t (*call)(unsigned long, ...);
- bool is64;
-} __packed;
-
#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index cbed1407a5cd..1d7fbbcc196d 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -207,7 +207,8 @@ relocated:
* Do the decompression, and jump to the new kernel..
*/
/* push arguments for decompress_kernel: */
- pushl $z_output_len /* decompressed length */
+ pushl $z_run_size /* size of kernel with .bss and .brk */
+ pushl $z_output_len /* decompressed length, end of relocs */
leal z_extract_offset_negative(%ebx), %ebp
pushl %ebp /* output address */
pushl $z_input_len /* input_len */
@@ -217,7 +218,7 @@ relocated:
pushl %eax /* heap area */
pushl %esi /* real mode pointer */
call decompress_kernel /* returns kernel location in %eax */
- addl $24, %esp
+ addl $28, %esp
/*
* Jump to the decompressed kernel.
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 2884e0c3e8a5..6b1766c6c082 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -402,13 +402,16 @@ relocated:
* Do the decompression, and jump to the new kernel..
*/
pushq %rsi /* Save the real mode argument */
+ movq $z_run_size, %r9 /* size of kernel with .bss and .brk */
+ pushq %r9
movq %rsi, %rdi /* real mode address */
leaq boot_heap(%rip), %rsi /* malloc area for uncompression */
leaq input_data(%rip), %rdx /* input_data */
movl $z_input_len, %ecx /* input_len */
movq %rbp, %r8 /* output target address */
- movq $z_output_len, %r9 /* decompressed length */
+ movq $z_output_len, %r9 /* decompressed length, end of relocs */
call decompress_kernel /* returns kernel location in %rax */
+ popq %r9
popq %rsi
/*
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 57ab74df7eea..dcc1c536cc21 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -260,7 +260,7 @@ static void handle_relocations(void *output, unsigned long output_len)
/*
* Process relocations: 32 bit relocations first then 64 bit after.
- * Two sets of binary relocations are added to the end of the kernel
+ * Three sets of binary relocations are added to the end of the kernel
* before compression. Each relocation table entry is the kernel
* address of the location which needs to be updated stored as a
* 32-bit value which is sign extended to 64 bits.
@@ -270,6 +270,8 @@ static void handle_relocations(void *output, unsigned long output_len)
* kernel bits...
* 0 - zero terminator for 64 bit relocations
* 64 bit relocation repeated
+ * 0 - zero terminator for inverse 32 bit relocations
+ * 32 bit inverse relocation repeated
* 0 - zero terminator for 32 bit relocations
* 32 bit relocation repeated
*
@@ -286,6 +288,16 @@ static void handle_relocations(void *output, unsigned long output_len)
*(uint32_t *)ptr += delta;
}
#ifdef CONFIG_X86_64
+ while (*--reloc) {
+ long extended = *reloc;
+ extended += map;
+
+ ptr = (unsigned long)extended;
+ if (ptr < min_addr || ptr > max_addr)
+ error("inverse 32-bit relocation outside of kernel!\n");
+
+ *(int32_t *)ptr -= delta;
+ }
for (reloc--; *reloc; reloc--) {
long extended = *reloc;
extended += map;
@@ -358,7 +370,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
unsigned char *input_data,
unsigned long input_len,
unsigned char *output,
- unsigned long output_len)
+ unsigned long output_len,
+ unsigned long run_size)
{
real_mode = rmode;
@@ -381,8 +394,14 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
free_mem_ptr = heap; /* Heap */
free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
- output = choose_kernel_location(input_data, input_len,
- output, output_len);
+ /*
+ * The memory hole needed for the kernel is the larger of either
+ * the entire decompressed kernel plus relocation table, or the
+ * entire decompressed kernel plus .bss and .brk sections.
+ */
+ output = choose_kernel_location(input_data, input_len, output,
+ output_len > run_size ? output_len
+ : run_size);
/* Validate memory location choices. */
if ((unsigned long)output & (MIN_KERNEL_ALIGN - 1))
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index b669ab65bf6c..d8222f213182 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -36,11 +36,13 @@ int main(int argc, char *argv[])
uint32_t olen;
long ilen;
unsigned long offs;
+ unsigned long run_size;
FILE *f = NULL;
int retval = 1;
- if (argc < 2) {
- fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
+ if (argc < 3) {
+ fprintf(stderr, "Usage: %s compressed_file run_size\n",
+ argv[0]);
goto bail;
}
@@ -74,6 +76,7 @@ int main(int argc, char *argv[])
offs += olen >> 12; /* Add 8 bytes for each 32K block */
offs += 64*1024 + 128; /* Add 64K + 128 bytes slack */
offs = (offs+4095) & ~4095; /* Round to a 4K boundary */
+ run_size = atoi(argv[2]);
printf(".section \".rodata..compressed\",\"a\",@progbits\n");
printf(".globl z_input_len\n");
@@ -85,6 +88,8 @@ int main(int argc, char *argv[])
/* z_extract_offset_negative allows simplification of head_32.S */
printf(".globl z_extract_offset_negative\n");
printf("z_extract_offset_negative = -0x%lx\n", offs);
+ printf(".globl z_run_size\n");
+ printf("z_run_size = %lu\n", run_size);
printf(".globl input_data, input_data_end\n");
printf("input_data:\n");
diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c
index 6ec6bb6e9957..29207f69ae8c 100644
--- a/arch/x86/boot/cpu.c
+++ b/arch/x86/boot/cpu.c
@@ -16,7 +16,9 @@
*/
#include "boot.h"
+#ifdef CONFIG_X86_FEATURE_NAMES
#include "cpustr.h"
+#endif
static char *cpu_name(int level)
{
@@ -32,11 +34,48 @@ static char *cpu_name(int level)
}
}
+static void show_cap_strs(u32 *err_flags)
+{
+ int i, j;
+#ifdef CONFIG_X86_FEATURE_NAMES
+ const unsigned char *msg_strs = (const unsigned char *)x86_cap_strs;
+ for (i = 0; i < NCAPINTS; i++) {
+ u32 e = err_flags[i];
+ for (j = 0; j < 32; j++) {
+ if (msg_strs[0] < i ||
+ (msg_strs[0] == i && msg_strs[1] < j)) {
+ /* Skip to the next string */
+ msg_strs += 2;
+ while (*msg_strs++)
+ ;
+ }
+ if (e & 1) {
+ if (msg_strs[0] == i &&
+ msg_strs[1] == j &&
+ msg_strs[2])
+ printf("%s ", msg_strs+2);
+ else
+ printf("%d:%d ", i, j);
+ }
+ e >>= 1;
+ }
+ }
+#else
+ for (i = 0; i < NCAPINTS; i++) {
+ u32 e = err_flags[i];
+ for (j = 0; j < 32; j++) {
+ if (e & 1)
+ printf("%d:%d ", i, j);
+ e >>= 1;
+ }
+ }
+#endif
+}
+
int validate_cpu(void)
{
u32 *err_flags;
int cpu_level, req_level;
- const unsigned char *msg_strs;
check_cpu(&cpu_level, &req_level, &err_flags);
@@ -49,34 +88,9 @@ int validate_cpu(void)
}
if (err_flags) {
- int i, j;
puts("This kernel requires the following features "
"not present on the CPU:\n");
-
- msg_strs = (const unsigned char *)x86_cap_strs;
-
- for (i = 0; i < NCAPINTS; i++) {
- u32 e = err_flags[i];
-
- for (j = 0; j < 32; j++) {
- if (msg_strs[0] < i ||
- (msg_strs[0] == i && msg_strs[1] < j)) {
- /* Skip to the next string */
- msg_strs += 2;
- while (*msg_strs++)
- ;
- }
- if (e & 1) {
- if (msg_strs[0] == i &&
- msg_strs[1] == j &&
- msg_strs[2])
- printf("%s ", msg_strs+2);
- else
- printf("%d:%d ", i, j);
- }
- e >>= 1;
- }
- }
+ show_cap_strs(err_flags);
putchar('\n');
return -1;
} else {
diff --git a/arch/x86/boot/mkcpustr.c b/arch/x86/boot/mkcpustr.c
index 4579eff0ef4d..637097e66a62 100644
--- a/arch/x86/boot/mkcpustr.c
+++ b/arch/x86/boot/mkcpustr.c
@@ -16,6 +16,7 @@
#include <stdio.h>
#include "../include/asm/required-features.h"
+#include "../include/asm/disabled-features.h"
#include "../include/asm/cpufeature.h"
#include "../kernel/cpu/capflags.c"
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 32d2e7056c87..419819d6dab3 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -8,6 +8,7 @@ CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_FHANDLE=y
CONFIG_AUDIT=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config
new file mode 100644
index 000000000000..4e2ecfa23c15
--- /dev/null
+++ b/arch/x86/configs/tiny.config
@@ -0,0 +1 @@
+CONFIG_NOHIGHMEM=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index a481dd4755d5..4c311ddd973b 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -7,6 +7,7 @@ CONFIG_TASKSTATS=y
CONFIG_TASK_DELAY_ACCT=y
CONFIG_TASK_XACCT=y
CONFIG_TASK_IO_ACCOUNTING=y
+CONFIG_FHANDLE=y
CONFIG_AUDIT=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index d551165a3159..5a4a089e8b1f 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -45,6 +45,7 @@ endif
ifeq ($(avx2_supported),yes)
obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX2_X86_64) += camellia-aesni-avx2.o
obj-$(CONFIG_CRYPTO_SERPENT_AVX2_X86_64) += serpent-avx2.o
+ obj-$(CONFIG_CRYPTO_SHA1_MB) += sha-mb/
endif
aes-i586-y := aes-i586-asm_32.o aes_glue.o
diff --git a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
index f091f122ed24..a916c4a61165 100644
--- a/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
+++ b/arch/x86/crypto/aes_ctrby8_avx-x86_64.S
@@ -79,9 +79,6 @@
#define xcounter %xmm8
#define xbyteswap %xmm9
#define xkey0 %xmm10
-#define xkey3 %xmm11
-#define xkey6 %xmm12
-#define xkey9 %xmm13
#define xkey4 %xmm11
#define xkey8 %xmm12
#define xkey12 %xmm13
@@ -108,6 +105,10 @@
byteswap_const:
.octa 0x000102030405060708090A0B0C0D0E0F
+ddq_low_msk:
+ .octa 0x0000000000000000FFFFFFFFFFFFFFFF
+ddq_high_add_1:
+ .octa 0x00000000000000010000000000000000
ddq_add_1:
.octa 0x00000000000000000000000000000001
ddq_add_2:
@@ -169,7 +170,12 @@ ddq_add_8:
.rept (by - 1)
club DDQ_DATA, i
club XDATA, i
- vpaddd var_ddq_add(%rip), xcounter, var_xdata
+ vpaddq var_ddq_add(%rip), xcounter, var_xdata
+ vptest ddq_low_msk(%rip), var_xdata
+ jnz 1f
+ vpaddq ddq_high_add_1(%rip), var_xdata, var_xdata
+ vpaddq ddq_high_add_1(%rip), xcounter, xcounter
+ 1:
vpshufb xbyteswap, var_xdata, var_xdata
.set i, (i +1)
.endr
@@ -178,7 +184,11 @@ ddq_add_8:
vpxor xkey0, xdata0, xdata0
club DDQ_DATA, by
- vpaddd var_ddq_add(%rip), xcounter, xcounter
+ vpaddq var_ddq_add(%rip), xcounter, xcounter
+ vptest ddq_low_msk(%rip), xcounter
+ jnz 1f
+ vpaddq ddq_high_add_1(%rip), xcounter, xcounter
+ 1:
.set i, 1
.rept (by - 1)
@@ -198,7 +208,7 @@ ddq_add_8:
.if (klen == KEY_128)
.if (load_keys)
- vmovdqa 3*16(p_keys), xkeyA
+ vmovdqa 3*16(p_keys), xkey4
.endif
.else
vmovdqa 3*16(p_keys), xkeyA
@@ -214,7 +224,7 @@ ddq_add_8:
add $(16*by), p_in
.if (klen == KEY_128)
- vmovdqa 4*16(p_keys), xkey4
+ vmovdqa 4*16(p_keys), xkeyB
.else
.if (load_keys)
vmovdqa 4*16(p_keys), xkey4
@@ -224,7 +234,12 @@ ddq_add_8:
.set i, 0
.rept by
club XDATA, i
- vaesenc xkeyA, var_xdata, var_xdata /* key 3 */
+ /* key 3 */
+ .if (klen == KEY_128)
+ vaesenc xkey4, var_xdata, var_xdata
+ .else
+ vaesenc xkeyA, var_xdata, var_xdata
+ .endif
.set i, (i +1)
.endr
@@ -233,13 +248,18 @@ ddq_add_8:
.set i, 0
.rept by
club XDATA, i
- vaesenc xkey4, var_xdata, var_xdata /* key 4 */
+ /* key 4 */
+ .if (klen == KEY_128)
+ vaesenc xkeyB, var_xdata, var_xdata
+ .else
+ vaesenc xkey4, var_xdata, var_xdata
+ .endif
.set i, (i +1)
.endr
.if (klen == KEY_128)
.if (load_keys)
- vmovdqa 6*16(p_keys), xkeyB
+ vmovdqa 6*16(p_keys), xkey8
.endif
.else
vmovdqa 6*16(p_keys), xkeyB
@@ -257,12 +277,17 @@ ddq_add_8:
.set i, 0
.rept by
club XDATA, i
- vaesenc xkeyB, var_xdata, var_xdata /* key 6 */
+ /* key 6 */
+ .if (klen == KEY_128)
+ vaesenc xkey8, var_xdata, var_xdata
+ .else
+ vaesenc xkeyB, var_xdata, var_xdata
+ .endif
.set i, (i +1)
.endr
.if (klen == KEY_128)
- vmovdqa 8*16(p_keys), xkey8
+ vmovdqa 8*16(p_keys), xkeyB
.else
.if (load_keys)
vmovdqa 8*16(p_keys), xkey8
@@ -278,7 +303,7 @@ ddq_add_8:
.if (klen == KEY_128)
.if (load_keys)
- vmovdqa 9*16(p_keys), xkeyA
+ vmovdqa 9*16(p_keys), xkey12
.endif
.else
vmovdqa 9*16(p_keys), xkeyA
@@ -287,7 +312,12 @@ ddq_add_8:
.set i, 0
.rept by
club XDATA, i
- vaesenc xkey8, var_xdata, var_xdata /* key 8 */
+ /* key 8 */
+ .if (klen == KEY_128)
+ vaesenc xkeyB, var_xdata, var_xdata
+ .else
+ vaesenc xkey8, var_xdata, var_xdata
+ .endif
.set i, (i +1)
.endr
@@ -296,7 +326,12 @@ ddq_add_8:
.set i, 0
.rept by
club XDATA, i
- vaesenc xkeyA, var_xdata, var_xdata /* key 9 */
+ /* key 9 */
+ .if (klen == KEY_128)
+ vaesenc xkey12, var_xdata, var_xdata
+ .else
+ vaesenc xkeyA, var_xdata, var_xdata
+ .endif
.set i, (i +1)
.endr
@@ -402,7 +437,6 @@ ddq_add_8:
/* main body of aes ctr load */
.macro do_aes_ctrmain key_len
-
cmp $16, num_bytes
jb .Ldo_return2\key_len
diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c
index aafe8ce0d65d..e26984f7ab8d 100644
--- a/arch/x86/crypto/aes_glue.c
+++ b/arch/x86/crypto/aes_glue.c
@@ -66,5 +66,5 @@ module_exit(aes_fini);
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, asm optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
-MODULE_ALIAS("aes-asm");
+MODULE_ALIAS_CRYPTO("aes");
+MODULE_ALIAS_CRYPTO("aes-asm");
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index a7ccd57f19e4..ae855f4f64b7 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -43,10 +43,6 @@
#include <asm/crypto/glue_helper.h>
#endif
-#if defined(CONFIG_CRYPTO_PCBC) || defined(CONFIG_CRYPTO_PCBC_MODULE)
-#define HAS_PCBC
-#endif
-
/* This data is stored at the end of the crypto_tfm struct.
* It's a type of per "session" data storage location.
* This needs to be 16 byte aligned.
@@ -481,7 +477,7 @@ static void ctr_crypt_final(struct crypto_aes_ctx *ctx,
crypto_inc(ctrblk, AES_BLOCK_SIZE);
}
-#if 0 /* temporary disabled due to failing crypto tests */
+#ifdef CONFIG_AS_AVX
static void aesni_ctr_enc_avx_tfm(struct crypto_aes_ctx *ctx, u8 *out,
const u8 *in, unsigned int len, u8 *iv)
{
@@ -547,7 +543,7 @@ static int ablk_ctr_init(struct crypto_tfm *tfm)
#endif
-#ifdef HAS_PCBC
+#if IS_ENABLED(CONFIG_CRYPTO_PCBC)
static int ablk_pcbc_init(struct crypto_tfm *tfm)
{
return ablk_init_common(tfm, "fpu(pcbc(__driver-aes-aesni))");
@@ -1377,7 +1373,7 @@ static struct crypto_alg aesni_algs[] = { {
},
},
#endif
-#ifdef HAS_PCBC
+#if IS_ENABLED(CONFIG_CRYPTO_PCBC)
}, {
.cra_name = "pcbc(aes)",
.cra_driver_name = "pcbc-aes-aesni",
@@ -1522,7 +1518,7 @@ static int __init aesni_init(void)
aesni_gcm_dec_tfm = aesni_gcm_dec;
}
aesni_ctr_enc_tfm = aesni_ctr_enc;
-#if 0 /* temporary disabled due to failing crypto tests */
+#ifdef CONFIG_AS_AVX
if (cpu_has_avx) {
/* optimize performance of ctr mode encryption transform */
aesni_ctr_enc_tfm = aesni_ctr_enc_avx_tfm;
@@ -1550,4 +1546,4 @@ module_exit(aesni_exit);
MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm, Intel AES-NI instructions optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("aes");
+MODULE_ALIAS_CRYPTO("aes");
diff --git a/arch/x86/crypto/blowfish_glue.c b/arch/x86/crypto/blowfish_glue.c
index 8af519ed73d1..17c05531dfd1 100644
--- a/arch/x86/crypto/blowfish_glue.c
+++ b/arch/x86/crypto/blowfish_glue.c
@@ -478,5 +478,5 @@ module_exit(fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Blowfish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("blowfish");
-MODULE_ALIAS("blowfish-asm");
+MODULE_ALIAS_CRYPTO("blowfish");
+MODULE_ALIAS_CRYPTO("blowfish-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 4209a76fcdaa..9a07fafe3831 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -582,5 +582,5 @@ module_exit(camellia_aesni_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX2 optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index 87a041a10f4a..ed38d959add6 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -574,5 +574,5 @@ module_exit(camellia_aesni_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, AES-NI/AVX optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index c171dcbf192d..5c8b6266a394 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -1725,5 +1725,5 @@ module_exit(fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Camellia Cipher Algorithm, asm optimized");
-MODULE_ALIAS("camellia");
-MODULE_ALIAS("camellia-asm");
+MODULE_ALIAS_CRYPTO("camellia");
+MODULE_ALIAS_CRYPTO("camellia-asm");
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index e57e20ab5e0b..60ada677a928 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -491,4 +491,4 @@ module_exit(cast5_exit);
MODULE_DESCRIPTION("Cast5 Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast5");
+MODULE_ALIAS_CRYPTO("cast5");
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 09f3677393e4..0160f68a57ff 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -611,4 +611,4 @@ module_exit(cast6_exit);
MODULE_DESCRIPTION("Cast6 Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("cast6");
+MODULE_ALIAS_CRYPTO("cast6");
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index 9d014a74ef96..1937fc1d8763 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -197,5 +197,5 @@ module_exit(crc32_pclmul_mod_fini);
MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32");
-MODULE_ALIAS("crc32-pclmul");
+MODULE_ALIAS_CRYPTO("crc32");
+MODULE_ALIAS_CRYPTO("crc32-pclmul");
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 6812ad98355c..28640c3d6af7 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -280,5 +280,5 @@ MODULE_AUTHOR("Austin Zhang <austin.zhang@intel.com>, Kent Liu <kent.liu@intel.c
MODULE_DESCRIPTION("CRC32c (Castagnoli) optimization using Intel Hardware.");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("crc32c");
-MODULE_ALIAS("crc32c-intel");
+MODULE_ALIAS_CRYPTO("crc32c");
+MODULE_ALIAS_CRYPTO("crc32c-intel");
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index 7845d7fd54c0..b6c67bf30fdf 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -147,5 +147,5 @@ MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("crct10dif");
-MODULE_ALIAS("crct10dif-pclmul");
+MODULE_ALIAS_CRYPTO("crct10dif");
+MODULE_ALIAS_CRYPTO("crct10dif-pclmul");
diff --git a/arch/x86/crypto/des3_ede_glue.c b/arch/x86/crypto/des3_ede_glue.c
index 0e9c0668fe4e..38a14f818ef1 100644
--- a/arch/x86/crypto/des3_ede_glue.c
+++ b/arch/x86/crypto/des3_ede_glue.c
@@ -502,8 +502,8 @@ module_exit(des3_ede_x86_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Triple DES EDE Cipher Algorithm, asm optimized");
-MODULE_ALIAS("des3_ede");
-MODULE_ALIAS("des3_ede-asm");
-MODULE_ALIAS("des");
-MODULE_ALIAS("des-asm");
+MODULE_ALIAS_CRYPTO("des3_ede");
+MODULE_ALIAS_CRYPTO("des3_ede-asm");
+MODULE_ALIAS_CRYPTO("des");
+MODULE_ALIAS_CRYPTO("des-asm");
MODULE_AUTHOR("Jussi Kivilinna <jussi.kivilinna@iki.fi>");
diff --git a/arch/x86/crypto/fpu.c b/arch/x86/crypto/fpu.c
index 98d7a188f46b..f368ba261739 100644
--- a/arch/x86/crypto/fpu.c
+++ b/arch/x86/crypto/fpu.c
@@ -17,6 +17,7 @@
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
+#include <linux/crypto.h>
#include <asm/i387.h>
struct crypto_fpu_ctx {
@@ -159,3 +160,5 @@ void __exit crypto_fpu_exit(void)
{
crypto_unregister_template(&crypto_fpu_tmpl);
}
+
+MODULE_ALIAS_CRYPTO("fpu");
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 88bb7ba8b175..8253d85aa165 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -341,4 +341,4 @@ module_exit(ghash_pclmulqdqni_mod_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("GHASH Message Digest Algorithm, "
"acclerated by PCLMULQDQ-NI");
-MODULE_ALIAS("ghash");
+MODULE_ALIAS_CRYPTO("ghash");
diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
index 5e8e67739bb5..399a29d067d6 100644
--- a/arch/x86/crypto/salsa20_glue.c
+++ b/arch/x86/crypto/salsa20_glue.c
@@ -119,5 +119,5 @@ module_exit(fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly version)");
-MODULE_ALIAS("salsa20");
-MODULE_ALIAS("salsa20-asm");
+MODULE_ALIAS_CRYPTO("salsa20");
+MODULE_ALIAS_CRYPTO("salsa20-asm");
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 2fae489b1524..437e47a4d302 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -558,5 +558,5 @@ module_exit(fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX2 optimized");
-MODULE_ALIAS("serpent");
-MODULE_ALIAS("serpent-asm");
+MODULE_ALIAS_CRYPTO("serpent");
+MODULE_ALIAS_CRYPTO("serpent-asm");
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index ff4870870972..7e217398b4eb 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -617,4 +617,4 @@ module_exit(serpent_exit);
MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 8c95f8637306..bf025adaea01 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -618,4 +618,4 @@ module_exit(serpent_sse2_exit);
MODULE_DESCRIPTION("Serpent Cipher Algorithm, SSE2 optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("serpent");
+MODULE_ALIAS_CRYPTO("serpent");
diff --git a/arch/x86/crypto/sha-mb/Makefile b/arch/x86/crypto/sha-mb/Makefile
new file mode 100644
index 000000000000..2f8756375df5
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/Makefile
@@ -0,0 +1,11 @@
+#
+# Arch-specific CryptoAPI modules.
+#
+
+avx2_supported := $(call as-instr,vpgatherdd %ymm0$(comma)(%eax$(comma)%ymm1\
+ $(comma)4)$(comma)%ymm2,yes,no)
+ifeq ($(avx2_supported),yes)
+ obj-$(CONFIG_CRYPTO_SHA1_MB) += sha1-mb.o
+ sha1-mb-y := sha1_mb.o sha1_mb_mgr_flush_avx2.o \
+ sha1_mb_mgr_init_avx2.o sha1_mb_mgr_submit_avx2.o sha1_x8_avx2.o
+endif
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
new file mode 100644
index 000000000000..a225a5ca1037
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -0,0 +1,934 @@
+/*
+ * Multi buffer SHA1 algorithm Glue Code
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/cryptohash.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <crypto/scatterwalk.h>
+#include <crypto/sha.h>
+#include <crypto/mcryptd.h>
+#include <crypto/crypto_wq.h>
+#include <asm/byteorder.h>
+#include <asm/i387.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <linux/hardirq.h>
+#include <asm/fpu-internal.h>
+#include "sha_mb_ctx.h"
+
+#define FLUSH_INTERVAL 1000 /* in usec */
+
+static struct mcryptd_alg_state sha1_mb_alg_state;
+
+struct sha1_mb_ctx {
+ struct mcryptd_ahash *mcryptd_tfm;
+};
+
+static inline struct mcryptd_hash_request_ctx *cast_hash_to_mcryptd_ctx(struct sha1_hash_ctx *hash_ctx)
+{
+ struct shash_desc *desc;
+
+ desc = container_of((void *) hash_ctx, struct shash_desc, __ctx);
+ return container_of(desc, struct mcryptd_hash_request_ctx, desc);
+}
+
+static inline struct ahash_request *cast_mcryptd_ctx_to_req(struct mcryptd_hash_request_ctx *ctx)
+{
+ return container_of((void *) ctx, struct ahash_request, __ctx);
+}
+
+static void req_ctx_init(struct mcryptd_hash_request_ctx *rctx,
+ struct shash_desc *desc)
+{
+ rctx->flag = HASH_UPDATE;
+}
+
+static asmlinkage void (*sha1_job_mgr_init)(struct sha1_mb_mgr *state);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_submit)(struct sha1_mb_mgr *state,
+ struct job_sha1 *job);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_flush)(struct sha1_mb_mgr *state);
+static asmlinkage struct job_sha1* (*sha1_job_mgr_get_comp_job)(struct sha1_mb_mgr *state);
+
+inline void sha1_init_digest(uint32_t *digest)
+{
+ static const uint32_t initial_digest[SHA1_DIGEST_LENGTH] = {SHA1_H0,
+ SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 };
+ memcpy(digest, initial_digest, sizeof(initial_digest));
+}
+
+inline uint32_t sha1_pad(uint8_t padblock[SHA1_BLOCK_SIZE * 2],
+ uint32_t total_len)
+{
+ uint32_t i = total_len & (SHA1_BLOCK_SIZE - 1);
+
+ memset(&padblock[i], 0, SHA1_BLOCK_SIZE);
+ padblock[i] = 0x80;
+
+ i += ((SHA1_BLOCK_SIZE - 1) &
+ (0 - (total_len + SHA1_PADLENGTHFIELD_SIZE + 1)))
+ + 1 + SHA1_PADLENGTHFIELD_SIZE;
+
+#if SHA1_PADLENGTHFIELD_SIZE == 16
+ *((uint64_t *) &padblock[i - 16]) = 0;
+#endif
+
+ *((uint64_t *) &padblock[i - 8]) = cpu_to_be64(total_len << 3);
+
+ /* Number of extra blocks to hash */
+ return i >> SHA1_LOG2_BLOCK_SIZE;
+}
+
+static struct sha1_hash_ctx *sha1_ctx_mgr_resubmit(struct sha1_ctx_mgr *mgr, struct sha1_hash_ctx *ctx)
+{
+ while (ctx) {
+ if (ctx->status & HASH_CTX_STS_COMPLETE) {
+ /* Clear PROCESSING bit */
+ ctx->status = HASH_CTX_STS_COMPLETE;
+ return ctx;
+ }
+
+ /*
+ * If the extra blocks are empty, begin hashing what remains
+ * in the user's buffer.
+ */
+ if (ctx->partial_block_buffer_length == 0 &&
+ ctx->incoming_buffer_length) {
+
+ const void *buffer = ctx->incoming_buffer;
+ uint32_t len = ctx->incoming_buffer_length;
+ uint32_t copy_len;
+
+ /*
+ * Only entire blocks can be hashed.
+ * Copy remainder to extra blocks buffer.
+ */
+ copy_len = len & (SHA1_BLOCK_SIZE-1);
+
+ if (copy_len) {
+ len -= copy_len;
+ memcpy(ctx->partial_block_buffer,
+ ((const char *) buffer + len),
+ copy_len);
+ ctx->partial_block_buffer_length = copy_len;
+ }
+
+ ctx->incoming_buffer_length = 0;
+
+ /* len should be a multiple of the block size now */
+ assert((len % SHA1_BLOCK_SIZE) == 0);
+
+ /* Set len to the number of blocks to be hashed */
+ len >>= SHA1_LOG2_BLOCK_SIZE;
+
+ if (len) {
+
+ ctx->job.buffer = (uint8_t *) buffer;
+ ctx->job.len = len;
+ ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr,
+ &ctx->job);
+ continue;
+ }
+ }
+
+ /*
+ * If the extra blocks are not empty, then we are
+ * either on the last block(s) or we need more
+ * user input before continuing.
+ */
+ if (ctx->status & HASH_CTX_STS_LAST) {
+
+ uint8_t *buf = ctx->partial_block_buffer;
+ uint32_t n_extra_blocks = sha1_pad(buf, ctx->total_length);
+
+ ctx->status = (HASH_CTX_STS_PROCESSING |
+ HASH_CTX_STS_COMPLETE);
+ ctx->job.buffer = buf;
+ ctx->job.len = (uint32_t) n_extra_blocks;
+ ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
+ continue;
+ }
+
+ ctx->status = HASH_CTX_STS_IDLE;
+ return ctx;
+ }
+
+ return NULL;
+}
+
+static struct sha1_hash_ctx *sha1_ctx_mgr_get_comp_ctx(struct sha1_ctx_mgr *mgr)
+{
+ /*
+ * If get_comp_job returns NULL, there are no jobs complete.
+ * If get_comp_job returns a job, verify that it is safe to return to the user.
+ * If it is not ready, resubmit the job to finish processing.
+ * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
+ * Otherwise, all jobs currently being managed by the hash_ctx_mgr still need processing.
+ */
+ struct sha1_hash_ctx *ctx;
+
+ ctx = (struct sha1_hash_ctx *) sha1_job_mgr_get_comp_job(&mgr->mgr);
+ return sha1_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static void sha1_ctx_mgr_init(struct sha1_ctx_mgr *mgr)
+{
+ sha1_job_mgr_init(&mgr->mgr);
+}
+
+static struct sha1_hash_ctx *sha1_ctx_mgr_submit(struct sha1_ctx_mgr *mgr,
+ struct sha1_hash_ctx *ctx,
+ const void *buffer,
+ uint32_t len,
+ int flags)
+{
+ if (flags & (~HASH_ENTIRE)) {
+ /* User should not pass anything other than FIRST, UPDATE, or LAST */
+ ctx->error = HASH_CTX_ERROR_INVALID_FLAGS;
+ return ctx;
+ }
+
+ if (ctx->status & HASH_CTX_STS_PROCESSING) {
+ /* Cannot submit to a currently processing job. */
+ ctx->error = HASH_CTX_ERROR_ALREADY_PROCESSING;
+ return ctx;
+ }
+
+ if ((ctx->status & HASH_CTX_STS_COMPLETE) && !(flags & HASH_FIRST)) {
+ /* Cannot update a finished job. */
+ ctx->error = HASH_CTX_ERROR_ALREADY_COMPLETED;
+ return ctx;
+ }
+
+
+ if (flags & HASH_FIRST) {
+ /* Init digest */
+ sha1_init_digest(ctx->job.result_digest);
+
+ /* Reset byte counter */
+ ctx->total_length = 0;
+
+ /* Clear extra blocks */
+ ctx->partial_block_buffer_length = 0;
+ }
+
+ /* If we made it here, there were no errors during this call to submit */
+ ctx->error = HASH_CTX_ERROR_NONE;
+
+ /* Store buffer ptr info from user */
+ ctx->incoming_buffer = buffer;
+ ctx->incoming_buffer_length = len;
+
+ /* Store the user's request flags and mark this ctx as currently being processed. */
+ ctx->status = (flags & HASH_LAST) ?
+ (HASH_CTX_STS_PROCESSING | HASH_CTX_STS_LAST) :
+ HASH_CTX_STS_PROCESSING;
+
+ /* Advance byte counter */
+ ctx->total_length += len;
+
+ /*
+ * If there is anything currently buffered in the extra blocks,
+ * append to it until it contains a whole block.
+ * Or if the user's buffer contains less than a whole block,
+ * append as much as possible to the extra block.
+ */
+ if ((ctx->partial_block_buffer_length) | (len < SHA1_BLOCK_SIZE)) {
+ /* Compute how many bytes to copy from user buffer into extra block */
+ uint32_t copy_len = SHA1_BLOCK_SIZE - ctx->partial_block_buffer_length;
+ if (len < copy_len)
+ copy_len = len;
+
+ if (copy_len) {
+ /* Copy and update relevant pointers and counters */
+ memcpy(&ctx->partial_block_buffer[ctx->partial_block_buffer_length],
+ buffer, copy_len);
+
+ ctx->partial_block_buffer_length += copy_len;
+ ctx->incoming_buffer = (const void *)((const char *)buffer + copy_len);
+ ctx->incoming_buffer_length = len - copy_len;
+ }
+
+ /* The extra block should never contain more than 1 block here */
+ assert(ctx->partial_block_buffer_length <= SHA1_BLOCK_SIZE);
+
+ /* If the extra block buffer contains exactly 1 block, it can be hashed. */
+ if (ctx->partial_block_buffer_length >= SHA1_BLOCK_SIZE) {
+ ctx->partial_block_buffer_length = 0;
+
+ ctx->job.buffer = ctx->partial_block_buffer;
+ ctx->job.len = 1;
+ ctx = (struct sha1_hash_ctx *) sha1_job_mgr_submit(&mgr->mgr, &ctx->job);
+ }
+ }
+
+ return sha1_ctx_mgr_resubmit(mgr, ctx);
+}
+
+static struct sha1_hash_ctx *sha1_ctx_mgr_flush(struct sha1_ctx_mgr *mgr)
+{
+ struct sha1_hash_ctx *ctx;
+
+ while (1) {
+ ctx = (struct sha1_hash_ctx *) sha1_job_mgr_flush(&mgr->mgr);
+
+ /* If flush returned 0, there are no more jobs in flight. */
+ if (!ctx)
+ return NULL;
+
+ /*
+ * If flush returned a job, resubmit the job to finish processing.
+ */
+ ctx = sha1_ctx_mgr_resubmit(mgr, ctx);
+
+ /*
+ * If sha1_ctx_mgr_resubmit returned a job, it is ready to be returned.
+ * Otherwise, all jobs currently being managed by the sha1_ctx_mgr
+ * still need processing. Loop.
+ */
+ if (ctx)
+ return ctx;
+ }
+}
+
+static int sha1_mb_init(struct shash_desc *desc)
+{
+ struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+
+ hash_ctx_init(sctx);
+ sctx->job.result_digest[0] = SHA1_H0;
+ sctx->job.result_digest[1] = SHA1_H1;
+ sctx->job.result_digest[2] = SHA1_H2;
+ sctx->job.result_digest[3] = SHA1_H3;
+ sctx->job.result_digest[4] = SHA1_H4;
+ sctx->total_length = 0;
+ sctx->partial_block_buffer_length = 0;
+ sctx->status = HASH_CTX_STS_IDLE;
+
+ return 0;
+}
+
+static int sha1_mb_set_results(struct mcryptd_hash_request_ctx *rctx)
+{
+ int i;
+ struct sha1_hash_ctx *sctx = shash_desc_ctx(&rctx->desc);
+ __be32 *dst = (__be32 *) rctx->out;
+
+ for (i = 0; i < 5; ++i)
+ dst[i] = cpu_to_be32(sctx->job.result_digest[i]);
+
+ return 0;
+}
+
+static int sha_finish_walk(struct mcryptd_hash_request_ctx **ret_rctx,
+ struct mcryptd_alg_cstate *cstate, bool flush)
+{
+ int flag = HASH_UPDATE;
+ int nbytes, err = 0;
+ struct mcryptd_hash_request_ctx *rctx = *ret_rctx;
+ struct sha1_hash_ctx *sha_ctx;
+
+ /* more work ? */
+ while (!(rctx->flag & HASH_DONE)) {
+ nbytes = crypto_ahash_walk_done(&rctx->walk, 0);
+ if (nbytes < 0) {
+ err = nbytes;
+ goto out;
+ }
+ /* check if the walk is done */
+ if (crypto_ahash_walk_last(&rctx->walk)) {
+ rctx->flag |= HASH_DONE;
+ if (rctx->flag & HASH_FINAL)
+ flag |= HASH_LAST;
+
+ }
+ sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(&rctx->desc);
+ kernel_fpu_begin();
+ sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, flag);
+ if (!sha_ctx) {
+ if (flush)
+ sha_ctx = sha1_ctx_mgr_flush(cstate->mgr);
+ }
+ kernel_fpu_end();
+ if (sha_ctx)
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ else {
+ rctx = NULL;
+ goto out;
+ }
+ }
+
+ /* copy the results */
+ if (rctx->flag & HASH_FINAL)
+ sha1_mb_set_results(rctx);
+
+out:
+ *ret_rctx = rctx;
+ return err;
+}
+
+static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
+ struct mcryptd_alg_cstate *cstate,
+ int err)
+{
+ struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+ struct sha1_hash_ctx *sha_ctx;
+ struct mcryptd_hash_request_ctx *req_ctx;
+ int ret;
+
+ /* remove from work list */
+ spin_lock(&cstate->work_lock);
+ list_del(&rctx->waiter);
+ spin_unlock(&cstate->work_lock);
+
+ if (irqs_disabled())
+ rctx->complete(&req->base, err);
+ else {
+ local_bh_disable();
+ rctx->complete(&req->base, err);
+ local_bh_enable();
+ }
+
+ /* check to see if there are other jobs that are done */
+ sha_ctx = sha1_ctx_mgr_get_comp_ctx(cstate->mgr);
+ while (sha_ctx) {
+ req_ctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ ret = sha_finish_walk(&req_ctx, cstate, false);
+ if (req_ctx) {
+ spin_lock(&cstate->work_lock);
+ list_del(&req_ctx->waiter);
+ spin_unlock(&cstate->work_lock);
+
+ req = cast_mcryptd_ctx_to_req(req_ctx);
+ if (irqs_disabled())
+ rctx->complete(&req->base, ret);
+ else {
+ local_bh_disable();
+ rctx->complete(&req->base, ret);
+ local_bh_enable();
+ }
+ }
+ sha_ctx = sha1_ctx_mgr_get_comp_ctx(cstate->mgr);
+ }
+
+ return 0;
+}
+
+static void sha1_mb_add_list(struct mcryptd_hash_request_ctx *rctx,
+ struct mcryptd_alg_cstate *cstate)
+{
+ unsigned long next_flush;
+ unsigned long delay = usecs_to_jiffies(FLUSH_INTERVAL);
+
+ /* initialize tag */
+ rctx->tag.arrival = jiffies; /* tag the arrival time */
+ rctx->tag.seq_num = cstate->next_seq_num++;
+ next_flush = rctx->tag.arrival + delay;
+ rctx->tag.expire = next_flush;
+
+ spin_lock(&cstate->work_lock);
+ list_add_tail(&rctx->waiter, &cstate->work_list);
+ spin_unlock(&cstate->work_lock);
+
+ mcryptd_arm_flusher(cstate, delay);
+}
+
+static int sha1_mb_update(struct shash_desc *desc, const u8 *data,
+ unsigned int len)
+{
+ struct mcryptd_hash_request_ctx *rctx =
+ container_of(desc, struct mcryptd_hash_request_ctx, desc);
+ struct mcryptd_alg_cstate *cstate =
+ this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
+
+ struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+ struct sha1_hash_ctx *sha_ctx;
+ int ret = 0, nbytes;
+
+
+ /* sanity check */
+ if (rctx->tag.cpu != smp_processor_id()) {
+ pr_err("mcryptd error: cpu clash\n");
+ goto done;
+ }
+
+ /* need to init context */
+ req_ctx_init(rctx, desc);
+
+ nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+ if (nbytes < 0) {
+ ret = nbytes;
+ goto done;
+ }
+
+ if (crypto_ahash_walk_last(&rctx->walk))
+ rctx->flag |= HASH_DONE;
+
+ /* submit */
+ sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+ sha1_mb_add_list(rctx, cstate);
+ kernel_fpu_begin();
+ sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, HASH_UPDATE);
+ kernel_fpu_end();
+
+ /* check if anything is returned */
+ if (!sha_ctx)
+ return -EINPROGRESS;
+
+ if (sha_ctx->error) {
+ ret = sha_ctx->error;
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ goto done;
+ }
+
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ ret = sha_finish_walk(&rctx, cstate, false);
+
+ if (!rctx)
+ return -EINPROGRESS;
+done:
+ sha_complete_job(rctx, cstate, ret);
+ return ret;
+}
+
+static int sha1_mb_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct mcryptd_hash_request_ctx *rctx =
+ container_of(desc, struct mcryptd_hash_request_ctx, desc);
+ struct mcryptd_alg_cstate *cstate =
+ this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
+
+ struct ahash_request *req = cast_mcryptd_ctx_to_req(rctx);
+ struct sha1_hash_ctx *sha_ctx;
+ int ret = 0, flag = HASH_UPDATE, nbytes;
+
+ /* sanity check */
+ if (rctx->tag.cpu != smp_processor_id()) {
+ pr_err("mcryptd error: cpu clash\n");
+ goto done;
+ }
+
+ /* need to init context */
+ req_ctx_init(rctx, desc);
+
+ nbytes = crypto_ahash_walk_first(req, &rctx->walk);
+
+ if (nbytes < 0) {
+ ret = nbytes;
+ goto done;
+ }
+
+ if (crypto_ahash_walk_last(&rctx->walk)) {
+ rctx->flag |= HASH_DONE;
+ flag = HASH_LAST;
+ }
+ rctx->out = out;
+
+ /* submit */
+ rctx->flag |= HASH_FINAL;
+ sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+ sha1_mb_add_list(rctx, cstate);
+
+ kernel_fpu_begin();
+ sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, rctx->walk.data, nbytes, flag);
+ kernel_fpu_end();
+
+ /* check if anything is returned */
+ if (!sha_ctx)
+ return -EINPROGRESS;
+
+ if (sha_ctx->error) {
+ ret = sha_ctx->error;
+ goto done;
+ }
+
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ ret = sha_finish_walk(&rctx, cstate, false);
+ if (!rctx)
+ return -EINPROGRESS;
+done:
+ sha_complete_job(rctx, cstate, ret);
+ return ret;
+}
+
+static int sha1_mb_final(struct shash_desc *desc, u8 *out)
+{
+ struct mcryptd_hash_request_ctx *rctx =
+ container_of(desc, struct mcryptd_hash_request_ctx, desc);
+ struct mcryptd_alg_cstate *cstate =
+ this_cpu_ptr(sha1_mb_alg_state.alg_cstate);
+
+ struct sha1_hash_ctx *sha_ctx;
+ int ret = 0;
+ u8 data;
+
+ /* sanity check */
+ if (rctx->tag.cpu != smp_processor_id()) {
+ pr_err("mcryptd error: cpu clash\n");
+ goto done;
+ }
+
+ /* need to init context */
+ req_ctx_init(rctx, desc);
+
+ rctx->out = out;
+ rctx->flag |= HASH_DONE | HASH_FINAL;
+
+ sha_ctx = (struct sha1_hash_ctx *) shash_desc_ctx(desc);
+ /* flag HASH_FINAL and 0 data size */
+ sha1_mb_add_list(rctx, cstate);
+ kernel_fpu_begin();
+ sha_ctx = sha1_ctx_mgr_submit(cstate->mgr, sha_ctx, &data, 0, HASH_LAST);
+ kernel_fpu_end();
+
+ /* check if anything is returned */
+ if (!sha_ctx)
+ return -EINPROGRESS;
+
+ if (sha_ctx->error) {
+ ret = sha_ctx->error;
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ goto done;
+ }
+
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ ret = sha_finish_walk(&rctx, cstate, false);
+ if (!rctx)
+ return -EINPROGRESS;
+done:
+ sha_complete_job(rctx, cstate, ret);
+ return ret;
+}
+
+static int sha1_mb_export(struct shash_desc *desc, void *out)
+{
+ struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+
+ memcpy(out, sctx, sizeof(*sctx));
+
+ return 0;
+}
+
+static int sha1_mb_import(struct shash_desc *desc, const void *in)
+{
+ struct sha1_hash_ctx *sctx = shash_desc_ctx(desc);
+
+ memcpy(sctx, in, sizeof(*sctx));
+
+ return 0;
+}
+
+
+static struct shash_alg sha1_mb_shash_alg = {
+ .digestsize = SHA1_DIGEST_SIZE,
+ .init = sha1_mb_init,
+ .update = sha1_mb_update,
+ .final = sha1_mb_final,
+ .finup = sha1_mb_finup,
+ .export = sha1_mb_export,
+ .import = sha1_mb_import,
+ .descsize = sizeof(struct sha1_hash_ctx),
+ .statesize = sizeof(struct sha1_hash_ctx),
+ .base = {
+ .cra_name = "__sha1-mb",
+ .cra_driver_name = "__intel_sha1-mb",
+ .cra_priority = 100,
+ /*
+ * use ASYNC flag as some buffers in multi-buffer
+ * algo may not have completed before hashing thread sleep
+ */
+ .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(sha1_mb_shash_alg.base.cra_list),
+ }
+};
+
+static int sha1_mb_async_init(struct ahash_request *req)
+{
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+ struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+ memcpy(mcryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+ return crypto_ahash_init(mcryptd_req);
+}
+
+static int sha1_mb_async_update(struct ahash_request *req)
+{
+ struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+ memcpy(mcryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+ return crypto_ahash_update(mcryptd_req);
+}
+
+static int sha1_mb_async_finup(struct ahash_request *req)
+{
+ struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+ memcpy(mcryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+ return crypto_ahash_finup(mcryptd_req);
+}
+
+static int sha1_mb_async_final(struct ahash_request *req)
+{
+ struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+ memcpy(mcryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+ return crypto_ahash_final(mcryptd_req);
+}
+
+static int sha1_mb_async_digest(struct ahash_request *req)
+{
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+ struct sha1_mb_ctx *ctx = crypto_ahash_ctx(tfm);
+ struct ahash_request *mcryptd_req = ahash_request_ctx(req);
+ struct mcryptd_ahash *mcryptd_tfm = ctx->mcryptd_tfm;
+
+ memcpy(mcryptd_req, req, sizeof(*req));
+ ahash_request_set_tfm(mcryptd_req, &mcryptd_tfm->base);
+ return crypto_ahash_digest(mcryptd_req);
+}
+
+static int sha1_mb_async_init_tfm(struct crypto_tfm *tfm)
+{
+ struct mcryptd_ahash *mcryptd_tfm;
+ struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+ struct mcryptd_hash_ctx *mctx;
+
+ mcryptd_tfm = mcryptd_alloc_ahash("__intel_sha1-mb", 0, 0);
+ if (IS_ERR(mcryptd_tfm))
+ return PTR_ERR(mcryptd_tfm);
+ mctx = crypto_ahash_ctx(&mcryptd_tfm->base);
+ mctx->alg_state = &sha1_mb_alg_state;
+ ctx->mcryptd_tfm = mcryptd_tfm;
+ crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
+ sizeof(struct ahash_request) +
+ crypto_ahash_reqsize(&mcryptd_tfm->base));
+
+ return 0;
+}
+
+static void sha1_mb_async_exit_tfm(struct crypto_tfm *tfm)
+{
+ struct sha1_mb_ctx *ctx = crypto_tfm_ctx(tfm);
+
+ mcryptd_free_ahash(ctx->mcryptd_tfm);
+}
+
+static struct ahash_alg sha1_mb_async_alg = {
+ .init = sha1_mb_async_init,
+ .update = sha1_mb_async_update,
+ .final = sha1_mb_async_final,
+ .finup = sha1_mb_async_finup,
+ .digest = sha1_mb_async_digest,
+ .halg = {
+ .digestsize = SHA1_DIGEST_SIZE,
+ .base = {
+ .cra_name = "sha1",
+ .cra_driver_name = "sha1_mb",
+ .cra_priority = 200,
+ .cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+ .cra_blocksize = SHA1_BLOCK_SIZE,
+ .cra_type = &crypto_ahash_type,
+ .cra_module = THIS_MODULE,
+ .cra_list = LIST_HEAD_INIT(sha1_mb_async_alg.halg.base.cra_list),
+ .cra_init = sha1_mb_async_init_tfm,
+ .cra_exit = sha1_mb_async_exit_tfm,
+ .cra_ctxsize = sizeof(struct sha1_mb_ctx),
+ .cra_alignmask = 0,
+ },
+ },
+};
+
+static unsigned long sha1_mb_flusher(struct mcryptd_alg_cstate *cstate)
+{
+ struct mcryptd_hash_request_ctx *rctx;
+ unsigned long cur_time;
+ unsigned long next_flush = 0;
+ struct sha1_hash_ctx *sha_ctx;
+
+
+ cur_time = jiffies;
+
+ while (!list_empty(&cstate->work_list)) {
+ rctx = list_entry(cstate->work_list.next,
+ struct mcryptd_hash_request_ctx, waiter);
+ if time_before(cur_time, rctx->tag.expire)
+ break;
+ kernel_fpu_begin();
+ sha_ctx = (struct sha1_hash_ctx *) sha1_ctx_mgr_flush(cstate->mgr);
+ kernel_fpu_end();
+ if (!sha_ctx) {
+ pr_err("sha1_mb error: nothing got flushed for non-empty list\n");
+ break;
+ }
+ rctx = cast_hash_to_mcryptd_ctx(sha_ctx);
+ sha_finish_walk(&rctx, cstate, true);
+ sha_complete_job(rctx, cstate, 0);
+ }
+
+ if (!list_empty(&cstate->work_list)) {
+ rctx = list_entry(cstate->work_list.next,
+ struct mcryptd_hash_request_ctx, waiter);
+ /* get the hash context and then flush time */
+ next_flush = rctx->tag.expire;
+ mcryptd_arm_flusher(cstate, get_delay(next_flush));
+ }
+ return next_flush;
+}
+
+static int __init sha1_mb_mod_init(void)
+{
+
+ int cpu;
+ int err;
+ struct mcryptd_alg_cstate *cpu_state;
+
+ /* check for dependent cpu features */
+ if (!boot_cpu_has(X86_FEATURE_AVX2) ||
+ !boot_cpu_has(X86_FEATURE_BMI2))
+ return -ENODEV;
+
+ /* initialize multibuffer structures */
+ sha1_mb_alg_state.alg_cstate = alloc_percpu(struct mcryptd_alg_cstate);
+
+ sha1_job_mgr_init = sha1_mb_mgr_init_avx2;
+ sha1_job_mgr_submit = sha1_mb_mgr_submit_avx2;
+ sha1_job_mgr_flush = sha1_mb_mgr_flush_avx2;
+ sha1_job_mgr_get_comp_job = sha1_mb_mgr_get_comp_job_avx2;
+
+ if (!sha1_mb_alg_state.alg_cstate)
+ return -ENOMEM;
+ for_each_possible_cpu(cpu) {
+ cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
+ cpu_state->next_flush = 0;
+ cpu_state->next_seq_num = 0;
+ cpu_state->flusher_engaged = false;
+ INIT_DELAYED_WORK(&cpu_state->flush, mcryptd_flusher);
+ cpu_state->cpu = cpu;
+ cpu_state->alg_state = &sha1_mb_alg_state;
+ cpu_state->mgr = (struct sha1_ctx_mgr *) kzalloc(sizeof(struct sha1_ctx_mgr), GFP_KERNEL);
+ if (!cpu_state->mgr)
+ goto err2;
+ sha1_ctx_mgr_init(cpu_state->mgr);
+ INIT_LIST_HEAD(&cpu_state->work_list);
+ spin_lock_init(&cpu_state->work_lock);
+ }
+ sha1_mb_alg_state.flusher = &sha1_mb_flusher;
+
+ err = crypto_register_shash(&sha1_mb_shash_alg);
+ if (err)
+ goto err2;
+ err = crypto_register_ahash(&sha1_mb_async_alg);
+ if (err)
+ goto err1;
+
+
+ return 0;
+err1:
+ crypto_unregister_shash(&sha1_mb_shash_alg);
+err2:
+ for_each_possible_cpu(cpu) {
+ cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
+ kfree(cpu_state->mgr);
+ }
+ free_percpu(sha1_mb_alg_state.alg_cstate);
+ return -ENODEV;
+}
+
+static void __exit sha1_mb_mod_fini(void)
+{
+ int cpu;
+ struct mcryptd_alg_cstate *cpu_state;
+
+ crypto_unregister_ahash(&sha1_mb_async_alg);
+ crypto_unregister_shash(&sha1_mb_shash_alg);
+ for_each_possible_cpu(cpu) {
+ cpu_state = per_cpu_ptr(sha1_mb_alg_state.alg_cstate, cpu);
+ kfree(cpu_state->mgr);
+ }
+ free_percpu(sha1_mb_alg_state.alg_cstate);
+}
+
+module_init(sha1_mb_mod_init);
+module_exit(sha1_mb_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, multi buffer accelerated");
+
+MODULE_ALIAS("sha1");
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S
new file mode 100644
index 000000000000..86688c6e7a25
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_datastruct.S
@@ -0,0 +1,287 @@
+/*
+ * Header file for multi buffer SHA1 algorithm data structure
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+# Macros for defining data structures
+
+# Usage example
+
+#START_FIELDS # JOB_AES
+### name size align
+#FIELD _plaintext, 8, 8 # pointer to plaintext
+#FIELD _ciphertext, 8, 8 # pointer to ciphertext
+#FIELD _IV, 16, 8 # IV
+#FIELD _keys, 8, 8 # pointer to keys
+#FIELD _len, 4, 4 # length in bytes
+#FIELD _status, 4, 4 # status enumeration
+#FIELD _user_data, 8, 8 # pointer to user data
+#UNION _union, size1, align1, \
+# size2, align2, \
+# size3, align3, \
+# ...
+#END_FIELDS
+#%assign _JOB_AES_size _FIELD_OFFSET
+#%assign _JOB_AES_align _STRUCT_ALIGN
+
+#########################################################################
+
+# Alternate "struc-like" syntax:
+# STRUCT job_aes2
+# RES_Q .plaintext, 1
+# RES_Q .ciphertext, 1
+# RES_DQ .IV, 1
+# RES_B .nested, _JOB_AES_SIZE, _JOB_AES_ALIGN
+# RES_U .union, size1, align1, \
+# size2, align2, \
+# ...
+# ENDSTRUCT
+# # Following only needed if nesting
+# %assign job_aes2_size _FIELD_OFFSET
+# %assign job_aes2_align _STRUCT_ALIGN
+#
+# RES_* macros take a name, a count and an optional alignment.
+# The count in in terms of the base size of the macro, and the
+# default alignment is the base size.
+# The macros are:
+# Macro Base size
+# RES_B 1
+# RES_W 2
+# RES_D 4
+# RES_Q 8
+# RES_DQ 16
+# RES_Y 32
+# RES_Z 64
+#
+# RES_U defines a union. It's arguments are a name and two or more
+# pairs of "size, alignment"
+#
+# The two assigns are only needed if this structure is being nested
+# within another. Even if the assigns are not done, one can still use
+# STRUCT_NAME_size as the size of the structure.
+#
+# Note that for nesting, you still need to assign to STRUCT_NAME_size.
+#
+# The differences between this and using "struc" directly are that each
+# type is implicitly aligned to its natural length (although this can be
+# over-ridden with an explicit third parameter), and that the structure
+# is padded at the end to its overall alignment.
+#
+
+#########################################################################
+
+#ifndef _SHA1_MB_MGR_DATASTRUCT_ASM_
+#define _SHA1_MB_MGR_DATASTRUCT_ASM_
+
+## START_FIELDS
+.macro START_FIELDS
+ _FIELD_OFFSET = 0
+ _STRUCT_ALIGN = 0
+.endm
+
+## FIELD name size align
+.macro FIELD name size align
+ _FIELD_OFFSET = (_FIELD_OFFSET + (\align) - 1) & (~ ((\align)-1))
+ \name = _FIELD_OFFSET
+ _FIELD_OFFSET = _FIELD_OFFSET + (\size)
+.if (\align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = \align
+.endif
+.endm
+
+## END_FIELDS
+.macro END_FIELDS
+ _FIELD_OFFSET = (_FIELD_OFFSET + _STRUCT_ALIGN-1) & (~ (_STRUCT_ALIGN-1))
+.endm
+
+########################################################################
+
+.macro STRUCT p1
+START_FIELDS
+.struc \p1
+.endm
+
+.macro ENDSTRUCT
+ tmp = _FIELD_OFFSET
+ END_FIELDS
+ tmp = (_FIELD_OFFSET - %%tmp)
+.if (tmp > 0)
+ .lcomm tmp
+.endif
+.endstruc
+.endm
+
+## RES_int name size align
+.macro RES_int p1 p2 p3
+ name = \p1
+ size = \p2
+ align = .\p3
+
+ _FIELD_OFFSET = (_FIELD_OFFSET + (align) - 1) & (~ ((align)-1))
+.align align
+.lcomm name size
+ _FIELD_OFFSET = _FIELD_OFFSET + (size)
+.if (align > _STRUCT_ALIGN)
+ _STRUCT_ALIGN = align
+.endif
+.endm
+
+
+
+# macro RES_B name, size [, align]
+.macro RES_B _name, _size, _align=1
+RES_int _name _size _align
+.endm
+
+# macro RES_W name, size [, align]
+.macro RES_W _name, _size, _align=2
+RES_int _name 2*(_size) _align
+.endm
+
+# macro RES_D name, size [, align]
+.macro RES_D _name, _size, _align=4
+RES_int _name 4*(_size) _align
+.endm
+
+# macro RES_Q name, size [, align]
+.macro RES_Q _name, _size, _align=8
+RES_int _name 8*(_size) _align
+.endm
+
+# macro RES_DQ name, size [, align]
+.macro RES_DQ _name, _size, _align=16
+RES_int _name 16*(_size) _align
+.endm
+
+# macro RES_Y name, size [, align]
+.macro RES_Y _name, _size, _align=32
+RES_int _name 32*(_size) _align
+.endm
+
+# macro RES_Z name, size [, align]
+.macro RES_Z _name, _size, _align=64
+RES_int _name 64*(_size) _align
+.endm
+
+
+#endif
+
+########################################################################
+#### Define constants
+########################################################################
+
+########################################################################
+#### Define SHA1 Out Of Order Data Structures
+########################################################################
+
+START_FIELDS # LANE_DATA
+### name size align
+FIELD _job_in_lane, 8, 8 # pointer to job object
+END_FIELDS
+
+_LANE_DATA_size = _FIELD_OFFSET
+_LANE_DATA_align = _STRUCT_ALIGN
+
+########################################################################
+
+START_FIELDS # SHA1_ARGS_X8
+### name size align
+FIELD _digest, 4*5*8, 16 # transposed digest
+FIELD _data_ptr, 8*8, 8 # array of pointers to data
+END_FIELDS
+
+_SHA1_ARGS_X4_size = _FIELD_OFFSET
+_SHA1_ARGS_X4_align = _STRUCT_ALIGN
+_SHA1_ARGS_X8_size = _FIELD_OFFSET
+_SHA1_ARGS_X8_align = _STRUCT_ALIGN
+
+########################################################################
+
+START_FIELDS # MB_MGR
+### name size align
+FIELD _args, _SHA1_ARGS_X4_size, _SHA1_ARGS_X4_align
+FIELD _lens, 4*8, 8
+FIELD _unused_lanes, 8, 8
+FIELD _ldata, _LANE_DATA_size*8, _LANE_DATA_align
+END_FIELDS
+
+_MB_MGR_size = _FIELD_OFFSET
+_MB_MGR_align = _STRUCT_ALIGN
+
+_args_digest = _args + _digest
+_args_data_ptr = _args + _data_ptr
+
+
+########################################################################
+#### Define constants
+########################################################################
+
+#define STS_UNKNOWN 0
+#define STS_BEING_PROCESSED 1
+#define STS_COMPLETED 2
+
+########################################################################
+#### Define JOB_SHA1 structure
+########################################################################
+
+START_FIELDS # JOB_SHA1
+
+### name size align
+FIELD _buffer, 8, 8 # pointer to buffer
+FIELD _len, 4, 4 # length in bytes
+FIELD _result_digest, 5*4, 32 # Digest (output)
+FIELD _status, 4, 4
+FIELD _user_data, 8, 8
+END_FIELDS
+
+_JOB_SHA1_size = _FIELD_OFFSET
+_JOB_SHA1_align = _STRUCT_ALIGN
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
new file mode 100644
index 000000000000..85c4e1cf7172
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_flush_avx2.S
@@ -0,0 +1,327 @@
+/*
+ * Flush routine for SHA1 multibuffer
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#include <linux/linkage.h>
+#include "sha1_mb_mgr_datastruct.S"
+
+
+.extern sha1_x8_avx2
+
+# LINUX register definitions
+#define arg1 %rdi
+#define arg2 %rsi
+
+# Common definitions
+#define state arg1
+#define job arg2
+#define len2 arg2
+
+# idx must be a register not clobbered by sha1_x8_avx2
+#define idx %r8
+#define DWORD_idx %r8d
+
+#define unused_lanes %rbx
+#define lane_data %rbx
+#define tmp2 %rbx
+#define tmp2_w %ebx
+
+#define job_rax %rax
+#define tmp1 %rax
+#define size_offset %rax
+#define tmp %rax
+#define start_offset %rax
+
+#define tmp3 %arg1
+
+#define extra_blocks %arg2
+#define p %arg2
+
+
+# STACK_SPACE needs to be an odd multiple of 8
+_XMM_SAVE_SIZE = 10*16
+_GPR_SAVE_SIZE = 8*8
+_ALIGN_SIZE = 8
+
+_XMM_SAVE = 0
+_GPR_SAVE = _XMM_SAVE + _XMM_SAVE_SIZE
+STACK_SPACE = _GPR_SAVE + _GPR_SAVE_SIZE + _ALIGN_SIZE
+
+.macro LABEL prefix n
+\prefix\n\():
+.endm
+
+.macro JNE_SKIP i
+jne skip_\i
+.endm
+
+.altmacro
+.macro SET_OFFSET _offset
+offset = \_offset
+.endm
+.noaltmacro
+
+# JOB* sha1_mb_mgr_flush_avx2(MB_MGR *state)
+# arg 1 : rcx : state
+ENTRY(sha1_mb_mgr_flush_avx2)
+ mov %rsp, %r10
+ sub $STACK_SPACE, %rsp
+ and $~31, %rsp
+ mov %rbx, _GPR_SAVE(%rsp)
+ mov %r10, _GPR_SAVE+8*1(%rsp) #save rsp
+ mov %rbp, _GPR_SAVE+8*3(%rsp)
+ mov %r12, _GPR_SAVE+8*4(%rsp)
+ mov %r13, _GPR_SAVE+8*5(%rsp)
+ mov %r14, _GPR_SAVE+8*6(%rsp)
+ mov %r15, _GPR_SAVE+8*7(%rsp)
+
+ # If bit (32+3) is set, then all lanes are empty
+ mov _unused_lanes(state), unused_lanes
+ bt $32+3, unused_lanes
+ jc return_null
+
+ # find a lane with a non-null job
+ xor idx, idx
+ offset = (_ldata + 1 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne one(%rip), idx
+ offset = (_ldata + 2 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne two(%rip), idx
+ offset = (_ldata + 3 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne three(%rip), idx
+ offset = (_ldata + 4 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne four(%rip), idx
+ offset = (_ldata + 5 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne five(%rip), idx
+ offset = (_ldata + 6 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne six(%rip), idx
+ offset = (_ldata + 7 * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+ cmovne seven(%rip), idx
+
+ # copy idx to empty lanes
+copy_lane_data:
+ offset = (_args + _data_ptr)
+ mov offset(state,idx,8), tmp
+
+ I = 0
+.rep 8
+ offset = (_ldata + I * _LANE_DATA_size + _job_in_lane)
+ cmpq $0, offset(state)
+.altmacro
+ JNE_SKIP %I
+ offset = (_args + _data_ptr + 8*I)
+ mov tmp, offset(state)
+ offset = (_lens + 4*I)
+ movl $0xFFFFFFFF, offset(state)
+LABEL skip_ %I
+ I = (I+1)
+.noaltmacro
+.endr
+
+ # Find min length
+ vmovdqa _lens+0*16(state), %xmm0
+ vmovdqa _lens+1*16(state), %xmm1
+
+ vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
+ vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
+ vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
+ vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
+ vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min value in low dword
+
+ vmovd %xmm2, DWORD_idx
+ mov idx, len2
+ and $0xF, idx
+ shr $4, len2
+ jz len_is_0
+
+ vpand clear_low_nibble(%rip), %xmm2, %xmm2
+ vpshufd $0, %xmm2, %xmm2
+
+ vpsubd %xmm2, %xmm0, %xmm0
+ vpsubd %xmm2, %xmm1, %xmm1
+
+ vmovdqa %xmm0, _lens+0*16(state)
+ vmovdqa %xmm1, _lens+1*16(state)
+
+ # "state" and "args" are the same address, arg1
+ # len is arg2
+ call sha1_x8_avx2
+ # state and idx are intact
+
+
+len_is_0:
+ # process completed job "idx"
+ imul $_LANE_DATA_size, idx, lane_data
+ lea _ldata(state, lane_data), lane_data
+
+ mov _job_in_lane(lane_data), job_rax
+ movq $0, _job_in_lane(lane_data)
+ movl $STS_COMPLETED, _status(job_rax)
+ mov _unused_lanes(state), unused_lanes
+ shl $4, unused_lanes
+ or idx, unused_lanes
+ mov unused_lanes, _unused_lanes(state)
+
+ movl $0xFFFFFFFF, _lens(state, idx, 4)
+
+ vmovd _args_digest(state , idx, 4) , %xmm0
+ vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
+ vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
+ vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
+ movl _args_digest+4*32(state, idx, 4), tmp2_w
+
+ vmovdqu %xmm0, _result_digest(job_rax)
+ offset = (_result_digest + 1*16)
+ mov tmp2_w, offset(job_rax)
+
+return:
+
+ mov _GPR_SAVE(%rsp), %rbx
+ mov _GPR_SAVE+8*1(%rsp), %r10 #saved rsp
+ mov _GPR_SAVE+8*3(%rsp), %rbp
+ mov _GPR_SAVE+8*4(%rsp), %r12
+ mov _GPR_SAVE+8*5(%rsp), %r13
+ mov _GPR_SAVE+8*6(%rsp), %r14
+ mov _GPR_SAVE+8*7(%rsp), %r15
+ mov %r10, %rsp
+
+ ret
+
+return_null:
+ xor job_rax, job_rax
+ jmp return
+ENDPROC(sha1_mb_mgr_flush_avx2)
+
+
+#################################################################
+
+.align 16
+ENTRY(sha1_mb_mgr_get_comp_job_avx2)
+ push %rbx
+
+ ## if bit 32+3 is set, then all lanes are empty
+ mov _unused_lanes(state), unused_lanes
+ bt $(32+3), unused_lanes
+ jc .return_null
+
+ # Find min length
+ vmovdqa _lens(state), %xmm0
+ vmovdqa _lens+1*16(state), %xmm1
+
+ vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
+ vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
+ vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
+ vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
+ vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min value in low dword
+
+ vmovd %xmm2, DWORD_idx
+ test $~0xF, idx
+ jnz .return_null
+
+ # process completed job "idx"
+ imul $_LANE_DATA_size, idx, lane_data
+ lea _ldata(state, lane_data), lane_data
+
+ mov _job_in_lane(lane_data), job_rax
+ movq $0, _job_in_lane(lane_data)
+ movl $STS_COMPLETED, _status(job_rax)
+ mov _unused_lanes(state), unused_lanes
+ shl $4, unused_lanes
+ or idx, unused_lanes
+ mov unused_lanes, _unused_lanes(state)
+
+ movl $0xFFFFFFFF, _lens(state, idx, 4)
+
+ vmovd _args_digest(state, idx, 4), %xmm0
+ vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
+ vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
+ vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
+ movl _args_digest+4*32(state, idx, 4), tmp2_w
+
+ vmovdqu %xmm0, _result_digest(job_rax)
+ movl tmp2_w, _result_digest+1*16(job_rax)
+
+ pop %rbx
+
+ ret
+
+.return_null:
+ xor job_rax, job_rax
+ pop %rbx
+ ret
+ENDPROC(sha1_mb_mgr_get_comp_job_avx2)
+
+.data
+
+.align 16
+clear_low_nibble:
+.octa 0x000000000000000000000000FFFFFFF0
+one:
+.quad 1
+two:
+.quad 2
+three:
+.quad 3
+four:
+.quad 4
+five:
+.quad 5
+six:
+.quad 6
+seven:
+.quad 7
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c b/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
new file mode 100644
index 000000000000..4ca7e166a2aa
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_init_avx2.c
@@ -0,0 +1,64 @@
+/*
+ * Initialization code for multi buffer SHA1 algorithm for AVX2
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include "sha_mb_mgr.h"
+
+void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state)
+{
+ unsigned int j;
+ state->unused_lanes = 0xF76543210;
+ for (j = 0; j < 8; j++) {
+ state->lens[j] = 0xFFFFFFFF;
+ state->ldata[j].job_in_lane = NULL;
+ }
+}
diff --git a/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S b/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
new file mode 100644
index 000000000000..2ab9560b53c8
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha1_mb_mgr_submit_avx2.S
@@ -0,0 +1,228 @@
+/*
+ * Buffer submit code for multi buffer SHA1 algorithm
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include "sha1_mb_mgr_datastruct.S"
+
+
+.extern sha1_x8_avx
+
+# LINUX register definitions
+arg1 = %rdi
+arg2 = %rsi
+size_offset = %rcx
+tmp2 = %rcx
+extra_blocks = %rdx
+
+# Common definitions
+#define state arg1
+#define job %rsi
+#define len2 arg2
+#define p2 arg2
+
+# idx must be a register not clobberred by sha1_x8_avx2
+idx = %r8
+DWORD_idx = %r8d
+last_len = %r8
+
+p = %r11
+start_offset = %r11
+
+unused_lanes = %rbx
+BYTE_unused_lanes = %bl
+
+job_rax = %rax
+len = %rax
+DWORD_len = %eax
+
+lane = %rbp
+tmp3 = %rbp
+
+tmp = %r9
+DWORD_tmp = %r9d
+
+lane_data = %r10
+
+# STACK_SPACE needs to be an odd multiple of 8
+STACK_SPACE = 8*8 + 16*10 + 8
+
+# JOB* submit_mb_mgr_submit_avx2(MB_MGR *state, job_sha1 *job)
+# arg 1 : rcx : state
+# arg 2 : rdx : job
+ENTRY(sha1_mb_mgr_submit_avx2)
+
+ mov %rsp, %r10
+ sub $STACK_SPACE, %rsp
+ and $~31, %rsp
+
+ mov %rbx, (%rsp)
+ mov %r10, 8*2(%rsp) #save old rsp
+ mov %rbp, 8*3(%rsp)
+ mov %r12, 8*4(%rsp)
+ mov %r13, 8*5(%rsp)
+ mov %r14, 8*6(%rsp)
+ mov %r15, 8*7(%rsp)
+
+ mov _unused_lanes(state), unused_lanes
+ mov unused_lanes, lane
+ and $0xF, lane
+ shr $4, unused_lanes
+ imul $_LANE_DATA_size, lane, lane_data
+ movl $STS_BEING_PROCESSED, _status(job)
+ lea _ldata(state, lane_data), lane_data
+ mov unused_lanes, _unused_lanes(state)
+ movl _len(job), DWORD_len
+
+ mov job, _job_in_lane(lane_data)
+ shl $4, len
+ or lane, len
+
+ movl DWORD_len, _lens(state , lane, 4)
+
+ # Load digest words from result_digest
+ vmovdqu _result_digest(job), %xmm0
+ mov _result_digest+1*16(job), DWORD_tmp
+ vmovd %xmm0, _args_digest(state, lane, 4)
+ vpextrd $1, %xmm0, _args_digest+1*32(state , lane, 4)
+ vpextrd $2, %xmm0, _args_digest+2*32(state , lane, 4)
+ vpextrd $3, %xmm0, _args_digest+3*32(state , lane, 4)
+ movl DWORD_tmp, _args_digest+4*32(state , lane, 4)
+
+ mov _buffer(job), p
+ mov p, _args_data_ptr(state, lane, 8)
+
+ cmp $0xF, unused_lanes
+ jne return_null
+
+start_loop:
+ # Find min length
+ vmovdqa _lens(state), %xmm0
+ vmovdqa _lens+1*16(state), %xmm1
+
+ vpminud %xmm1, %xmm0, %xmm2 # xmm2 has {D,C,B,A}
+ vpalignr $8, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,D,C}
+ vpminud %xmm3, %xmm2, %xmm2 # xmm2 has {x,x,E,F}
+ vpalignr $4, %xmm2, %xmm3, %xmm3 # xmm3 has {x,x,x,E}
+ vpminud %xmm3, %xmm2, %xmm2 # xmm2 has min value in low dword
+
+ vmovd %xmm2, DWORD_idx
+ mov idx, len2
+ and $0xF, idx
+ shr $4, len2
+ jz len_is_0
+
+ vpand clear_low_nibble(%rip), %xmm2, %xmm2
+ vpshufd $0, %xmm2, %xmm2
+
+ vpsubd %xmm2, %xmm0, %xmm0
+ vpsubd %xmm2, %xmm1, %xmm1
+
+ vmovdqa %xmm0, _lens + 0*16(state)
+ vmovdqa %xmm1, _lens + 1*16(state)
+
+
+ # "state" and "args" are the same address, arg1
+ # len is arg2
+ call sha1_x8_avx2
+
+ # state and idx are intact
+
+len_is_0:
+ # process completed job "idx"
+ imul $_LANE_DATA_size, idx, lane_data
+ lea _ldata(state, lane_data), lane_data
+
+ mov _job_in_lane(lane_data), job_rax
+ mov _unused_lanes(state), unused_lanes
+ movq $0, _job_in_lane(lane_data)
+ movl $STS_COMPLETED, _status(job_rax)
+ shl $4, unused_lanes
+ or idx, unused_lanes
+ mov unused_lanes, _unused_lanes(state)
+
+ movl $0xFFFFFFFF, _lens(state, idx, 4)
+
+ vmovd _args_digest(state, idx, 4), %xmm0
+ vpinsrd $1, _args_digest+1*32(state , idx, 4), %xmm0, %xmm0
+ vpinsrd $2, _args_digest+2*32(state , idx, 4), %xmm0, %xmm0
+ vpinsrd $3, _args_digest+3*32(state , idx, 4), %xmm0, %xmm0
+ movl 4*32(state, idx, 4), DWORD_tmp
+
+ vmovdqu %xmm0, _result_digest(job_rax)
+ movl DWORD_tmp, _result_digest+1*16(job_rax)
+
+return:
+
+ mov (%rsp), %rbx
+ mov 8*2(%rsp), %r10 #save old rsp
+ mov 8*3(%rsp), %rbp
+ mov 8*4(%rsp), %r12
+ mov 8*5(%rsp), %r13
+ mov 8*6(%rsp), %r14
+ mov 8*7(%rsp), %r15
+ mov %r10, %rsp
+
+ ret
+
+return_null:
+ xor job_rax, job_rax
+ jmp return
+
+ENDPROC(sha1_mb_mgr_submit_avx2)
+
+.data
+
+.align 16
+clear_low_nibble:
+ .octa 0x000000000000000000000000FFFFFFF0
diff --git a/arch/x86/crypto/sha-mb/sha1_x8_avx2.S b/arch/x86/crypto/sha-mb/sha1_x8_avx2.S
new file mode 100644
index 000000000000..8e1b47792b31
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha1_x8_avx2.S
@@ -0,0 +1,472 @@
+/*
+ * Multi-buffer SHA1 algorithm hash compute routine
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/linkage.h>
+#include "sha1_mb_mgr_datastruct.S"
+
+## code to compute oct SHA1 using SSE-256
+## outer calling routine takes care of save and restore of XMM registers
+
+## Function clobbers: rax, rcx, rdx, rbx, rsi, rdi, r9-r15# ymm0-15
+##
+## Linux clobbers: rax rbx rcx rdx rsi r9 r10 r11 r12 r13 r14 r15
+## Linux preserves: rdi rbp r8
+##
+## clobbers ymm0-15
+
+
+# TRANSPOSE8 r0, r1, r2, r3, r4, r5, r6, r7, t0, t1
+# "transpose" data in {r0...r7} using temps {t0...t1}
+# Input looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
+# r0 = {a7 a6 a5 a4 a3 a2 a1 a0}
+# r1 = {b7 b6 b5 b4 b3 b2 b1 b0}
+# r2 = {c7 c6 c5 c4 c3 c2 c1 c0}
+# r3 = {d7 d6 d5 d4 d3 d2 d1 d0}
+# r4 = {e7 e6 e5 e4 e3 e2 e1 e0}
+# r5 = {f7 f6 f5 f4 f3 f2 f1 f0}
+# r6 = {g7 g6 g5 g4 g3 g2 g1 g0}
+# r7 = {h7 h6 h5 h4 h3 h2 h1 h0}
+#
+# Output looks like: {r0 r1 r2 r3 r4 r5 r6 r7}
+# r0 = {h0 g0 f0 e0 d0 c0 b0 a0}
+# r1 = {h1 g1 f1 e1 d1 c1 b1 a1}
+# r2 = {h2 g2 f2 e2 d2 c2 b2 a2}
+# r3 = {h3 g3 f3 e3 d3 c3 b3 a3}
+# r4 = {h4 g4 f4 e4 d4 c4 b4 a4}
+# r5 = {h5 g5 f5 e5 d5 c5 b5 a5}
+# r6 = {h6 g6 f6 e6 d6 c6 b6 a6}
+# r7 = {h7 g7 f7 e7 d7 c7 b7 a7}
+#
+
+.macro TRANSPOSE8 r0 r1 r2 r3 r4 r5 r6 r7 t0 t1
+ # process top half (r0..r3) {a...d}
+ vshufps $0x44, \r1, \r0, \t0 # t0 = {b5 b4 a5 a4 b1 b0 a1 a0}
+ vshufps $0xEE, \r1, \r0, \r0 # r0 = {b7 b6 a7 a6 b3 b2 a3 a2}
+ vshufps $0x44, \r3, \r2, \t1 # t1 = {d5 d4 c5 c4 d1 d0 c1 c0}
+ vshufps $0xEE, \r3, \r2, \r2 # r2 = {d7 d6 c7 c6 d3 d2 c3 c2}
+ vshufps $0xDD, \t1, \t0, \r3 # r3 = {d5 c5 b5 a5 d1 c1 b1 a1}
+ vshufps $0x88, \r2, \r0, \r1 # r1 = {d6 c6 b6 a6 d2 c2 b2 a2}
+ vshufps $0xDD, \r2, \r0, \r0 # r0 = {d7 c7 b7 a7 d3 c3 b3 a3}
+ vshufps $0x88, \t1, \t0, \t0 # t0 = {d4 c4 b4 a4 d0 c0 b0 a0}
+
+ # use r2 in place of t0
+ # process bottom half (r4..r7) {e...h}
+ vshufps $0x44, \r5, \r4, \r2 # r2 = {f5 f4 e5 e4 f1 f0 e1 e0}
+ vshufps $0xEE, \r5, \r4, \r4 # r4 = {f7 f6 e7 e6 f3 f2 e3 e2}
+ vshufps $0x44, \r7, \r6, \t1 # t1 = {h5 h4 g5 g4 h1 h0 g1 g0}
+ vshufps $0xEE, \r7, \r6, \r6 # r6 = {h7 h6 g7 g6 h3 h2 g3 g2}
+ vshufps $0xDD, \t1, \r2, \r7 # r7 = {h5 g5 f5 e5 h1 g1 f1 e1}
+ vshufps $0x88, \r6, \r4, \r5 # r5 = {h6 g6 f6 e6 h2 g2 f2 e2}
+ vshufps $0xDD, \r6, \r4, \r4 # r4 = {h7 g7 f7 e7 h3 g3 f3 e3}
+ vshufps $0x88, \t1, \r2, \t1 # t1 = {h4 g4 f4 e4 h0 g0 f0 e0}
+
+ vperm2f128 $0x13, \r1, \r5, \r6 # h6...a6
+ vperm2f128 $0x02, \r1, \r5, \r2 # h2...a2
+ vperm2f128 $0x13, \r3, \r7, \r5 # h5...a5
+ vperm2f128 $0x02, \r3, \r7, \r1 # h1...a1
+ vperm2f128 $0x13, \r0, \r4, \r7 # h7...a7
+ vperm2f128 $0x02, \r0, \r4, \r3 # h3...a3
+ vperm2f128 $0x13, \t0, \t1, \r4 # h4...a4
+ vperm2f128 $0x02, \t0, \t1, \r0 # h0...a0
+
+.endm
+##
+## Magic functions defined in FIPS 180-1
+##
+# macro MAGIC_F0 F,B,C,D,T ## F = (D ^ (B & (C ^ D)))
+.macro MAGIC_F0 regF regB regC regD regT
+ vpxor \regD, \regC, \regF
+ vpand \regB, \regF, \regF
+ vpxor \regD, \regF, \regF
+.endm
+
+# macro MAGIC_F1 F,B,C,D,T ## F = (B ^ C ^ D)
+.macro MAGIC_F1 regF regB regC regD regT
+ vpxor \regC, \regD, \regF
+ vpxor \regB, \regF, \regF
+.endm
+
+# macro MAGIC_F2 F,B,C,D,T ## F = ((B & C) | (B & D) | (C & D))
+.macro MAGIC_F2 regF regB regC regD regT
+ vpor \regC, \regB, \regF
+ vpand \regC, \regB, \regT
+ vpand \regD, \regF, \regF
+ vpor \regT, \regF, \regF
+.endm
+
+# macro MAGIC_F3 F,B,C,D,T ## F = (B ^ C ^ D)
+.macro MAGIC_F3 regF regB regC regD regT
+ MAGIC_F1 \regF,\regB,\regC,\regD,\regT
+.endm
+
+# PROLD reg, imm, tmp
+.macro PROLD reg imm tmp
+ vpsrld $(32-\imm), \reg, \tmp
+ vpslld $\imm, \reg, \reg
+ vpor \tmp, \reg, \reg
+.endm
+
+.macro PROLD_nd reg imm tmp src
+ vpsrld $(32-\imm), \src, \tmp
+ vpslld $\imm, \src, \reg
+ vpor \tmp, \reg, \reg
+.endm
+
+.macro SHA1_STEP_00_15 regA regB regC regD regE regT regF memW immCNT MAGIC
+ vpaddd \immCNT, \regE, \regE
+ vpaddd \memW*32(%rsp), \regE, \regE
+ PROLD_nd \regT, 5, \regF, \regA
+ vpaddd \regT, \regE, \regE
+ \MAGIC \regF, \regB, \regC, \regD, \regT
+ PROLD \regB, 30, \regT
+ vpaddd \regF, \regE, \regE
+.endm
+
+.macro SHA1_STEP_16_79 regA regB regC regD regE regT regF memW immCNT MAGIC
+ vpaddd \immCNT, \regE, \regE
+ offset = ((\memW - 14) & 15) * 32
+ vmovdqu offset(%rsp), W14
+ vpxor W14, W16, W16
+ offset = ((\memW - 8) & 15) * 32
+ vpxor offset(%rsp), W16, W16
+ offset = ((\memW - 3) & 15) * 32
+ vpxor offset(%rsp), W16, W16
+ vpsrld $(32-1), W16, \regF
+ vpslld $1, W16, W16
+ vpor W16, \regF, \regF
+
+ ROTATE_W
+
+ offset = ((\memW - 0) & 15) * 32
+ vmovdqu \regF, offset(%rsp)
+ vpaddd \regF, \regE, \regE
+ PROLD_nd \regT, 5, \regF, \regA
+ vpaddd \regT, \regE, \regE
+ \MAGIC \regF,\regB,\regC,\regD,\regT ## FUN = MAGIC_Fi(B,C,D)
+ PROLD \regB,30, \regT
+ vpaddd \regF, \regE, \regE
+.endm
+
+########################################################################
+########################################################################
+########################################################################
+
+## FRAMESZ plus pushes must be an odd multiple of 8
+YMM_SAVE = (15-15)*32
+FRAMESZ = 32*16 + YMM_SAVE
+_YMM = FRAMESZ - YMM_SAVE
+
+#define VMOVPS vmovups
+
+IDX = %rax
+inp0 = %r9
+inp1 = %r10
+inp2 = %r11
+inp3 = %r12
+inp4 = %r13
+inp5 = %r14
+inp6 = %r15
+inp7 = %rcx
+arg1 = %rdi
+arg2 = %rsi
+RSP_SAVE = %rdx
+
+# ymm0 A
+# ymm1 B
+# ymm2 C
+# ymm3 D
+# ymm4 E
+# ymm5 F AA
+# ymm6 T0 BB
+# ymm7 T1 CC
+# ymm8 T2 DD
+# ymm9 T3 EE
+# ymm10 T4 TMP
+# ymm11 T5 FUN
+# ymm12 T6 K
+# ymm13 T7 W14
+# ymm14 T8 W15
+# ymm15 T9 W16
+
+
+A = %ymm0
+B = %ymm1
+C = %ymm2
+D = %ymm3
+E = %ymm4
+F = %ymm5
+T0 = %ymm6
+T1 = %ymm7
+T2 = %ymm8
+T3 = %ymm9
+T4 = %ymm10
+T5 = %ymm11
+T6 = %ymm12
+T7 = %ymm13
+T8 = %ymm14
+T9 = %ymm15
+
+AA = %ymm5
+BB = %ymm6
+CC = %ymm7
+DD = %ymm8
+EE = %ymm9
+TMP = %ymm10
+FUN = %ymm11
+K = %ymm12
+W14 = %ymm13
+W15 = %ymm14
+W16 = %ymm15
+
+.macro ROTATE_ARGS
+ TMP_ = E
+ E = D
+ D = C
+ C = B
+ B = A
+ A = TMP_
+.endm
+
+.macro ROTATE_W
+TMP_ = W16
+W16 = W15
+W15 = W14
+W14 = TMP_
+.endm
+
+# 8 streams x 5 32bit words per digest x 4 bytes per word
+#define DIGEST_SIZE (8*5*4)
+
+.align 32
+
+# void sha1_x8_avx2(void **input_data, UINT128 *digest, UINT32 size)
+# arg 1 : pointer to array[4] of pointer to input data
+# arg 2 : size (in blocks) ;; assumed to be >= 1
+#
+ENTRY(sha1_x8_avx2)
+
+ push RSP_SAVE
+
+ #save rsp
+ mov %rsp, RSP_SAVE
+ sub $FRAMESZ, %rsp
+
+ #align rsp to 32 Bytes
+ and $~0x1F, %rsp
+
+ ## Initialize digests
+ vmovdqu 0*32(arg1), A
+ vmovdqu 1*32(arg1), B
+ vmovdqu 2*32(arg1), C
+ vmovdqu 3*32(arg1), D
+ vmovdqu 4*32(arg1), E
+
+ ## transpose input onto stack
+ mov _data_ptr+0*8(arg1),inp0
+ mov _data_ptr+1*8(arg1),inp1
+ mov _data_ptr+2*8(arg1),inp2
+ mov _data_ptr+3*8(arg1),inp3
+ mov _data_ptr+4*8(arg1),inp4
+ mov _data_ptr+5*8(arg1),inp5
+ mov _data_ptr+6*8(arg1),inp6
+ mov _data_ptr+7*8(arg1),inp7
+
+ xor IDX, IDX
+lloop:
+ vmovdqu PSHUFFLE_BYTE_FLIP_MASK(%rip), F
+ I=0
+.rep 2
+ VMOVPS (inp0, IDX), T0
+ VMOVPS (inp1, IDX), T1
+ VMOVPS (inp2, IDX), T2
+ VMOVPS (inp3, IDX), T3
+ VMOVPS (inp4, IDX), T4
+ VMOVPS (inp5, IDX), T5
+ VMOVPS (inp6, IDX), T6
+ VMOVPS (inp7, IDX), T7
+
+ TRANSPOSE8 T0, T1, T2, T3, T4, T5, T6, T7, T8, T9
+ vpshufb F, T0, T0
+ vmovdqu T0, (I*8)*32(%rsp)
+ vpshufb F, T1, T1
+ vmovdqu T1, (I*8+1)*32(%rsp)
+ vpshufb F, T2, T2
+ vmovdqu T2, (I*8+2)*32(%rsp)
+ vpshufb F, T3, T3
+ vmovdqu T3, (I*8+3)*32(%rsp)
+ vpshufb F, T4, T4
+ vmovdqu T4, (I*8+4)*32(%rsp)
+ vpshufb F, T5, T5
+ vmovdqu T5, (I*8+5)*32(%rsp)
+ vpshufb F, T6, T6
+ vmovdqu T6, (I*8+6)*32(%rsp)
+ vpshufb F, T7, T7
+ vmovdqu T7, (I*8+7)*32(%rsp)
+ add $32, IDX
+ I = (I+1)
+.endr
+ # save old digests
+ vmovdqu A,AA
+ vmovdqu B,BB
+ vmovdqu C,CC
+ vmovdqu D,DD
+ vmovdqu E,EE
+
+##
+## perform 0-79 steps
+##
+ vmovdqu K00_19(%rip), K
+## do rounds 0...15
+ I = 0
+.rep 16
+ SHA1_STEP_00_15 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F0
+ ROTATE_ARGS
+ I = (I+1)
+.endr
+
+## do rounds 16...19
+ vmovdqu ((16 - 16) & 15) * 32 (%rsp), W16
+ vmovdqu ((16 - 15) & 15) * 32 (%rsp), W15
+.rep 4
+ SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F0
+ ROTATE_ARGS
+ I = (I+1)
+.endr
+
+## do rounds 20...39
+ vmovdqu K20_39(%rip), K
+.rep 20
+ SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F1
+ ROTATE_ARGS
+ I = (I+1)
+.endr
+
+## do rounds 40...59
+ vmovdqu K40_59(%rip), K
+.rep 20
+ SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F2
+ ROTATE_ARGS
+ I = (I+1)
+.endr
+
+## do rounds 60...79
+ vmovdqu K60_79(%rip), K
+.rep 20
+ SHA1_STEP_16_79 A,B,C,D,E, TMP,FUN, I, K, MAGIC_F3
+ ROTATE_ARGS
+ I = (I+1)
+.endr
+
+ vpaddd AA,A,A
+ vpaddd BB,B,B
+ vpaddd CC,C,C
+ vpaddd DD,D,D
+ vpaddd EE,E,E
+
+ sub $1, arg2
+ jne lloop
+
+ # write out digests
+ vmovdqu A, 0*32(arg1)
+ vmovdqu B, 1*32(arg1)
+ vmovdqu C, 2*32(arg1)
+ vmovdqu D, 3*32(arg1)
+ vmovdqu E, 4*32(arg1)
+
+ # update input pointers
+ add IDX, inp0
+ add IDX, inp1
+ add IDX, inp2
+ add IDX, inp3
+ add IDX, inp4
+ add IDX, inp5
+ add IDX, inp6
+ add IDX, inp7
+ mov inp0, _data_ptr (arg1)
+ mov inp1, _data_ptr + 1*8(arg1)
+ mov inp2, _data_ptr + 2*8(arg1)
+ mov inp3, _data_ptr + 3*8(arg1)
+ mov inp4, _data_ptr + 4*8(arg1)
+ mov inp5, _data_ptr + 5*8(arg1)
+ mov inp6, _data_ptr + 6*8(arg1)
+ mov inp7, _data_ptr + 7*8(arg1)
+
+ ################
+ ## Postamble
+
+ mov RSP_SAVE, %rsp
+ pop RSP_SAVE
+
+ ret
+ENDPROC(sha1_x8_avx2)
+
+
+.data
+
+.align 32
+K00_19:
+.octa 0x5A8279995A8279995A8279995A827999
+.octa 0x5A8279995A8279995A8279995A827999
+K20_39:
+.octa 0x6ED9EBA16ED9EBA16ED9EBA16ED9EBA1
+.octa 0x6ED9EBA16ED9EBA16ED9EBA16ED9EBA1
+K40_59:
+.octa 0x8F1BBCDC8F1BBCDC8F1BBCDC8F1BBCDC
+.octa 0x8F1BBCDC8F1BBCDC8F1BBCDC8F1BBCDC
+K60_79:
+.octa 0xCA62C1D6CA62C1D6CA62C1D6CA62C1D6
+.octa 0xCA62C1D6CA62C1D6CA62C1D6CA62C1D6
+PSHUFFLE_BYTE_FLIP_MASK:
+.octa 0x0c0d0e0f08090a0b0405060700010203
+.octa 0x0c0d0e0f08090a0b0405060700010203
diff --git a/arch/x86/crypto/sha-mb/sha_mb_ctx.h b/arch/x86/crypto/sha-mb/sha_mb_ctx.h
new file mode 100644
index 000000000000..e36069d0c1bd
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha_mb_ctx.h
@@ -0,0 +1,136 @@
+/*
+ * Header file for multi buffer SHA context
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _SHA_MB_CTX_INTERNAL_H
+#define _SHA_MB_CTX_INTERNAL_H
+
+#include "sha_mb_mgr.h"
+
+#define HASH_UPDATE 0x00
+#define HASH_FIRST 0x01
+#define HASH_LAST 0x02
+#define HASH_ENTIRE 0x03
+#define HASH_DONE 0x04
+#define HASH_FINAL 0x08
+
+#define HASH_CTX_STS_IDLE 0x00
+#define HASH_CTX_STS_PROCESSING 0x01
+#define HASH_CTX_STS_LAST 0x02
+#define HASH_CTX_STS_COMPLETE 0x04
+
+enum hash_ctx_error {
+ HASH_CTX_ERROR_NONE = 0,
+ HASH_CTX_ERROR_INVALID_FLAGS = -1,
+ HASH_CTX_ERROR_ALREADY_PROCESSING = -2,
+ HASH_CTX_ERROR_ALREADY_COMPLETED = -3,
+
+#ifdef HASH_CTX_DEBUG
+ HASH_CTX_ERROR_DEBUG_DIGEST_MISMATCH = -4,
+#endif
+};
+
+
+#define hash_ctx_user_data(ctx) ((ctx)->user_data)
+#define hash_ctx_digest(ctx) ((ctx)->job.result_digest)
+#define hash_ctx_processing(ctx) ((ctx)->status & HASH_CTX_STS_PROCESSING)
+#define hash_ctx_complete(ctx) ((ctx)->status == HASH_CTX_STS_COMPLETE)
+#define hash_ctx_status(ctx) ((ctx)->status)
+#define hash_ctx_error(ctx) ((ctx)->error)
+#define hash_ctx_init(ctx) \
+ do { \
+ (ctx)->error = HASH_CTX_ERROR_NONE; \
+ (ctx)->status = HASH_CTX_STS_COMPLETE; \
+ } while (0)
+
+
+/* Hash Constants and Typedefs */
+#define SHA1_DIGEST_LENGTH 5
+#define SHA1_LOG2_BLOCK_SIZE 6
+
+#define SHA1_PADLENGTHFIELD_SIZE 8
+
+#ifdef SHA_MB_DEBUG
+#define assert(expr) \
+do { \
+ if (unlikely(!(expr))) { \
+ printk(KERN_ERR "Assertion failed! %s,%s,%s,line=%d\n", \
+ #expr, __FILE__, __func__, __LINE__); \
+ } \
+} while (0)
+#else
+#define assert(expr) do {} while (0)
+#endif
+
+struct sha1_ctx_mgr {
+ struct sha1_mb_mgr mgr;
+};
+
+/* typedef struct sha1_ctx_mgr sha1_ctx_mgr; */
+
+struct sha1_hash_ctx {
+ /* Must be at struct offset 0 */
+ struct job_sha1 job;
+ /* status flag */
+ int status;
+ /* error flag */
+ int error;
+
+ uint32_t total_length;
+ const void *incoming_buffer;
+ uint32_t incoming_buffer_length;
+ uint8_t partial_block_buffer[SHA1_BLOCK_SIZE * 2];
+ uint32_t partial_block_buffer_length;
+ void *user_data;
+};
+
+#endif
diff --git a/arch/x86/crypto/sha-mb/sha_mb_mgr.h b/arch/x86/crypto/sha-mb/sha_mb_mgr.h
new file mode 100644
index 000000000000..08ad1a9acfd7
--- /dev/null
+++ b/arch/x86/crypto/sha-mb/sha_mb_mgr.h
@@ -0,0 +1,110 @@
+/*
+ * Header file for multi buffer SHA1 algorithm manager
+ *
+ * This file is provided under a dual BSD/GPLv2 license. When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * Contact Information:
+ * James Guilford <james.guilford@intel.com>
+ * Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2014 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * * Redistributions of source code must retain the above copyright
+ * notice, this list of conditions and the following disclaimer.
+ * * Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in
+ * the documentation and/or other materials provided with the
+ * distribution.
+ * * Neither the name of Intel Corporation nor the names of its
+ * contributors may be used to endorse or promote products derived
+ * from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef __SHA_MB_MGR_H
+#define __SHA_MB_MGR_H
+
+
+#include <linux/types.h>
+
+#define NUM_SHA1_DIGEST_WORDS 5
+
+enum job_sts { STS_UNKNOWN = 0,
+ STS_BEING_PROCESSED = 1,
+ STS_COMPLETED = 2,
+ STS_INTERNAL_ERROR = 3,
+ STS_ERROR = 4
+};
+
+struct job_sha1 {
+ u8 *buffer;
+ u32 len;
+ u32 result_digest[NUM_SHA1_DIGEST_WORDS] __aligned(32);
+ enum job_sts status;
+ void *user_data;
+};
+
+/* SHA1 out-of-order scheduler */
+
+/* typedef uint32_t sha1_digest_array[5][8]; */
+
+struct sha1_args_x8 {
+ uint32_t digest[5][8];
+ uint8_t *data_ptr[8];
+};
+
+struct sha1_lane_data {
+ struct job_sha1 *job_in_lane;
+};
+
+struct sha1_mb_mgr {
+ struct sha1_args_x8 args;
+
+ uint32_t lens[8];
+
+ /* each byte is index (0...7) of unused lanes */
+ uint64_t unused_lanes;
+ /* byte 4 is set to FF as a flag */
+ struct sha1_lane_data ldata[8];
+};
+
+
+#define SHA1_MB_MGR_NUM_LANES_AVX2 8
+
+void sha1_mb_mgr_init_avx2(struct sha1_mb_mgr *state);
+struct job_sha1 *sha1_mb_mgr_submit_avx2(struct sha1_mb_mgr *state,
+ struct job_sha1 *job);
+struct job_sha1 *sha1_mb_mgr_flush_avx2(struct sha1_mb_mgr *state);
+struct job_sha1 *sha1_mb_mgr_get_comp_job_avx2(struct sha1_mb_mgr *state);
+
+#endif
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 74d16ef707c7..6c20fe04a738 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -278,4 +278,4 @@ module_exit(sha1_ssse3_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-MODULE_ALIAS("sha1");
+MODULE_ALIAS_CRYPTO("sha1");
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index f248546da1ca..8fad72f4dfd2 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -211,7 +211,7 @@ static int sha224_ssse3_final(struct shash_desc *desc, u8 *hash)
sha256_ssse3_final(desc, D);
memcpy(hash, D, SHA224_DIGEST_SIZE);
- memset(D, 0, SHA256_DIGEST_SIZE);
+ memzero_explicit(D, SHA256_DIGEST_SIZE);
return 0;
}
@@ -318,5 +318,5 @@ module_exit(sha256_ssse3_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-MODULE_ALIAS("sha256");
-MODULE_ALIAS("sha224");
+MODULE_ALIAS_CRYPTO("sha256");
+MODULE_ALIAS_CRYPTO("sha224");
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 8626b03e83b7..0b6af26832bf 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -219,7 +219,7 @@ static int sha384_ssse3_final(struct shash_desc *desc, u8 *hash)
sha512_ssse3_final(desc, D);
memcpy(hash, D, SHA384_DIGEST_SIZE);
- memset(D, 0, SHA512_DIGEST_SIZE);
+ memzero_explicit(D, SHA512_DIGEST_SIZE);
return 0;
}
@@ -326,5 +326,5 @@ module_exit(sha512_ssse3_mod_fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-MODULE_ALIAS("sha512");
-MODULE_ALIAS("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384");
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 4e3c665be129..1ac531ea9bcc 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -579,4 +579,4 @@ module_exit(twofish_exit);
MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized");
MODULE_LICENSE("GPL");
-MODULE_ALIAS("twofish");
+MODULE_ALIAS_CRYPTO("twofish");
diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c
index 0a5202303501..77e06c2da83d 100644
--- a/arch/x86/crypto/twofish_glue.c
+++ b/arch/x86/crypto/twofish_glue.c
@@ -96,5 +96,5 @@ module_exit(fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION ("Twofish Cipher Algorithm, asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 13e63b3e1dfb..56d8a08ee479 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -495,5 +495,5 @@ module_exit(fini);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Twofish Cipher Algorithm, 3-way parallel asm optimized");
-MODULE_ALIAS("twofish");
-MODULE_ALIAS("twofish-asm");
+MODULE_ALIAS_CRYPTO("twofish");
+MODULE_ALIAS_CRYPTO("twofish-asm");
diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c
index 5d7b381da692..2eccc8932ae6 100644
--- a/arch/x86/ia32/audit.c
+++ b/arch/x86/ia32/audit.c
@@ -35,6 +35,7 @@ int ia32_classify_syscall(unsigned syscall)
case __NR_socketcall:
return 4;
case __NR_execve:
+ case __NR_execveat:
return 5;
default:
return 1;
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index d21ff89207cd..ae6aad1d24f7 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -308,11 +308,8 @@ static int load_aout_binary(struct linux_binprm *bprm)
(current->mm->start_brk = N_BSSADDR(ex));
retval = setup_arg_pages(bprm, IA32_STACK_TOP, EXSTACK_DEFAULT);
- if (retval < 0) {
- /* Someone check-me: is this error path enough? */
- send_sig(SIGKILL, current, 0);
+ if (retval < 0)
return retval;
- }
install_exec_creds(bprm);
@@ -324,17 +321,13 @@ static int load_aout_binary(struct linux_binprm *bprm)
error = vm_brk(text_addr & PAGE_MASK, map_size);
- if (error != (text_addr & PAGE_MASK)) {
- send_sig(SIGKILL, current, 0);
+ if (error != (text_addr & PAGE_MASK))
return error;
- }
error = read_code(bprm->file, text_addr, 32,
ex.a_text + ex.a_data);
- if ((signed long)error < 0) {
- send_sig(SIGKILL, current, 0);
+ if ((signed long)error < 0)
return error;
- }
} else {
#ifdef WARN_OLD
static unsigned long error_time, error_time2;
@@ -349,8 +342,8 @@ static int load_aout_binary(struct linux_binprm *bprm)
time_after(jiffies, error_time + 5*HZ)) {
printk(KERN_WARNING
"fd_offset is not page aligned. Please convert "
- "program: %s\n",
- bprm->file->f_path.dentry->d_name.name);
+ "program: %pD\n",
+ bprm->file);
error_time = jiffies;
}
#endif
@@ -368,20 +361,16 @@ static int load_aout_binary(struct linux_binprm *bprm)
MAP_EXECUTABLE | MAP_32BIT,
fd_offset);
- if (error != N_TXTADDR(ex)) {
- send_sig(SIGKILL, current, 0);
+ if (error != N_TXTADDR(ex))
return error;
- }
error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
MAP_EXECUTABLE | MAP_32BIT,
fd_offset + ex.a_text);
- if (error != N_DATADDR(ex)) {
- send_sig(SIGKILL, current, 0);
+ if (error != N_DATADDR(ex))
return error;
- }
}
beyond_if:
set_binfmt(&aout_format);
@@ -440,8 +429,8 @@ static int load_aout_library(struct file *file)
if (time_after(jiffies, error_time + 5*HZ)) {
printk(KERN_WARNING
"N_TXTOFF is not page aligned. Please convert "
- "library: %s\n",
- file->f_path.dentry->d_name.name);
+ "library: %pD\n",
+ file);
error_time = jiffies;
}
#endif
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 4299eb05023c..82e8a1d44658 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -151,6 +151,16 @@ ENTRY(ia32_sysenter_target)
1: movl (%rbp),%ebp
_ASM_EXTABLE(1b,ia32_badarg)
ASM_CLAC
+
+ /*
+ * Sysenter doesn't filter flags, so we need to clear NT
+ * ourselves. To save a few cycles, we can check whether
+ * NT was set instead of doing an unconditional popfq.
+ */
+ testl $X86_EFLAGS_NT,EFLAGS-ARGOFFSET(%rsp)
+ jnz sysenter_fix_flags
+sysenter_flags_fixed:
+
orl $TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
CFI_REMEMBER_STATE
@@ -184,14 +194,16 @@ sysexit_from_sys_call:
TRACE_IRQS_ON
ENABLE_INTERRUPTS_SYSEXIT32
+ CFI_RESTORE_STATE
+
#ifdef CONFIG_AUDITSYSCALL
.macro auditsys_entry_common
- movl %esi,%r9d /* 6th arg: 4th syscall arg */
- movl %edx,%r8d /* 5th arg: 3rd syscall arg */
- /* (already in %ecx) 4th arg: 2nd syscall arg */
- movl %ebx,%edx /* 3rd arg: 1st syscall arg */
- movl %eax,%esi /* 2nd arg: syscall number */
- movl $AUDIT_ARCH_I386,%edi /* 1st arg: audit arch */
+ movl %esi,%r8d /* 5th arg: 4th syscall arg */
+ movl %ecx,%r9d /*swap with edx*/
+ movl %edx,%ecx /* 4th arg: 3rd syscall arg */
+ movl %r9d,%edx /* 3rd arg: 2nd syscall arg */
+ movl %ebx,%esi /* 2nd arg: 1st syscall arg */
+ movl %eax,%edi /* 1st arg: syscall number */
call __audit_syscall_entry
movl RAX-ARGOFFSET(%rsp),%eax /* reload syscall number */
cmpq $(IA32_NR_syscalls-1),%rax
@@ -226,7 +238,6 @@ sysexit_from_sys_call:
.endm
sysenter_auditsys:
- CFI_RESTORE_STATE
auditsys_entry_common
movl %ebp,%r9d /* reload 6th syscall arg */
jmp sysenter_dispatch
@@ -235,6 +246,11 @@ sysexit_audit:
auditsys_exit sysexit_from_sys_call
#endif
+sysenter_fix_flags:
+ pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+ popfq_cfi
+ jmp sysenter_flags_fixed
+
sysenter_tracesys:
#ifdef CONFIG_AUDITSYSCALL
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
@@ -464,6 +480,7 @@ GLOBAL(\label)
PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
PTREGSCALL stub32_sigreturn, sys32_sigreturn
PTREGSCALL stub32_execve, compat_sys_execve
+ PTREGSCALL stub32_execveat, compat_sys_execveat
PTREGSCALL stub32_fork, sys_fork
PTREGSCALL stub32_vfork, sys_vfork
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 3bf000fab0ae..d55a210a49bf 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -6,6 +6,7 @@ genhdr-y += unistd_x32.h
generic-y += clkdev.h
generic-y += cputime.h
+generic-y += dma-contiguous.h
generic-y += early_ioremap.h
generic-y += mcs_spinlock.h
generic-y += scatterlist.h
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 6dd1c7dd0473..5e5cd123fdfb 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -24,7 +24,7 @@
*/
static inline int atomic_read(const atomic_t *v)
{
- return (*(volatile int *)&(v)->counter);
+ return ACCESS_ONCE((v)->counter);
}
/**
@@ -219,21 +219,6 @@ static inline short int atomic_inc_short(short int *v)
return *v;
}
-#ifdef CONFIG_X86_64
-/**
- * atomic_or_long - OR of two long integers
- * @v1: pointer to type unsigned long
- * @v2: pointer to type unsigned long
- *
- * Atomically ORs @v1 and @v2
- * Returns the result of the OR
- */
-static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
-{
- asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
-}
-#endif
-
/* These are x86-specific, used by some header files */
#define atomic_clear_mask(mask, addr) \
asm volatile(LOCK_PREFIX "andl %0,%1" \
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 46e9052bbd28..f8d273e18516 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -18,7 +18,7 @@
*/
static inline long atomic64_read(const atomic64_t *v)
{
- return (*(volatile long *)&(v)->counter);
+ return ACCESS_ONCE((v)->counter);
}
/**
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 0f4460b5636d..2ab1eb33106e 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -24,78 +24,28 @@
#define wmb() asm volatile("sfence" ::: "memory")
#endif
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier. All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads. This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies. See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * b = 2;
- * memory_barrier();
- * p = &b; q = p;
- * read_barrier_depends();
- * d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends(). However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- * CPU 0 CPU 1
- *
- * a = 2;
- * memory_barrier();
- * b = 3; y = b;
- * read_barrier_depends();
- * x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b". Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends() do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb() mb()
#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb() rmb()
+#define dma_rmb() rmb()
#else
-# define smp_rmb() barrier()
+#define dma_rmb() barrier()
#endif
+#define dma_wmb() barrier()
+
+#ifdef CONFIG_SMP
+#define smp_mb() mb()
+#define smp_rmb() dma_rmb()
#define smp_wmb() barrier()
-#define smp_read_barrier_depends() read_barrier_depends()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* !SMP */
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define smp_read_barrier_depends() do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif /* SMP */
+#define read_barrier_depends() do { } while (0)
+#define smp_read_barrier_depends() do { } while (0)
+
#if defined(CONFIG_X86_PPRO_FENCE)
/*
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 9863ee3747da..47c8e32f621a 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -5,65 +5,6 @@
#include <asm-generic/cacheflush.h>
#include <asm/special_insns.h>
-#ifdef CONFIG_X86_PAT
-/*
- * X86 PAT uses page flags WC and Uncached together to keep track of
- * memory type of pages that have backing page struct. X86 PAT supports 3
- * different memory types, _PAGE_CACHE_WB, _PAGE_CACHE_WC and
- * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not
- * been changed from its default (value of -1 used to denote this).
- * Note we do not support _PAGE_CACHE_UC here.
- */
-
-#define _PGMT_DEFAULT 0
-#define _PGMT_WC (1UL << PG_arch_1)
-#define _PGMT_UC_MINUS (1UL << PG_uncached)
-#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1)
-#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1)
-#define _PGMT_CLEAR_MASK (~_PGMT_MASK)
-
-static inline unsigned long get_page_memtype(struct page *pg)
-{
- unsigned long pg_flags = pg->flags & _PGMT_MASK;
-
- if (pg_flags == _PGMT_DEFAULT)
- return -1;
- else if (pg_flags == _PGMT_WC)
- return _PAGE_CACHE_WC;
- else if (pg_flags == _PGMT_UC_MINUS)
- return _PAGE_CACHE_UC_MINUS;
- else
- return _PAGE_CACHE_WB;
-}
-
-static inline void set_page_memtype(struct page *pg, unsigned long memtype)
-{
- unsigned long memtype_flags = _PGMT_DEFAULT;
- unsigned long old_flags;
- unsigned long new_flags;
-
- switch (memtype) {
- case _PAGE_CACHE_WC:
- memtype_flags = _PGMT_WC;
- break;
- case _PAGE_CACHE_UC_MINUS:
- memtype_flags = _PGMT_UC_MINUS;
- break;
- case _PAGE_CACHE_WB:
- memtype_flags = _PGMT_WB;
- break;
- }
-
- do {
- old_flags = pg->flags;
- new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
- } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
-}
-#else
-static inline unsigned long get_page_memtype(struct page *pg) { return -1; }
-static inline void set_page_memtype(struct page *pg, unsigned long memtype) { }
-#endif
-
/*
* The set_memory_* API can be used to change various attributes of a virtual
* address range. The attributes include:
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index cb4c73bfeb48..76659b67fd11 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -85,7 +85,7 @@ For 32-bit we have the following conventions - kernel is built with
#define ARGOFFSET R11
#define SWFRAME ORIG_RAX
- .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1
+ .macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0
subq $9*8+\addskip, %rsp
CFI_ADJUST_CFA_OFFSET 9*8+\addskip
movq_cfi rdi, 8*8
@@ -96,7 +96,11 @@ For 32-bit we have the following conventions - kernel is built with
movq_cfi rcx, 5*8
.endif
+ .if \rax_enosys
+ movq $-ENOSYS, 4*8(%rsp)
+ .else
movq_cfi rax, 4*8
+ .endif
.if \save_r891011
movq_cfi r8, 3*8
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index bb9b258d60e7..aede2c347bde 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -8,6 +8,10 @@
#include <asm/required-features.h>
#endif
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#include <asm/disabled-features.h>
+#endif
+
#define NCAPINTS 11 /* N 32-bit words worth of info */
#define NBUGINTS 1 /* N 32-bit bug flags */
@@ -185,6 +189,11 @@
#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
+#define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */
+#define X86_FEATURE_HWP_NOITFY ( 7*32+ 11) /* Intel HWP_NOTIFY */
+#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */
+#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */
+#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
/* Virtualization flags: Linux defined, word 8 */
#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */
@@ -202,6 +211,7 @@
#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */
#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */
#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */
+#define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
@@ -250,8 +260,15 @@
#include <asm/asm.h>
#include <linux/bitops.h>
+#ifdef CONFIG_X86_FEATURE_NAMES
extern const char * const x86_cap_flags[NCAPINTS*32];
extern const char * const x86_power_flags[32];
+#define X86_CAP_FMT "%s"
+#define x86_cap_flag(flag) x86_cap_flags[flag]
+#else
+#define X86_CAP_FMT "%d:%d"
+#define x86_cap_flag(flag) ((flag) >> 5), ((flag) & 31)
+#endif
/*
* In order to save room, we index into this array by doing
@@ -274,6 +291,18 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
(((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \
(((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) )
+#define DISABLED_MASK_BIT_SET(bit) \
+ ( (((bit)>>5)==0 && (1UL<<((bit)&31) & DISABLED_MASK0)) || \
+ (((bit)>>5)==1 && (1UL<<((bit)&31) & DISABLED_MASK1)) || \
+ (((bit)>>5)==2 && (1UL<<((bit)&31) & DISABLED_MASK2)) || \
+ (((bit)>>5)==3 && (1UL<<((bit)&31) & DISABLED_MASK3)) || \
+ (((bit)>>5)==4 && (1UL<<((bit)&31) & DISABLED_MASK4)) || \
+ (((bit)>>5)==5 && (1UL<<((bit)&31) & DISABLED_MASK5)) || \
+ (((bit)>>5)==6 && (1UL<<((bit)&31) & DISABLED_MASK6)) || \
+ (((bit)>>5)==7 && (1UL<<((bit)&31) & DISABLED_MASK7)) || \
+ (((bit)>>5)==8 && (1UL<<((bit)&31) & DISABLED_MASK8)) || \
+ (((bit)>>5)==9 && (1UL<<((bit)&31) & DISABLED_MASK9)) )
+
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
test_cpu_cap(c, bit))
@@ -282,6 +311,18 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+/*
+ * This macro is for detection of features which need kernel
+ * infrastructure to be used. It may *not* directly test the CPU
+ * itself. Use the cpu_has() family if you want true runtime
+ * testing of CPU features, like in hypervisor code where you are
+ * supporting a possible guest feature where host support for it
+ * is not relevant.
+ */
+#define cpu_feature_enabled(bit) \
+ (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : \
+ cpu_has(&boot_cpu_data, bit))
+
#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit)
#define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability))
@@ -296,11 +337,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
} while (0)
#define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_vme boot_cpu_has(X86_FEATURE_VME)
#define cpu_has_de boot_cpu_has(X86_FEATURE_DE)
#define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE)
#define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC)
-#define cpu_has_pae boot_cpu_has(X86_FEATURE_PAE)
#define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE)
#define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC)
#define cpu_has_sep boot_cpu_has(X86_FEATURE_SEP)
@@ -316,9 +355,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
#define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2)
#define cpu_has_ht boot_cpu_has(X86_FEATURE_HT)
#define cpu_has_nx boot_cpu_has(X86_FEATURE_NX)
-#define cpu_has_k6_mtrr boot_cpu_has(X86_FEATURE_K6_MTRR)
-#define cpu_has_cyrix_arr boot_cpu_has(X86_FEATURE_CYRIX_ARR)
-#define cpu_has_centaur_mcr boot_cpu_has(X86_FEATURE_CENTAUR_MCR)
#define cpu_has_xstore boot_cpu_has(X86_FEATURE_XSTORE)
#define cpu_has_xstore_enabled boot_cpu_has(X86_FEATURE_XSTORE_EN)
#define cpu_has_xcrypt boot_cpu_has(X86_FEATURE_XCRYPT)
@@ -353,25 +389,6 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU)
#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT)
-#ifdef CONFIG_X86_64
-
-#undef cpu_has_vme
-#define cpu_has_vme 0
-
-#undef cpu_has_pae
-#define cpu_has_pae ___BUG___
-
-#undef cpu_has_k6_mtrr
-#define cpu_has_k6_mtrr 0
-
-#undef cpu_has_cyrix_arr
-#define cpu_has_cyrix_arr 0
-
-#undef cpu_has_centaur_mcr
-#define cpu_has_centaur_mcr 0
-
-#endif /* CONFIG_X86_64 */
-
#if __GNUC__ >= 4
extern void warn_pre_alternatives(void);
extern bool __static_cpu_has_safe(u16 bit);
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 4b528a970bd4..61fd18b83b6c 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -97,11 +97,11 @@ extern void hw_breakpoint_restore(void);
DECLARE_PER_CPU(int, debug_stack_usage);
static inline void debug_stack_usage_inc(void)
{
- __get_cpu_var(debug_stack_usage)++;
+ __this_cpu_inc(debug_stack_usage);
}
static inline void debug_stack_usage_dec(void)
{
- __get_cpu_var(debug_stack_usage)--;
+ __this_cpu_dec(debug_stack_usage);
}
int is_debug_stack(unsigned long addr);
void debug_stack_set_zero(void);
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
new file mode 100644
index 000000000000..f226df064660
--- /dev/null
+++ b/arch/x86/include/asm/disabled-features.h
@@ -0,0 +1,45 @@
+#ifndef _ASM_X86_DISABLED_FEATURES_H
+#define _ASM_X86_DISABLED_FEATURES_H
+
+/* These features, although they might be available in a CPU
+ * will not be used because the compile options to support
+ * them are not present.
+ *
+ * This code allows them to be checked and disabled at
+ * compile time without an explicit #ifdef. Use
+ * cpu_feature_enabled().
+ */
+
+#ifdef CONFIG_X86_INTEL_MPX
+# define DISABLE_MPX 0
+#else
+# define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31))
+#endif
+
+#ifdef CONFIG_X86_64
+# define DISABLE_VME (1<<(X86_FEATURE_VME & 31))
+# define DISABLE_K6_MTRR (1<<(X86_FEATURE_K6_MTRR & 31))
+# define DISABLE_CYRIX_ARR (1<<(X86_FEATURE_CYRIX_ARR & 31))
+# define DISABLE_CENTAUR_MCR (1<<(X86_FEATURE_CENTAUR_MCR & 31))
+#else
+# define DISABLE_VME 0
+# define DISABLE_K6_MTRR 0
+# define DISABLE_CYRIX_ARR 0
+# define DISABLE_CENTAUR_MCR 0
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Make sure to add features to the correct mask
+ */
+#define DISABLED_MASK0 (DISABLE_VME)
+#define DISABLED_MASK1 0
+#define DISABLED_MASK2 0
+#define DISABLED_MASK3 (DISABLE_CYRIX_ARR|DISABLE_CENTAUR_MCR|DISABLE_K6_MTRR)
+#define DISABLED_MASK4 0
+#define DISABLED_MASK5 0
+#define DISABLED_MASK6 0
+#define DISABLED_MASK7 0
+#define DISABLED_MASK8 0
+#define DISABLED_MASK9 (DISABLE_MPX)
+
+#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
deleted file mode 100644
index b4b38bacb404..000000000000
--- a/arch/x86/include/asm/dma-contiguous.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASMX86_DMA_CONTIGUOUS_H
-#define ASMX86_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
-#endif
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
index 0bdb0c54d9a1..fe884e18fa6e 100644
--- a/arch/x86/include/asm/dma.h
+++ b/arch/x86/include/asm/dma.h
@@ -70,7 +70,7 @@
#define MAX_DMA_CHANNELS 8
/* 16MB ISA DMA zone */
-#define MAX_DMA_PFN ((16 * 1024 * 1024) >> PAGE_SHIFT)
+#define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT)
/* 4GB broken PCI/AGP hardware bus master zone */
#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 0ec241ede5a2..25bce45c6fc4 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -81,24 +81,23 @@ extern u64 asmlinkage efi_call(void *fp, ...);
*/
#define __efi_call_virt(f, args...) efi_call_virt(f, args)
-extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
- u32 type, u64 attribute);
+extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
+ u32 type, u64 attribute);
#endif /* CONFIG_X86_32 */
-extern int add_efi_memmap;
extern struct efi_scratch efi_scratch;
-extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
-extern int efi_memblock_x86_reserve_range(void);
-extern void efi_call_phys_prelog(void);
-extern void efi_call_phys_epilog(void);
-extern void efi_unmap_memmap(void);
-extern void efi_memory_uc(u64 addr, unsigned long size);
+extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable);
+extern int __init efi_memblock_x86_reserve_range(void);
+extern void __init efi_call_phys_prolog(void);
+extern void __init efi_call_phys_epilog(void);
+extern void __init efi_unmap_memmap(void);
+extern void __init efi_memory_uc(u64 addr, unsigned long size);
extern void __init efi_map_region(efi_memory_desc_t *md);
extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
extern void efi_sync_low_kernel_mappings(void);
-extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
-extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
extern void __init old_map_region(efi_memory_desc_t *md);
extern void __init runtime_code_page_mkexec(void);
extern void __init efi_runtime_mkexec(void);
@@ -159,19 +158,33 @@ static inline efi_status_t efi_thunk_set_virtual_address_map(
}
#endif /* CONFIG_EFI_MIXED */
+
+/* arch specific definitions used by the stub code */
+
+struct efi_config {
+ u64 image_handle;
+ u64 table;
+ u64 allocate_pool;
+ u64 allocate_pages;
+ u64 get_memory_map;
+ u64 free_pool;
+ u64 free_pages;
+ u64 locate_handle;
+ u64 handle_protocol;
+ u64 exit_boot_services;
+ u64 text_output;
+ efi_status_t (*call)(unsigned long, ...);
+ bool is64;
+} __packed;
+
+__pure const struct efi_config *__efi_early(void);
+
+#define efi_call_early(f, ...) \
+ __efi_early()->call(__efi_early()->f, __VA_ARGS__);
+
extern bool efi_reboot_required(void);
#else
-/*
- * IF EFI is not configured, have the EFI calls return -ENOSYS.
- */
-#define efi_call0(_f) (-ENOSYS)
-#define efi_call1(_f, _a1) (-ENOSYS)
-#define efi_call2(_f, _a1, _a2) (-ENOSYS)
-#define efi_call3(_f, _a1, _a2, _a3) (-ENOSYS)
-#define efi_call4(_f, _a1, _a2, _a3, _a4) (-ENOSYS)
-#define efi_call5(_f, _a1, _a2, _a3, _a4, _a5) (-ENOSYS)
-#define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6) (-ENOSYS)
static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {}
static inline bool efi_reboot_required(void)
{
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1a055c81d864..ca3347a9dab5 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -160,8 +160,9 @@ do { \
#define elf_check_arch(x) \
((x)->e_machine == EM_X86_64)
-#define compat_elf_check_arch(x) \
- (elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+#define compat_elf_check_arch(x) \
+ (elf_check_arch_ia32(x) || \
+ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
#if __USER32_DS != __USER_DS
# error "The following code assumes __USER32_DS == __USER_DS"
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
index 2519d0679d99..c3dd5e71f439 100644
--- a/arch/x86/include/asm/fb.h
+++ b/arch/x86/include/asm/fb.h
@@ -8,8 +8,12 @@
static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
unsigned long off)
{
+ unsigned long prot;
+
+ prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK;
if (boot_cpu_data.x86 > 3)
- pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
+ pgprot_val(vma->vm_page_prot) =
+ prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
}
extern int fb_is_primary_device(struct fb_info *info);
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index ffb1733ac91f..f80d70009ff8 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -69,7 +69,9 @@ enum fixed_addresses {
#ifdef CONFIG_X86_32
FIX_HOLE,
#else
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT,
+#endif
#ifdef CONFIG_PARAVIRT_CLOCK
PVCLOCK_FIXMAP_BEGIN,
PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
@@ -136,9 +138,7 @@ enum fixed_addresses {
extern void reserve_top_address(unsigned long reserve);
#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_BOOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT)
#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE)
-#define FIXADDR_BOOT_START (FIXADDR_TOP - FIXADDR_BOOT_SIZE)
extern int fixmaps_set;
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 412ececa00b9..e97622f57722 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -344,7 +344,7 @@ static inline void __thread_fpu_end(struct task_struct *tsk)
static inline void __thread_fpu_begin(struct task_struct *tsk)
{
- if (!static_cpu_has_safe(X86_FEATURE_EAGER_FPU))
+ if (!use_eager_fpu())
clts();
__thread_set_has_fpu(tsk);
}
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index e1f7fecaa7d6..f45acad3c4b6 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -1,39 +1,6 @@
#ifndef _ASM_X86_FTRACE_H
#define _ASM_X86_FTRACE_H
-#ifdef __ASSEMBLY__
-
- /* skip is set if the stack was already partially adjusted */
- .macro MCOUNT_SAVE_FRAME skip=0
- /*
- * We add enough stack to save all regs.
- */
- subq $(SS+8-\skip), %rsp
- movq %rax, RAX(%rsp)
- movq %rcx, RCX(%rsp)
- movq %rdx, RDX(%rsp)
- movq %rsi, RSI(%rsp)
- movq %rdi, RDI(%rsp)
- movq %r8, R8(%rsp)
- movq %r9, R9(%rsp)
- /* Move RIP to its proper location */
- movq SS+8(%rsp), %rdx
- movq %rdx, RIP(%rsp)
- .endm
-
- .macro MCOUNT_RESTORE_FRAME skip=0
- movq R9(%rsp), %r9
- movq R8(%rsp), %r8
- movq RDI(%rsp), %rdi
- movq RSI(%rsp), %rsi
- movq RDX(%rsp), %rdx
- movq RCX(%rsp), %rcx
- movq RAX(%rsp), %rax
- addq $(SS+8-\skip), %rsp
- .endm
-
-#endif
-
#ifdef CONFIG_FUNCTION_TRACER
#ifdef CC_USING_FENTRY
# define MCOUNT_ADDR ((long)(__fentry__))
diff --git a/arch/x86/include/asm/hash.h b/arch/x86/include/asm/hash.h
deleted file mode 100644
index e8c58f88b1d4..000000000000
--- a/arch/x86/include/asm/hash.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_X86_HASH_H
-#define _ASM_X86_HASH_H
-
-struct fast_hash_ops;
-extern void setup_arch_fast_hash(struct fast_hash_ops *ops);
-
-#endif /* _ASM_X86_HASH_H */
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 302a323b3f67..04e9d023168f 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -38,17 +38,20 @@ extern unsigned long highstart_pfn, highend_pfn;
/*
* Ordering is:
*
- * FIXADDR_TOP
- * fixed_addresses
- * FIXADDR_START
- * temp fixed addresses
- * FIXADDR_BOOT_START
- * Persistent kmap area
- * PKMAP_BASE
- * VMALLOC_END
- * Vmalloc area
- * VMALLOC_START
- * high_memory
+ * high memory on: high_memory off:
+ * FIXADDR_TOP FIXADDR_TOP
+ * fixed addresses fixed addresses
+ * FIXADDR_START FIXADDR_START
+ * temp fixed addresses/persistent kmap area VMALLOC_END
+ * PKMAP_BASE temp fixed addresses/vmalloc area
+ * VMALLOC_END VMALLOC_START
+ * vmalloc area high_memory
+ * VMALLOC_START
+ * high_memory
+ *
+ * The temp fixed area is only used during boot for early_ioremap(), and
+ * it is unused when the ioremap() is functional. vmalloc/pkmap area become
+ * available after early boot so the temp fixed area is available for re-use.
*/
#define LAST_PKMAP_MASK (LAST_PKMAP-1)
#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT)
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 4615906d83df..9662290e0b20 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -94,30 +94,7 @@ extern void trace_call_function_single_interrupt(void);
#define trace_kvm_posted_intr_ipi kvm_posted_intr_ipi
#endif /* CONFIG_TRACING */
-/* IOAPIC */
-#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1<<(x)) & io_apic_irqs))
-extern unsigned long io_apic_irqs;
-
-extern void setup_IO_APIC(void);
-extern void disable_IO_APIC(void);
-
-struct io_apic_irq_attr {
- int ioapic;
- int ioapic_pin;
- int trigger;
- int polarity;
-};
-
-static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
- int ioapic, int ioapic_pin,
- int trigger, int polarity)
-{
- irq_attr->ioapic = ioapic;
- irq_attr->ioapic_pin = ioapic_pin;
- irq_attr->trigger = trigger;
- irq_attr->polarity = polarity;
-}
-
+#ifdef CONFIG_IRQ_REMAP
/* Intel specific interrupt remapping information */
struct irq_2_iommu {
struct intel_iommu *iommu;
@@ -131,14 +108,12 @@ struct irq_2_irte {
u16 devid; /* Device ID for IRTE table */
u16 index; /* Index into IRTE table*/
};
+#endif /* CONFIG_IRQ_REMAP */
+
+#ifdef CONFIG_X86_LOCAL_APIC
+struct irq_data;
-/*
- * This is performance-critical, we want to do it O(1)
- *
- * Most irqs are mapped 1:1 with pins.
- */
struct irq_cfg {
- struct irq_pin_list *irq_2_pin;
cpumask_var_t domain;
cpumask_var_t old_domain;
u8 vector;
@@ -150,18 +125,39 @@ struct irq_cfg {
struct irq_2_irte irq_2_irte;
};
#endif
+ union {
+#ifdef CONFIG_X86_IO_APIC
+ struct {
+ struct list_head irq_2_pin;
+ };
+#endif
+ };
};
+extern struct irq_cfg *irq_cfg(unsigned int irq);
+extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
+extern struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
+extern void clear_irq_vector(int irq, struct irq_cfg *cfg);
+extern void setup_vector_irq(int cpu);
+#ifdef CONFIG_SMP
extern void send_cleanup_vector(struct irq_cfg *);
+extern void irq_complete_move(struct irq_cfg *cfg);
+#else
+static inline void send_cleanup_vector(struct irq_cfg *c) { }
+static inline void irq_complete_move(struct irq_cfg *c) { }
+#endif
-struct irq_data;
-int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
- unsigned int *dest_id);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
-extern void setup_ioapic_dest(void);
-
-extern void enable_IO_APIC(void);
+extern int apic_retrigger_irq(struct irq_data *data);
+extern void apic_ack_edge(struct irq_data *data);
+extern int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ unsigned int *dest_id);
+#else /* CONFIG_X86_LOCAL_APIC */
+static inline void lock_vector_lock(void) {}
+static inline void unlock_vector_lock(void) {}
+#endif /* CONFIG_X86_LOCAL_APIC */
/* Statistics */
extern atomic_t irq_err_count;
@@ -185,7 +181,8 @@ extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
extern __visible void smp_invalidate_interrupt(struct pt_regs *);
#endif
-extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
+extern void (*__initconst interrupt[FIRST_SYSTEM_VECTOR
+ - FIRST_EXTERNAL_VECTOR])(void);
#ifdef CONFIG_TRACING
#define trace_interrupt interrupt
#endif
@@ -195,17 +192,6 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
typedef int vector_irq_t[NR_VECTORS];
DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern void setup_vector_irq(int cpu);
-
-#ifdef CONFIG_X86_IO_APIC
-extern void lock_vector_lock(void);
-extern void unlock_vector_lock(void);
-extern void __setup_vector_irq(int cpu);
-#else
-static inline void lock_vector_lock(void) {}
-static inline void unlock_vector_lock(void) {}
-static inline void __setup_vector_irq(int cpu) {}
-#endif
#endif /* !ASSEMBLY_ */
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 48eb30a86062..47f29b1d1846 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -65,6 +65,7 @@ struct insn {
unsigned char x86_64;
const insn_byte_t *kaddr; /* kernel address of insn to analyze */
+ const insn_byte_t *end_kaddr; /* kernel address of last insn in buffer */
const insn_byte_t *next_byte;
};
@@ -96,7 +97,7 @@ struct insn {
#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */
#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */
-extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
+extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64);
extern void insn_get_prefixes(struct insn *insn);
extern void insn_get_opcode(struct insn *insn);
extern void insn_get_modrm(struct insn *insn);
@@ -115,12 +116,13 @@ static inline void insn_get_attribute(struct insn *insn)
extern int insn_rip_relative(struct insn *insn);
/* Init insn for kernel text */
-static inline void kernel_insn_init(struct insn *insn, const void *kaddr)
+static inline void kernel_insn_init(struct insn *insn,
+ const void *kaddr, int buf_len)
{
#ifdef CONFIG_X86_64
- insn_init(insn, kaddr, 1);
+ insn_init(insn, kaddr, buf_len, 1);
#else /* CONFIG_X86_32 */
- insn_init(insn, kaddr, 0);
+ insn_init(insn, kaddr, buf_len, 0);
#endif
}
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index b8237d8a1e0c..34a5b93704d3 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -74,6 +74,9 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
#define __raw_readw __readw
#define __raw_readl __readl
+#define writeb_relaxed(v, a) __writeb(v, a)
+#define writew_relaxed(v, a) __writew(v, a)
+#define writel_relaxed(v, a) __writel(v, a)
#define __raw_writeb __writeb
#define __raw_writew __writew
#define __raw_writel __writel
@@ -86,6 +89,7 @@ build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
#define readq_relaxed(a) readq(a)
+#define writeq_relaxed(v, a) writeq(v, a)
#define __raw_readq(a) readq(a)
#define __raw_writeq(val, addr) writeq(val, addr)
@@ -310,11 +314,11 @@ BUILDIO(b, b, char)
BUILDIO(w, w, short)
BUILDIO(l, , int)
-extern void *xlate_dev_mem_ptr(unsigned long phys);
-extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
+extern void *xlate_dev_mem_ptr(phys_addr_t phys);
+extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
- unsigned long prot_val);
+ enum page_cache_mode pcm);
extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size);
extern bool is_early_ioremap_ptep(pte_t *ptep);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 1733ab49ac5e..bf006cce9418 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -132,6 +132,10 @@ extern int noioapicquirk;
/* -1 if "noapic" boot option passed */
extern int noioapicreroute;
+extern unsigned long io_apic_irqs;
+
+#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs))
+
/*
* If we use the IO-APIC for IRQ routing, disable automatic
* assignment of PCI IRQ's.
@@ -139,18 +143,15 @@ extern int noioapicreroute;
#define io_apic_assign_pci_irqs \
(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
-struct io_apic_irq_attr;
struct irq_cfg;
extern void ioapic_insert_resources(void);
+extern int arch_early_ioapic_init(void);
extern int native_setup_ioapic_entry(int, struct IO_APIC_route_entry *,
unsigned int, int,
struct io_apic_irq_attr *);
extern void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg);
-extern void native_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id);
extern void native_eoi_ioapic_pin(int apic, int pin, int vector);
extern int save_ioapic_entries(void);
@@ -160,6 +161,13 @@ extern int restore_ioapic_entries(void);
extern void setup_ioapic_ids_from_mpc(void);
extern void setup_ioapic_ids_from_mpc_nocheck(void);
+struct io_apic_irq_attr {
+ int ioapic;
+ int ioapic_pin;
+ int trigger;
+ int polarity;
+};
+
enum ioapic_domain_type {
IOAPIC_DOMAIN_INVALID,
IOAPIC_DOMAIN_LEGACY,
@@ -188,8 +196,10 @@ extern int mp_find_ioapic_pin(int ioapic, u32 gsi);
extern u32 mp_pin_to_gsi(int ioapic, int pin);
extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags);
extern void mp_unmap_irq(int irq);
-extern void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
- struct ioapic_domain_cfg *cfg);
+extern int mp_register_ioapic(int id, u32 address, u32 gsi_base,
+ struct ioapic_domain_cfg *cfg);
+extern int mp_unregister_ioapic(u32 gsi_base);
+extern int mp_ioapic_registered(u32 gsi_base);
extern int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
irq_hw_number_t hwirq);
extern void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq);
@@ -227,19 +237,25 @@ static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned
extern void io_apic_eoi(unsigned int apic, unsigned int vector);
-extern bool mp_should_keep_irq(struct device *dev);
-
+extern void setup_IO_APIC(void);
+extern void enable_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern void setup_ioapic_dest(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin);
+extern void print_IO_APICs(void);
#else /* !CONFIG_X86_IO_APIC */
+#define IO_APIC_IRQ(x) 0
#define io_apic_assign_pci_irqs 0
#define setup_ioapic_ids_from_mpc x86_init_noop
static inline void ioapic_insert_resources(void) { }
+static inline int arch_early_ioapic_init(void) { return 0; }
+static inline void print_IO_APICs(void) {}
#define gsi_top (NR_IRQS_LEGACY)
static inline int mp_find_ioapic(u32 gsi) { return 0; }
static inline u32 mp_pin_to_gsi(int ioapic, int pin) { return UINT_MAX; }
static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags) { return gsi; }
static inline void mp_unmap_irq(int irq) { }
-static inline bool mp_should_keep_irq(struct device *dev) { return 1; }
static inline int save_ioapic_entries(void)
{
@@ -262,7 +278,6 @@ static inline void disable_ioapic_support(void) { }
#define native_io_apic_print_entries NULL
#define native_ioapic_set_affinity NULL
#define native_setup_ioapic_entry NULL
-#define native_compose_msi_msg NULL
#define native_eoi_ioapic_pin NULL
#endif
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 5702d7e3111d..666c89ec4bd7 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -126,6 +126,12 @@
#define NR_VECTORS 256
+#ifdef CONFIG_X86_LOCAL_APIC
+#define FIRST_SYSTEM_VECTOR LOCAL_TIMER_VECTOR
+#else
+#define FIRST_SYSTEM_VECTOR NR_VECTORS
+#endif
+
#define FPU_IRQ 13
#define FIRST_VM86_IRQ 3
diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h
new file mode 100644
index 000000000000..78162f8e248b
--- /dev/null
+++ b/arch/x86/include/asm/irq_work.h
@@ -0,0 +1,11 @@
+#ifndef _ASM_IRQ_WORK_H
+#define _ASM_IRQ_WORK_H
+
+#include <asm/processor.h>
+
+static inline bool arch_irq_work_has_interrupt(void)
+{
+ return cpu_has_apic;
+}
+
+#endif /* _ASM_IRQ_WORK_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 53cdfb2857ab..4421b5da409d 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -27,7 +27,6 @@
#include <asm/insn.h>
#define __ARCH_WANT_KPROBES_INSN_SLOT
-#define ARCH_SUPPORTS_KPROBES_ON_FTRACE
struct pt_regs;
struct kprobe;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7c492ed9087b..d89c6b828c96 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -33,7 +33,7 @@
#define KVM_MAX_VCPUS 255
#define KVM_SOFT_MAX_VCPUS 160
-#define KVM_USER_MEM_SLOTS 125
+#define KVM_USER_MEM_SLOTS 509
/* memory slots that are not exposed to userspace */
#define KVM_PRIVATE_MEM_SLOTS 3
#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
@@ -51,6 +51,7 @@
| X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
+#define CR3_PCID_INVD (1UL << 63)
#define CR4_RESERVED_BITS \
(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
| X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
@@ -99,10 +100,6 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
#define ASYNC_PF_PER_VCPU 64
-struct kvm_vcpu;
-struct kvm;
-struct kvm_async_pf;
-
enum kvm_reg {
VCPU_REGS_RAX = 0,
VCPU_REGS_RCX = 1,
@@ -266,7 +263,8 @@ struct kvm_mmu {
struct x86_exception *fault);
gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
struct x86_exception *exception);
- gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
+ gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception);
int (*sync_page)(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp);
void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
@@ -364,6 +362,7 @@ struct kvm_vcpu_arch {
int mp_state;
u64 ia32_misc_enable_msr;
bool tpr_access_reporting;
+ u64 ia32_xss;
/*
* Paging state of the vcpu
@@ -481,6 +480,7 @@ struct kvm_vcpu_arch {
u64 mmio_gva;
unsigned access;
gfn_t mmio_gfn;
+ u64 mmio_gen;
struct kvm_pmu pmu;
@@ -544,7 +544,7 @@ struct kvm_apic_map {
struct rcu_head rcu;
u8 ldr_bits;
/* fields bellow are used to decode ldr values in different modes */
- u32 cid_shift, cid_mask, lid_mask;
+ u32 cid_shift, cid_mask, lid_mask, broadcast;
struct kvm_lapic *phys_map[256];
/* first index is cluster id second is cpu id in a cluster */
struct kvm_lapic *logical_map[16][16];
@@ -576,11 +576,10 @@ struct kvm_arch {
struct kvm_apic_map *apic_map;
unsigned int tss_addr;
- struct page *apic_access_page;
+ bool apic_access_page_done;
gpa_t wall_clock;
- struct page *ept_identity_pagetable;
bool ept_identity_pagetable_done;
gpa_t ept_identity_map_addr;
@@ -605,6 +604,9 @@ struct kvm_arch {
struct kvm_xen_hvm_config xen_hvm_config;
+ /* reads protected by irq_srcu, writes by irq_lock */
+ struct hlist_head mask_notifier_list;
+
/* fields used by HYPER-V emulation */
u64 hv_guest_os_id;
u64 hv_hypercall;
@@ -662,11 +664,21 @@ struct msr_data {
u64 data;
};
+struct kvm_lapic_irq {
+ u32 vector;
+ u32 delivery_mode;
+ u32 dest_mode;
+ u32 level;
+ u32 trig_mode;
+ u32 shorthand;
+ u32 dest_id;
+};
+
struct kvm_x86_ops {
int (*cpu_has_kvm_support)(void); /* __init */
int (*disabled_by_bios)(void); /* __init */
- int (*hardware_enable)(void *dummy);
- void (*hardware_disable)(void *dummy);
+ int (*hardware_enable)(void);
+ void (*hardware_disable)(void);
void (*check_processor_compatibility)(void *rtn);
int (*hardware_setup)(void); /* __init */
void (*hardware_unsetup)(void); /* __exit */
@@ -710,7 +722,6 @@ struct kvm_x86_ops {
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
- void (*fpu_activate)(struct kvm_vcpu *vcpu);
void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
void (*tlb_flush)(struct kvm_vcpu *vcpu);
@@ -740,6 +751,7 @@ struct kvm_x86_ops {
void (*hwapic_isr_update)(struct kvm *kvm, int isr);
void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
+ void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
@@ -770,8 +782,11 @@ struct kvm_x86_ops {
enum x86_intercept_stage stage);
void (*handle_external_intr)(struct kvm_vcpu *vcpu);
bool (*mpx_supported)(void);
+ bool (*xsaves_supported)(void);
int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
+
+ void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
};
struct kvm_arch_async_pf {
@@ -819,6 +834,19 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
const void *val, int bytes);
u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
+struct kvm_irq_mask_notifier {
+ void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
+ int irq;
+ struct hlist_node link;
+};
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn);
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn);
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+ bool mask);
+
extern bool tdp_enabled;
u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
@@ -864,7 +892,7 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
-void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector);
+void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
int reason, bool has_error_code, u32 error_code);
@@ -895,8 +923,8 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t gfn, void *data, int offset, int len,
u32 access);
-void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
+bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr);
static inline int __kvm_irq_line_state(unsigned long *irq_state,
int irq_source_id, int level)
@@ -917,7 +945,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu);
int fx_init(struct kvm_vcpu *vcpu);
-void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
const u8 *new, int bytes);
int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn);
@@ -926,7 +953,8 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
int kvm_mmu_load(struct kvm_vcpu *vcpu);
void kvm_mmu_unload(struct kvm_vcpu *vcpu);
void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
@@ -946,7 +974,8 @@ void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu);
void kvm_enable_tdp(void);
void kvm_disable_tdp(void);
-static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception)
{
return gpa;
}
@@ -990,6 +1019,20 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
}
+static inline u64 get_canonical(u64 la)
+{
+ return ((int64_t)la << 16) >> 16;
+}
+
+static inline bool is_noncanonical_address(u64 la)
+{
+#ifdef CONFIG_X86_64
+ return get_canonical(la) != la;
+#else
+ return false;
+#endif
+}
+
#define TSS_IOPB_BASE_OFFSET 0x66
#define TSS_BASE_SIZE 0x68
#define TSS_IOPB_SIZE (65536 / 8)
@@ -1037,7 +1080,7 @@ asmlinkage void kvm_spurious_fault(void);
#define KVM_ARCH_WANT_MMU_NOTIFIER
int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
-int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
@@ -1046,10 +1089,14 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);
int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu);
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address);
void kvm_define_shared_msr(unsigned index, u32 msr);
-void kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
+unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu);
bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c7678e43465b..e62cf897f781 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -2,6 +2,7 @@
#define _ASM_X86_KVM_PARA_H
#include <asm/processor.h>
+#include <asm/alternative.h>
#include <uapi/asm/kvm_para.h>
extern void kvmclock_init(void);
@@ -16,10 +17,15 @@ static inline bool kvm_check_and_clear_guest_paused(void)
}
#endif /* CONFIG_KVM_GUEST */
-/* This instruction is vmcall. On non-VT architectures, it will generate a
- * trap that we will then rewrite to the appropriate instruction.
+#ifdef CONFIG_DEBUG_RODATA
+#define KVM_HYPERCALL \
+ ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
+#else
+/* On AMD processors, vmcall will generate a trap that we will
+ * then rewrite to the appropriate instruction.
*/
#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
+#endif
/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
* instruction. The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 958b90f761e5..51b26e895933 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -34,6 +34,10 @@
#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
+/* AMD-specific bits */
+#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */
+#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
+
/*
* Note that the full MCACOD field of IA32_MCi_STATUS MSR is
* bits 15:0. But bit 12 is the 'F' bit, defined for corrected
@@ -78,7 +82,6 @@
/* Software defined banks */
#define MCE_EXTENDED_BANK 128
#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0)
-#define K8_MCE_THRESHOLD_BASE (MCE_EXTENDED_BANK + 1)
#define MCE_LOG_LEN 32
#define MCE_LOG_SIGNATURE "MACHINECHECK"
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 64dc362506b7..201b520521ed 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -78,6 +78,7 @@ static inline void __exit exit_amd_microcode(void) {}
extern void __init load_ucode_bsp(void);
extern void load_ucode_ap(void);
extern int __init save_microcode_in_initrd(void);
+void reload_early_microcode(void);
#else
static inline void __init load_ucode_bsp(void) {}
static inline void load_ucode_ap(void) {}
@@ -85,6 +86,7 @@ static inline int __init save_microcode_in_initrd(void)
{
return 0;
}
+static inline void reload_early_microcode(void) {}
#endif
#endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index b7b10b82d3e5..af935397e053 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table,
extern int __apply_microcode_amd(struct microcode_amd *mc_amd);
extern int apply_microcode_amd(int cpu);
-extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
+extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size);
#define PATCH_MAX_SIZE PAGE_SIZE
extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
@@ -68,10 +68,12 @@ extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
extern void __init load_ucode_amd_bsp(void);
extern void load_ucode_amd_ap(void);
extern int __init save_microcode_in_initrd_amd(void);
+void reload_ucode_amd(void);
#else
static inline void __init load_ucode_amd_bsp(void) {}
static inline void load_ucode_amd_ap(void) {}
static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
+void reload_ucode_amd(void) {}
#endif
#endif /* _ASM_X86_MICROCODE_AMD_H */
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 9067166409bf..dd4c20043ce7 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -43,7 +43,7 @@ struct extended_sigtable {
#define DWSIZE (sizeof(u32))
#define get_totalsize(mc) \
- (((struct microcode_intel *)mc)->hdr.totalsize ? \
+ (((struct microcode_intel *)mc)->hdr.datasize ? \
((struct microcode_intel *)mc)->hdr.totalsize : \
DEFAULT_UCODE_TOTALSIZE)
@@ -68,11 +68,13 @@ extern void __init load_ucode_intel_bsp(void);
extern void load_ucode_intel_ap(void);
extern void show_ucode_info_early(void);
extern int __init save_microcode_in_initrd_intel(void);
+void reload_ucode_intel(void);
#else
static inline __init void load_ucode_intel_bsp(void) {}
static inline void load_ucode_intel_ap(void) {}
static inline void show_ucode_info_early(void) {}
static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL; }
+static inline void reload_ucode_intel(void) {}
#endif
#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 166af2a8e865..40269a2bf6f9 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -10,9 +10,8 @@
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include <asm/paravirt.h>
+#include <asm/mpx.h>
#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-
static inline void paravirt_activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
@@ -53,7 +52,16 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
/* Stop flush ipis for the previous mm */
cpumask_clear_cpu(cpu, mm_cpumask(prev));
- /* Load the LDT, if the LDT is different: */
+ /*
+ * Load the LDT, if the LDT is different.
+ *
+ * It's possible leave_mm(prev) has been called. If so,
+ * then prev->context.ldt could be out of sync with the
+ * LDT descriptor or the LDT register. This can only happen
+ * if prev->context.ldt is non-null, since we never free
+ * an LDT. But LDTs can't be shared across mms, so
+ * prev->context.ldt won't be equal to next->context.ldt.
+ */
if (unlikely(prev->context.ldt != next->context.ldt))
load_LDT_nolock(&next->context);
}
@@ -102,4 +110,27 @@ do { \
} while (0)
#endif
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
+{
+ paravirt_arch_dup_mmap(oldmm, mm);
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+ paravirt_arch_exit_mmap(mm);
+}
+
+static inline void arch_bprm_mm_init(struct mm_struct *mm,
+ struct vm_area_struct *vma)
+{
+ mpx_mm_init(mm);
+}
+
+static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ mpx_notify_unmap(mm, vma, start, end);
+}
+
#endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mpx.h b/arch/x86/include/asm/mpx.h
new file mode 100644
index 000000000000..a952a13d59a7
--- /dev/null
+++ b/arch/x86/include/asm/mpx.h
@@ -0,0 +1,103 @@
+#ifndef _ASM_X86_MPX_H
+#define _ASM_X86_MPX_H
+
+#include <linux/types.h>
+#include <asm/ptrace.h>
+#include <asm/insn.h>
+
+/*
+ * NULL is theoretically a valid place to put the bounds
+ * directory, so point this at an invalid address.
+ */
+#define MPX_INVALID_BOUNDS_DIR ((void __user *)-1)
+#define MPX_BNDCFG_ENABLE_FLAG 0x1
+#define MPX_BD_ENTRY_VALID_FLAG 0x1
+
+#ifdef CONFIG_X86_64
+
+/* upper 28 bits [47:20] of the virtual address in 64-bit used to
+ * index into bounds directory (BD).
+ */
+#define MPX_BD_ENTRY_OFFSET 28
+#define MPX_BD_ENTRY_SHIFT 3
+/* bits [19:3] of the virtual address in 64-bit used to index into
+ * bounds table (BT).
+ */
+#define MPX_BT_ENTRY_OFFSET 17
+#define MPX_BT_ENTRY_SHIFT 5
+#define MPX_IGN_BITS 3
+#define MPX_BD_ENTRY_TAIL 3
+
+#else
+
+#define MPX_BD_ENTRY_OFFSET 20
+#define MPX_BD_ENTRY_SHIFT 2
+#define MPX_BT_ENTRY_OFFSET 10
+#define MPX_BT_ENTRY_SHIFT 4
+#define MPX_IGN_BITS 2
+#define MPX_BD_ENTRY_TAIL 2
+
+#endif
+
+#define MPX_BD_SIZE_BYTES (1UL<<(MPX_BD_ENTRY_OFFSET+MPX_BD_ENTRY_SHIFT))
+#define MPX_BT_SIZE_BYTES (1UL<<(MPX_BT_ENTRY_OFFSET+MPX_BT_ENTRY_SHIFT))
+
+#define MPX_BNDSTA_TAIL 2
+#define MPX_BNDCFG_TAIL 12
+#define MPX_BNDSTA_ADDR_MASK (~((1UL<<MPX_BNDSTA_TAIL)-1))
+#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BT_ADDR_MASK (~((1UL<<MPX_BD_ENTRY_TAIL)-1))
+
+#define MPX_BNDCFG_ADDR_MASK (~((1UL<<MPX_BNDCFG_TAIL)-1))
+#define MPX_BNDSTA_ERROR_CODE 0x3
+
+#define MPX_BD_ENTRY_MASK ((1<<MPX_BD_ENTRY_OFFSET)-1)
+#define MPX_BT_ENTRY_MASK ((1<<MPX_BT_ENTRY_OFFSET)-1)
+#define MPX_GET_BD_ENTRY_OFFSET(addr) ((((addr)>>(MPX_BT_ENTRY_OFFSET+ \
+ MPX_IGN_BITS)) & MPX_BD_ENTRY_MASK) << MPX_BD_ENTRY_SHIFT)
+#define MPX_GET_BT_ENTRY_OFFSET(addr) ((((addr)>>MPX_IGN_BITS) & \
+ MPX_BT_ENTRY_MASK) << MPX_BT_ENTRY_SHIFT)
+
+#ifdef CONFIG_X86_INTEL_MPX
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+ struct xsave_struct *xsave_buf);
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf);
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+ return (mm->bd_addr != MPX_INVALID_BOUNDS_DIR);
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+ /*
+ * NULL is theoretically a valid place to put the bounds
+ * directory, so point this at an invalid address.
+ */
+ mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+}
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
+#else
+static inline siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+ struct xsave_struct *xsave_buf)
+{
+ return NULL;
+}
+static inline int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+ return -EINVAL;
+}
+static inline int kernel_managing_mpx_tables(struct mm_struct *mm)
+{
+ return 0;
+}
+static inline void mpx_mm_init(struct mm_struct *mm)
+{
+}
+static inline void mpx_notify_unmap(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
+#endif /* _ASM_X86_MPX_H */
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 4064acae625d..01b493e5a99b 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -9,7 +9,6 @@
#ifdef CONFIG_NUMA
#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
/*
* Too small node sizes may confuse the VM badly. Usually they
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index f48b17df4224..3a52ee0e726d 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -20,7 +20,6 @@
#define THREAD_SIZE_ORDER 1
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define STACKFAULT_STACK 0
#define DOUBLEFAULT_STACK 1
#define NMI_STACK 0
#define DEBUG_STACK 0
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index f408caf73430..b3bebf9e5746 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -39,6 +39,8 @@ void copy_page(void *to, void *from);
#endif /* !__ASSEMBLY__ */
-#define __HAVE_ARCH_GATE_AREA 1
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+# define __HAVE_ARCH_GATE_AREA 1
+#endif
#endif /* _ASM_X86_PAGE_64_H */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 678205195ae1..75450b2c7be4 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,12 +14,11 @@
#define IRQ_STACK_ORDER 2
#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5 /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4 /* hw limit: 7 */
#define PUD_PAGE_SIZE (_AC(1, UL) << PUD_SHIFT)
#define PUD_PAGE_MASK (~(PUD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cd6e1610e29e..32444ae939ca 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -330,13 +330,13 @@ static inline void paravirt_activate_mm(struct mm_struct *prev,
PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
}
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
- struct mm_struct *mm)
+static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
{
PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
}
-static inline void arch_exit_mmap(struct mm_struct *mm)
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
{
PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
}
@@ -986,5 +986,15 @@ extern void default_banner(void);
#endif /* __ASSEMBLY__ */
#else /* CONFIG_PARAVIRT */
# define default_banner x86_init_noop
+#ifndef __ASSEMBLY__
+static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm,
+ struct mm_struct *mm)
+{
+}
+
+static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
+{
+}
+#endif /* __ASSEMBLY__ */
#endif /* !CONFIG_PARAVIRT */
#endif /* _ASM_X86_PARAVIRT_H */
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index e2c1668dde7a..91bc4ba95f91 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -11,16 +11,17 @@ static const int pat_enabled;
#endif
extern void pat_init(void);
+void pat_init_cache_modes(void);
extern int reserve_memtype(u64 start, u64 end,
- unsigned long req_type, unsigned long *ret_type);
+ enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
extern int free_memtype(u64 start, u64 end);
extern int kernel_map_sync_memtype(u64 base, unsigned long size,
- unsigned long flag);
+ enum page_cache_mode pcm);
int io_reserve_memtype(resource_size_t start, resource_size_t end,
- unsigned long *type);
+ enum page_cache_mode *pcm);
void io_free_memtype(resource_size_t start, resource_size_t end);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 0892ea0e683f..4e370a5d8117 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -96,12 +96,15 @@ extern void pci_iommu_alloc(void);
#ifdef CONFIG_PCI_MSI
/* implemented in arch/x86/kernel/apic/io_apic. */
struct msi_desc;
+void native_compose_msi_msg(struct pci_dev *pdev, unsigned int irq,
+ unsigned int dest, struct msi_msg *msg, u8 hpet_id);
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
void native_teardown_msi_irq(unsigned int irq);
void native_restore_msi_irqs(struct pci_dev *dev);
int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
unsigned int irq_base, unsigned int irq_offset);
#else
+#define native_compose_msi_msg NULL
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
#endif
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195dae425..164e3f8d3c3d 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
extern int (*pcibios_enable_irq)(struct pci_dev *dev);
extern void (*pcibios_disable_irq)(struct pci_dev *dev);
+extern bool mp_should_keep_irq(struct device *dev);
+
struct pci_raw_ops {
int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index fd472181a1d0..e0ba66ca68c6 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -64,7 +64,7 @@
#define __percpu_prefix ""
#endif
-#define __percpu_arg(x) __percpu_prefix "%P" #x
+#define __percpu_arg(x) __percpu_prefix "%" #x
/*
* Initialized pointers to per-cpu variables needed for the boot
@@ -179,29 +179,58 @@ do { \
} \
} while (0)
-#define percpu_from_op(op, var, constraint) \
+#define percpu_from_op(op, var) \
({ \
typeof(var) pfo_ret__; \
switch (sizeof(var)) { \
case 1: \
asm(op "b "__percpu_arg(1)",%0" \
: "=q" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
break; \
case 2: \
asm(op "w "__percpu_arg(1)",%0" \
: "=r" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
break; \
case 4: \
asm(op "l "__percpu_arg(1)",%0" \
: "=r" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
break; \
case 8: \
asm(op "q "__percpu_arg(1)",%0" \
: "=r" (pfo_ret__) \
- : constraint); \
+ : "m" (var)); \
+ break; \
+ default: __bad_percpu_size(); \
+ } \
+ pfo_ret__; \
+})
+
+#define percpu_stable_op(op, var) \
+({ \
+ typeof(var) pfo_ret__; \
+ switch (sizeof(var)) { \
+ case 1: \
+ asm(op "b "__percpu_arg(P1)",%0" \
+ : "=q" (pfo_ret__) \
+ : "p" (&(var))); \
+ break; \
+ case 2: \
+ asm(op "w "__percpu_arg(P1)",%0" \
+ : "=r" (pfo_ret__) \
+ : "p" (&(var))); \
+ break; \
+ case 4: \
+ asm(op "l "__percpu_arg(P1)",%0" \
+ : "=r" (pfo_ret__) \
+ : "p" (&(var))); \
+ break; \
+ case 8: \
+ asm(op "q "__percpu_arg(P1)",%0" \
+ : "=r" (pfo_ret__) \
+ : "p" (&(var))); \
break; \
default: __bad_percpu_size(); \
} \
@@ -359,11 +388,11 @@ do { \
* per-thread variables implemented as per-cpu variables and thus
* stable for the duration of the respective task.
*/
-#define this_cpu_read_stable(var) percpu_from_op("mov", var, "p" (&(var)))
+#define this_cpu_read_stable(var) percpu_stable_op("mov", var)
-#define raw_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define raw_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define raw_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_read_1(pcp) percpu_from_op("mov", pcp)
+#define raw_cpu_read_2(pcp) percpu_from_op("mov", pcp)
+#define raw_cpu_read_4(pcp) percpu_from_op("mov", pcp)
#define raw_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val)
#define raw_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val)
@@ -381,9 +410,9 @@ do { \
#define raw_cpu_xchg_2(pcp, val) percpu_xchg_op(pcp, val)
#define raw_cpu_xchg_4(pcp, val) percpu_xchg_op(pcp, val)
-#define this_cpu_read_1(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define this_cpu_read_2(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
-#define this_cpu_read_4(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_1(pcp) percpu_from_op("mov", pcp)
+#define this_cpu_read_2(pcp) percpu_from_op("mov", pcp)
+#define this_cpu_read_4(pcp) percpu_from_op("mov", pcp)
#define this_cpu_write_1(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_write_2(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_write_4(pcp, val) percpu_to_op("mov", (pcp), val)
@@ -435,7 +464,7 @@ do { \
* 32 bit must fall back to generic operations.
*/
#ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define raw_cpu_read_8(pcp) percpu_from_op("mov", pcp)
#define raw_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
#define raw_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define raw_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
@@ -444,7 +473,7 @@ do { \
#define raw_cpu_xchg_8(pcp, nval) percpu_xchg_op(pcp, nval)
#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(pcp, oval, nval)
-#define this_cpu_read_8(pcp) percpu_from_op("mov", (pcp), "m"(pcp))
+#define this_cpu_read_8(pcp) percpu_from_op("mov", pcp)
#define this_cpu_write_8(pcp, val) percpu_to_op("mov", (pcp), val)
#define this_cpu_add_8(pcp, val) percpu_add_op((pcp), val)
#define this_cpu_and_8(pcp, val) percpu_to_op("and", (pcp), val)
@@ -522,7 +551,7 @@ static inline int x86_this_cpu_variable_test_bit(int nr,
#include <asm-generic/percpu.h>
/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8249df45d2f2..dc0f6ed35b08 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -51,6 +51,14 @@
ARCH_PERFMON_EVENTSEL_EDGE | \
ARCH_PERFMON_EVENTSEL_INV | \
ARCH_PERFMON_EVENTSEL_CMASK)
+#define X86_ALL_EVENT_FLAGS \
+ (ARCH_PERFMON_EVENTSEL_EDGE | \
+ ARCH_PERFMON_EVENTSEL_INV | \
+ ARCH_PERFMON_EVENTSEL_CMASK | \
+ ARCH_PERFMON_EVENTSEL_ANY | \
+ ARCH_PERFMON_EVENTSEL_PIN_CONTROL | \
+ HSW_IN_TX | \
+ HSW_IN_TX_CHECKPOINTED)
#define AMD64_RAW_EVENT_MASK \
(X86_RAW_EVENT_MASK | \
AMD64_EVENTSEL_EVENT)
@@ -169,6 +177,9 @@ struct x86_pmu_capability {
#define IBS_CAPS_BRNTRGT (1U<<5)
#define IBS_CAPS_OPCNTEXT (1U<<6)
#define IBS_CAPS_RIPINVALIDCHK (1U<<7)
+#define IBS_CAPS_OPBRNFUSE (1U<<8)
+#define IBS_CAPS_FETCHCTLEXTD (1U<<9)
+#define IBS_CAPS_OPDATA4 (1U<<10)
#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \
| IBS_CAPS_FETCHSAM \
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 85e13ccf15c4..d725382c2ae0 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu)
{
#ifdef CONFIG_SMP
if (smp_num_siblings == 2)
- return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+ return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
#endif
return 0;
}
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index aa97a070f09f..e8a5454acc99 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -9,9 +9,10 @@
/*
* Macro to mark a page protection value as UC-
*/
-#define pgprot_noncached(prot) \
- ((boot_cpu_data.x86 > 3) \
- ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS)) \
+#define pgprot_noncached(prot) \
+ ((boot_cpu_data.x86 > 3) \
+ ? (__pgprot(pgprot_val(prot) | \
+ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \
: (prot))
#ifndef __ASSEMBLY__
@@ -99,6 +100,11 @@ static inline int pte_young(pte_t pte)
return pte_flags(pte) & _PAGE_ACCESSED;
}
+static inline int pmd_dirty(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_DIRTY;
+}
+
static inline int pmd_young(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_ACCESSED;
@@ -404,8 +410,8 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
#define canon_pgprot(p) __pgprot(massage_pgprot(p))
static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
- unsigned long flags,
- unsigned long new_flags)
+ enum page_cache_mode pcm,
+ enum page_cache_mode new_pcm)
{
/*
* PAT type is always WB for untracked ranges, so no need to check.
@@ -419,10 +425,10 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
* - request is uncached, return cannot be write-back
* - request is write-combine, return cannot be write-back
*/
- if ((flags == _PAGE_CACHE_UC_MINUS &&
- new_flags == _PAGE_CACHE_WB) ||
- (flags == _PAGE_CACHE_WC &&
- new_flags == _PAGE_CACHE_WB)) {
+ if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
+ new_pcm == _PAGE_CACHE_MODE_WB) ||
+ (pcm == _PAGE_CACHE_MODE_WC &&
+ new_pcm == _PAGE_CACHE_MODE_WB)) {
return 0;
}
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 9ee322103c6d..b6c0b404898a 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,9 +32,6 @@ static inline void pgtable_cache_init(void) { }
static inline void check_pgt_cache(void) { }
void paging_init(void);
-extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
-
-
/*
* Define this if things work differently on an i386 and an i486:
* it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index ed5903be26fe..9fb2f2bc8245 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -37,7 +37,7 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
#define LAST_PKMAP 1024
#endif
-#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
+#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
& PMD_MASK)
#ifdef CONFIG_HIGHMEM
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 3874693c0e53..4572b2f30237 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -116,7 +116,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
native_set_pgd(pgd, native_make_pgd(0));
}
-extern void sync_global_pgds(unsigned long start, unsigned long end);
+extern void sync_global_pgds(unsigned long start, unsigned long end,
+ int removed);
/*
* Conversion functions: convert a page and protection to a page entry,
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 7166e25ecb57..602b6028c5b6 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -63,6 +63,8 @@ typedef struct { pteval_t pte; } pte_t;
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
#define ESPFIX_PGD_ENTRY _AC(-2, UL)
#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
+#define EFI_VA_START ( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END (-68 * (_AC(1, UL) << 30))
#define EARLY_DYNAMIC_PAGE_TABLES 64
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f216963760e5..25bcd4a89517 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -23,7 +23,6 @@
#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1
#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */
-#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */
#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */
#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
@@ -52,7 +51,7 @@
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
-#define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
+#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
@@ -129,11 +128,28 @@
_PAGE_SOFT_DIRTY | _PAGE_NUMA)
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA)
-#define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT)
-#define _PAGE_CACHE_WB (0)
-#define _PAGE_CACHE_WC (_PAGE_PWT)
-#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD)
-#define _PAGE_CACHE_UC (_PAGE_PCD | _PAGE_PWT)
+/*
+ * The cache modes defined here are used to translate between pure SW usage
+ * and the HW defined cache mode bits and/or PAT entries.
+ *
+ * The resulting bits for PWT, PCD and PAT should be chosen in a way
+ * to have the WB mode at index 0 (all bits clear). This is the default
+ * right now and likely would break too much if changed.
+ */
+#ifndef __ASSEMBLY__
+enum page_cache_mode {
+ _PAGE_CACHE_MODE_WB = 0,
+ _PAGE_CACHE_MODE_WC = 1,
+ _PAGE_CACHE_MODE_UC_MINUS = 2,
+ _PAGE_CACHE_MODE_UC = 3,
+ _PAGE_CACHE_MODE_WT = 4,
+ _PAGE_CACHE_MODE_WP = 5,
+ _PAGE_CACHE_MODE_NUM = 8
+};
+#endif
+
+#define _PAGE_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)
+#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC))
#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
@@ -157,41 +173,27 @@
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
-#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_WC (__PAGE_KERNEL | _PAGE_CACHE_WC)
-#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE)
#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER)
#define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER)
-#define __PAGE_KERNEL_VVAR_NOCACHE (__PAGE_KERNEL_VVAR | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
-#define __PAGE_KERNEL_IO (__PAGE_KERNEL | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO (__PAGE_KERNEL)
+#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_WC __pgprot(__PAGE_KERNEL_WC)
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_UC_MINUS __pgprot(__PAGE_KERNEL_UC_MINUS)
-#define PAGE_KERNEL_EXEC_NOCACHE __pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_NOCACHE __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR)
-#define PAGE_KERNEL_VVAR_NOCACHE __pgprot(__PAGE_KERNEL_VVAR_NOCACHE)
#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO)
#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE)
-#define PAGE_KERNEL_IO_UC_MINUS __pgprot(__PAGE_KERNEL_IO_UC_MINUS)
-#define PAGE_KERNEL_IO_WC __pgprot(__PAGE_KERNEL_IO_WC)
/* xwr */
#define __P000 PAGE_NONE
@@ -325,9 +327,76 @@ static inline pteval_t pte_flags(pte_t pte)
return native_pte_val(pte) & PTE_FLAGS_MASK;
}
+#ifdef CONFIG_NUMA_BALANCING
+/* Set of bits that distinguishes present, prot_none and numa ptes */
+#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT)
+static inline pteval_t ptenuma_flags(pte_t pte)
+{
+ return pte_flags(pte) & _PAGE_NUMA_MASK;
+}
+
+static inline pmdval_t pmdnuma_flags(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_NUMA_MASK;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
#define pgprot_val(x) ((x).pgprot)
#define __pgprot(x) ((pgprot_t) { (x) } )
+extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM];
+extern uint8_t __pte2cachemode_tbl[8];
+
+#define __pte2cm_idx(cb) \
+ ((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) | \
+ (((cb) >> (_PAGE_BIT_PCD - 1)) & 2) | \
+ (((cb) >> _PAGE_BIT_PWT) & 1))
+#define __cm_idx2pte(i) \
+ ((((i) & 4) << (_PAGE_BIT_PAT - 2)) | \
+ (((i) & 2) << (_PAGE_BIT_PCD - 1)) | \
+ (((i) & 1) << _PAGE_BIT_PWT))
+
+static inline unsigned long cachemode2protval(enum page_cache_mode pcm)
+{
+ if (likely(pcm == 0))
+ return 0;
+ return __cachemode2pte_tbl[pcm];
+}
+static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
+{
+ return __pgprot(cachemode2protval(pcm));
+}
+static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot)
+{
+ unsigned long masked;
+
+ masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK;
+ if (likely(masked == 0))
+ return 0;
+ return __pte2cachemode_tbl[__pte2cm_idx(masked)];
+}
+static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
+{
+ pgprot_t new;
+ unsigned long val;
+
+ val = pgprot_val(pgprot);
+ pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
+ ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
+ return new;
+}
+static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
+{
+ pgprot_t new;
+ unsigned long val;
+
+ val = pgprot_val(pgprot);
+ pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
+ ((val & _PAGE_PAT_LARGE) >>
+ (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
+ return new;
+}
+
typedef struct page *pgtable_t;
@@ -383,6 +452,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
extern pte_t *lookup_address(unsigned long address, unsigned int *level);
extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
unsigned int *level);
+extern pmd_t *lookup_pmd_address(unsigned long address);
extern phys_addr_t slow_virt_to_phys(void *__address);
extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
unsigned numpages, unsigned long page_flags);
diff --git a/arch/x86/include/asm/platform_sst_audio.h b/arch/x86/include/asm/platform_sst_audio.h
index 0a4e140315b6..7249e6d0902d 100644
--- a/arch/x86/include/asm/platform_sst_audio.h
+++ b/arch/x86/include/asm/platform_sst_audio.h
@@ -16,6 +16,9 @@
#include <linux/sfi.h>
+#define MAX_NUM_STREAMS_MRFLD 25
+#define MAX_NUM_STREAMS MAX_NUM_STREAMS_MRFLD
+
enum sst_audio_task_id_mrfld {
SST_TASK_ID_NONE = 0,
SST_TASK_ID_SBA = 1,
@@ -73,6 +76,65 @@ struct sst_platform_data {
unsigned int strm_map_size;
};
+struct sst_info {
+ u32 iram_start;
+ u32 iram_end;
+ bool iram_use;
+ u32 dram_start;
+ u32 dram_end;
+ bool dram_use;
+ u32 imr_start;
+ u32 imr_end;
+ bool imr_use;
+ u32 mailbox_start;
+ bool use_elf;
+ bool lpe_viewpt_rqd;
+ unsigned int max_streams;
+ u32 dma_max_len;
+ u8 num_probes;
+};
+
+struct sst_lib_dnld_info {
+ unsigned int mod_base;
+ unsigned int mod_end;
+ unsigned int mod_table_offset;
+ unsigned int mod_table_size;
+ bool mod_ddr_dnld;
+};
+
+struct sst_res_info {
+ unsigned int shim_offset;
+ unsigned int shim_size;
+ unsigned int shim_phy_addr;
+ unsigned int ssp0_offset;
+ unsigned int ssp0_size;
+ unsigned int dma0_offset;
+ unsigned int dma0_size;
+ unsigned int dma1_offset;
+ unsigned int dma1_size;
+ unsigned int iram_offset;
+ unsigned int iram_size;
+ unsigned int dram_offset;
+ unsigned int dram_size;
+ unsigned int mbox_offset;
+ unsigned int mbox_size;
+ unsigned int acpi_lpe_res_index;
+ unsigned int acpi_ddr_index;
+ unsigned int acpi_ipc_irq_index;
+};
+
+struct sst_ipc_info {
+ int ipc_offset;
+ unsigned int mbox_recv_off;
+};
+
+struct sst_platform_info {
+ const struct sst_info *probe_data;
+ const struct sst_ipc_info *ipc_info;
+ const struct sst_res_info *res_info;
+ const struct sst_lib_dnld_info *lib_info;
+ const char *platform;
+};
int add_sst_platform_device(void);
#endif
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 7024c12f7bfe..8f3271842533 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -30,9 +30,6 @@ static __always_inline void preempt_count_set(int pc)
/*
* must be macros to avoid header recursion hell
*/
-#define task_preempt_count(p) \
- (task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED)
-
#define init_task_preempt_count(p) do { \
task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
} while (0)
@@ -105,6 +102,7 @@ static __always_inline bool should_resched(void)
# ifdef CONFIG_CONTEXT_TRACKING
extern asmlinkage void ___preempt_schedule_context(void);
# define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+ extern asmlinkage void preempt_schedule_context(void);
# endif
#endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index eb71ec794732..a092a0cce0b7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -127,7 +127,7 @@ struct cpuinfo_x86 {
/* Index into per_cpu list: */
u16 cpu_index;
u32 microcode;
-} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+};
#define X86_VENDOR_INTEL 0
#define X86_VENDOR_CYRIX 1
@@ -151,7 +151,7 @@ extern __u32 cpu_caps_cleared[NCAPINTS];
extern __u32 cpu_caps_set[NCAPINTS];
#ifdef CONFIG_SMP
-DECLARE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
+DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
#define cpu_data(cpu) per_cpu(cpu_info, cpu)
#else
#define cpu_info boot_cpu_data
@@ -374,13 +374,14 @@ struct lwp_struct {
u8 reserved[128];
};
-struct bndregs_struct {
- u64 bndregs[8];
+struct bndreg {
+ u64 lower_bound;
+ u64 upper_bound;
} __packed;
-struct bndcsr_struct {
- u64 cfg_reg_u;
- u64 status_reg;
+struct bndcsr {
+ u64 bndcfgu;
+ u64 bndstatus;
} __packed;
struct xsave_hdr_struct {
@@ -394,8 +395,8 @@ struct xsave_struct {
struct xsave_hdr_struct xsave_hdr;
struct ymmh_struct ymmh;
struct lwp_struct lwp;
- struct bndregs_struct bndregs;
- struct bndcsr_struct bndcsr;
+ struct bndreg bndreg[4];
+ struct bndcsr bndcsr;
/* new processor state extensions will go here */
} __attribute__ ((packed, aligned (64)));
@@ -893,7 +894,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
#else
/*
- * User space process size. 47bits minus one guard page.
+ * User space process size. 47bits minus one guard page. The guard
+ * page is necessary on Intel CPUs: if a SYSCALL instruction is at
+ * the highest possible canonical userspace address, then that
+ * syscall will enter the kernel with a non-canonical return
+ * address, and SYSRET will explode dangerously. We avoid this
+ * particular problem by preventing anything from being mapped
+ * at the maximum canonical address.
*/
#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE)
@@ -953,6 +960,24 @@ extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
extern int get_tsc_mode(unsigned long adr);
extern int set_tsc_mode(unsigned int val);
+/* Register/unregister a process' MPX related resource */
+#define MPX_ENABLE_MANAGEMENT(tsk) mpx_enable_management((tsk))
+#define MPX_DISABLE_MANAGEMENT(tsk) mpx_disable_management((tsk))
+
+#ifdef CONFIG_X86_INTEL_MPX
+extern int mpx_enable_management(struct task_struct *tsk);
+extern int mpx_disable_management(struct task_struct *tsk);
+#else
+static inline int mpx_enable_management(struct task_struct *tsk)
+{
+ return -EINVAL;
+}
+static inline int mpx_disable_management(struct task_struct *tsk)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_X86_INTEL_MPX */
+
extern u16 amd_get_nb_id(int cpu);
static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 6205f0c434db..86fc2bb82287 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -75,6 +75,11 @@ convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
int error_code, int si_code);
+
+extern unsigned long syscall_trace_enter_phase1(struct pt_regs *, u32 arch);
+extern long syscall_trace_enter_phase2(struct pt_regs *, u32 arch,
+ unsigned long phase1_result);
+
extern long syscall_trace_enter(struct pt_regs *);
extern void syscall_trace_leave(struct pt_regs *);
diff --git a/arch/x86/include/asm/rwlock.h b/arch/x86/include/asm/rwlock.h
deleted file mode 100644
index a5370a03d90c..000000000000
--- a/arch/x86/include/asm/rwlock.h
+++ /dev/null
@@ -1,49 +0,0 @@
-#ifndef _ASM_X86_RWLOCK_H
-#define _ASM_X86_RWLOCK_H
-
-#include <asm/asm.h>
-
-#if CONFIG_NR_CPUS <= 2048
-
-#ifndef __ASSEMBLY__
-typedef union {
- s32 lock;
- s32 write;
-} arch_rwlock_t;
-#endif
-
-#define RW_LOCK_BIAS 0x00100000
-#define READ_LOCK_SIZE(insn) __ASM_FORM(insn##l)
-#define READ_LOCK_ATOMIC(n) atomic_##n
-#define WRITE_LOCK_ADD(n) __ASM_FORM_COMMA(addl n)
-#define WRITE_LOCK_SUB(n) __ASM_FORM_COMMA(subl n)
-#define WRITE_LOCK_CMP RW_LOCK_BIAS
-
-#else /* CONFIG_NR_CPUS > 2048 */
-
-#include <linux/const.h>
-
-#ifndef __ASSEMBLY__
-typedef union {
- s64 lock;
- struct {
- u32 read;
- s32 write;
- };
-} arch_rwlock_t;
-#endif
-
-#define RW_LOCK_BIAS (_AC(1,L) << 32)
-#define READ_LOCK_SIZE(insn) __ASM_FORM(insn##q)
-#define READ_LOCK_ATOMIC(n) atomic64_##n
-#define WRITE_LOCK_ADD(n) __ASM_FORM(incl)
-#define WRITE_LOCK_SUB(n) __ASM_FORM(decl)
-#define WRITE_LOCK_CMP 1
-
-#endif /* CONFIG_NR_CPUS */
-
-#define __ARCH_RW_LOCK_UNLOCKED { RW_LOCK_BIAS }
-
-/* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
-
-#endif /* _ASM_X86_RWLOCK_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 6f1c3a8a33ab..db257a58571f 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -23,6 +23,15 @@
#define GDT_ENTRY_BOOT_TSS (GDT_ENTRY_BOOT_CS + 2)
#define __BOOT_TSS (GDT_ENTRY_BOOT_TSS * 8)
+#define SEGMENT_RPL_MASK 0x3 /*
+ * Bottom two bits of selector give the ring
+ * privilege level
+ */
+#define SEGMENT_TI_MASK 0x4 /* Bit 2 is table indicator (LDT/GDT) */
+#define USER_RPL 0x3 /* User mode is privilege level 3 */
+#define SEGMENT_LDT 0x4 /* LDT segment has TI set... */
+#define SEGMENT_GDT 0x0 /* ... GDT has it cleared */
+
#ifdef CONFIG_X86_32
/*
* The layout of the per-CPU GDT under Linux:
@@ -125,16 +134,6 @@
#define PNP_TS1 (GDT_ENTRY_PNPBIOS_TS1 * 8) /* transfer data segment */
#define PNP_TS2 (GDT_ENTRY_PNPBIOS_TS2 * 8) /* another data segment */
-/* Bottom two bits of selector give the ring privilege level */
-#define SEGMENT_RPL_MASK 0x3
-/* Bit 2 is table indicator (LDT/GDT) */
-#define SEGMENT_TI_MASK 0x4
-
-/* User mode is privilege level 3 */
-#define USER_RPL 0x3
-/* LDT segment has TI set, GDT has it cleared */
-#define SEGMENT_LDT 0x4
-#define SEGMENT_GDT 0x0
/*
* Matching rules for certain types of segments.
@@ -192,17 +191,6 @@
#define get_kernel_rpl() 0
#endif
-/* User mode is privilege level 3 */
-#define USER_RPL 0x3
-/* LDT segment has TI set, GDT has it cleared */
-#define SEGMENT_LDT 0x4
-#define SEGMENT_GDT 0x0
-
-/* Bottom two bits of selector give the ring privilege level */
-#define SEGMENT_RPL_MASK 0x3
-/* Bit 2 is table indicator (LDT/GDT) */
-#define SEGMENT_TI_MASK 0x4
-
#define IDT_ENTRIES 256
#define NUM_EXCEPTION_VECTORS 32
/* Bitmask of exception vectors which push an error code on the stack */
diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h
index 628c801535ea..460b84f64556 100644
--- a/arch/x86/include/asm/serial.h
+++ b/arch/x86/include/asm/serial.h
@@ -6,24 +6,24 @@
*
* It'd be nice if someone built a serial card with a 24.576 MHz
* clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
+ * megabits/second; but this requires a faster clock.
*/
-#define BASE_BAUD ( 1843200 / 16 )
+#define BASE_BAUD (1843200/16)
/* Standard COM flags (except for COM4, because of the 8514 problem) */
#ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+# define STD_COMX_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+# define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | 0 | ASYNC_AUTO_IRQ)
#else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+# define STD_COMX_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | 0 )
+# define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | 0 | 0 )
#endif
-#define SERIAL_PORT_DFNS \
- /* UART CLK PORT IRQ FLAGS */ \
- { 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS }, /* ttyS0 */ \
- { 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS }, /* ttyS1 */ \
- { 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS }, /* ttyS2 */ \
- { 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */
+#define SERIAL_PORT_DFNS \
+ /* UART CLK PORT IRQ FLAGS */ \
+ { .uart = 0, BASE_BAUD, 0x3F8, 4, STD_COMX_FLAGS }, /* ttyS0 */ \
+ { .uart = 0, BASE_BAUD, 0x2F8, 3, STD_COMX_FLAGS }, /* ttyS1 */ \
+ { .uart = 0, BASE_BAUD, 0x3E8, 4, STD_COMX_FLAGS }, /* ttyS2 */ \
+ { .uart = 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */
#endif /* _ASM_X86_SERIAL_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 8cd27e08e23c..8cd1cc3bc835 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -150,6 +150,7 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
}
void cpu_disable_common(void);
+void cpu_die_common(unsigned int cpu);
void native_smp_prepare_boot_cpu(void);
void native_smp_prepare_cpus(unsigned int max_cpus);
void native_smp_cpus_done(unsigned int max_cpus);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 54f1c8068c02..625660f8a2fc 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -92,7 +92,7 @@ static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
unsigned count = SPIN_THRESHOLD;
do {
- if (ACCESS_ONCE(lock->tickets.head) == inc.tail)
+ if (READ_ONCE(lock->tickets.head) == inc.tail)
goto out;
cpu_relax();
} while (--count);
@@ -105,7 +105,7 @@ static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
{
arch_spinlock_t old, new;
- old.tickets = ACCESS_ONCE(lock->tickets);
+ old.tickets = READ_ONCE(lock->tickets);
if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
return 0;
@@ -162,14 +162,14 @@ static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
- struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+ struct __raw_tickets tmp = READ_ONCE(lock->tickets);
return tmp.tail != tmp.head;
}
static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
- struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+ struct __raw_tickets tmp = READ_ONCE(lock->tickets);
return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
}
@@ -183,11 +183,22 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
- while (arch_spin_is_locked(lock))
+ __ticket_t head = ACCESS_ONCE(lock->tickets.head);
+
+ for (;;) {
+ struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+ /*
+ * We need to check "unlocked" in a loop, tmp.head == head
+ * can be false positive because of overflow.
+ */
+ if (tmp.head == (tmp.tail & ~TICKET_SLOWPATH_FLAG) ||
+ tmp.head != head)
+ break;
+
cpu_relax();
+ }
}
-#ifndef CONFIG_QUEUE_RWLOCK
/*
* Read-write spinlocks, allowing multiple readers
* but only one writer.
@@ -198,91 +209,15 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
* irq-safe write-lock, but readers can get non-irqsafe
* read-locks.
*
- * On x86, we implement read-write locks as a 32-bit counter
- * with the high bit (sign) being the "contended" bit.
- */
-
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int arch_read_can_lock(arch_rwlock_t *lock)
-{
- return lock->lock > 0;
-}
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
+ * On x86, we implement read-write locks using the generic qrwlock with
+ * x86 specific optimization.
*/
-static inline int arch_write_can_lock(arch_rwlock_t *lock)
-{
- return lock->write == WRITE_LOCK_CMP;
-}
-static inline void arch_read_lock(arch_rwlock_t *rw)
-{
- asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t"
- "jns 1f\n"
- "call __read_lock_failed\n\t"
- "1:\n"
- ::LOCK_PTR_REG (rw) : "memory");
-}
-
-static inline void arch_write_lock(arch_rwlock_t *rw)
-{
- asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t"
- "jz 1f\n"
- "call __write_lock_failed\n\t"
- "1:\n"
- ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS)
- : "memory");
-}
-
-static inline int arch_read_trylock(arch_rwlock_t *lock)
-{
- READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock;
-
- if (READ_LOCK_ATOMIC(dec_return)(count) >= 0)
- return 1;
- READ_LOCK_ATOMIC(inc)(count);
- return 0;
-}
-
-static inline int arch_write_trylock(arch_rwlock_t *lock)
-{
- atomic_t *count = (atomic_t *)&lock->write;
-
- if (atomic_sub_and_test(WRITE_LOCK_CMP, count))
- return 1;
- atomic_add(WRITE_LOCK_CMP, count);
- return 0;
-}
-
-static inline void arch_read_unlock(arch_rwlock_t *rw)
-{
- asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0"
- :"+m" (rw->lock) : : "memory");
-}
-
-static inline void arch_write_unlock(arch_rwlock_t *rw)
-{
- asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0"
- : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory");
-}
-#else
#include <asm/qrwlock.h>
-#endif /* CONFIG_QUEUE_RWLOCK */
#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
-#undef READ_LOCK_SIZE
-#undef READ_LOCK_ATOMIC
-#undef WRITE_LOCK_ADD
-#undef WRITE_LOCK_SUB
-#undef WRITE_LOCK_CMP
-
#define arch_spin_relax(lock) cpu_relax()
#define arch_read_relax(lock) cpu_relax()
#define arch_write_relax(lock) cpu_relax()
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 73c4c007200f..5f9d7572d82b 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -34,10 +34,6 @@ typedef struct arch_spinlock {
#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
-#ifdef CONFIG_QUEUE_RWLOCK
#include <asm-generic/qrwlock_types.h>
-#else
-#include <asm/rwlock.h>
-#endif
#endif /* _ASM_X86_SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index d7f3b3b78ac3..751bf4b7bf11 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -79,12 +79,12 @@ do { \
#else /* CONFIG_X86_32 */
/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
#define __EXTRA_CLOBBER \
, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
- "r12", "r13", "r14", "r15"
+ "r12", "r13", "r14", "r15", "flags"
#ifdef CONFIG_CC_STACKPROTECTOR
#define __switch_canary \
@@ -100,7 +100,11 @@ do { \
#define __switch_canary_iparam
#endif /* CC_STACKPROTECTOR */
-/* Save restore flags to clear handle leaking NT */
+/*
+ * There is no need to save or restore flags, because flags are always
+ * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL
+ * has no effect.
+ */
#define switch_to(prev, next, last) \
asm volatile(SAVE_CONTEXT \
"movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 854053889d4d..547e344a6dc6 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -141,7 +141,7 @@ struct thread_info {
/* Only used for 64 bit */
#define _TIF_DO_NOTIFY_MASK \
(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME | \
- _TIF_USER_RETURN_NOTIFY)
+ _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
/* flags to check in __switch_to() */
#define _TIF_WORK_CTXSW \
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index bc8352e7010a..707adc6549d8 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void);
#ifdef CONFIG_TRACING
asmlinkage void trace_page_fault(void);
+#define trace_stack_segment stack_segment
#define trace_divide_error divide_error
#define trace_bounds bounds
#define trace_invalid_op invalid_op
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 2d60a7813dfe..fc808b83fccb 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -33,8 +33,8 @@
* Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
*/
-#define MAX_CPUS_PER_UVHUB 64
-#define MAX_CPUS_PER_SOCKET 32
+#define MAX_CPUS_PER_UVHUB 128
+#define MAX_CPUS_PER_SOCKET 64
#define ADP_SZ 64 /* hardware-provided max. */
#define UV_CPUS_PER_AS 32 /* hardware-provided max. */
#define ITEMS_PER_DESC 8
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index c63e925fd6b7..a00ad8f2a657 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -164,7 +164,7 @@ struct uv_hub_info_s {
};
DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info (&__get_cpu_var(__uv_hub_info))
+#define uv_hub_info this_cpu_ptr(&__uv_hub_info)
#define uv_cpu_hub_info(cpu) (&per_cpu(__uv_hub_info, cpu))
/*
@@ -601,16 +601,16 @@ struct uv_hub_nmi_s {
struct uv_cpu_nmi_s {
struct uv_hub_nmi_s *hub;
- atomic_t state;
- atomic_t pinging;
+ int state;
+ int pinging;
int queries;
int pings;
};
-DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-#define uv_cpu_nmi (__get_cpu_var(__uv_cpu_nmi))
+DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+
#define uv_hub_nmi (uv_cpu_nmi.hub)
-#define uv_cpu_nmi_per(cpu) (per_cpu(__uv_cpu_nmi, cpu))
+#define uv_cpu_nmi_per(cpu) (per_cpu(uv_cpu_nmi, cpu))
#define uv_hub_nmi_per(cpu) (uv_cpu_nmi_per(cpu).hub)
/* uv_cpu_nmi_states */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 3c3366c2e37f..f556c4843aa1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -70,4 +70,25 @@ static inline void gtod_write_end(struct vsyscall_gtod_data *s)
++s->seq;
}
+#ifdef CONFIG_X86_64
+
+#define VGETCPU_CPU_MASK 0xfff
+
+static inline unsigned int __getcpu(void)
+{
+ unsigned int p;
+
+ /*
+ * Load per CPU data from GDT. LSL is faster than RDTSCP and
+ * works on all CPUs. This is volatile so that it orders
+ * correctly wrt barrier() and to keep gcc from cleverly
+ * hoisting it out of the calling function.
+ */
+ asm volatile ("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+
+ return p;
+}
+
+#endif /* CONFIG_X86_64 */
+
#endif /* _ASM_X86_VGTOD_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index bcbfade26d8d..45afaee9555c 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -69,6 +69,7 @@
#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
+#define SECONDARY_EXEC_XSAVES 0x00100000
#define PIN_BASED_EXT_INTR_MASK 0x00000001
@@ -159,6 +160,8 @@ enum vmcs_field {
EOI_EXIT_BITMAP3_HIGH = 0x00002023,
VMREAD_BITMAP = 0x00002026,
VMWRITE_BITMAP = 0x00002028,
+ XSS_EXIT_BITMAP = 0x0000202C,
+ XSS_EXIT_BITMAP_HIGH = 0x0000202D,
GUEST_PHYSICAL_ADDRESS = 0x00002400,
GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
VMCS_LINK_POINTER = 0x00002800,
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index 2a46ca720afc..6ba66ee79710 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,15 +4,7 @@
#include <linux/seqlock.h>
#include <uapi/asm/vsyscall.h>
-#define VGETCPU_RDTSCP 1
-#define VGETCPU_LSL 2
-
-/* kernel space (writeable) */
-extern int vgetcpu_mode;
-extern struct timezone sys_tz;
-
-#include <asm/vvar.h>
-
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
extern void map_vsyscall(void);
/*
@@ -20,25 +12,12 @@ extern void map_vsyscall(void);
* Returns true if handled.
*/
extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
-
-#ifdef CONFIG_X86_64
-
-#define VGETCPU_CPU_MASK 0xfff
-
-static inline unsigned int __getcpu(void)
+#else
+static inline void map_vsyscall(void) {}
+static inline bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
{
- unsigned int p;
-
- if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) {
- /* Load per CPU data from RDTSCP */
- native_read_tscp(&p);
- } else {
- /* Load per CPU data from GDT */
- asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
- }
-
- return p;
+ return false;
}
-#endif /* CONFIG_X86_64 */
+#endif
#endif /* _ASM_X86_VSYSCALL_H */
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index 5d2b9ad2c6d2..3f32dfc2ab73 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -44,8 +44,6 @@ extern char __vvar_page;
/* DECLARE_VVAR(offset, type, name) */
-DECLARE_VVAR(0, volatile unsigned long, jiffies)
-DECLARE_VVAR(16, int, vgetcpu_mode)
DECLARE_VVAR(128, struct vsyscall_gtod_data, vsyscall_gtod_data)
#undef DECLARE_VVAR
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index e45e4da96bf1..f58a9c7a3c86 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -172,7 +172,6 @@ struct x86_platform_ops {
struct pci_dev;
struct msi_msg;
-struct msi_desc;
struct x86_msi_ops {
int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
@@ -183,8 +182,6 @@ struct x86_msi_ops {
void (*teardown_msi_irqs)(struct pci_dev *dev);
void (*restore_msi_irqs)(struct pci_dev *dev);
int (*setup_hpet_msi)(unsigned int irq, unsigned int id);
- u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag);
- u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag);
};
struct IO_APIC_route_entry;
diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h
new file mode 100644
index 000000000000..0d809e9fc975
--- /dev/null
+++ b/arch/x86/include/asm/xen/cpuid.h
@@ -0,0 +1,91 @@
+/******************************************************************************
+ * arch-x86/cpuid.h
+ *
+ * CPUID interface to Xen.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Copyright (c) 2007 Citrix Systems, Inc.
+ *
+ * Authors:
+ * Keir Fraser <keir@xen.org>
+ */
+
+#ifndef __XEN_PUBLIC_ARCH_X86_CPUID_H__
+#define __XEN_PUBLIC_ARCH_X86_CPUID_H__
+
+/*
+ * For compatibility with other hypervisor interfaces, the Xen cpuid leaves
+ * can be found at the first otherwise unused 0x100 aligned boundary starting
+ * from 0x40000000.
+ *
+ * e.g If viridian extensions are enabled for an HVM domain, the Xen cpuid
+ * leaves will start at 0x40000100
+ */
+
+#define XEN_CPUID_FIRST_LEAF 0x40000000
+#define XEN_CPUID_LEAF(i) (XEN_CPUID_FIRST_LEAF + (i))
+
+/*
+ * Leaf 1 (0x40000x00)
+ * EAX: Largest Xen-information leaf. All leaves up to an including @EAX
+ * are supported by the Xen host.
+ * EBX-EDX: "XenVMMXenVMM" signature, allowing positive identification
+ * of a Xen host.
+ */
+#define XEN_CPUID_SIGNATURE_EBX 0x566e6558 /* "XenV" */
+#define XEN_CPUID_SIGNATURE_ECX 0x65584d4d /* "MMXe" */
+#define XEN_CPUID_SIGNATURE_EDX 0x4d4d566e /* "nVMM" */
+
+/*
+ * Leaf 2 (0x40000x01)
+ * EAX[31:16]: Xen major version.
+ * EAX[15: 0]: Xen minor version.
+ * EBX-EDX: Reserved (currently all zeroes).
+ */
+
+/*
+ * Leaf 3 (0x40000x02)
+ * EAX: Number of hypercall transfer pages. This register is always guaranteed
+ * to specify one hypercall page.
+ * EBX: Base address of Xen-specific MSRs.
+ * ECX: Features 1. Unused bits are set to zero.
+ * EDX: Features 2. Unused bits are set to zero.
+ */
+
+/* Does the host support MMU_PT_UPDATE_PRESERVE_AD for this guest? */
+#define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0
+#define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD (1u<<0)
+
+/*
+ * Leaf 5 (0x40000x04)
+ * HVM-specific features
+ */
+
+/* EAX Features */
+/* Virtualized APIC registers */
+#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0)
+/* Virtualized x2APIC accesses */
+#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1)
+/* Memory mapped from other domains has valid IOMMU entries */
+#define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2)
+
+#define XEN_CPUID_MAX_NUM_LEAVES 4
+
+#endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */
diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
index 7f02fe4e2c7b..acd844c017d3 100644
--- a/arch/x86/include/asm/xen/page-coherent.h
+++ b/arch/x86/include/asm/xen/page-coherent.h
@@ -22,8 +22,8 @@ static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
}
static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
- unsigned long offset, size_t size, enum dma_data_direction dir,
- struct dma_attrs *attrs) { }
+ dma_addr_t dev_addr, unsigned long offset, size_t size,
+ enum dma_data_direction dir, struct dma_attrs *attrs) { }
static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
size_t size, enum dma_data_direction dir,
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index c949923a5668..5eea09915a15 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -41,10 +41,12 @@ typedef struct xpaddr {
extern unsigned long *machine_to_phys_mapping;
extern unsigned long machine_to_phys_nr;
+extern unsigned long *xen_p2m_addr;
+extern unsigned long xen_p2m_size;
+extern unsigned long xen_max_p2m_pfn;
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-extern bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern unsigned long set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e);
@@ -52,17 +54,52 @@ extern unsigned long set_phys_range_identity(unsigned long pfn_s,
extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count);
-extern int m2p_add_override(unsigned long mfn, struct page *page,
- struct gnttab_map_grant_ref *kmap_op);
extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_map_grant_ref *kmap_ops,
struct page **pages, unsigned int count);
-extern int m2p_remove_override(struct page *page,
- struct gnttab_map_grant_ref *kmap_op,
- unsigned long mfn);
-extern struct page *m2p_find_override(unsigned long mfn);
extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
+/*
+ * Helper functions to write or read unsigned long values to/from
+ * memory, when the access may fault.
+ */
+static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val)
+{
+ return __put_user(val, (unsigned long __user *)addr);
+}
+
+static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val)
+{
+ return __get_user(*val, (unsigned long __user *)addr);
+}
+
+/*
+ * When to use pfn_to_mfn(), __pfn_to_mfn() or get_phys_to_machine():
+ * - pfn_to_mfn() returns either INVALID_P2M_ENTRY or the mfn. No indicator
+ * bits (identity or foreign) are set.
+ * - __pfn_to_mfn() returns the found entry of the p2m table. A possibly set
+ * identity or foreign indicator will be still set. __pfn_to_mfn() is
+ * encapsulating get_phys_to_machine() which is called in special cases only.
+ * - get_phys_to_machine() is to be called by __pfn_to_mfn() only in special
+ * cases needing an extended handling.
+ */
+static inline unsigned long __pfn_to_mfn(unsigned long pfn)
+{
+ unsigned long mfn;
+
+ if (pfn < xen_p2m_size)
+ mfn = xen_p2m_addr[pfn];
+ else if (unlikely(pfn < xen_max_p2m_pfn))
+ return get_phys_to_machine(pfn);
+ else
+ return IDENTITY_FRAME(pfn);
+
+ if (unlikely(mfn == INVALID_P2M_ENTRY))
+ return get_phys_to_machine(pfn);
+
+ return mfn;
+}
+
static inline unsigned long pfn_to_mfn(unsigned long pfn)
{
unsigned long mfn;
@@ -70,7 +107,7 @@ static inline unsigned long pfn_to_mfn(unsigned long pfn)
if (xen_feature(XENFEAT_auto_translated_physmap))
return pfn;
- mfn = get_phys_to_machine(pfn);
+ mfn = __pfn_to_mfn(pfn);
if (mfn != INVALID_P2M_ENTRY)
mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
@@ -83,7 +120,7 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
if (xen_feature(XENFEAT_auto_translated_physmap))
return 1;
- return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
+ return __pfn_to_mfn(pfn) != INVALID_P2M_ENTRY;
}
static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
@@ -102,7 +139,7 @@ static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+ ret = xen_safe_read_ulong(&machine_to_phys_mapping[mfn], &pfn);
if (ret < 0)
return ~0;
@@ -117,7 +154,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
return mfn;
pfn = mfn_to_pfn_no_overrides(mfn);
- if (get_phys_to_machine(pfn) != mfn) {
+ if (__pfn_to_mfn(pfn) != mfn) {
/*
* If this appears to be a foreign mfn (because the pfn
* doesn't map back to the mfn), then check the local override
@@ -133,8 +170,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
* entry doesn't map back to the mfn and m2p_override doesn't have a
* valid entry for it.
*/
- if (pfn == ~0 &&
- get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+ if (pfn == ~0 && __pfn_to_mfn(mfn) == IDENTITY_FRAME(mfn))
pfn = mfn;
return pfn;
@@ -180,7 +216,7 @@ static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
return mfn;
pfn = mfn_to_pfn(mfn);
- if (get_phys_to_machine(pfn) != mfn)
+ if (__pfn_to_mfn(pfn) != mfn)
return -1; /* force !pfn_valid() */
return pfn;
}
@@ -236,4 +272,11 @@ void make_lowmem_page_readwrite(void *vaddr);
#define xen_remap(cookie, size) ioremap((cookie), (size));
#define xen_unmap(cookie) iounmap((cookie))
+static inline bool xen_arch_need_swiotlb(struct device *dev,
+ unsigned long pfn,
+ unsigned long mfn)
+{
+ return false;
+}
+
#endif /* _ASM_X86_XEN_PAGE_H */
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 7e7a79ada658..5fa9770035dc 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -16,6 +16,7 @@
#define XSTATE_Hi16_ZMM 0x80
#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE)
+#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
/* Bit 63 of XCR0 is reserved for future expansion */
#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63)))
diff --git a/arch/x86/include/uapi/asm/e820.h b/arch/x86/include/uapi/asm/e820.h
index bbae02470701..d993e33f5236 100644
--- a/arch/x86/include/uapi/asm/e820.h
+++ b/arch/x86/include/uapi/asm/e820.h
@@ -21,11 +21,6 @@
* this size.
*/
-/*
- * Odd: 'make headers_check' complains about numa.h if I try
- * to collapse the next two #ifdef lines to a single line:
- * #if defined(__KERNEL__) && defined(CONFIG_EFI)
- */
#ifndef __KERNEL__
#define E820_X_MAX E820MAX
#endif
diff --git a/arch/x86/include/uapi/asm/ldt.h b/arch/x86/include/uapi/asm/ldt.h
index 46727eb37bfe..6e1aaf73852a 100644
--- a/arch/x86/include/uapi/asm/ldt.h
+++ b/arch/x86/include/uapi/asm/ldt.h
@@ -28,6 +28,13 @@ struct user_desc {
unsigned int seg_not_present:1;
unsigned int useable:1;
#ifdef __x86_64__
+ /*
+ * Because this bit is not present in 32-bit user code, user
+ * programs can pass uninitialized values here. Therefore, in
+ * any context in which a user_desc comes from a 32-bit program,
+ * the kernel must act as though lm == 0, regardless of the
+ * actual value.
+ */
unsigned int lm:1;
#endif
};
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index e21331ce368f..c8aa65d56027 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -152,6 +152,45 @@
#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668
#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669
+/* Hardware P state interface */
+#define MSR_PPERF 0x0000064e
+#define MSR_PERF_LIMIT_REASONS 0x0000064f
+#define MSR_PM_ENABLE 0x00000770
+#define MSR_HWP_CAPABILITIES 0x00000771
+#define MSR_HWP_REQUEST_PKG 0x00000772
+#define MSR_HWP_INTERRUPT 0x00000773
+#define MSR_HWP_REQUEST 0x00000774
+#define MSR_HWP_STATUS 0x00000777
+
+/* CPUID.6.EAX */
+#define HWP_BASE_BIT (1<<7)
+#define HWP_NOTIFICATIONS_BIT (1<<8)
+#define HWP_ACTIVITY_WINDOW_BIT (1<<9)
+#define HWP_ENERGY_PERF_PREFERENCE_BIT (1<<10)
+#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11)
+
+/* IA32_HWP_CAPABILITIES */
+#define HWP_HIGHEST_PERF(x) (x & 0xff)
+#define HWP_GUARANTEED_PERF(x) ((x & (0xff << 8)) >>8)
+#define HWP_MOSTEFFICIENT_PERF(x) ((x & (0xff << 16)) >>16)
+#define HWP_LOWEST_PERF(x) ((x & (0xff << 24)) >>24)
+
+/* IA32_HWP_REQUEST */
+#define HWP_MIN_PERF(x) (x & 0xff)
+#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
+#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16)
+#define HWP_ENERGY_PERF_PREFERENCE(x) ((x & 0xff) << 24)
+#define HWP_ACTIVITY_WINDOW(x) ((x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x) ((x & 0x1) << 42)
+
+/* IA32_HWP_STATUS */
+#define HWP_GUARANTEED_CHANGE(x) (x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM(x) (x & 0x4)
+
+/* IA32_HWP_INTERRUPT */
+#define HWP_CHANGE_TO_GUARANTEED_INT(x) (x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM_INT(x) (x & 0x2)
+
#define MSR_AMD64_MC0_MASK 0xc0010044
#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x))
@@ -206,6 +245,7 @@
#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
#define MSR_AMD64_IBSCTL 0xc001103a
#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_IBSOPDATA4 0xc001103d
#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
/* Fam 16h MSRs */
@@ -345,6 +385,8 @@
#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2
+#define MSR_MISC_PWR_MGMT 0x000001aa
+
#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
#define ENERGY_PERF_BIAS_PERFORMANCE 0
#define ENERGY_PERF_BIAS_NORMAL 6
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 0e79420376eb..b813bf9da1e2 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -67,10 +67,13 @@
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
#define EXIT_REASON_PREEMPTION_TIMER 52
+#define EXIT_REASON_INVVPID 53
#define EXIT_REASON_WBINVD 54
#define EXIT_REASON_XSETBV 55
#define EXIT_REASON_APIC_WRITE 56
#define EXIT_REASON_INVPCID 58
+#define EXIT_REASON_XSAVES 63
+#define EXIT_REASON_XRSTORS 64
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
@@ -114,6 +117,9 @@
{ EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \
{ EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \
{ EXIT_REASON_INVD, "INVD" }, \
- { EXIT_REASON_INVPCID, "INVPCID" }
+ { EXIT_REASON_INVVPID, "INVVPID" }, \
+ { EXIT_REASON_INVPCID, "INVPCID" }, \
+ { EXIT_REASON_XSAVES, "XSAVES" }, \
+ { EXIT_REASON_XRSTORS, "XRSTORS" }
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index ada2e2d6be3e..5d4502c8b983 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,8 +28,7 @@ obj-$(CONFIG_X86_32) += i386_ksyms_32.o
obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o
obj-$(CONFIG_X86_64) += mcount_64.o
obj-y += syscall_$(BITS).o vsyscall_gtod.o
-obj-$(CONFIG_X86_64) += vsyscall_64.o
-obj-$(CONFIG_X86_64) += vsyscall_emu_64.o
+obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-y += bootflag.o e820.o
@@ -39,8 +38,6 @@ obj-y += tsc.o tsc_msr.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
-obj-$(CONFIG_PREEMPT) += preempt.o
-
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index b436fc735aa4..d1626364a28a 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -76,6 +76,19 @@ int acpi_fix_pin2_polarity __initdata;
static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
#endif
+/*
+ * Locks related to IOAPIC hotplug
+ * Hotplug side:
+ * ->device_hotplug_lock
+ * ->acpi_ioapic_lock
+ * ->ioapic_lock
+ * Interrupt mapping side:
+ * ->acpi_ioapic_lock
+ * ->ioapic_mutex
+ * ->ioapic_lock
+ */
+static DEFINE_MUTEX(acpi_ioapic_lock);
+
/* --------------------------------------------------------------------------
Boot-time Configuration
-------------------------------------------------------------------------- */
@@ -395,10 +408,6 @@ static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
return gsi;
- /* Don't set up the ACPI SCI because it's already set up */
- if (acpi_gbl_FADT.sci_interrupt == gsi)
- return gsi;
-
trigger = trigger == ACPI_EDGE_SENSITIVE ? 0 : 1;
polarity = polarity == ACPI_ACTIVE_HIGH ? 0 : 1;
node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
@@ -411,7 +420,8 @@ static int mp_register_gsi(struct device *dev, u32 gsi, int trigger,
if (irq < 0)
return irq;
- if (enable_update_mptable)
+ /* Don't set up the ACPI SCI because it's already set up */
+ if (enable_update_mptable && acpi_gbl_FADT.sci_interrupt != gsi)
mp_config_acpi_gsi(dev, gsi, trigger, polarity);
return irq;
@@ -424,9 +434,6 @@ static void mp_unregister_gsi(u32 gsi)
if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
return;
- if (acpi_gbl_FADT.sci_interrupt == gsi)
- return;
-
irq = mp_map_gsi_to_irq(gsi, 0);
if (irq > 0)
mp_unmap_irq(irq);
@@ -604,14 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
{
- int irq = mp_map_gsi_to_irq(gsi, IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
+ int irq;
- if (irq >= 0) {
+ if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
+ *irqp = gsi;
+ } else {
+ mutex_lock(&acpi_ioapic_lock);
+ irq = mp_map_gsi_to_irq(gsi,
+ IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
+ mutex_unlock(&acpi_ioapic_lock);
+ if (irq < 0)
+ return -1;
*irqp = irq;
- return 0;
}
-
- return -1;
+ return 0;
}
EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
@@ -646,7 +659,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
int irq = gsi;
#ifdef CONFIG_X86_IO_APIC
+ mutex_lock(&acpi_ioapic_lock);
irq = mp_register_gsi(dev, gsi, trigger, polarity);
+ mutex_unlock(&acpi_ioapic_lock);
#endif
return irq;
@@ -655,7 +670,9 @@ static int acpi_register_gsi_ioapic(struct device *dev, u32 gsi,
static void acpi_unregister_gsi_ioapic(u32 gsi)
{
#ifdef CONFIG_X86_IO_APIC
+ mutex_lock(&acpi_ioapic_lock);
mp_unregister_gsi(gsi);
+ mutex_unlock(&acpi_ioapic_lock);
#endif
}
@@ -686,6 +703,7 @@ void acpi_unregister_gsi(u32 gsi)
}
EXPORT_SYMBOL_GPL(acpi_unregister_gsi);
+#ifdef CONFIG_X86_LOCAL_APIC
static void __init acpi_set_irq_model_ioapic(void)
{
acpi_irq_model = ACPI_IRQ_MODEL_IOAPIC;
@@ -693,6 +711,7 @@ static void __init acpi_set_irq_model_ioapic(void)
__acpi_unregister_gsi = acpi_unregister_gsi_ioapic;
acpi_ioapic = 1;
}
+#endif
/*
* ACPI based hotplug support for CPU
@@ -731,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
}
/* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
{
return _acpi_map_lsapic(handle, physid, pcpu);
}
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
{
#ifdef CONFIG_ACPI_NUMA
set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
@@ -749,26 +768,79 @@ int acpi_unmap_lsapic(int cpu)
return (0);
}
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
#endif /* CONFIG_ACPI_HOTPLUG_CPU */
int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
{
- /* TBD */
- return -EINVAL;
-}
+ int ret = -ENOSYS;
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+ int ioapic_id;
+ u64 addr;
+ struct ioapic_domain_cfg cfg = {
+ .type = IOAPIC_DOMAIN_DYNAMIC,
+ .ops = &acpi_irqdomain_ops,
+ };
+
+ ioapic_id = acpi_get_ioapic_id(handle, gsi_base, &addr);
+ if (ioapic_id < 0) {
+ unsigned long long uid;
+ acpi_status status;
+
+ status = acpi_evaluate_integer(handle, METHOD_NAME__UID,
+ NULL, &uid);
+ if (ACPI_FAILURE(status)) {
+ acpi_handle_warn(handle, "failed to get IOAPIC ID.\n");
+ return -EINVAL;
+ }
+ ioapic_id = (int)uid;
+ }
+ mutex_lock(&acpi_ioapic_lock);
+ ret = mp_register_ioapic(ioapic_id, phys_addr, gsi_base, &cfg);
+ mutex_unlock(&acpi_ioapic_lock);
+#endif
+
+ return ret;
+}
EXPORT_SYMBOL(acpi_register_ioapic);
int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base)
{
- /* TBD */
- return -EINVAL;
-}
+ int ret = -ENOSYS;
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+ mutex_lock(&acpi_ioapic_lock);
+ ret = mp_unregister_ioapic(gsi_base);
+ mutex_unlock(&acpi_ioapic_lock);
+#endif
+ return ret;
+}
EXPORT_SYMBOL(acpi_unregister_ioapic);
+/**
+ * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base
+ * has been registered
+ * @handle: ACPI handle of the IOAPIC deivce
+ * @gsi_base: GSI base associated with the IOAPIC
+ *
+ * Assume caller holds some type of lock to serialize acpi_ioapic_registered()
+ * with acpi_register_ioapic()/acpi_unregister_ioapic().
+ */
+int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base)
+{
+ int ret = 0;
+
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+ mutex_lock(&acpi_ioapic_lock);
+ ret = mp_ioapic_registered(gsi_base);
+ mutex_unlock(&acpi_ioapic_lock);
+#endif
+
+ return ret;
+}
+
static int __init acpi_parse_sbf(struct acpi_table_header *table)
{
struct acpi_table_boot *sb;
@@ -1181,7 +1253,9 @@ static void __init acpi_process_madt(void)
/*
* Parse MADT IO-APIC entries
*/
+ mutex_lock(&acpi_ioapic_lock);
error = acpi_parse_madt_ioapic_entries();
+ mutex_unlock(&acpi_ioapic_lock);
if (!error) {
acpi_set_irq_model_ioapic();
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index f04dbb3069b8..5caed1dd7ccf 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -21,6 +21,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) },
{}
@@ -30,6 +31,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids);
static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) },
{}
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index af5b08ab3b71..b708738d016e 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -146,7 +146,7 @@ static inline int is_apbt_capable(void)
static int __init apbt_clockevent_register(void)
{
struct sfi_timer_table_entry *mtmr;
- struct apbt_dev *adev = &__get_cpu_var(cpu_apbt_dev);
+ struct apbt_dev *adev = this_cpu_ptr(&cpu_apbt_dev);
mtmr = sfi_get_mtmr(APBT_CLOCKEVENT0_NUM);
if (mtmr == NULL) {
@@ -185,8 +185,6 @@ static void apbt_setup_irq(struct apbt_dev *adev)
irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
- /* APB timer irqs are set up as mp_irqs, timer is edge type */
- __irq_set_handler(adev->irq, handle_edge_irq, 0, "edge");
}
/* Should be called with per cpu */
@@ -200,7 +198,7 @@ void apbt_setup_secondary_clock(void)
if (!cpu)
return;
- adev = &__get_cpu_var(cpu_apbt_dev);
+ adev = this_cpu_ptr(&cpu_apbt_dev);
if (!adev->timer) {
adev->timer = dw_apb_clockevent_init(cpu, adev->name,
APBT_CLOCKEVENT_RATING, adev_virt_addr(adev),
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index dcb5b15401ce..8bb12ddc5db8 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -2,10 +2,12 @@
# Makefile for local APIC drivers and for the IO-APIC code
#
-obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o
+obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o ipi.o vector.o
obj-y += hw_nmi.o
obj-$(CONFIG_X86_IO_APIC) += io_apic.o
+obj-$(CONFIG_PCI_MSI) += msi.o
+obj-$(CONFIG_HT_IRQ) += htirq.o
obj-$(CONFIG_SMP) += ipi.o
ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 67760275544b..29b5b18afa27 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -196,7 +196,7 @@ static int disable_apic_timer __initdata;
int local_apic_timer_c2_ok;
EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
-int first_system_vector = 0xfe;
+int first_system_vector = FIRST_SYSTEM_VECTOR;
/*
* Debug level, exported for io_apic.c
@@ -561,7 +561,7 @@ static DEFINE_PER_CPU(struct clock_event_device, lapic_events);
*/
static void setup_APIC_timer(void)
{
- struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+ struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
if (this_cpu_has(X86_FEATURE_ARAT)) {
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
@@ -696,7 +696,7 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
static int __init calibrate_APIC_clock(void)
{
- struct clock_event_device *levt = &__get_cpu_var(lapic_events);
+ struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
void (*real_handler)(struct clock_event_device *dev);
unsigned long deltaj;
long delta, deltatsc;
@@ -1297,7 +1297,7 @@ void setup_local_APIC(void)
unsigned int value, queued;
int i, j, acked = 0;
unsigned long long tsc = 0, ntsc;
- long long max_loops = cpu_khz;
+ long long max_loops = cpu_khz ? cpu_khz : 1000000;
if (cpu_has_tsc)
rdtscll(tsc);
@@ -1383,7 +1383,7 @@ void setup_local_APIC(void)
break;
}
if (queued) {
- if (cpu_has_tsc) {
+ if (cpu_has_tsc && cpu_khz) {
rdtscll(ntsc);
max_loops = (cpu_khz << 10) - (ntsc - tsc);
} else
@@ -1930,7 +1930,7 @@ int __init APIC_init_uniprocessor(void)
/*
* This interrupt should _never_ happen with our APIC/SMP architecture
*/
-static inline void __smp_spurious_interrupt(void)
+static inline void __smp_spurious_interrupt(u8 vector)
{
u32 v;
@@ -1939,30 +1939,32 @@ static inline void __smp_spurious_interrupt(void)
* if it is a vectored one. Just in case...
* Spurious interrupts should not be ACKed.
*/
- v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
- if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
+ v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1));
+ if (v & (1 << (vector & 0x1f)))
ack_APIC_irq();
inc_irq_stat(irq_spurious_count);
/* see sw-dev-man vol 3, chapter 7.4.13.5 */
- pr_info("spurious APIC interrupt on CPU#%d, "
- "should never happen.\n", smp_processor_id());
+ pr_info("spurious APIC interrupt through vector %02x on CPU#%d, "
+ "should never happen.\n", vector, smp_processor_id());
}
__visible void smp_spurious_interrupt(struct pt_regs *regs)
{
entering_irq();
- __smp_spurious_interrupt();
+ __smp_spurious_interrupt(~regs->orig_ax);
exiting_irq();
}
__visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
{
+ u8 vector = ~regs->orig_ax;
+
entering_irq();
- trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
- __smp_spurious_interrupt();
- trace_spurious_apic_exit(SPURIOUS_APIC_VECTOR);
+ trace_spurious_apic_entry(vector);
+ __smp_spurious_interrupt(vector);
+ trace_spurious_apic_exit(vector);
exiting_irq();
}
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index ae915391ebec..c2fd21fed002 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -32,7 +32,7 @@
static int numachip_system __read_mostly;
-static const struct apic apic_numachip __read_mostly;
+static const struct apic apic_numachip;
static unsigned int get_apic_id(unsigned long x)
{
@@ -40,7 +40,7 @@ static unsigned int get_apic_id(unsigned long x)
unsigned int id;
rdmsrl(MSR_FAM10H_NODE_ID, value);
- id = ((x >> 24) & 0xffU) | ((value << 2) & 0x3f00U);
+ id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
return id;
}
@@ -145,7 +145,7 @@ static void numachip_send_IPI_all(int vector)
static void numachip_send_IPI_self(int vector)
{
- __default_send_IPI_shortcut(APIC_DEST_SELF, vector, APIC_DEST_PHYSICAL);
+ apic_write(APIC_SELF_IPI, vector);
}
static int __init numachip_probe(void)
@@ -153,20 +153,8 @@ static int __init numachip_probe(void)
return apic == &apic_numachip;
}
-static void __init map_csrs(void)
-{
- printk(KERN_INFO "NumaChip: Mapping local CSR space (%016llx - %016llx)\n",
- NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_BASE + NUMACHIP_LCSR_SIZE - 1);
- init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE);
-
- printk(KERN_INFO "NumaChip: Mapping global CSR space (%016llx - %016llx)\n",
- NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_BASE + NUMACHIP_GCSR_SIZE - 1);
- init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE);
-}
-
static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
{
-
if (c->phys_proc_id != node) {
c->phys_proc_id = node;
per_cpu(cpu_llc_id, smp_processor_id()) = node;
@@ -175,19 +163,15 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
static int __init numachip_system_init(void)
{
- unsigned int val;
-
if (!numachip_system)
return 0;
+ init_extra_mapping_uc(NUMACHIP_LCSR_BASE, NUMACHIP_LCSR_SIZE);
+ init_extra_mapping_uc(NUMACHIP_GCSR_BASE, NUMACHIP_GCSR_SIZE);
+
x86_cpuinit.fixup_cpu_id = fixup_cpu_id;
x86_init.pci.arch_init = pci_numachip_init;
- map_csrs();
-
- val = read_lcsr(CSR_G0_NODE_IDS);
- printk(KERN_INFO "NumaChip: Local NodeID = %08x\n", val);
-
return 0;
}
early_initcall(numachip_system_init);
diff --git a/arch/x86/kernel/apic/htirq.c b/arch/x86/kernel/apic/htirq.c
new file mode 100644
index 000000000000..816f36e979ad
--- /dev/null
+++ b/arch/x86/kernel/apic/htirq.c
@@ -0,0 +1,107 @@
+/*
+ * Support Hypertransport IRQ
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ * Moved from arch/x86/kernel/apic/io_apic.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/htirq.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/hypertransport.h>
+
+/*
+ * Hypertransport interrupt support
+ */
+static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
+{
+ struct ht_irq_msg msg;
+
+ fetch_ht_irq_msg(irq, &msg);
+
+ msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
+ msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+
+ msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
+ msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
+
+ write_ht_irq_msg(irq, &msg);
+}
+
+static int
+ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+{
+ struct irq_cfg *cfg = irqd_cfg(data);
+ unsigned int dest;
+ int ret;
+
+ ret = apic_set_affinity(data, mask, &dest);
+ if (ret)
+ return ret;
+
+ target_ht_irq(data->irq, dest, cfg->vector);
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static struct irq_chip ht_irq_chip = {
+ .name = "PCI-HT",
+ .irq_mask = mask_ht_irq,
+ .irq_unmask = unmask_ht_irq,
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = ht_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
+{
+ struct irq_cfg *cfg;
+ struct ht_irq_msg msg;
+ unsigned dest;
+ int err;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ cfg = irq_cfg(irq);
+ err = assign_irq_vector(irq, cfg, apic->target_cpus());
+ if (err)
+ return err;
+
+ err = apic->cpu_mask_to_apicid_and(cfg->domain,
+ apic->target_cpus(), &dest);
+ if (err)
+ return err;
+
+ msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
+
+ msg.address_lo =
+ HT_IRQ_LOW_BASE |
+ HT_IRQ_LOW_DEST_ID(dest) |
+ HT_IRQ_LOW_VECTOR(cfg->vector) |
+ ((apic->irq_dest_mode == 0) ?
+ HT_IRQ_LOW_DM_PHYSICAL :
+ HT_IRQ_LOW_DM_LOGICAL) |
+ HT_IRQ_LOW_RQEOI_EDGE |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ HT_IRQ_LOW_MT_FIXED :
+ HT_IRQ_LOW_MT_ARBITRATED) |
+ HT_IRQ_LOW_IRQ_MASKED;
+
+ write_ht_irq_msg(irq, &msg);
+
+ irq_set_chip_and_handler_name(irq, &ht_irq_chip,
+ handle_edge_irq, "edge");
+
+ dev_dbg(&dev->dev, "irq %d for HT\n", irq);
+
+ return 0;
+}
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 6a1e71bde323..6873ab925d00 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -18,6 +18,7 @@
#include <linux/nmi.h>
#include <linux/module.h>
#include <linux/delay.h>
+#include <linux/seq_buf.h>
#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(int watchdog_thresh)
@@ -29,14 +30,35 @@ u64 hw_nmi_get_sample_period(int watchdog_thresh)
#ifdef arch_trigger_all_cpu_backtrace
/* For reliability, we're prepared to waste bits here. */
static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+static cpumask_t printtrace_mask;
+
+#define NMI_BUF_SIZE 4096
+
+struct nmi_seq_buf {
+ unsigned char buffer[NMI_BUF_SIZE];
+ struct seq_buf seq;
+};
+
+/* Safe printing in NMI context */
+static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);
/* "in progress" flag of arch_trigger_all_cpu_backtrace */
static unsigned long backtrace_flag;
+static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
+{
+ const char *buf = s->buffer + start;
+
+ printk("%.*s", (end - start) + 1, buf);
+}
+
void arch_trigger_all_cpu_backtrace(bool include_self)
{
+ struct nmi_seq_buf *s;
+ int len;
+ int cpu;
int i;
- int cpu = get_cpu();
+ int this_cpu = get_cpu();
if (test_and_set_bit(0, &backtrace_flag)) {
/*
@@ -49,7 +71,17 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
if (!include_self)
- cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+ cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask));
+
+ cpumask_copy(&printtrace_mask, to_cpumask(backtrace_mask));
+ /*
+ * Set up per_cpu seq_buf buffers that the NMIs running on the other
+ * CPUs will write to.
+ */
+ for_each_cpu(cpu, to_cpumask(backtrace_mask)) {
+ s = &per_cpu(nmi_print_seq, cpu);
+ seq_buf_init(&s->seq, s->buffer, NMI_BUF_SIZE);
+ }
if (!cpumask_empty(to_cpumask(backtrace_mask))) {
pr_info("sending NMI to %s CPUs:\n",
@@ -65,11 +97,58 @@ void arch_trigger_all_cpu_backtrace(bool include_self)
touch_softlockup_watchdog();
}
+ /*
+ * Now that all the NMIs have triggered, we can dump out their
+ * back traces safely to the console.
+ */
+ for_each_cpu(cpu, &printtrace_mask) {
+ int last_i = 0;
+
+ s = &per_cpu(nmi_print_seq, cpu);
+ len = seq_buf_used(&s->seq);
+ if (!len)
+ continue;
+
+ /* Print line by line. */
+ for (i = 0; i < len; i++) {
+ if (s->buffer[i] == '\n') {
+ print_seq_line(s, last_i, i);
+ last_i = i + 1;
+ }
+ }
+ /* Check if there was a partial line. */
+ if (last_i < len) {
+ print_seq_line(s, last_i, len - 1);
+ pr_cont("\n");
+ }
+ }
+
clear_bit(0, &backtrace_flag);
smp_mb__after_atomic();
put_cpu();
}
+/*
+ * It is not safe to call printk() directly from NMI handlers.
+ * It may be fine if the NMI detected a lock up and we have no choice
+ * but to do so, but doing a NMI on all other CPUs to get a back trace
+ * can be done with a sysrq-l. We don't want that to lock up, which
+ * can happen if the NMI interrupts a printk in progress.
+ *
+ * Instead, we redirect the vprintk() to this nmi_vprintk() that writes
+ * the content into a per cpu seq_buf buffer. Then when the NMIs are
+ * all done, we can safely dump the contents of the seq_buf to a printk()
+ * from a non NMI context.
+ */
+static int nmi_vprintk(const char *fmt, va_list args)
+{
+ struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
+ unsigned int len = seq_buf_used(&s->seq);
+
+ seq_buf_vprintf(&s->seq, fmt, args);
+ return seq_buf_used(&s->seq) - len;
+}
+
static int
arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
{
@@ -78,12 +157,14 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
cpu = smp_processor_id();
if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
- static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
+ printk_func_t printk_func_save = this_cpu_read(printk_func);
- arch_spin_lock(&lock);
+ /* Replace printk to write into the NMI seq */
+ this_cpu_write(printk_func, nmi_vprintk);
printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
show_regs(regs);
- arch_spin_unlock(&lock);
+ this_cpu_write(printk_func, printk_func_save);
+
cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
return NMI_HANDLED;
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 337ce5a9b15c..3f5f60406ab1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -32,15 +32,11 @@
#include <linux/module.h>
#include <linux/syscore_ops.h>
#include <linux/irqdomain.h>
-#include <linux/msi.h>
-#include <linux/htirq.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/jiffies.h> /* time_after() */
#include <linux/slab.h>
#include <linux/bootmem.h>
-#include <linux/dmar.h>
-#include <linux/hpet.h>
#include <asm/idle.h>
#include <asm/io.h>
@@ -52,17 +48,12 @@
#include <asm/dma.h>
#include <asm/timer.h>
#include <asm/i8259.h>
-#include <asm/msidef.h>
-#include <asm/hypertransport.h>
#include <asm/setup.h>
#include <asm/irq_remapping.h>
-#include <asm/hpet.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
-#define __apicdebuginit(type) static type __init
-
#define for_each_ioapic(idx) \
for ((idx) = 0; (idx) < nr_ioapics; (idx)++)
#define for_each_ioapic_reverse(idx) \
@@ -74,7 +65,7 @@
for_each_pin((idx), (pin))
#define for_each_irq_pin(entry, head) \
- for (entry = head; entry; entry = entry->next)
+ list_for_each_entry(entry, &head, list)
/*
* Is the SiS APIC rmw bug present ?
@@ -83,7 +74,6 @@
int sis_apic_bug = -1;
static DEFINE_RAW_SPINLOCK(ioapic_lock);
-static DEFINE_RAW_SPINLOCK(vector_lock);
static DEFINE_MUTEX(ioapic_mutex);
static unsigned int ioapic_dynirq_base;
static int ioapic_initialized;
@@ -112,6 +102,7 @@ static struct ioapic {
struct ioapic_domain_cfg irqdomain_cfg;
struct irq_domain *irqdomain;
struct mp_pin_info *pin_info;
+ struct resource *iomem_res;
} ioapics[MAX_IO_APICS];
#define mpc_ioapic_ver(ioapic_idx) ioapics[ioapic_idx].mp_config.apicver
@@ -205,8 +196,6 @@ static int __init parse_noapic(char *str)
}
early_param("noapic", parse_noapic);
-static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node);
-
/* Will be called in mpparse/acpi/sfi codes for saving IRQ info */
void mp_save_irq(struct mpc_intsrc *m)
{
@@ -228,8 +217,8 @@ void mp_save_irq(struct mpc_intsrc *m)
}
struct irq_pin_list {
+ struct list_head list;
int apic, pin;
- struct irq_pin_list *next;
};
static struct irq_pin_list *alloc_irq_pin_list(int node)
@@ -237,7 +226,26 @@ static struct irq_pin_list *alloc_irq_pin_list(int node)
return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
}
-int __init arch_early_irq_init(void)
+static void alloc_ioapic_saved_registers(int idx)
+{
+ size_t size;
+
+ if (ioapics[idx].saved_registers)
+ return;
+
+ size = sizeof(struct IO_APIC_route_entry) * ioapics[idx].nr_registers;
+ ioapics[idx].saved_registers = kzalloc(size, GFP_KERNEL);
+ if (!ioapics[idx].saved_registers)
+ pr_err("IOAPIC %d: suspend/resume impossible!\n", idx);
+}
+
+static void free_ioapic_saved_registers(int idx)
+{
+ kfree(ioapics[idx].saved_registers);
+ ioapics[idx].saved_registers = NULL;
+}
+
+int __init arch_early_ioapic_init(void)
{
struct irq_cfg *cfg;
int i, node = cpu_to_node(0);
@@ -245,13 +253,8 @@ int __init arch_early_irq_init(void)
if (!nr_legacy_irqs())
io_apic_irqs = ~0UL;
- for_each_ioapic(i) {
- ioapics[i].saved_registers =
- kzalloc(sizeof(struct IO_APIC_route_entry) *
- ioapics[i].nr_registers, GFP_KERNEL);
- if (!ioapics[i].saved_registers)
- pr_err("IOAPIC %d: suspend/resume impossible!\n", i);
- }
+ for_each_ioapic(i)
+ alloc_ioapic_saved_registers(i);
/*
* For legacy IRQ's, start with assigning irq0 to irq15 to
@@ -266,61 +269,6 @@ int __init arch_early_irq_init(void)
return 0;
}
-static inline struct irq_cfg *irq_cfg(unsigned int irq)
-{
- return irq_get_chip_data(irq);
-}
-
-static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
-{
- struct irq_cfg *cfg;
-
- cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
- if (!cfg)
- return NULL;
- if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
- goto out_cfg;
- if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
- goto out_domain;
- return cfg;
-out_domain:
- free_cpumask_var(cfg->domain);
-out_cfg:
- kfree(cfg);
- return NULL;
-}
-
-static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
-{
- if (!cfg)
- return;
- irq_set_chip_data(at, NULL);
- free_cpumask_var(cfg->domain);
- free_cpumask_var(cfg->old_domain);
- kfree(cfg);
-}
-
-static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
-{
- int res = irq_alloc_desc_at(at, node);
- struct irq_cfg *cfg;
-
- if (res < 0) {
- if (res != -EEXIST)
- return NULL;
- cfg = irq_cfg(at);
- if (cfg)
- return cfg;
- }
-
- cfg = alloc_irq_cfg(at, node);
- if (cfg)
- irq_set_chip_data(at, cfg);
- else
- irq_free_desc(at);
- return cfg;
-}
-
struct io_apic {
unsigned int index;
unsigned int unused[3];
@@ -445,15 +393,12 @@ static void ioapic_mask_entry(int apic, int pin)
*/
static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
{
- struct irq_pin_list **last, *entry;
+ struct irq_pin_list *entry;
/* don't allow duplicates */
- last = &cfg->irq_2_pin;
- for_each_irq_pin(entry, cfg->irq_2_pin) {
+ for_each_irq_pin(entry, cfg->irq_2_pin)
if (entry->apic == apic && entry->pin == pin)
return 0;
- last = &entry->next;
- }
entry = alloc_irq_pin_list(node);
if (!entry) {
@@ -464,22 +409,19 @@ static int __add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pi
entry->apic = apic;
entry->pin = pin;
- *last = entry;
+ list_add_tail(&entry->list, &cfg->irq_2_pin);
return 0;
}
static void __remove_pin_from_irq(struct irq_cfg *cfg, int apic, int pin)
{
- struct irq_pin_list **last, *entry;
+ struct irq_pin_list *tmp, *entry;
- last = &cfg->irq_2_pin;
- for_each_irq_pin(entry, cfg->irq_2_pin)
+ list_for_each_entry_safe(entry, tmp, &cfg->irq_2_pin, list)
if (entry->apic == apic && entry->pin == pin) {
- *last = entry->next;
+ list_del(&entry->list);
kfree(entry);
return;
- } else {
- last = &entry->next;
}
}
@@ -559,7 +501,7 @@ static void mask_ioapic(struct irq_cfg *cfg)
static void mask_ioapic_irq(struct irq_data *data)
{
- mask_ioapic(data->chip_data);
+ mask_ioapic(irqd_cfg(data));
}
static void __unmask_ioapic(struct irq_cfg *cfg)
@@ -578,7 +520,7 @@ static void unmask_ioapic(struct irq_cfg *cfg)
static void unmask_ioapic_irq(struct irq_data *data)
{
- unmask_ioapic(data->chip_data);
+ unmask_ioapic(irqd_cfg(data));
}
/*
@@ -1164,8 +1106,7 @@ void mp_unmap_irq(int irq)
* Find a specific PCI IRQ entry.
* Not an __init, possibly needed by modules
*/
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
- struct io_apic_irq_attr *irq_attr)
+int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
{
int irq, i, best_ioapic = -1, best_idx = -1;
@@ -1219,195 +1160,11 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin,
return -1;
out:
- irq = pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq,
- IOAPIC_MAP_ALLOC);
- if (irq > 0)
- set_io_apic_irq_attr(irq_attr, best_ioapic,
- mp_irqs[best_idx].dstirq,
- irq_trigger(best_idx),
- irq_polarity(best_idx));
- return irq;
+ return pin_2_irq(best_idx, best_ioapic, mp_irqs[best_idx].dstirq,
+ IOAPIC_MAP_ALLOC);
}
EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
-void lock_vector_lock(void)
-{
- /* Used to the online set of cpus does not change
- * during assign_irq_vector.
- */
- raw_spin_lock(&vector_lock);
-}
-
-void unlock_vector_lock(void)
-{
- raw_spin_unlock(&vector_lock);
-}
-
-static int
-__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
-{
- /*
- * NOTE! The local APIC isn't very good at handling
- * multiple interrupts at the same interrupt level.
- * As the interrupt level is determined by taking the
- * vector number and shifting that right by 4, we
- * want to spread these out a bit so that they don't
- * all fall in the same interrupt level.
- *
- * Also, we've got to be careful not to trash gate
- * 0x80, because int 0x80 is hm, kind of importantish. ;)
- */
- static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
- static int current_offset = VECTOR_OFFSET_START % 16;
- int cpu, err;
- cpumask_var_t tmp_mask;
-
- if (cfg->move_in_progress)
- return -EBUSY;
-
- if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
- return -ENOMEM;
-
- /* Only try and allocate irqs on cpus that are present */
- err = -ENOSPC;
- cpumask_clear(cfg->old_domain);
- cpu = cpumask_first_and(mask, cpu_online_mask);
- while (cpu < nr_cpu_ids) {
- int new_cpu, vector, offset;
-
- apic->vector_allocation_domain(cpu, tmp_mask, mask);
-
- if (cpumask_subset(tmp_mask, cfg->domain)) {
- err = 0;
- if (cpumask_equal(tmp_mask, cfg->domain))
- break;
- /*
- * New cpumask using the vector is a proper subset of
- * the current in use mask. So cleanup the vector
- * allocation for the members that are not used anymore.
- */
- cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
- cpumask_and(cfg->domain, cfg->domain, tmp_mask);
- break;
- }
-
- vector = current_vector;
- offset = current_offset;
-next:
- vector += 16;
- if (vector >= first_system_vector) {
- offset = (offset + 1) % 16;
- vector = FIRST_EXTERNAL_VECTOR + offset;
- }
-
- if (unlikely(current_vector == vector)) {
- cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
- cpumask_andnot(tmp_mask, mask, cfg->old_domain);
- cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
- continue;
- }
-
- if (test_bit(vector, used_vectors))
- goto next;
-
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
- if (per_cpu(vector_irq, new_cpu)[vector] > VECTOR_UNDEFINED)
- goto next;
- }
- /* Found one! */
- current_vector = vector;
- current_offset = offset;
- if (cfg->vector) {
- cpumask_copy(cfg->old_domain, cfg->domain);
- cfg->move_in_progress =
- cpumask_intersects(cfg->old_domain, cpu_online_mask);
- }
- for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
- per_cpu(vector_irq, new_cpu)[vector] = irq;
- cfg->vector = vector;
- cpumask_copy(cfg->domain, tmp_mask);
- err = 0;
- break;
- }
- free_cpumask_var(tmp_mask);
- return err;
-}
-
-int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
-{
- int err;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&vector_lock, flags);
- err = __assign_irq_vector(irq, cfg, mask);
- raw_spin_unlock_irqrestore(&vector_lock, flags);
- return err;
-}
-
-static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
-{
- int cpu, vector;
-
- BUG_ON(!cfg->vector);
-
- vector = cfg->vector;
- for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
- per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
-
- cfg->vector = 0;
- cpumask_clear(cfg->domain);
-
- if (likely(!cfg->move_in_progress))
- return;
- for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
- for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
- if (per_cpu(vector_irq, cpu)[vector] != irq)
- continue;
- per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
- break;
- }
- }
- cfg->move_in_progress = 0;
-}
-
-void __setup_vector_irq(int cpu)
-{
- /* Initialize vector_irq on a new cpu */
- int irq, vector;
- struct irq_cfg *cfg;
-
- /*
- * vector_lock will make sure that we don't run into irq vector
- * assignments that might be happening on another cpu in parallel,
- * while we setup our initial vector to irq mappings.
- */
- raw_spin_lock(&vector_lock);
- /* Mark the inuse vectors */
- for_each_active_irq(irq) {
- cfg = irq_cfg(irq);
- if (!cfg)
- continue;
-
- if (!cpumask_test_cpu(cpu, cfg->domain))
- continue;
- vector = cfg->vector;
- per_cpu(vector_irq, cpu)[vector] = irq;
- }
- /* Mark the free vectors */
- for (vector = 0; vector < NR_VECTORS; ++vector) {
- irq = per_cpu(vector_irq, cpu)[vector];
- if (irq <= VECTOR_UNDEFINED)
- continue;
-
- cfg = irq_cfg(irq);
- if (!cpumask_test_cpu(cpu, cfg->domain))
- per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
- }
- raw_spin_unlock(&vector_lock);
-}
-
static struct irq_chip ioapic_chip;
#ifdef CONFIG_X86_32
@@ -1496,7 +1253,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
&dest)) {
pr_warn("Failed to obtain apicid for ioapic %d, pin %d\n",
mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- __clear_irq_vector(irq, cfg);
+ clear_irq_vector(irq, cfg);
return;
}
@@ -1510,7 +1267,7 @@ static void setup_ioapic_irq(unsigned int irq, struct irq_cfg *cfg,
if (x86_io_apic_ops.setup_entry(irq, &entry, dest, cfg->vector, attr)) {
pr_warn("Failed to setup ioapic entry for ioapic %d, pin %d\n",
mpc_ioapic_id(attr->ioapic), attr->ioapic_pin);
- __clear_irq_vector(irq, cfg);
+ clear_irq_vector(irq, cfg);
return;
}
@@ -1641,7 +1398,7 @@ void ioapic_zap_locks(void)
raw_spin_lock_init(&ioapic_lock);
}
-__apicdebuginit(void) print_IO_APIC(int ioapic_idx)
+static void __init print_IO_APIC(int ioapic_idx)
{
union IO_APIC_reg_00 reg_00;
union IO_APIC_reg_01 reg_01;
@@ -1698,7 +1455,7 @@ __apicdebuginit(void) print_IO_APIC(int ioapic_idx)
x86_io_apic_ops.print_entries(ioapic_idx, reg_01.bits.entries);
}
-__apicdebuginit(void) print_IO_APICs(void)
+void __init print_IO_APICs(void)
{
int ioapic_idx;
struct irq_cfg *cfg;
@@ -1731,8 +1488,7 @@ __apicdebuginit(void) print_IO_APICs(void)
cfg = irq_cfg(irq);
if (!cfg)
continue;
- entry = cfg->irq_2_pin;
- if (!entry)
+ if (list_empty(&cfg->irq_2_pin))
continue;
printk(KERN_DEBUG "IRQ%d ", irq);
for_each_irq_pin(entry, cfg->irq_2_pin)
@@ -1743,205 +1499,6 @@ __apicdebuginit(void) print_IO_APICs(void)
printk(KERN_INFO ".................................... done.\n");
}
-__apicdebuginit(void) print_APIC_field(int base)
-{
- int i;
-
- printk(KERN_DEBUG);
-
- for (i = 0; i < 8; i++)
- pr_cont("%08x", apic_read(base + i*0x10));
-
- pr_cont("\n");
-}
-
-__apicdebuginit(void) print_local_APIC(void *dummy)
-{
- unsigned int i, v, ver, maxlvt;
- u64 icr;
-
- printk(KERN_DEBUG "printing local APIC contents on CPU#%d/%d:\n",
- smp_processor_id(), hard_smp_processor_id());
- v = apic_read(APIC_ID);
- printk(KERN_INFO "... APIC ID: %08x (%01x)\n", v, read_apic_id());
- v = apic_read(APIC_LVR);
- printk(KERN_INFO "... APIC VERSION: %08x\n", v);
- ver = GET_APIC_VERSION(v);
- maxlvt = lapic_get_maxlvt();
-
- v = apic_read(APIC_TASKPRI);
- printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
-
- if (APIC_INTEGRATED(ver)) { /* !82489DX */
- if (!APIC_XAPIC(ver)) {
- v = apic_read(APIC_ARBPRI);
- printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
- v & APIC_ARBPRI_MASK);
- }
- v = apic_read(APIC_PROCPRI);
- printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v);
- }
-
- /*
- * Remote read supported only in the 82489DX and local APIC for
- * Pentium processors.
- */
- if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
- v = apic_read(APIC_RRR);
- printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
- }
-
- v = apic_read(APIC_LDR);
- printk(KERN_DEBUG "... APIC LDR: %08x\n", v);
- if (!x2apic_enabled()) {
- v = apic_read(APIC_DFR);
- printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
- }
- v = apic_read(APIC_SPIV);
- printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
-
- printk(KERN_DEBUG "... APIC ISR field:\n");
- print_APIC_field(APIC_ISR);
- printk(KERN_DEBUG "... APIC TMR field:\n");
- print_APIC_field(APIC_TMR);
- printk(KERN_DEBUG "... APIC IRR field:\n");
- print_APIC_field(APIC_IRR);
-
- if (APIC_INTEGRATED(ver)) { /* !82489DX */
- if (maxlvt > 3) /* Due to the Pentium erratum 3AP. */
- apic_write(APIC_ESR, 0);
-
- v = apic_read(APIC_ESR);
- printk(KERN_DEBUG "... APIC ESR: %08x\n", v);
- }
-
- icr = apic_icr_read();
- printk(KERN_DEBUG "... APIC ICR: %08x\n", (u32)icr);
- printk(KERN_DEBUG "... APIC ICR2: %08x\n", (u32)(icr >> 32));
-
- v = apic_read(APIC_LVTT);
- printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);
-
- if (maxlvt > 3) { /* PC is LVT#4. */
- v = apic_read(APIC_LVTPC);
- printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v);
- }
- v = apic_read(APIC_LVT0);
- printk(KERN_DEBUG "... APIC LVT0: %08x\n", v);
- v = apic_read(APIC_LVT1);
- printk(KERN_DEBUG "... APIC LVT1: %08x\n", v);
-
- if (maxlvt > 2) { /* ERR is LVT#3. */
- v = apic_read(APIC_LVTERR);
- printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v);
- }
-
- v = apic_read(APIC_TMICT);
- printk(KERN_DEBUG "... APIC TMICT: %08x\n", v);
- v = apic_read(APIC_TMCCT);
- printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
- v = apic_read(APIC_TDCR);
- printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
-
- if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
- v = apic_read(APIC_EFEAT);
- maxlvt = (v >> 16) & 0xff;
- printk(KERN_DEBUG "... APIC EFEAT: %08x\n", v);
- v = apic_read(APIC_ECTRL);
- printk(KERN_DEBUG "... APIC ECTRL: %08x\n", v);
- for (i = 0; i < maxlvt; i++) {
- v = apic_read(APIC_EILVTn(i));
- printk(KERN_DEBUG "... APIC EILVT%d: %08x\n", i, v);
- }
- }
- pr_cont("\n");
-}
-
-__apicdebuginit(void) print_local_APICs(int maxcpu)
-{
- int cpu;
-
- if (!maxcpu)
- return;
-
- preempt_disable();
- for_each_online_cpu(cpu) {
- if (cpu >= maxcpu)
- break;
- smp_call_function_single(cpu, print_local_APIC, NULL, 1);
- }
- preempt_enable();
-}
-
-__apicdebuginit(void) print_PIC(void)
-{
- unsigned int v;
- unsigned long flags;
-
- if (!nr_legacy_irqs())
- return;
-
- printk(KERN_DEBUG "\nprinting PIC contents\n");
-
- raw_spin_lock_irqsave(&i8259A_lock, flags);
-
- v = inb(0xa1) << 8 | inb(0x21);
- printk(KERN_DEBUG "... PIC IMR: %04x\n", v);
-
- v = inb(0xa0) << 8 | inb(0x20);
- printk(KERN_DEBUG "... PIC IRR: %04x\n", v);
-
- outb(0x0b,0xa0);
- outb(0x0b,0x20);
- v = inb(0xa0) << 8 | inb(0x20);
- outb(0x0a,0xa0);
- outb(0x0a,0x20);
-
- raw_spin_unlock_irqrestore(&i8259A_lock, flags);
-
- printk(KERN_DEBUG "... PIC ISR: %04x\n", v);
-
- v = inb(0x4d1) << 8 | inb(0x4d0);
- printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
-}
-
-static int __initdata show_lapic = 1;
-static __init int setup_show_lapic(char *arg)
-{
- int num = -1;
-
- if (strcmp(arg, "all") == 0) {
- show_lapic = CONFIG_NR_CPUS;
- } else {
- get_option(&arg, &num);
- if (num >= 0)
- show_lapic = num;
- }
-
- return 1;
-}
-__setup("show_lapic=", setup_show_lapic);
-
-__apicdebuginit(int) print_ICs(void)
-{
- if (apic_verbosity == APIC_QUIET)
- return 0;
-
- print_PIC();
-
- /* don't print out if apic is not there */
- if (!cpu_has_apic && !apic_from_smp_config())
- return 0;
-
- print_local_APICs(show_lapic);
- print_IO_APICs();
-
- return 0;
-}
-
-late_initcall(print_ICs);
-
-
/* Where if anywhere is the i8259 connect in external int mode */
static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
@@ -2244,26 +1801,12 @@ static unsigned int startup_ioapic_irq(struct irq_data *data)
if (legacy_pic->irq_pending(irq))
was_pending = 1;
}
- __unmask_ioapic(data->chip_data);
+ __unmask_ioapic(irqd_cfg(data));
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return was_pending;
}
-static int ioapic_retrigger_irq(struct irq_data *data)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned long flags;
- int cpu;
-
- raw_spin_lock_irqsave(&vector_lock, flags);
- cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
- apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
- raw_spin_unlock_irqrestore(&vector_lock, flags);
-
- return 1;
-}
-
/*
* Level and edge triggered IO-APIC interrupts need different handling,
* so we use two separate IRQ descriptors. Edge triggered IRQs can be
@@ -2273,113 +1816,6 @@ static int ioapic_retrigger_irq(struct irq_data *data)
* races.
*/
-#ifdef CONFIG_SMP
-void send_cleanup_vector(struct irq_cfg *cfg)
-{
- cpumask_var_t cleanup_mask;
-
- if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
- unsigned int i;
- for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
- apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
- } else {
- cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
- apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
- free_cpumask_var(cleanup_mask);
- }
- cfg->move_in_progress = 0;
-}
-
-asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
-{
- unsigned vector, me;
-
- ack_APIC_irq();
- irq_enter();
- exit_idle();
-
- me = smp_processor_id();
- for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
- int irq;
- unsigned int irr;
- struct irq_desc *desc;
- struct irq_cfg *cfg;
- irq = __this_cpu_read(vector_irq[vector]);
-
- if (irq <= VECTOR_UNDEFINED)
- continue;
-
- desc = irq_to_desc(irq);
- if (!desc)
- continue;
-
- cfg = irq_cfg(irq);
- if (!cfg)
- continue;
-
- raw_spin_lock(&desc->lock);
-
- /*
- * Check if the irq migration is in progress. If so, we
- * haven't received the cleanup request yet for this irq.
- */
- if (cfg->move_in_progress)
- goto unlock;
-
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
- goto unlock;
-
- irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
- /*
- * Check if the vector that needs to be cleanedup is
- * registered at the cpu's IRR. If so, then this is not
- * the best time to clean it up. Lets clean it up in the
- * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR
- * to myself.
- */
- if (irr & (1 << (vector % 32))) {
- apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
- goto unlock;
- }
- __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
-unlock:
- raw_spin_unlock(&desc->lock);
- }
-
- irq_exit();
-}
-
-static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
-{
- unsigned me;
-
- if (likely(!cfg->move_in_progress))
- return;
-
- me = smp_processor_id();
-
- if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
- send_cleanup_vector(cfg);
-}
-
-static void irq_complete_move(struct irq_cfg *cfg)
-{
- __irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
-}
-
-void irq_force_complete_move(int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- if (!cfg)
- return;
-
- __irq_complete_move(cfg, cfg->vector);
-}
-#else
-static inline void irq_complete_move(struct irq_cfg *cfg) { }
-#endif
-
static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
{
int apic, pin;
@@ -2400,41 +1836,6 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
}
}
-/*
- * Either sets data->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves data->affinity untouched.
- */
-int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
- unsigned int *dest_id)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned int irq = data->irq;
- int err;
-
- if (!config_enabled(CONFIG_SMP))
- return -EPERM;
-
- if (!cpumask_intersects(mask, cpu_online_mask))
- return -EINVAL;
-
- err = assign_irq_vector(irq, cfg, mask);
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
- if (err) {
- if (assign_irq_vector(irq, cfg, data->affinity))
- pr_err("Failed to recover vector for irq %d\n", irq);
- return err;
- }
-
- cpumask_copy(data->affinity, mask);
-
- return 0;
-}
-
-
int native_ioapic_set_affinity(struct irq_data *data,
const struct cpumask *mask,
bool force)
@@ -2447,24 +1848,17 @@ int native_ioapic_set_affinity(struct irq_data *data,
return -EPERM;
raw_spin_lock_irqsave(&ioapic_lock, flags);
- ret = __ioapic_set_affinity(data, mask, &dest);
+ ret = apic_set_affinity(data, mask, &dest);
if (!ret) {
/* Only the high 8 bits are valid. */
dest = SET_APIC_LOGICAL_ID(dest);
- __target_IO_APIC_irq(irq, dest, data->chip_data);
+ __target_IO_APIC_irq(irq, dest, irqd_cfg(data));
ret = IRQ_SET_MASK_OK_NOCOPY;
}
raw_spin_unlock_irqrestore(&ioapic_lock, flags);
return ret;
}
-static void ack_apic_edge(struct irq_data *data)
-{
- irq_complete_move(data->chip_data);
- irq_move_irq(data);
- ack_APIC_irq();
-}
-
atomic_t irq_mis_count;
#ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -2547,9 +1941,9 @@ static inline void ioapic_irqd_unmask(struct irq_data *data,
}
#endif
-static void ack_apic_level(struct irq_data *data)
+static void ack_ioapic_level(struct irq_data *data)
{
- struct irq_cfg *cfg = data->chip_data;
+ struct irq_cfg *cfg = irqd_cfg(data);
int i, irq = data->irq;
unsigned long v;
bool masked;
@@ -2619,10 +2013,11 @@ static struct irq_chip ioapic_chip __read_mostly = {
.irq_startup = startup_ioapic_irq,
.irq_mask = mask_ioapic_irq,
.irq_unmask = unmask_ioapic_irq,
- .irq_ack = ack_apic_edge,
- .irq_eoi = ack_apic_level,
+ .irq_ack = apic_ack_edge,
+ .irq_eoi = ack_ioapic_level,
.irq_set_affinity = native_ioapic_set_affinity,
- .irq_retrigger = ioapic_retrigger_irq,
+ .irq_retrigger = apic_retrigger_irq,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
};
static inline void init_IO_APIC_traps(void)
@@ -2964,6 +2359,16 @@ static int mp_irqdomain_create(int ioapic)
return 0;
}
+static void ioapic_destroy_irqdomain(int idx)
+{
+ if (ioapics[idx].irqdomain) {
+ irq_domain_remove(ioapics[idx].irqdomain);
+ ioapics[idx].irqdomain = NULL;
+ }
+ kfree(ioapics[idx].pin_info);
+ ioapics[idx].pin_info = NULL;
+}
+
void __init setup_IO_APIC(void)
{
int ioapic;
@@ -3043,395 +2448,6 @@ static int __init ioapic_init_ops(void)
device_initcall(ioapic_init_ops);
-/*
- * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
- */
-int arch_setup_hwirq(unsigned int irq, int node)
-{
- struct irq_cfg *cfg;
- unsigned long flags;
- int ret;
-
- cfg = alloc_irq_cfg(irq, node);
- if (!cfg)
- return -ENOMEM;
-
- raw_spin_lock_irqsave(&vector_lock, flags);
- ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
- raw_spin_unlock_irqrestore(&vector_lock, flags);
-
- if (!ret)
- irq_set_chip_data(irq, cfg);
- else
- free_irq_cfg(irq, cfg);
- return ret;
-}
-
-void arch_teardown_hwirq(unsigned int irq)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
- unsigned long flags;
-
- free_remapped_irq(irq);
- raw_spin_lock_irqsave(&vector_lock, flags);
- __clear_irq_vector(irq, cfg);
- raw_spin_unlock_irqrestore(&vector_lock, flags);
- free_irq_cfg(irq, cfg);
-}
-
-/*
- * MSI message composition
- */
-void native_compose_msi_msg(struct pci_dev *pdev,
- unsigned int irq, unsigned int dest,
- struct msi_msg *msg, u8 hpet_id)
-{
- struct irq_cfg *cfg = irq_cfg(irq);
-
- msg->address_hi = MSI_ADDR_BASE_HI;
-
- if (x2apic_enabled())
- msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
-
- msg->address_lo =
- MSI_ADDR_BASE_LO |
- ((apic->irq_dest_mode == 0) ?
- MSI_ADDR_DEST_MODE_PHYSICAL:
- MSI_ADDR_DEST_MODE_LOGICAL) |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_ADDR_REDIRECTION_CPU:
- MSI_ADDR_REDIRECTION_LOWPRI) |
- MSI_ADDR_DEST_ID(dest);
-
- msg->data =
- MSI_DATA_TRIGGER_EDGE |
- MSI_DATA_LEVEL_ASSERT |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- MSI_DATA_DELIVERY_FIXED:
- MSI_DATA_DELIVERY_LOWPRI) |
- MSI_DATA_VECTOR(cfg->vector);
-}
-
-#ifdef CONFIG_PCI_MSI
-static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
- struct msi_msg *msg, u8 hpet_id)
-{
- struct irq_cfg *cfg;
- int err;
- unsigned dest;
-
- if (disable_apic)
- return -ENXIO;
-
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
-
- x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
-
- return 0;
-}
-
-static int
-msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- struct msi_msg msg;
- unsigned int dest;
- int ret;
-
- ret = __ioapic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- __get_cached_msi_msg(data->msi_desc, &msg);
-
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-
- __write_msi_msg(data->msi_desc, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-/*
- * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI or MSI-X Capability Structure.
- */
-static struct irq_chip msi_chip = {
- .name = "PCI-MSI",
- .irq_unmask = unmask_msi_irq,
- .irq_mask = mask_msi_irq,
- .irq_ack = ack_apic_edge,
- .irq_set_affinity = msi_set_affinity,
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
-int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
- unsigned int irq_base, unsigned int irq_offset)
-{
- struct irq_chip *chip = &msi_chip;
- struct msi_msg msg;
- unsigned int irq = irq_base + irq_offset;
- int ret;
-
- ret = msi_compose_msg(dev, irq, &msg, -1);
- if (ret < 0)
- return ret;
-
- irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
-
- /*
- * MSI-X message is written per-IRQ, the offset is always 0.
- * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
- */
- if (!irq_offset)
- write_msi_msg(irq, &msg);
-
- setup_remapped_irq(irq, irq_cfg(irq), chip);
-
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
-
- dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
-
- return 0;
-}
-
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
- struct msi_desc *msidesc;
- unsigned int irq;
- int node, ret;
-
- /* Multiple MSI vectors only supported with interrupt remapping */
- if (type == PCI_CAP_ID_MSI && nvec > 1)
- return 1;
-
- node = dev_to_node(&dev->dev);
-
- list_for_each_entry(msidesc, &dev->msi_list, list) {
- irq = irq_alloc_hwirq(node);
- if (!irq)
- return -ENOSPC;
-
- ret = setup_msi_irq(dev, msidesc, irq, 0);
- if (ret < 0) {
- irq_free_hwirq(irq);
- return ret;
- }
-
- }
- return 0;
-}
-
-void native_teardown_msi_irq(unsigned int irq)
-{
- irq_free_hwirq(irq);
-}
-
-#ifdef CONFIG_DMAR_TABLE
-static int
-dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
- bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned int dest, irq = data->irq;
- struct msi_msg msg;
- int ret;
-
- ret = __ioapic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- dmar_msi_read(irq, &msg);
-
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
- msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
-
- dmar_msi_write(irq, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip dmar_msi_type = {
- .name = "DMAR_MSI",
- .irq_unmask = dmar_msi_unmask,
- .irq_mask = dmar_msi_mask,
- .irq_ack = ack_apic_edge,
- .irq_set_affinity = dmar_msi_set_affinity,
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
-int arch_setup_dmar_msi(unsigned int irq)
-{
- int ret;
- struct msi_msg msg;
-
- ret = msi_compose_msg(NULL, irq, &msg, -1);
- if (ret < 0)
- return ret;
- dmar_msi_write(irq, &msg);
- irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
- "edge");
- return 0;
-}
-#endif
-
-#ifdef CONFIG_HPET_TIMER
-
-static int hpet_msi_set_affinity(struct irq_data *data,
- const struct cpumask *mask, bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- struct msi_msg msg;
- unsigned int dest;
- int ret;
-
- ret = __ioapic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- hpet_msi_read(data->handler_data, &msg);
-
- msg.data &= ~MSI_DATA_VECTOR_MASK;
- msg.data |= MSI_DATA_VECTOR(cfg->vector);
- msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
- msg.address_lo |= MSI_ADDR_DEST_ID(dest);
-
- hpet_msi_write(data->handler_data, &msg);
-
- return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip hpet_msi_type = {
- .name = "HPET_MSI",
- .irq_unmask = hpet_msi_unmask,
- .irq_mask = hpet_msi_mask,
- .irq_ack = ack_apic_edge,
- .irq_set_affinity = hpet_msi_set_affinity,
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
-int default_setup_hpet_msi(unsigned int irq, unsigned int id)
-{
- struct irq_chip *chip = &hpet_msi_type;
- struct msi_msg msg;
- int ret;
-
- ret = msi_compose_msg(NULL, irq, &msg, id);
- if (ret < 0)
- return ret;
-
- hpet_msi_write(irq_get_handler_data(irq), &msg);
- irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
- setup_remapped_irq(irq, irq_cfg(irq), chip);
-
- irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
- return 0;
-}
-#endif
-
-#endif /* CONFIG_PCI_MSI */
-/*
- * Hypertransport interrupt support
- */
-#ifdef CONFIG_HT_IRQ
-
-static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
-{
- struct ht_irq_msg msg;
- fetch_ht_irq_msg(irq, &msg);
-
- msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
- msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-
- msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
- msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
-
- write_ht_irq_msg(irq, &msg);
-}
-
-static int
-ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
- struct irq_cfg *cfg = data->chip_data;
- unsigned int dest;
- int ret;
-
- ret = __ioapic_set_affinity(data, mask, &dest);
- if (ret)
- return ret;
-
- target_ht_irq(data->irq, dest, cfg->vector);
- return IRQ_SET_MASK_OK_NOCOPY;
-}
-
-static struct irq_chip ht_irq_chip = {
- .name = "PCI-HT",
- .irq_mask = mask_ht_irq,
- .irq_unmask = unmask_ht_irq,
- .irq_ack = ack_apic_edge,
- .irq_set_affinity = ht_set_affinity,
- .irq_retrigger = ioapic_retrigger_irq,
-};
-
-int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
-{
- struct irq_cfg *cfg;
- struct ht_irq_msg msg;
- unsigned dest;
- int err;
-
- if (disable_apic)
- return -ENXIO;
-
- cfg = irq_cfg(irq);
- err = assign_irq_vector(irq, cfg, apic->target_cpus());
- if (err)
- return err;
-
- err = apic->cpu_mask_to_apicid_and(cfg->domain,
- apic->target_cpus(), &dest);
- if (err)
- return err;
-
- msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
-
- msg.address_lo =
- HT_IRQ_LOW_BASE |
- HT_IRQ_LOW_DEST_ID(dest) |
- HT_IRQ_LOW_VECTOR(cfg->vector) |
- ((apic->irq_dest_mode == 0) ?
- HT_IRQ_LOW_DM_PHYSICAL :
- HT_IRQ_LOW_DM_LOGICAL) |
- HT_IRQ_LOW_RQEOI_EDGE |
- ((apic->irq_delivery_mode != dest_LowestPrio) ?
- HT_IRQ_LOW_MT_FIXED :
- HT_IRQ_LOW_MT_ARBITRATED) |
- HT_IRQ_LOW_IRQ_MASKED;
-
- write_ht_irq_msg(irq, &msg);
-
- irq_set_chip_and_handler_name(irq, &ht_irq_chip,
- handle_edge_irq, "edge");
-
- dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
-
- return 0;
-}
-#endif /* CONFIG_HT_IRQ */
-
static int
io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
{
@@ -3446,7 +2462,7 @@ io_apic_setup_irq_pin(unsigned int irq, int node, struct io_apic_irq_attr *attr)
return ret;
}
-static int __init io_apic_get_redir_entries(int ioapic)
+static int io_apic_get_redir_entries(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -3471,28 +2487,8 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
}
-int __init arch_probe_nr_irqs(void)
-{
- int nr;
-
- if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
- nr_irqs = NR_VECTORS * nr_cpu_ids;
-
- nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
-#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
- /*
- * for MSI and HT dyn irq
- */
- nr += gsi_top * 16;
-#endif
- if (nr < nr_irqs)
- nr_irqs = nr;
-
- return 0;
-}
-
#ifdef CONFIG_X86_32
-static int __init io_apic_get_unique_id(int ioapic, int apic_id)
+static int io_apic_get_unique_id(int ioapic, int apic_id)
{
union IO_APIC_reg_00 reg_00;
static physid_mask_t apic_id_map = PHYSID_MASK_NONE;
@@ -3567,30 +2563,63 @@ static int __init io_apic_get_unique_id(int ioapic, int apic_id)
return apic_id;
}
-static u8 __init io_apic_unique_id(u8 id)
+static u8 io_apic_unique_id(int idx, u8 id)
{
if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) &&
!APIC_XAPIC(apic_version[boot_cpu_physical_apicid]))
- return io_apic_get_unique_id(nr_ioapics, id);
+ return io_apic_get_unique_id(idx, id);
else
return id;
}
#else
-static u8 __init io_apic_unique_id(u8 id)
+static u8 io_apic_unique_id(int idx, u8 id)
{
- int i;
+ union IO_APIC_reg_00 reg_00;
DECLARE_BITMAP(used, 256);
+ unsigned long flags;
+ u8 new_id;
+ int i;
bitmap_zero(used, 256);
for_each_ioapic(i)
__set_bit(mpc_ioapic_id(i), used);
+
+ /* Hand out the requested id if available */
if (!test_bit(id, used))
return id;
- return find_first_zero_bit(used, 256);
+
+ /*
+ * Read the current id from the ioapic and keep it if
+ * available.
+ */
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ reg_00.raw = io_apic_read(idx, 0);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+ new_id = reg_00.bits.ID;
+ if (!test_bit(new_id, used)) {
+ apic_printk(APIC_VERBOSE, KERN_INFO
+ "IOAPIC[%d]: Using reg apic_id %d instead of %d\n",
+ idx, new_id, id);
+ return new_id;
+ }
+
+ /*
+ * Get the next free id and write it to the ioapic.
+ */
+ new_id = find_first_zero_bit(used, 256);
+ reg_00.bits.ID = new_id;
+ raw_spin_lock_irqsave(&ioapic_lock, flags);
+ io_apic_write(idx, 0, reg_00.raw);
+ reg_00.raw = io_apic_read(idx, 0);
+ raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+ /* Sanity check */
+ BUG_ON(reg_00.bits.ID != new_id);
+
+ return new_id;
}
#endif
-static int __init io_apic_get_version(int ioapic)
+static int io_apic_get_version(int ioapic)
{
union IO_APIC_reg_01 reg_01;
unsigned long flags;
@@ -3697,6 +2726,7 @@ static struct resource * __init ioapic_setup_resources(void)
snprintf(mem, IOAPIC_RESOURCE_NAME_SIZE, "IOAPIC %u", i);
mem += IOAPIC_RESOURCE_NAME_SIZE;
num++;
+ ioapics[i].iomem_res = res;
}
ioapic_resources = res;
@@ -3794,21 +2824,7 @@ int mp_find_ioapic_pin(int ioapic, u32 gsi)
return gsi - gsi_cfg->gsi_base;
}
-static __init int bad_ioapic(unsigned long address)
-{
- if (nr_ioapics >= MAX_IO_APICS) {
- pr_warn("WARNING: Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
- MAX_IO_APICS, nr_ioapics);
- return 1;
- }
- if (!address) {
- pr_warn("WARNING: Bogus (zero) I/O APIC address found in table, skipping!\n");
- return 1;
- }
- return 0;
-}
-
-static __init int bad_ioapic_register(int idx)
+static int bad_ioapic_register(int idx)
{
union IO_APIC_reg_00 reg_00;
union IO_APIC_reg_01 reg_01;
@@ -3827,32 +2843,61 @@ static __init int bad_ioapic_register(int idx)
return 0;
}
-void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
- struct ioapic_domain_cfg *cfg)
+static int find_free_ioapic_entry(void)
{
- int idx = 0;
- int entries;
+ int idx;
+
+ for (idx = 0; idx < MAX_IO_APICS; idx++)
+ if (ioapics[idx].nr_registers == 0)
+ return idx;
+
+ return MAX_IO_APICS;
+}
+
+/**
+ * mp_register_ioapic - Register an IOAPIC device
+ * @id: hardware IOAPIC ID
+ * @address: physical address of IOAPIC register area
+ * @gsi_base: base of GSI associated with the IOAPIC
+ * @cfg: configuration information for the IOAPIC
+ */
+int mp_register_ioapic(int id, u32 address, u32 gsi_base,
+ struct ioapic_domain_cfg *cfg)
+{
+ bool hotplug = !!ioapic_initialized;
struct mp_ioapic_gsi *gsi_cfg;
+ int idx, ioapic, entries;
+ u32 gsi_end;
- if (bad_ioapic(address))
- return;
+ if (!address) {
+ pr_warn("Bogus (zero) I/O APIC address found, skipping!\n");
+ return -EINVAL;
+ }
+ for_each_ioapic(ioapic)
+ if (ioapics[ioapic].mp_config.apicaddr == address) {
+ pr_warn("address 0x%x conflicts with IOAPIC%d\n",
+ address, ioapic);
+ return -EEXIST;
+ }
- idx = nr_ioapics;
+ idx = find_free_ioapic_entry();
+ if (idx >= MAX_IO_APICS) {
+ pr_warn("Max # of I/O APICs (%d) exceeded (found %d), skipping\n",
+ MAX_IO_APICS, idx);
+ return -ENOSPC;
+ }
ioapics[idx].mp_config.type = MP_IOAPIC;
ioapics[idx].mp_config.flags = MPC_APIC_USABLE;
ioapics[idx].mp_config.apicaddr = address;
- ioapics[idx].irqdomain = NULL;
- ioapics[idx].irqdomain_cfg = *cfg;
set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
-
if (bad_ioapic_register(idx)) {
clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
- return;
+ return -ENODEV;
}
- ioapics[idx].mp_config.apicid = io_apic_unique_id(id);
+ ioapics[idx].mp_config.apicid = io_apic_unique_id(idx, id);
ioapics[idx].mp_config.apicver = io_apic_get_version(idx);
/*
@@ -3860,24 +2905,112 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base,
* and to prevent reprogramming of IOAPIC pins (PCI GSIs).
*/
entries = io_apic_get_redir_entries(idx);
+ gsi_end = gsi_base + entries - 1;
+ for_each_ioapic(ioapic) {
+ gsi_cfg = mp_ioapic_gsi_routing(ioapic);
+ if ((gsi_base >= gsi_cfg->gsi_base &&
+ gsi_base <= gsi_cfg->gsi_end) ||
+ (gsi_end >= gsi_cfg->gsi_base &&
+ gsi_end <= gsi_cfg->gsi_end)) {
+ pr_warn("GSI range [%u-%u] for new IOAPIC conflicts with GSI[%u-%u]\n",
+ gsi_base, gsi_end,
+ gsi_cfg->gsi_base, gsi_cfg->gsi_end);
+ clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+ return -ENOSPC;
+ }
+ }
gsi_cfg = mp_ioapic_gsi_routing(idx);
gsi_cfg->gsi_base = gsi_base;
- gsi_cfg->gsi_end = gsi_base + entries - 1;
+ gsi_cfg->gsi_end = gsi_end;
+
+ ioapics[idx].irqdomain = NULL;
+ ioapics[idx].irqdomain_cfg = *cfg;
/*
- * The number of IO-APIC IRQ registers (== #pins):
+ * If mp_register_ioapic() is called during early boot stage when
+ * walking ACPI/SFI/DT tables, it's too early to create irqdomain,
+ * we are still using bootmem allocator. So delay it to setup_IO_APIC().
*/
- ioapics[idx].nr_registers = entries;
+ if (hotplug) {
+ if (mp_irqdomain_create(idx)) {
+ clear_fixmap(FIX_IO_APIC_BASE_0 + idx);
+ return -ENOMEM;
+ }
+ alloc_ioapic_saved_registers(idx);
+ }
if (gsi_cfg->gsi_end >= gsi_top)
gsi_top = gsi_cfg->gsi_end + 1;
+ if (nr_ioapics <= idx)
+ nr_ioapics = idx + 1;
+
+ /* Set nr_registers to mark entry present */
+ ioapics[idx].nr_registers = entries;
pr_info("IOAPIC[%d]: apic_id %d, version %d, address 0x%x, GSI %d-%d\n",
idx, mpc_ioapic_id(idx),
mpc_ioapic_ver(idx), mpc_ioapic_addr(idx),
gsi_cfg->gsi_base, gsi_cfg->gsi_end);
- nr_ioapics++;
+ return 0;
+}
+
+int mp_unregister_ioapic(u32 gsi_base)
+{
+ int ioapic, pin;
+ int found = 0;
+ struct mp_pin_info *pin_info;
+
+ for_each_ioapic(ioapic)
+ if (ioapics[ioapic].gsi_config.gsi_base == gsi_base) {
+ found = 1;
+ break;
+ }
+ if (!found) {
+ pr_warn("can't find IOAPIC for GSI %d\n", gsi_base);
+ return -ENODEV;
+ }
+
+ for_each_pin(ioapic, pin) {
+ pin_info = mp_pin_info(ioapic, pin);
+ if (pin_info->count) {
+ pr_warn("pin%d on IOAPIC%d is still in use.\n",
+ pin, ioapic);
+ return -EBUSY;
+ }
+ }
+
+ /* Mark entry not present */
+ ioapics[ioapic].nr_registers = 0;
+ ioapic_destroy_irqdomain(ioapic);
+ free_ioapic_saved_registers(ioapic);
+ if (ioapics[ioapic].iomem_res)
+ release_resource(ioapics[ioapic].iomem_res);
+ clear_fixmap(FIX_IO_APIC_BASE_0 + ioapic);
+ memset(&ioapics[ioapic], 0, sizeof(ioapics[ioapic]));
+
+ return 0;
+}
+
+int mp_ioapic_registered(u32 gsi_base)
+{
+ int ioapic;
+
+ for_each_ioapic(ioapic)
+ if (ioapics[ioapic].gsi_config.gsi_base == gsi_base)
+ return 1;
+
+ return 0;
+}
+
+static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
+ int ioapic, int ioapic_pin,
+ int trigger, int polarity)
+{
+ irq_attr->ioapic = ioapic;
+ irq_attr->ioapic_pin = ioapic_pin;
+ irq_attr->trigger = trigger;
+ irq_attr->polarity = polarity;
}
int mp_irqdomain_map(struct irq_domain *domain, unsigned int virq,
@@ -3926,7 +3059,7 @@ void mp_irqdomain_unmap(struct irq_domain *domain, unsigned int virq)
ioapic_mask_entry(ioapic, pin);
__remove_pin_from_irq(cfg, ioapic, pin);
- WARN_ON(cfg->irq_2_pin != NULL);
+ WARN_ON(!list_empty(&cfg->irq_2_pin));
arch_teardown_hwirq(virq);
}
@@ -3959,18 +3092,6 @@ int mp_set_gsi_attr(u32 gsi, int trigger, int polarity, int node)
return ret;
}
-bool mp_should_keep_irq(struct device *dev)
-{
- if (dev->power.is_prepared)
- return true;
-#ifdef CONFIG_PM_RUNTIME
- if (dev->power.runtime_status == RPM_SUSPENDING)
- return true;
-#endif
-
- return false;
-}
-
/* Enable IOAPIC early just for system timer */
void __init pre_init_apic_IRQ0(void)
{
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
new file mode 100644
index 000000000000..d6ba2d660dc5
--- /dev/null
+++ b/arch/x86/kernel/apic/msi.c
@@ -0,0 +1,286 @@
+/*
+ * Support of MSI, HPET and DMAR interrupts.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ * Moved from arch/x86/kernel/apic/io_apic.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/dmar.h>
+#include <linux/hpet.h>
+#include <linux/msi.h>
+#include <asm/msidef.h>
+#include <asm/hpet.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/irq_remapping.h>
+
+void native_compose_msi_msg(struct pci_dev *pdev,
+ unsigned int irq, unsigned int dest,
+ struct msi_msg *msg, u8 hpet_id)
+{
+ struct irq_cfg *cfg = irq_cfg(irq);
+
+ msg->address_hi = MSI_ADDR_BASE_HI;
+
+ if (x2apic_enabled())
+ msg->address_hi |= MSI_ADDR_EXT_DEST_ID(dest);
+
+ msg->address_lo =
+ MSI_ADDR_BASE_LO |
+ ((apic->irq_dest_mode == 0) ?
+ MSI_ADDR_DEST_MODE_PHYSICAL :
+ MSI_ADDR_DEST_MODE_LOGICAL) |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_ADDR_REDIRECTION_CPU :
+ MSI_ADDR_REDIRECTION_LOWPRI) |
+ MSI_ADDR_DEST_ID(dest);
+
+ msg->data =
+ MSI_DATA_TRIGGER_EDGE |
+ MSI_DATA_LEVEL_ASSERT |
+ ((apic->irq_delivery_mode != dest_LowestPrio) ?
+ MSI_DATA_DELIVERY_FIXED :
+ MSI_DATA_DELIVERY_LOWPRI) |
+ MSI_DATA_VECTOR(cfg->vector);
+}
+
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
+ struct msi_msg *msg, u8 hpet_id)
+{
+ struct irq_cfg *cfg;
+ int err;
+ unsigned dest;
+
+ if (disable_apic)
+ return -ENXIO;
+
+ cfg = irq_cfg(irq);
+ err = assign_irq_vector(irq, cfg, apic->target_cpus());
+ if (err)
+ return err;
+
+ err = apic->cpu_mask_to_apicid_and(cfg->domain,
+ apic->target_cpus(), &dest);
+ if (err)
+ return err;
+
+ x86_msi.compose_msi_msg(pdev, irq, dest, msg, hpet_id);
+
+ return 0;
+}
+
+static int
+msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
+{
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct msi_msg msg;
+ unsigned int dest;
+ int ret;
+
+ ret = apic_set_affinity(data, mask, &dest);
+ if (ret)
+ return ret;
+
+ __get_cached_msi_msg(data->msi_desc, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(cfg->vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+ __pci_write_msi_msg(data->msi_desc, &msg);
+
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip msi_chip = {
+ .name = "PCI-MSI",
+ .irq_unmask = pci_msi_unmask_irq,
+ .irq_mask = pci_msi_mask_irq,
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = msi_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+ unsigned int irq_base, unsigned int irq_offset)
+{
+ struct irq_chip *chip = &msi_chip;
+ struct msi_msg msg;
+ unsigned int irq = irq_base + irq_offset;
+ int ret;
+
+ ret = msi_compose_msg(dev, irq, &msg, -1);
+ if (ret < 0)
+ return ret;
+
+ irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
+
+ /*
+ * MSI-X message is written per-IRQ, the offset is always 0.
+ * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
+ */
+ if (!irq_offset)
+ pci_write_msi_msg(irq, &msg);
+
+ setup_remapped_irq(irq, irq_cfg(irq), chip);
+
+ irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+
+ dev_dbg(&dev->dev, "irq %d for MSI/MSI-X\n", irq);
+
+ return 0;
+}
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ struct msi_desc *msidesc;
+ unsigned int irq;
+ int node, ret;
+
+ /* Multiple MSI vectors only supported with interrupt remapping */
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
+
+ node = dev_to_node(&dev->dev);
+
+ list_for_each_entry(msidesc, &dev->msi_list, list) {
+ irq = irq_alloc_hwirq(node);
+ if (!irq)
+ return -ENOSPC;
+
+ ret = setup_msi_irq(dev, msidesc, irq, 0);
+ if (ret < 0) {
+ irq_free_hwirq(irq);
+ return ret;
+ }
+
+ }
+ return 0;
+}
+
+void native_teardown_msi_irq(unsigned int irq)
+{
+ irq_free_hwirq(irq);
+}
+
+#ifdef CONFIG_DMAR_TABLE
+static int
+dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ bool force)
+{
+ struct irq_cfg *cfg = irqd_cfg(data);
+ unsigned int dest, irq = data->irq;
+ struct msi_msg msg;
+ int ret;
+
+ ret = apic_set_affinity(data, mask, &dest);
+ if (ret)
+ return ret;
+
+ dmar_msi_read(irq, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(cfg->vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+ msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
+
+ dmar_msi_write(irq, &msg);
+
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static struct irq_chip dmar_msi_type = {
+ .name = "DMAR_MSI",
+ .irq_unmask = dmar_msi_unmask,
+ .irq_mask = dmar_msi_mask,
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = dmar_msi_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int arch_setup_dmar_msi(unsigned int irq)
+{
+ int ret;
+ struct msi_msg msg;
+
+ ret = msi_compose_msg(NULL, irq, &msg, -1);
+ if (ret < 0)
+ return ret;
+ dmar_msi_write(irq, &msg);
+ irq_set_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+ "edge");
+ return 0;
+}
+#endif
+
+/*
+ * MSI message composition
+ */
+#ifdef CONFIG_HPET_TIMER
+
+static int hpet_msi_set_affinity(struct irq_data *data,
+ const struct cpumask *mask, bool force)
+{
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct msi_msg msg;
+ unsigned int dest;
+ int ret;
+
+ ret = apic_set_affinity(data, mask, &dest);
+ if (ret)
+ return ret;
+
+ hpet_msi_read(data->handler_data, &msg);
+
+ msg.data &= ~MSI_DATA_VECTOR_MASK;
+ msg.data |= MSI_DATA_VECTOR(cfg->vector);
+ msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+ msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+ hpet_msi_write(data->handler_data, &msg);
+
+ return IRQ_SET_MASK_OK_NOCOPY;
+}
+
+static struct irq_chip hpet_msi_type = {
+ .name = "HPET_MSI",
+ .irq_unmask = hpet_msi_unmask,
+ .irq_mask = hpet_msi_mask,
+ .irq_ack = apic_ack_edge,
+ .irq_set_affinity = hpet_msi_set_affinity,
+ .irq_retrigger = apic_retrigger_irq,
+ .flags = IRQCHIP_SKIP_SET_WAKE,
+};
+
+int default_setup_hpet_msi(unsigned int irq, unsigned int id)
+{
+ struct irq_chip *chip = &hpet_msi_type;
+ struct msi_msg msg;
+ int ret;
+
+ ret = msi_compose_msg(NULL, irq, &msg, id);
+ if (ret < 0)
+ return ret;
+
+ hpet_msi_write(irq_get_handler_data(irq), &msg);
+ irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+ setup_remapped_irq(irq, irq_cfg(irq), chip);
+
+ irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
+ return 0;
+}
+#endif
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
new file mode 100644
index 000000000000..6cedd7914581
--- /dev/null
+++ b/arch/x86/kernel/apic/vector.c
@@ -0,0 +1,719 @@
+/*
+ * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
+ * Moved from arch/x86/kernel/apic/io_apic.c.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/irqdomain.h>
+#include <linux/slab.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/i8259.h>
+#include <asm/desc.h>
+#include <asm/irq_remapping.h>
+
+static DEFINE_RAW_SPINLOCK(vector_lock);
+
+void lock_vector_lock(void)
+{
+ /* Used to the online set of cpus does not change
+ * during assign_irq_vector.
+ */
+ raw_spin_lock(&vector_lock);
+}
+
+void unlock_vector_lock(void)
+{
+ raw_spin_unlock(&vector_lock);
+}
+
+struct irq_cfg *irq_cfg(unsigned int irq)
+{
+ return irq_get_chip_data(irq);
+}
+
+struct irq_cfg *irqd_cfg(struct irq_data *irq_data)
+{
+ return irq_data->chip_data;
+}
+
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
+{
+ struct irq_cfg *cfg;
+
+ cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
+ if (!cfg)
+ return NULL;
+ if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
+ goto out_cfg;
+ if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+ goto out_domain;
+#ifdef CONFIG_X86_IO_APIC
+ INIT_LIST_HEAD(&cfg->irq_2_pin);
+#endif
+ return cfg;
+out_domain:
+ free_cpumask_var(cfg->domain);
+out_cfg:
+ kfree(cfg);
+ return NULL;
+}
+
+struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
+{
+ int res = irq_alloc_desc_at(at, node);
+ struct irq_cfg *cfg;
+
+ if (res < 0) {
+ if (res != -EEXIST)
+ return NULL;
+ cfg = irq_cfg(at);
+ if (cfg)
+ return cfg;
+ }
+
+ cfg = alloc_irq_cfg(at, node);
+ if (cfg)
+ irq_set_chip_data(at, cfg);
+ else
+ irq_free_desc(at);
+ return cfg;
+}
+
+static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
+{
+ if (!cfg)
+ return;
+ irq_set_chip_data(at, NULL);
+ free_cpumask_var(cfg->domain);
+ free_cpumask_var(cfg->old_domain);
+ kfree(cfg);
+}
+
+static int
+__assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+{
+ /*
+ * NOTE! The local APIC isn't very good at handling
+ * multiple interrupts at the same interrupt level.
+ * As the interrupt level is determined by taking the
+ * vector number and shifting that right by 4, we
+ * want to spread these out a bit so that they don't
+ * all fall in the same interrupt level.
+ *
+ * Also, we've got to be careful not to trash gate
+ * 0x80, because int 0x80 is hm, kind of importantish. ;)
+ */
+ static int current_vector = FIRST_EXTERNAL_VECTOR + VECTOR_OFFSET_START;
+ static int current_offset = VECTOR_OFFSET_START % 16;
+ int cpu, err;
+ cpumask_var_t tmp_mask;
+
+ if (cfg->move_in_progress)
+ return -EBUSY;
+
+ if (!alloc_cpumask_var(&tmp_mask, GFP_ATOMIC))
+ return -ENOMEM;
+
+ /* Only try and allocate irqs on cpus that are present */
+ err = -ENOSPC;
+ cpumask_clear(cfg->old_domain);
+ cpu = cpumask_first_and(mask, cpu_online_mask);
+ while (cpu < nr_cpu_ids) {
+ int new_cpu, vector, offset;
+
+ apic->vector_allocation_domain(cpu, tmp_mask, mask);
+
+ if (cpumask_subset(tmp_mask, cfg->domain)) {
+ err = 0;
+ if (cpumask_equal(tmp_mask, cfg->domain))
+ break;
+ /*
+ * New cpumask using the vector is a proper subset of
+ * the current in use mask. So cleanup the vector
+ * allocation for the members that are not used anymore.
+ */
+ cpumask_andnot(cfg->old_domain, cfg->domain, tmp_mask);
+ cfg->move_in_progress =
+ cpumask_intersects(cfg->old_domain, cpu_online_mask);
+ cpumask_and(cfg->domain, cfg->domain, tmp_mask);
+ break;
+ }
+
+ vector = current_vector;
+ offset = current_offset;
+next:
+ vector += 16;
+ if (vector >= first_system_vector) {
+ offset = (offset + 1) % 16;
+ vector = FIRST_EXTERNAL_VECTOR + offset;
+ }
+
+ if (unlikely(current_vector == vector)) {
+ cpumask_or(cfg->old_domain, cfg->old_domain, tmp_mask);
+ cpumask_andnot(tmp_mask, mask, cfg->old_domain);
+ cpu = cpumask_first_and(tmp_mask, cpu_online_mask);
+ continue;
+ }
+
+ if (test_bit(vector, used_vectors))
+ goto next;
+
+ for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask) {
+ if (per_cpu(vector_irq, new_cpu)[vector] >
+ VECTOR_UNDEFINED)
+ goto next;
+ }
+ /* Found one! */
+ current_vector = vector;
+ current_offset = offset;
+ if (cfg->vector) {
+ cpumask_copy(cfg->old_domain, cfg->domain);
+ cfg->move_in_progress =
+ cpumask_intersects(cfg->old_domain, cpu_online_mask);
+ }
+ for_each_cpu_and(new_cpu, tmp_mask, cpu_online_mask)
+ per_cpu(vector_irq, new_cpu)[vector] = irq;
+ cfg->vector = vector;
+ cpumask_copy(cfg->domain, tmp_mask);
+ err = 0;
+ break;
+ }
+ free_cpumask_var(tmp_mask);
+
+ return err;
+}
+
+int assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask)
+{
+ int err;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&vector_lock, flags);
+ err = __assign_irq_vector(irq, cfg, mask);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+ return err;
+}
+
+void clear_irq_vector(int irq, struct irq_cfg *cfg)
+{
+ int cpu, vector;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&vector_lock, flags);
+ BUG_ON(!cfg->vector);
+
+ vector = cfg->vector;
+ for_each_cpu_and(cpu, cfg->domain, cpu_online_mask)
+ per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+
+ cfg->vector = 0;
+ cpumask_clear(cfg->domain);
+
+ if (likely(!cfg->move_in_progress)) {
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+ return;
+ }
+
+ for_each_cpu_and(cpu, cfg->old_domain, cpu_online_mask) {
+ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+ vector++) {
+ if (per_cpu(vector_irq, cpu)[vector] != irq)
+ continue;
+ per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+ break;
+ }
+ }
+ cfg->move_in_progress = 0;
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+}
+
+int __init arch_probe_nr_irqs(void)
+{
+ int nr;
+
+ if (nr_irqs > (NR_VECTORS * nr_cpu_ids))
+ nr_irqs = NR_VECTORS * nr_cpu_ids;
+
+ nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
+#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
+ /*
+ * for MSI and HT dyn irq
+ */
+ if (gsi_top <= NR_IRQS_LEGACY)
+ nr += 8 * nr_cpu_ids;
+ else
+ nr += gsi_top * 16;
+#endif
+ if (nr < nr_irqs)
+ nr_irqs = nr;
+
+ return nr_legacy_irqs();
+}
+
+int __init arch_early_irq_init(void)
+{
+ return arch_early_ioapic_init();
+}
+
+static void __setup_vector_irq(int cpu)
+{
+ /* Initialize vector_irq on a new cpu */
+ int irq, vector;
+ struct irq_cfg *cfg;
+
+ /*
+ * vector_lock will make sure that we don't run into irq vector
+ * assignments that might be happening on another cpu in parallel,
+ * while we setup our initial vector to irq mappings.
+ */
+ raw_spin_lock(&vector_lock);
+ /* Mark the inuse vectors */
+ for_each_active_irq(irq) {
+ cfg = irq_cfg(irq);
+ if (!cfg)
+ continue;
+
+ if (!cpumask_test_cpu(cpu, cfg->domain))
+ continue;
+ vector = cfg->vector;
+ per_cpu(vector_irq, cpu)[vector] = irq;
+ }
+ /* Mark the free vectors */
+ for (vector = 0; vector < NR_VECTORS; ++vector) {
+ irq = per_cpu(vector_irq, cpu)[vector];
+ if (irq <= VECTOR_UNDEFINED)
+ continue;
+
+ cfg = irq_cfg(irq);
+ if (!cpumask_test_cpu(cpu, cfg->domain))
+ per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
+ }
+ raw_spin_unlock(&vector_lock);
+}
+
+/*
+ * Setup the vector to irq mappings.
+ */
+void setup_vector_irq(int cpu)
+{
+ int irq;
+
+ /*
+ * On most of the platforms, legacy PIC delivers the interrupts on the
+ * boot cpu. But there are certain platforms where PIC interrupts are
+ * delivered to multiple cpu's. If the legacy IRQ is handled by the
+ * legacy PIC, for the new cpu that is coming online, setup the static
+ * legacy vector to irq mapping:
+ */
+ for (irq = 0; irq < nr_legacy_irqs(); irq++)
+ per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
+
+ __setup_vector_irq(cpu);
+}
+
+int apic_retrigger_irq(struct irq_data *data)
+{
+ struct irq_cfg *cfg = irqd_cfg(data);
+ unsigned long flags;
+ int cpu;
+
+ raw_spin_lock_irqsave(&vector_lock, flags);
+ cpu = cpumask_first_and(cfg->domain, cpu_online_mask);
+ apic->send_IPI_mask(cpumask_of(cpu), cfg->vector);
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+ return 1;
+}
+
+void apic_ack_edge(struct irq_data *data)
+{
+ irq_complete_move(irqd_cfg(data));
+ irq_move_irq(data);
+ ack_APIC_irq();
+}
+
+/*
+ * Either sets data->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
+ * leaves data->affinity untouched.
+ */
+int apic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+ unsigned int *dest_id)
+{
+ struct irq_cfg *cfg = irqd_cfg(data);
+ unsigned int irq = data->irq;
+ int err;
+
+ if (!config_enabled(CONFIG_SMP))
+ return -EPERM;
+
+ if (!cpumask_intersects(mask, cpu_online_mask))
+ return -EINVAL;
+
+ err = assign_irq_vector(irq, cfg, mask);
+ if (err)
+ return err;
+
+ err = apic->cpu_mask_to_apicid_and(mask, cfg->domain, dest_id);
+ if (err) {
+ if (assign_irq_vector(irq, cfg, data->affinity))
+ pr_err("Failed to recover vector for irq %d\n", irq);
+ return err;
+ }
+
+ cpumask_copy(data->affinity, mask);
+
+ return 0;
+}
+
+#ifdef CONFIG_SMP
+void send_cleanup_vector(struct irq_cfg *cfg)
+{
+ cpumask_var_t cleanup_mask;
+
+ if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+ unsigned int i;
+
+ for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+ apic->send_IPI_mask(cpumask_of(i),
+ IRQ_MOVE_CLEANUP_VECTOR);
+ } else {
+ cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+ apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+ free_cpumask_var(cleanup_mask);
+ }
+ cfg->move_in_progress = 0;
+}
+
+asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
+{
+ unsigned vector, me;
+
+ ack_APIC_irq();
+ irq_enter();
+ exit_idle();
+
+ me = smp_processor_id();
+ for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+ int irq;
+ unsigned int irr;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+
+ irq = __this_cpu_read(vector_irq[vector]);
+
+ if (irq <= VECTOR_UNDEFINED)
+ continue;
+
+ desc = irq_to_desc(irq);
+ if (!desc)
+ continue;
+
+ cfg = irq_cfg(irq);
+ if (!cfg)
+ continue;
+
+ raw_spin_lock(&desc->lock);
+
+ /*
+ * Check if the irq migration is in progress. If so, we
+ * haven't received the cleanup request yet for this irq.
+ */
+ if (cfg->move_in_progress)
+ goto unlock;
+
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+ goto unlock;
+
+ irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+ /*
+ * Check if the vector that needs to be cleanedup is
+ * registered at the cpu's IRR. If so, then this is not
+ * the best time to clean it up. Lets clean it up in the
+ * next attempt by sending another IRQ_MOVE_CLEANUP_VECTOR
+ * to myself.
+ */
+ if (irr & (1 << (vector % 32))) {
+ apic->send_IPI_self(IRQ_MOVE_CLEANUP_VECTOR);
+ goto unlock;
+ }
+ __this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+unlock:
+ raw_spin_unlock(&desc->lock);
+ }
+
+ irq_exit();
+}
+
+static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
+{
+ unsigned me;
+
+ if (likely(!cfg->move_in_progress))
+ return;
+
+ me = smp_processor_id();
+
+ if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
+ send_cleanup_vector(cfg);
+}
+
+void irq_complete_move(struct irq_cfg *cfg)
+{
+ __irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
+}
+
+void irq_force_complete_move(int irq)
+{
+ struct irq_cfg *cfg = irq_cfg(irq);
+
+ if (!cfg)
+ return;
+
+ __irq_complete_move(cfg, cfg->vector);
+}
+#endif
+
+/*
+ * Dynamic irq allocate and deallocation. Should be replaced by irq domains!
+ */
+int arch_setup_hwirq(unsigned int irq, int node)
+{
+ struct irq_cfg *cfg;
+ unsigned long flags;
+ int ret;
+
+ cfg = alloc_irq_cfg(irq, node);
+ if (!cfg)
+ return -ENOMEM;
+
+ raw_spin_lock_irqsave(&vector_lock, flags);
+ ret = __assign_irq_vector(irq, cfg, apic->target_cpus());
+ raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+ if (!ret)
+ irq_set_chip_data(irq, cfg);
+ else
+ free_irq_cfg(irq, cfg);
+ return ret;
+}
+
+void arch_teardown_hwirq(unsigned int irq)
+{
+ struct irq_cfg *cfg = irq_cfg(irq);
+
+ free_remapped_irq(irq);
+ clear_irq_vector(irq, cfg);
+ free_irq_cfg(irq, cfg);
+}
+
+static void __init print_APIC_field(int base)
+{
+ int i;
+
+ printk(KERN_DEBUG);
+
+ for (i = 0; i < 8; i++)
+ pr_cont("%08x", apic_read(base + i*0x10));
+
+ pr_cont("\n");
+}
+
+static void __init print_local_APIC(void *dummy)
+{
+ unsigned int i, v, ver, maxlvt;
+ u64 icr;
+
+ pr_debug("printing local APIC contents on CPU#%d/%d:\n",
+ smp_processor_id(), hard_smp_processor_id());
+ v = apic_read(APIC_ID);
+ pr_info("... APIC ID: %08x (%01x)\n", v, read_apic_id());
+ v = apic_read(APIC_LVR);
+ pr_info("... APIC VERSION: %08x\n", v);
+ ver = GET_APIC_VERSION(v);
+ maxlvt = lapic_get_maxlvt();
+
+ v = apic_read(APIC_TASKPRI);
+ pr_debug("... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
+
+ /* !82489DX */
+ if (APIC_INTEGRATED(ver)) {
+ if (!APIC_XAPIC(ver)) {
+ v = apic_read(APIC_ARBPRI);
+ pr_debug("... APIC ARBPRI: %08x (%02x)\n",
+ v, v & APIC_ARBPRI_MASK);
+ }
+ v = apic_read(APIC_PROCPRI);
+ pr_debug("... APIC PROCPRI: %08x\n", v);
+ }
+
+ /*
+ * Remote read supported only in the 82489DX and local APIC for
+ * Pentium processors.
+ */
+ if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
+ v = apic_read(APIC_RRR);
+ pr_debug("... APIC RRR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_LDR);
+ pr_debug("... APIC LDR: %08x\n", v);
+ if (!x2apic_enabled()) {
+ v = apic_read(APIC_DFR);
+ pr_debug("... APIC DFR: %08x\n", v);
+ }
+ v = apic_read(APIC_SPIV);
+ pr_debug("... APIC SPIV: %08x\n", v);
+
+ pr_debug("... APIC ISR field:\n");
+ print_APIC_field(APIC_ISR);
+ pr_debug("... APIC TMR field:\n");
+ print_APIC_field(APIC_TMR);
+ pr_debug("... APIC IRR field:\n");
+ print_APIC_field(APIC_IRR);
+
+ /* !82489DX */
+ if (APIC_INTEGRATED(ver)) {
+ /* Due to the Pentium erratum 3AP. */
+ if (maxlvt > 3)
+ apic_write(APIC_ESR, 0);
+
+ v = apic_read(APIC_ESR);
+ pr_debug("... APIC ESR: %08x\n", v);
+ }
+
+ icr = apic_icr_read();
+ pr_debug("... APIC ICR: %08x\n", (u32)icr);
+ pr_debug("... APIC ICR2: %08x\n", (u32)(icr >> 32));
+
+ v = apic_read(APIC_LVTT);
+ pr_debug("... APIC LVTT: %08x\n", v);
+
+ if (maxlvt > 3) {
+ /* PC is LVT#4. */
+ v = apic_read(APIC_LVTPC);
+ pr_debug("... APIC LVTPC: %08x\n", v);
+ }
+ v = apic_read(APIC_LVT0);
+ pr_debug("... APIC LVT0: %08x\n", v);
+ v = apic_read(APIC_LVT1);
+ pr_debug("... APIC LVT1: %08x\n", v);
+
+ if (maxlvt > 2) {
+ /* ERR is LVT#3. */
+ v = apic_read(APIC_LVTERR);
+ pr_debug("... APIC LVTERR: %08x\n", v);
+ }
+
+ v = apic_read(APIC_TMICT);
+ pr_debug("... APIC TMICT: %08x\n", v);
+ v = apic_read(APIC_TMCCT);
+ pr_debug("... APIC TMCCT: %08x\n", v);
+ v = apic_read(APIC_TDCR);
+ pr_debug("... APIC TDCR: %08x\n", v);
+
+ if (boot_cpu_has(X86_FEATURE_EXTAPIC)) {
+ v = apic_read(APIC_EFEAT);
+ maxlvt = (v >> 16) & 0xff;
+ pr_debug("... APIC EFEAT: %08x\n", v);
+ v = apic_read(APIC_ECTRL);
+ pr_debug("... APIC ECTRL: %08x\n", v);
+ for (i = 0; i < maxlvt; i++) {
+ v = apic_read(APIC_EILVTn(i));
+ pr_debug("... APIC EILVT%d: %08x\n", i, v);
+ }
+ }
+ pr_cont("\n");
+}
+
+static void __init print_local_APICs(int maxcpu)
+{
+ int cpu;
+
+ if (!maxcpu)
+ return;
+
+ preempt_disable();
+ for_each_online_cpu(cpu) {
+ if (cpu >= maxcpu)
+ break;
+ smp_call_function_single(cpu, print_local_APIC, NULL, 1);
+ }
+ preempt_enable();
+}
+
+static void __init print_PIC(void)
+{
+ unsigned int v;
+ unsigned long flags;
+
+ if (!nr_legacy_irqs())
+ return;
+
+ pr_debug("\nprinting PIC contents\n");
+
+ raw_spin_lock_irqsave(&i8259A_lock, flags);
+
+ v = inb(0xa1) << 8 | inb(0x21);
+ pr_debug("... PIC IMR: %04x\n", v);
+
+ v = inb(0xa0) << 8 | inb(0x20);
+ pr_debug("... PIC IRR: %04x\n", v);
+
+ outb(0x0b, 0xa0);
+ outb(0x0b, 0x20);
+ v = inb(0xa0) << 8 | inb(0x20);
+ outb(0x0a, 0xa0);
+ outb(0x0a, 0x20);
+
+ raw_spin_unlock_irqrestore(&i8259A_lock, flags);
+
+ pr_debug("... PIC ISR: %04x\n", v);
+
+ v = inb(0x4d1) << 8 | inb(0x4d0);
+ pr_debug("... PIC ELCR: %04x\n", v);
+}
+
+static int show_lapic __initdata = 1;
+static __init int setup_show_lapic(char *arg)
+{
+ int num = -1;
+
+ if (strcmp(arg, "all") == 0) {
+ show_lapic = CONFIG_NR_CPUS;
+ } else {
+ get_option(&arg, &num);
+ if (num >= 0)
+ show_lapic = num;
+ }
+
+ return 1;
+}
+__setup("show_lapic=", setup_show_lapic);
+
+static int __init print_ICs(void)
+{
+ if (apic_verbosity == APIC_QUIET)
+ return 0;
+
+ print_PIC();
+
+ /* don't print out if apic is not there */
+ if (!cpu_has_apic && !apic_from_smp_config())
+ return 0;
+
+ print_local_APICs(show_lapic);
+ print_IO_APICs();
+
+ return 0;
+}
+
+late_initcall(print_ICs);
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 6ce600f9bc78..e658f21681c8 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -42,7 +42,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
* We are to modify mask, so we need an own copy
* and be sure it's manipulated with irq off.
*/
- ipi_mask_ptr = __raw_get_cpu_var(ipi_mask);
+ ipi_mask_ptr = this_cpu_cpumask_var_ptr(ipi_mask);
cpumask_copy(ipi_mask_ptr, mask);
/*
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 004f017aa7b9..8e9dcfd630e4 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -204,7 +204,6 @@ EXPORT_SYMBOL(sn_rtc_cycles_per_second);
static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
{
-#ifdef CONFIG_SMP
unsigned long val;
int pnode;
@@ -223,7 +222,6 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
atomic_set(&init_deasserted, 1);
-#endif
return 0;
}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 584874451414..927ec9235947 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -378,7 +378,6 @@ static struct cpuidle_driver apm_idle_driver = {
{ /* entry 1 is for APM idle */
.name = "APM",
.desc = "APM idle",
- .flags = CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 250, /* WAG */
.target_residency = 500, /* WAG */
.enter = &apm_cpu_idle
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index d67c4be3e8b1..3b3b9d33ac1d 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -1,3 +1,7 @@
+#ifndef __LINUX_KBUILD_H
+# error "Please do not build this file directly, build asm-offsets.c instead"
+#endif
+
#include <asm/ucontext.h>
#include <linux/lguest.h>
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index e7c798b354fa..fdcbb4d27c9f 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -1,3 +1,7 @@
+#ifndef __LINUX_KBUILD_H
+# error "Please do not build this file directly, build asm-offsets.c instead"
+#endif
+
#include <asm/ia32.h>
#define __SYSCALL_64(nr, sym, compat) [nr] = 1,
@@ -48,7 +52,6 @@ int main(void)
#define ENTRY(entry) OFFSET(pt_regs_ ## entry, pt_regs, entry)
ENTRY(bx);
- ENTRY(bx);
ENTRY(cx);
ENTRY(dx);
ENTRY(sp);
diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c
index 06d3e5a14d9d..f3672508b249 100644
--- a/arch/x86/kernel/audit_64.c
+++ b/arch/x86/kernel/audit_64.c
@@ -50,6 +50,7 @@ int audit_classify_syscall(int abi, unsigned syscall)
case __NR_openat:
return 3;
case __NR_execve:
+ case __NR_execveat:
return 5;
default:
return 0;
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7fd54f09b011..80091ae54c2b 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -13,10 +13,13 @@ nostackp := $(call cc-option, -fno-stack-protector)
CFLAGS_common.o := $(nostackp)
obj-y := intel_cacheinfo.o scattered.o topology.o
-obj-y += proc.o capflags.o powerflags.o common.o
+obj-y += common.o
obj-y += rdrand.o
obj-y += match.o
+obj-$(CONFIG_PROC_FS) += proc.o
+obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
+
obj-$(CONFIG_X86_32) += bugs.o
obj-$(CONFIG_X86_64) += bugs_64.o
@@ -36,7 +39,12 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o
endif
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_rapl.o
+
+obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE) += perf_event_intel_uncore.o \
+ perf_event_intel_uncore_snb.o \
+ perf_event_intel_uncore_snbep.o \
+ perf_event_intel_uncore_nhmex.o
endif
@@ -48,6 +56,7 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o
obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o
+ifdef CONFIG_X86_FEATURE_NAMES
quiet_cmd_mkcapflags = MKCAP $@
cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@
@@ -56,3 +65,5 @@ cpufeature = $(src)/../../include/asm/cpufeature.h
targets += capflags.c
$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
$(call if_changed,mkcapflags)
+endif
+clean-files += capflags.c
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 60e5497681f5..15c5df92f74e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -525,6 +525,13 @@ static void early_init_amd(struct cpuinfo_x86 *c)
}
#endif
+ /*
+ * This is only needed to tell the kernel whether to use VMCALL
+ * and VMMCALL. VMMCALL is never executed except under virt, so
+ * we can set it unconditionally.
+ */
+ set_cpu_cap(c, X86_FEATURE_VMMCALL);
+
/* F16h erratum 793, CVE-2013-6885 */
if (c->x86 == 0x16 && c->x86_model <= 0xf)
msr_set_bit(MSR_AMD64_LS_CFG, 15);
@@ -559,6 +566,17 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
if (!c->x86_model_id[0])
strcpy(c->x86_model_id, "Hammer");
+
+#ifdef CONFIG_SMP
+ /*
+ * Disable TLB flush filter by setting HWCR.FFDIS on K8
+ * bit 6 of msr C001_0015
+ *
+ * Errata 63 for SH-B3 steppings
+ * Errata 122 for all steppings (F+ have it disabled by default)
+ */
+ msr_set_bit(MSR_K7_HWCR, 6);
+#endif
}
static void init_amd_gh(struct cpuinfo_x86 *c)
@@ -629,18 +647,6 @@ static void init_amd(struct cpuinfo_x86 *c)
{
u32 dummy;
-#ifdef CONFIG_SMP
- /*
- * Disable TLB flush filter by setting HWCR.FFDIS on K8
- * bit 6 of msr C001_0015
- *
- * Errata 63 for SH-B3 steppings
- * Errata 122 for all steppings (F+ have it disabled by default)
- */
- if (c->x86 == 0xf)
- msr_set_bit(MSR_K7_HWCR, 6);
-#endif
-
early_init_amd(c);
/*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e4ab2b42bd6f..c6049650c093 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -146,6 +146,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
static int __init x86_xsave_setup(char *s)
{
+ if (strlen(s))
+ return 0;
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
setup_clear_cpu_cap(X86_FEATURE_XSAVES);
@@ -346,8 +348,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
continue;
printk(KERN_WARNING
- "CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
- x86_cap_flags[df->feature], df->level);
+ "CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
+ x86_cap_flag(df->feature), df->level);
}
}
@@ -956,14 +958,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
}
#ifdef CONFIG_X86_64
-static void vgetcpu_set_mode(void)
-{
- if (cpu_has(&boot_cpu_data, X86_FEATURE_RDTSCP))
- vgetcpu_mode = VGETCPU_RDTSCP;
- else
- vgetcpu_mode = VGETCPU_LSL;
-}
-
+#ifdef CONFIG_IA32_EMULATION
/* May not be __init: called during resume */
static void syscall32_cpu_init(void)
{
@@ -975,7 +970,8 @@ static void syscall32_cpu_init(void)
wrmsrl(MSR_CSTAR, ia32_cstar_target);
}
-#endif
+#endif /* CONFIG_IA32_EMULATION */
+#endif /* CONFIG_X86_64 */
#ifdef CONFIG_X86_32
void enable_sep_cpu(void)
@@ -1004,8 +1000,6 @@ void __init identify_boot_cpu(void)
#ifdef CONFIG_X86_32
sysenter_setup();
enable_sep_cpu();
-#else
- vgetcpu_set_mode();
#endif
cpu_detect_tlb(&boot_cpu_data);
}
@@ -1184,7 +1178,7 @@ void syscall_init(void)
/* Flags to clear on syscall */
wrmsrl(MSR_SYSCALL_MASK,
X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
- X86_EFLAGS_IOPL|X86_EFLAGS_AC);
+ X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
}
/*
@@ -1198,9 +1192,9 @@ DEFINE_PER_CPU(int, debug_stack_usage);
int is_debug_stack(unsigned long addr)
{
- return __get_cpu_var(debug_stack_usage) ||
- (addr <= __get_cpu_var(debug_stack_addr) &&
- addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ));
+ return __this_cpu_read(debug_stack_usage) ||
+ (addr <= __this_cpu_read(debug_stack_addr) &&
+ addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
}
NOKPROBE_SYMBOL(is_debug_stack);
@@ -1266,6 +1260,19 @@ static void dbg_restore_debug_regs(void)
#define dbg_restore_debug_regs()
#endif /* ! CONFIG_KGDB */
+static void wait_for_master_cpu(int cpu)
+{
+#ifdef CONFIG_SMP
+ /*
+ * wait for ACK from master CPU before continuing
+ * with AP initialization
+ */
+ WARN_ON(cpumask_test_and_set_cpu(cpu, cpu_initialized_mask));
+ while (!cpumask_test_cpu(cpu, cpu_callout_mask))
+ cpu_relax();
+#endif
+}
+
/*
* cpu_init() initializes state that is per-CPU. Some data is already
* initialized (naturally) in the bootstrap process, such as the GDT
@@ -1281,16 +1288,17 @@ void cpu_init(void)
struct task_struct *me;
struct tss_struct *t;
unsigned long v;
- int cpu;
+ int cpu = stack_smp_processor_id();
int i;
+ wait_for_master_cpu(cpu);
+
/*
* Load microcode on this cpu if a valid microcode is available.
* This is early microcode loading procedure.
*/
load_ucode_ap();
- cpu = stack_smp_processor_id();
t = &per_cpu(init_tss, cpu);
oist = &per_cpu(orig_ist, cpu);
@@ -1302,9 +1310,6 @@ void cpu_init(void)
me = current;
- if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
- panic("CPU#%d already initialized!\n", cpu);
-
pr_debug("Initializing CPU#%d\n", cpu);
clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
@@ -1381,17 +1386,13 @@ void cpu_init(void)
struct tss_struct *t = &per_cpu(init_tss, cpu);
struct thread_struct *thread = &curr->thread;
- show_ucode_info_early();
+ wait_for_master_cpu(cpu);
- if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
- printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
- for (;;)
- local_irq_enable();
- }
+ show_ucode_info_early();
printk(KERN_INFO "Initializing CPU#%d\n", cpu);
- if (cpu_has_vme || cpu_has_tsc || cpu_has_de)
+ if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de)
clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
load_current_idt();
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 74e804ddc5c7..9cc6b6f25f42 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -144,6 +144,21 @@ static void early_init_intel(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_ERMS);
}
}
+
+ /*
+ * Intel Quark Core DevMan_001.pdf section 6.4.11
+ * "The operating system also is required to invalidate (i.e., flush)
+ * the TLB when any changes are made to any of the page table entries.
+ * The operating system must reload CR3 to cause the TLB to be flushed"
+ *
+ * As a result cpu_has_pge() in arch/x86/include/asm/tlbflush.h should
+ * be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+ * to be modified
+ */
+ if (c->x86 == 5 && c->x86_model == 9) {
+ pr_info("Disabling PGE capability bit\n");
+ setup_clear_cpu_cap(X86_FEATURE_PGE);
+ }
}
#ifdef CONFIG_X86_32
@@ -198,12 +213,13 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_F00F_BUG
/*
- * All current models of Pentium and Pentium with MMX technology CPUs
+ * All models of Pentium and Pentium with MMX technology CPUs
* have the F0 0F bug, which lets nonprivileged users lock up the
* system. Announce that the fault handler will be checking for it.
+ * The Quark is also family 5, but does not have the same bug.
*/
clear_cpu_bug(c, X86_BUG_F00F);
- if (!paravirt_enabled() && c->x86 == 5) {
+ if (!paravirt_enabled() && c->x86 == 5 && c->x86_model < 9) {
static int f00f_workaround_enabled;
set_cpu_bug(c, X86_BUG_F00F);
@@ -382,6 +398,13 @@ static void init_intel(struct cpuinfo_x86 *c)
}
l2 = init_intel_cacheinfo(c);
+
+ /* Detect legacy cache sizes if init_intel_cacheinfo did not */
+ if (l2 == 0) {
+ cpu_detect_cache_sizes(c);
+ l2 = c->x86_cache_size;
+ }
+
if (c->cpuid_level > 9) {
unsigned eax = cpuid_eax(10);
/* Check for version and the number of counters */
@@ -485,6 +508,13 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
*/
if ((c->x86 == 6) && (c->x86_model == 11) && (size == 0))
size = 256;
+
+ /*
+ * Intel Quark SoC X1000 contains a 4-way set associative
+ * 16K cache with a 16 byte cache line and 256 lines per tag
+ */
+ if ((c->x86 == 5) && (c->x86_model == 9))
+ size = 16;
return size;
}
#endif
@@ -686,7 +716,8 @@ static const struct cpu_dev intel_cpu_dev = {
[3] = "OverDrive PODP5V83",
[4] = "Pentium MMX",
[7] = "Mobile Pentium 75 - 200",
- [8] = "Mobile Pentium MMX"
+ [8] = "Mobile Pentium MMX",
+ [9] = "Quark SoC X1000",
}
},
{ .family = 6, .model_names =
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 5ac2d1fb28bc..4cfba4371a71 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -83,7 +83,7 @@ static DEFINE_MUTEX(mce_inject_mutex);
static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
{
int cpu = smp_processor_id();
- struct mce *m = &__get_cpu_var(injectm);
+ struct mce *m = this_cpu_ptr(&injectm);
if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
return NMI_DONE;
cpumask_clear_cpu(cpu, mce_inject_cpumask);
@@ -97,7 +97,7 @@ static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
static void mce_irq_ipi(void *info)
{
int cpu = smp_processor_id();
- struct mce *m = &__get_cpu_var(injectm);
+ struct mce *m = this_cpu_ptr(&injectm);
if (cpumask_test_cpu(cpu, mce_inject_cpumask) &&
m->inject_flags & MCJ_EXCEPTION) {
@@ -109,7 +109,7 @@ static void mce_irq_ipi(void *info)
/* Inject mce on current CPU */
static int raise_local(void)
{
- struct mce *m = &__get_cpu_var(injectm);
+ struct mce *m = this_cpu_ptr(&injectm);
int context = MCJ_CTX(m->inject_flags);
int ret = 0;
int cpu = m->extcpu;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 09edd0b65fef..10b46906767f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -3,6 +3,8 @@
enum severity_level {
MCE_NO_SEVERITY,
+ MCE_DEFERRED_SEVERITY,
+ MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY,
MCE_KEEP_SEVERITY,
MCE_SOME_SEVERITY,
MCE_AO_SEVERITY,
@@ -21,7 +23,7 @@ struct mce_bank {
char attrname[ATTR_LEN]; /* attribute name */
};
-int mce_severity(struct mce *a, int tolerant, char **msg);
+int mce_severity(struct mce *a, int tolerant, char **msg, bool is_excp);
struct dentry *mce_get_debugfs_dir(void);
extern struct mce_bank *mce_banks;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index c370e1c4468b..8bb433043a7f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -31,6 +31,7 @@
enum context { IN_KERNEL = 1, IN_USER = 2 };
enum ser { SER_REQUIRED = 1, NO_SER = 2 };
+enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 };
static struct severity {
u64 mask;
@@ -40,6 +41,7 @@ static struct severity {
unsigned char mcgres;
unsigned char ser;
unsigned char context;
+ unsigned char excp;
unsigned char covered;
char *msg;
} severities[] = {
@@ -48,6 +50,8 @@ static struct severity {
#define USER .context = IN_USER
#define SER .ser = SER_REQUIRED
#define NOSER .ser = NO_SER
+#define EXCP .excp = EXCP_CONTEXT
+#define NOEXCP .excp = NO_EXCP
#define BITCLR(x) .mask = x, .result = 0
#define BITSET(x) .mask = x, .result = x
#define MCGMASK(x, y) .mcgmask = x, .mcgres = y
@@ -62,7 +66,7 @@ static struct severity {
),
MCESEV(
NO, "Not enabled",
- BITCLR(MCI_STATUS_EN)
+ EXCP, BITCLR(MCI_STATUS_EN)
),
MCESEV(
PANIC, "Processor context corrupt",
@@ -71,16 +75,20 @@ static struct severity {
/* When MCIP is not set something is very confused */
MCESEV(
PANIC, "MCIP not set in MCA handler",
- MCGMASK(MCG_STATUS_MCIP, 0)
+ EXCP, MCGMASK(MCG_STATUS_MCIP, 0)
),
/* Neither return not error IP -- no chance to recover -> PANIC */
MCESEV(
PANIC, "Neither restart nor error IP",
- MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0)
+ EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0)
),
MCESEV(
PANIC, "In kernel and no restart IP",
- KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
+ EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0)
+ ),
+ MCESEV(
+ DEFERRED, "Deferred error",
+ NOSER, MASK(MCI_STATUS_UC|MCI_STATUS_DEFERRED|MCI_STATUS_POISON, MCI_STATUS_DEFERRED)
),
MCESEV(
KEEP, "Corrected error",
@@ -89,7 +97,7 @@ static struct severity {
/* ignore OVER for UCNA */
MCESEV(
- KEEP, "Uncorrected no action required",
+ UCNA, "Uncorrected no action required",
SER, MASK(MCI_UC_SAR, MCI_STATUS_UC)
),
MCESEV(
@@ -178,8 +186,9 @@ static int error_context(struct mce *m)
return ((m->cs & 3) == 3) ? IN_USER : IN_KERNEL;
}
-int mce_severity(struct mce *m, int tolerant, char **msg)
+int mce_severity(struct mce *m, int tolerant, char **msg, bool is_excp)
{
+ enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP);
enum context ctx = error_context(m);
struct severity *s;
@@ -194,6 +203,8 @@ int mce_severity(struct mce *m, int tolerant, char **msg)
continue;
if (s->context && ctx != s->context)
continue;
+ if (s->excp && excp != s->excp)
+ continue;
if (msg)
*msg = s->msg;
s->covered = 1;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bd9ccda8087f..d2c611699cd9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -292,10 +292,10 @@ static void print_mce(struct mce *m)
#define PANIC_TIMEOUT 5 /* 5 seconds */
-static atomic_t mce_paniced;
+static atomic_t mce_panicked;
static int fake_panic;
-static atomic_t mce_fake_paniced;
+static atomic_t mce_fake_panicked;
/* Panic in progress. Enable interrupts and wait for final IPI */
static void wait_for_panic(void)
@@ -319,7 +319,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
/*
* Make sure only one CPU runs in machine check panic
*/
- if (atomic_inc_return(&mce_paniced) > 1)
+ if (atomic_inc_return(&mce_panicked) > 1)
wait_for_panic();
barrier();
@@ -327,7 +327,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
console_verbose();
} else {
/* Don't log too much for fake panic */
- if (atomic_inc_return(&mce_fake_paniced) > 1)
+ if (atomic_inc_return(&mce_fake_panicked) > 1)
return;
}
/* First print corrected ones that are still unlogged */
@@ -400,7 +400,7 @@ static u64 mce_rdmsrl(u32 msr)
if (offset < 0)
return 0;
- return *(u64 *)((char *)&__get_cpu_var(injectm) + offset);
+ return *(u64 *)((char *)this_cpu_ptr(&injectm) + offset);
}
if (rdmsrl_safe(msr, &v)) {
@@ -422,7 +422,7 @@ static void mce_wrmsrl(u32 msr, u64 v)
int offset = msr_to_offset(msr);
if (offset >= 0)
- *(u64 *)((char *)&__get_cpu_var(injectm) + offset) = v;
+ *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v;
return;
}
wrmsrl(msr, v);
@@ -478,7 +478,7 @@ static DEFINE_PER_CPU(struct mce_ring, mce_ring);
/* Runs with CPU affinity in workqueue */
static int mce_ring_empty(void)
{
- struct mce_ring *r = &__get_cpu_var(mce_ring);
+ struct mce_ring *r = this_cpu_ptr(&mce_ring);
return r->start == r->end;
}
@@ -490,7 +490,7 @@ static int mce_ring_get(unsigned long *pfn)
*pfn = 0;
get_cpu();
- r = &__get_cpu_var(mce_ring);
+ r = this_cpu_ptr(&mce_ring);
if (r->start == r->end)
goto out;
*pfn = r->ring[r->start];
@@ -504,7 +504,7 @@ out:
/* Always runs in MCE context with preempt off */
static int mce_ring_add(unsigned long pfn)
{
- struct mce_ring *r = &__get_cpu_var(mce_ring);
+ struct mce_ring *r = this_cpu_ptr(&mce_ring);
unsigned next;
next = (r->end + 1) % MCE_RING_SIZE;
@@ -526,7 +526,7 @@ int mce_available(struct cpuinfo_x86 *c)
static void mce_schedule_work(void)
{
if (!mce_ring_empty())
- schedule_work(&__get_cpu_var(mce_work));
+ schedule_work(this_cpu_ptr(&mce_work));
}
DEFINE_PER_CPU(struct irq_work, mce_irq_work);
@@ -551,7 +551,7 @@ static void mce_report_event(struct pt_regs *regs)
return;
}
- irq_work_queue(&__get_cpu_var(mce_irq_work));
+ irq_work_queue(this_cpu_ptr(&mce_irq_work));
}
/*
@@ -575,6 +575,37 @@ static void mce_read_aux(struct mce *m, int i)
}
}
+static bool memory_error(struct mce *m)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (c->x86_vendor == X86_VENDOR_AMD) {
+ /*
+ * coming soon
+ */
+ return false;
+ } else if (c->x86_vendor == X86_VENDOR_INTEL) {
+ /*
+ * Intel SDM Volume 3B - 15.9.2 Compound Error Codes
+ *
+ * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for
+ * indicating a memory error. Bit 8 is used for indicating a
+ * cache hierarchy error. The combination of bit 2 and bit 3
+ * is used for indicating a `generic' cache hierarchy error
+ * But we can't just blindly check the above bits, because if
+ * bit 11 is set, then it is a bus/interconnect error - and
+ * either way the above bits just gives more detail on what
+ * bus/interconnect error happened. Note that bit 12 can be
+ * ignored, as it's the "filter" bit.
+ */
+ return (m->status & 0xef80) == BIT(7) ||
+ (m->status & 0xef00) == BIT(8) ||
+ (m->status & 0xeffc) == 0xc;
+ }
+
+ return false;
+}
+
DEFINE_PER_CPU(unsigned, mce_poll_count);
/*
@@ -595,6 +626,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count);
void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
{
struct mce m;
+ int severity;
int i;
this_cpu_inc(mce_poll_count);
@@ -630,6 +662,20 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!(flags & MCP_TIMESTAMP))
m.tsc = 0;
+
+ severity = mce_severity(&m, mca_cfg.tolerant, NULL, false);
+
+ /*
+ * In the cases where we don't have a valid address after all,
+ * do not add it into the ring buffer.
+ */
+ if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) {
+ if (m.status & MCI_STATUS_ADDRV) {
+ mce_ring_add(m.addr >> PAGE_SHIFT);
+ mce_schedule_work();
+ }
+ }
+
/*
* Don't get the IP here because it's unlikely to
* have anything to do with the actual error location.
@@ -668,7 +714,8 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
if (quirk_no_way_out)
quirk_no_way_out(i, m, regs);
}
- if (mce_severity(m, mca_cfg.tolerant, msg) >= MCE_PANIC_SEVERITY)
+ if (mce_severity(m, mca_cfg.tolerant, msg, true) >=
+ MCE_PANIC_SEVERITY)
ret = 1;
}
return ret;
@@ -697,7 +744,7 @@ static int mce_timed_out(u64 *t)
* might have been modified by someone else.
*/
rmb();
- if (atomic_read(&mce_paniced))
+ if (atomic_read(&mce_panicked))
wait_for_panic();
if (!mca_cfg.monarch_timeout)
goto out;
@@ -754,7 +801,7 @@ static void mce_reign(void)
for_each_possible_cpu(cpu) {
int severity = mce_severity(&per_cpu(mces_seen, cpu),
mca_cfg.tolerant,
- &nmsg);
+ &nmsg, true);
if (severity > global_worst) {
msg = nmsg;
global_worst = severity;
@@ -1045,7 +1092,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
mce_gather_info(&m, regs);
- final = &__get_cpu_var(mces_seen);
+ final = this_cpu_ptr(&mces_seen);
*final = m;
memset(valid_banks, 0, sizeof(valid_banks));
@@ -1095,13 +1142,14 @@ void do_machine_check(struct pt_regs *regs, long error_code)
*/
add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
- severity = mce_severity(&m, cfg->tolerant, NULL);
+ severity = mce_severity(&m, cfg->tolerant, NULL, true);
/*
- * When machine check was for corrected handler don't touch,
- * unless we're panicing.
+ * When machine check was for corrected/deferred handler don't
+ * touch, unless we're panicing.
*/
- if (severity == MCE_KEEP_SEVERITY && !no_way_out)
+ if ((severity == MCE_KEEP_SEVERITY ||
+ severity == MCE_UCNA_SEVERITY) && !no_way_out)
continue;
__set_bit(i, toclear);
if (severity == MCE_NO_SEVERITY) {
@@ -1278,22 +1326,22 @@ static unsigned long (*mce_adjust_timer)(unsigned long interval) =
static int cmc_error_seen(void)
{
- unsigned long *v = &__get_cpu_var(mce_polled_error);
+ unsigned long *v = this_cpu_ptr(&mce_polled_error);
return test_and_clear_bit(0, v);
}
static void mce_timer_fn(unsigned long data)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned long iv;
int notify;
WARN_ON(smp_processor_id() != data);
- if (mce_available(__this_cpu_ptr(&cpu_info))) {
+ if (mce_available(this_cpu_ptr(&cpu_info))) {
machine_check_poll(MCP_TIMESTAMP,
- &__get_cpu_var(mce_poll_banks));
+ this_cpu_ptr(&mce_poll_banks));
mce_intel_cmci_poll();
}
@@ -1323,7 +1371,7 @@ static void mce_timer_fn(unsigned long data)
*/
void mce_timer_kick(unsigned long interval)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned long when = jiffies + interval;
unsigned long iv = __this_cpu_read(mce_next_interval);
@@ -1659,7 +1707,7 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
static void __mcheck_cpu_init_timer(void)
{
- struct timer_list *t = &__get_cpu_var(mce_timer);
+ struct timer_list *t = this_cpu_ptr(&mce_timer);
unsigned int cpu = smp_processor_id();
setup_timer(t, mce_timer_fn, cpu);
@@ -1702,8 +1750,8 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
__mcheck_cpu_init_generic();
__mcheck_cpu_init_vendor(c);
__mcheck_cpu_init_timer();
- INIT_WORK(&__get_cpu_var(mce_work), mce_process_work);
- init_irq_work(&__get_cpu_var(mce_irq_work), &mce_irq_work_cb);
+ INIT_WORK(this_cpu_ptr(&mce_work), mce_process_work);
+ init_irq_work(this_cpu_ptr(&mce_irq_work), &mce_irq_work_cb);
}
/*
@@ -1955,7 +2003,7 @@ static struct miscdevice mce_chrdev_device = {
static void __mce_disable_bank(void *arg)
{
int bank = *((int *)arg);
- __clear_bit(bank, __get_cpu_var(mce_poll_banks));
+ __clear_bit(bank, this_cpu_ptr(mce_poll_banks));
cmci_disable_bank(bank);
}
@@ -2065,7 +2113,7 @@ static void mce_syscore_shutdown(void)
static void mce_syscore_resume(void)
{
__mcheck_cpu_init_generic();
- __mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
+ __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
}
static struct syscore_ops mce_syscore_ops = {
@@ -2080,7 +2128,7 @@ static struct syscore_ops mce_syscore_ops = {
static void mce_cpu_restart(void *data)
{
- if (!mce_available(__this_cpu_ptr(&cpu_info)))
+ if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
__mcheck_cpu_init_timer();
@@ -2096,14 +2144,14 @@ static void mce_restart(void)
/* Toggle features for corrected errors */
static void mce_disable_cmci(void *data)
{
- if (!mce_available(__this_cpu_ptr(&cpu_info)))
+ if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
cmci_clear();
}
static void mce_enable_ce(void *all)
{
- if (!mce_available(__this_cpu_ptr(&cpu_info)))
+ if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
cmci_reenable();
cmci_recheck();
@@ -2336,7 +2384,7 @@ static void mce_disable_cpu(void *h)
unsigned long action = *(unsigned long *)h;
int i;
- if (!mce_available(__this_cpu_ptr(&cpu_info)))
+ if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
if (!(action & CPU_TASKS_FROZEN))
@@ -2354,7 +2402,7 @@ static void mce_reenable_cpu(void *h)
unsigned long action = *(unsigned long *)h;
int i;
- if (!mce_available(__this_cpu_ptr(&cpu_info)))
+ if (!mce_available(raw_cpu_ptr(&cpu_info)))
return;
if (!(action & CPU_TASKS_FROZEN))
@@ -2520,7 +2568,7 @@ struct dentry *mce_get_debugfs_dir(void)
static void mce_reset(void)
{
cpu_missing = 0;
- atomic_set(&mce_fake_paniced, 0);
+ atomic_set(&mce_fake_panicked, 0);
atomic_set(&mce_executing, 0);
atomic_set(&mce_callin, 0);
atomic_set(&global_nwo, 0);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 1e49f8f41276..f1c3769bbd64 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -212,12 +212,12 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
unsigned int cpu = smp_processor_id();
u32 low = 0, high = 0, address = 0;
unsigned int bank, block;
- int offset = -1;
+ int offset = -1, new;
for (bank = 0; bank < mca_cfg.banks; ++bank) {
for (block = 0; block < NR_BLOCKS; ++block) {
if (block == 0)
- address = MSR_IA32_MC0_MISC + bank * 4;
+ address = MSR_IA32_MCx_MISC(bank);
else if (block == 1) {
address = (low & MASK_BLKPTR_LO) >> 21;
if (!address)
@@ -247,13 +247,18 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
b.address = address;
b.interrupt_capable = lvt_interrupt_supported(bank, high);
- if (b.interrupt_capable) {
- int new = (high & MASK_LVTOFF_HI) >> 20;
- offset = setup_APIC_mce(offset, new);
- }
+ if (!b.interrupt_capable)
+ goto init;
+
+ new = (high & MASK_LVTOFF_HI) >> 20;
+ offset = setup_APIC_mce(offset, new);
+
+ if ((offset == new) &&
+ (mce_threshold_vector != amd_threshold_interrupt))
+ mce_threshold_vector = amd_threshold_interrupt;
+init:
mce_threshold_block_init(&b, offset);
- mce_threshold_vector = amd_threshold_interrupt;
}
}
}
@@ -270,18 +275,17 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
static void amd_threshold_interrupt(void)
{
u32 low = 0, high = 0, address = 0;
+ int cpu = smp_processor_id();
unsigned int bank, block;
struct mce m;
- mce_setup(&m);
-
/* assume first bank caused it */
for (bank = 0; bank < mca_cfg.banks; ++bank) {
- if (!(per_cpu(bank_map, m.cpu) & (1 << bank)))
+ if (!(per_cpu(bank_map, cpu) & (1 << bank)))
continue;
for (block = 0; block < NR_BLOCKS; ++block) {
if (block == 0) {
- address = MSR_IA32_MC0_MISC + bank * 4;
+ address = MSR_IA32_MCx_MISC(bank);
} else if (block == 1) {
address = (low & MASK_BLKPTR_LO) >> 21;
if (!address)
@@ -309,21 +313,20 @@ static void amd_threshold_interrupt(void)
* Log the machine check that caused the threshold
* event.
*/
- machine_check_poll(MCP_TIMESTAMP,
- &__get_cpu_var(mce_poll_banks));
-
- if (high & MASK_OVERFLOW_HI) {
- rdmsrl(address, m.misc);
- rdmsrl(MSR_IA32_MC0_STATUS + bank * 4,
- m.status);
- m.bank = K8_MCE_THRESHOLD_BASE
- + bank * NR_BLOCKS
- + block;
- mce_log(&m);
- return;
- }
+ if (high & MASK_OVERFLOW_HI)
+ goto log;
}
}
+ return;
+
+log:
+ mce_setup(&m);
+ rdmsrl(MSR_IA32_MCx_STATUS(bank), m.status);
+ m.misc = ((u64)high << 32) | low;
+ m.bank = bank;
+ mce_log(&m);
+
+ wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
}
/*
@@ -617,8 +620,7 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
}
}
- err = allocate_threshold_blocks(cpu, bank, 0,
- MSR_IA32_MC0_MISC + bank * 4);
+ err = allocate_threshold_blocks(cpu, bank, 0, MSR_IA32_MCx_MISC(bank));
if (!err)
goto out;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 3bdb95ae8c43..b3c97bafc123 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -86,7 +86,7 @@ void mce_intel_cmci_poll(void)
{
if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE)
return;
- machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+ machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
}
void mce_intel_hcpu_update(unsigned long cpu)
@@ -145,7 +145,7 @@ static void cmci_storm_disable_banks(void)
u64 val;
raw_spin_lock_irqsave(&cmci_discover_lock, flags);
- owned = __get_cpu_var(mce_banks_owned);
+ owned = this_cpu_ptr(mce_banks_owned);
for_each_set_bit(bank, owned, MAX_NR_BANKS) {
rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
val &= ~MCI_CTL2_CMCI_EN;
@@ -195,7 +195,7 @@ static void intel_threshold_interrupt(void)
{
if (cmci_storm_detect())
return;
- machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+ machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
mce_notify_irq();
}
@@ -206,7 +206,7 @@ static void intel_threshold_interrupt(void)
*/
static void cmci_discover(int banks)
{
- unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+ unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned);
unsigned long flags;
int i;
int bios_wrong_thresh = 0;
@@ -228,7 +228,7 @@ static void cmci_discover(int banks)
/* Already owned by someone else? */
if (val & MCI_CTL2_CMCI_EN) {
clear_bit(i, owned);
- __clear_bit(i, __get_cpu_var(mce_poll_banks));
+ __clear_bit(i, this_cpu_ptr(mce_poll_banks));
continue;
}
@@ -252,7 +252,7 @@ static void cmci_discover(int banks)
/* Did the enable bit stick? -- the bank supports CMCI */
if (val & MCI_CTL2_CMCI_EN) {
set_bit(i, owned);
- __clear_bit(i, __get_cpu_var(mce_poll_banks));
+ __clear_bit(i, this_cpu_ptr(mce_poll_banks));
/*
* We are able to set thresholds for some banks that
* had a threshold of 0. This means the BIOS has not
@@ -263,7 +263,7 @@ static void cmci_discover(int banks)
(val & MCI_CTL2_CMCI_THRESHOLD_MASK))
bios_wrong_thresh = 1;
} else {
- WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
+ WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks)));
}
}
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
@@ -284,10 +284,10 @@ void cmci_recheck(void)
unsigned long flags;
int banks;
- if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
+ if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
return;
local_irq_save(flags);
- machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+ machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned));
local_irq_restore(flags);
}
@@ -296,12 +296,12 @@ static void __cmci_disable_bank(int bank)
{
u64 val;
- if (!test_bit(bank, __get_cpu_var(mce_banks_owned)))
+ if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
return;
rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
val &= ~MCI_CTL2_CMCI_EN;
wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
- __clear_bit(bank, __get_cpu_var(mce_banks_owned));
+ __clear_bit(bank, this_cpu_ptr(mce_banks_owned));
}
/*
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 36a1bb6d1ee0..1af51b1586d7 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -498,8 +498,8 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
- printk(KERN_DEBUG
- "CPU%d: Thermal monitoring handled by SMI\n", cpu);
+ if (system_state == SYSTEM_BOOTING)
+ printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n", cpu);
return;
}
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 8fffd845e22b..bfbbe6195e2d 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -376,7 +376,7 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
return UCODE_OK;
}
-enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
+enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, size_t size)
{
enum ucode_state ret;
@@ -390,8 +390,8 @@ enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
#if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32)
/* save BSP's matching patch for early load */
- if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) {
- struct ucode_patch *p = find_patch(smp_processor_id());
+ if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) {
+ struct ucode_patch *p = find_patch(cpu);
if (p) {
memset(amd_ucode_patch, 0, PATCH_MAX_SIZE);
memcpy(amd_ucode_patch, p->data, min_t(u32, ksize(p->data),
@@ -444,7 +444,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device,
goto fw_release;
}
- ret = load_microcode_amd(c->x86, fw->data, fw->size);
+ ret = load_microcode_amd(cpu, c->x86, fw->data, fw->size);
fw_release:
release_firmware(fw);
diff --git a/arch/x86/kernel/cpu/microcode/amd_early.c b/arch/x86/kernel/cpu/microcode/amd_early.c
index 617a9e284245..737737edbd1e 100644
--- a/arch/x86/kernel/cpu/microcode/amd_early.c
+++ b/arch/x86/kernel/cpu/microcode/amd_early.c
@@ -27,7 +27,7 @@ static u32 ucode_new_rev;
u8 amd_ucode_patch[PATCH_MAX_SIZE];
static u16 this_equiv_id;
-struct cpio_data ucode_cpio;
+static struct cpio_data ucode_cpio;
/*
* Microcode patch container file is prepended to the initrd in cpio format.
@@ -108,12 +108,13 @@ static size_t compute_container_size(u8 *data, u32 total_size)
* load_microcode_amd() to save equivalent cpu table and microcode patches in
* kernel heap memory.
*/
-static void apply_ucode_in_initrd(void *ucode, size_t size)
+static void apply_ucode_in_initrd(void *ucode, size_t size, bool save_patch)
{
struct equiv_cpu_entry *eq;
size_t *cont_sz;
u32 *header;
u8 *data, **cont;
+ u8 (*patch)[PATCH_MAX_SIZE];
u16 eq_id = 0;
int offset, left;
u32 rev, eax, ebx, ecx, edx;
@@ -123,10 +124,12 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
new_rev = (u32 *)__pa_nodebug(&ucode_new_rev);
cont_sz = (size_t *)__pa_nodebug(&container_size);
cont = (u8 **)__pa_nodebug(&container);
+ patch = (u8 (*)[PATCH_MAX_SIZE])__pa_nodebug(&amd_ucode_patch);
#else
new_rev = &ucode_new_rev;
cont_sz = &container_size;
cont = &container;
+ patch = &amd_ucode_patch;
#endif
data = ucode;
@@ -213,9 +216,9 @@ static void apply_ucode_in_initrd(void *ucode, size_t size)
rev = mc->hdr.patch_id;
*new_rev = rev;
- /* save ucode patch */
- memcpy(amd_ucode_patch, mc,
- min_t(u32, header[1], PATCH_MAX_SIZE));
+ if (save_patch)
+ memcpy(patch, mc,
+ min_t(u32, header[1], PATCH_MAX_SIZE));
}
}
@@ -246,7 +249,7 @@ void __init load_ucode_amd_bsp(void)
*data = cp.data;
*size = cp.size;
- apply_ucode_in_initrd(cp.data, cp.size);
+ apply_ucode_in_initrd(cp.data, cp.size, true);
}
#ifdef CONFIG_X86_32
@@ -263,7 +266,7 @@ void load_ucode_amd_ap(void)
size_t *usize;
void **ucode;
- mc = (struct microcode_amd *)__pa(amd_ucode_patch);
+ mc = (struct microcode_amd *)__pa_nodebug(amd_ucode_patch);
if (mc->hdr.patch_id && mc->hdr.processor_rev_id) {
__apply_microcode_amd(mc);
return;
@@ -275,7 +278,7 @@ void load_ucode_amd_ap(void)
if (!*ucode || !*usize)
return;
- apply_ucode_in_initrd(*ucode, *usize);
+ apply_ucode_in_initrd(*ucode, *usize, false);
}
static void __init collect_cpu_sig_on_bsp(void *arg)
@@ -339,7 +342,7 @@ void load_ucode_amd_ap(void)
* AP has a different equivalence ID than BSP, looks like
* mixed-steppings silicon so go through the ucode blob anew.
*/
- apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size);
+ apply_ucode_in_initrd(ucode_cpio.data, ucode_cpio.size, false);
}
}
#endif
@@ -347,7 +350,9 @@ void load_ucode_amd_ap(void)
int __init save_microcode_in_initrd_amd(void)
{
unsigned long cont;
+ int retval = 0;
enum ucode_state ret;
+ u8 *cont_va;
u32 eax;
if (!container)
@@ -355,13 +360,15 @@ int __init save_microcode_in_initrd_amd(void)
#ifdef CONFIG_X86_32
get_bsp_sig();
- cont = (unsigned long)container;
+ cont = (unsigned long)container;
+ cont_va = __va(container);
#else
/*
* We need the physical address of the container for both bitness since
* boot_params.hdr.ramdisk_image is a physical address.
*/
- cont = __pa(container);
+ cont = __pa(container);
+ cont_va = container;
#endif
/*
@@ -372,6 +379,8 @@ int __init save_microcode_in_initrd_amd(void)
if (relocated_ramdisk)
container = (u8 *)(__va(relocated_ramdisk) +
(cont - boot_params.hdr.ramdisk_image));
+ else
+ container = cont_va;
if (ucode_new_rev)
pr_info("microcode: updated early to new patch_level=0x%08x\n",
@@ -380,9 +389,9 @@ int __init save_microcode_in_initrd_amd(void)
eax = cpuid_eax(0x00000001);
eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
- ret = load_microcode_amd(eax, container, container_size);
+ ret = load_microcode_amd(smp_processor_id(), eax, container, container_size);
if (ret != UCODE_OK)
- return -EINVAL;
+ retval = -EINVAL;
/*
* This will be freed any msec now, stash patches for the current
@@ -391,5 +400,23 @@ int __init save_microcode_in_initrd_amd(void)
container = NULL;
container_size = 0;
- return 0;
+ return retval;
+}
+
+void reload_ucode_amd(void)
+{
+ struct microcode_amd *mc;
+ u32 rev, eax;
+
+ rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax);
+
+ mc = (struct microcode_amd *)amd_ucode_patch;
+
+ if (mc && rev < mc->hdr.patch_id) {
+ if (!__apply_microcode_amd(mc)) {
+ ucode_new_rev = mc->hdr.patch_id;
+ pr_info("microcode: reload patch_level=0x%08x\n",
+ ucode_new_rev);
+ }
+ }
}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index dd9d6190b08d..15c29096136b 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -465,6 +465,8 @@ static void mc_bp_resume(void)
if (uci->valid && uci->mc)
microcode_ops->apply_microcode(cpu);
+ else if (!uci->mc)
+ reload_early_microcode();
}
static struct syscore_ops mc_syscore_ops = {
@@ -549,7 +551,7 @@ static int __init microcode_init(void)
struct cpuinfo_x86 *c = &cpu_data(0);
int error;
- if (dis_ucode_ldr)
+ if (paravirt_enabled() || dis_ucode_ldr)
return 0;
if (c->x86_vendor == X86_VENDOR_INTEL)
diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c
index 5f28a64e71ea..d45df4bd16ab 100644
--- a/arch/x86/kernel/cpu/microcode/core_early.c
+++ b/arch/x86/kernel/cpu/microcode/core_early.c
@@ -124,7 +124,7 @@ void __init load_ucode_bsp(void)
static bool check_loader_disabled_ap(void)
{
#ifdef CONFIG_X86_32
- return __pa_nodebug(dis_ucode_ldr);
+ return *((bool *)__pa_nodebug(&dis_ucode_ldr));
#else
return dis_ucode_ldr;
#endif
@@ -176,3 +176,24 @@ int __init save_microcode_in_initrd(void)
return 0;
}
+
+void reload_early_microcode(void)
+{
+ int vendor, x86;
+
+ vendor = x86_vendor();
+ x86 = x86_family();
+
+ switch (vendor) {
+ case X86_VENDOR_INTEL:
+ if (x86 >= 6)
+ reload_ucode_intel();
+ break;
+ case X86_VENDOR_AMD:
+ if (x86 >= 0x10)
+ reload_ucode_amd();
+ break;
+ default:
+ break;
+ }
+}
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index a276fa75d9b5..c6826d1e8082 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -127,7 +127,7 @@ static int get_matching_mc(struct microcode_intel *mc_intel, int cpu)
return get_matching_microcode(csig, cpf, mc_intel, crev);
}
-int apply_microcode(int cpu)
+static int apply_microcode_intel(int cpu)
{
struct microcode_intel *mc_intel;
struct ucode_cpu_info *uci;
@@ -314,7 +314,7 @@ static struct microcode_ops microcode_intel_ops = {
.request_microcode_user = request_microcode_user,
.request_microcode_fw = request_microcode_fw,
.collect_cpu_info = collect_cpu_info,
- .apply_microcode = apply_microcode,
+ .apply_microcode = apply_microcode_intel,
.microcode_fini_cpu = microcode_fini_cpu,
};
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index 18f739129e72..ec9df6f9cd47 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -28,8 +28,8 @@
#include <asm/tlbflush.h>
#include <asm/setup.h>
-unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
-struct mc_saved_data {
+static unsigned long mc_saved_in_initrd[MAX_UCODE_COUNT];
+static struct mc_saved_data {
unsigned int mc_saved_count;
struct microcode_intel **mc_saved;
} mc_saved_data;
@@ -415,7 +415,7 @@ static void __ref show_saved_mc(void)
struct ucode_cpu_info uci;
if (mc_saved_data.mc_saved_count == 0) {
- pr_debug("no micorcode data saved.\n");
+ pr_debug("no microcode data saved.\n");
return;
}
pr_debug("Total microcode saved: %d\n", mc_saved_data.mc_saved_count);
@@ -506,7 +506,7 @@ int save_mc_for_early(u8 *mc)
if (mc_saved && mc_saved_count)
memcpy(mc_saved_tmp, mc_saved,
- mc_saved_count * sizeof(struct mirocode_intel *));
+ mc_saved_count * sizeof(struct microcode_intel *));
/*
* Save the microcode patch mc in mc_save_tmp structure if it's a newer
* version.
@@ -526,7 +526,7 @@ int save_mc_for_early(u8 *mc)
show_saved_mc();
/*
- * Free old saved microcod data.
+ * Free old saved microcode data.
*/
if (mc_saved) {
for (i = 0; i < mc_saved_count_init; i++)
@@ -650,8 +650,7 @@ static inline void print_ucode(struct ucode_cpu_info *uci)
}
#endif
-static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
- struct ucode_cpu_info *uci)
+static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
{
struct microcode_intel *mc_intel;
unsigned int val[2];
@@ -680,7 +679,10 @@ static int apply_microcode_early(struct mc_saved_data *mc_saved_data,
#endif
uci->cpu_sig.rev = val[1];
- print_ucode(uci);
+ if (early)
+ print_ucode(uci);
+ else
+ print_ucode_info(uci, mc_intel->hdr.date);
return 0;
}
@@ -715,12 +717,17 @@ _load_ucode_intel_bsp(struct mc_saved_data *mc_saved_data,
unsigned long initrd_end_early,
struct ucode_cpu_info *uci)
{
+ enum ucode_state ret;
+
collect_cpu_info_early(uci);
scan_microcode(initrd_start_early, initrd_end_early, mc_saved_data,
mc_saved_in_initrd, uci);
- load_microcode(mc_saved_data, mc_saved_in_initrd,
- initrd_start_early, uci);
- apply_microcode_early(mc_saved_data, uci);
+
+ ret = load_microcode(mc_saved_data, mc_saved_in_initrd,
+ initrd_start_early, uci);
+
+ if (ret == UCODE_OK)
+ apply_microcode_early(uci, true);
}
void __init
@@ -749,7 +756,8 @@ load_ucode_intel_bsp(void)
initrd_end_early = initrd_start_early + ramdisk_size;
_load_ucode_intel_bsp(&mc_saved_data, mc_saved_in_initrd,
- initrd_start_early, initrd_end_early, &uci);
+ initrd_start_early, initrd_end_early,
+ &uci);
#endif
}
@@ -783,5 +791,23 @@ void load_ucode_intel_ap(void)
collect_cpu_info_early(&uci);
load_microcode(mc_saved_data_p, mc_saved_in_initrd_p,
initrd_start_addr, &uci);
- apply_microcode_early(mc_saved_data_p, &uci);
+ apply_microcode_early(&uci, true);
+}
+
+void reload_ucode_intel(void)
+{
+ struct ucode_cpu_info uci;
+ enum ucode_state ret;
+
+ if (!mc_saved_data.mc_saved_count)
+ return;
+
+ collect_cpu_info_early(&uci);
+
+ ret = generic_load_microcode_early(mc_saved_data.mc_saved,
+ mc_saved_data.mc_saved_count, &uci);
+ if (ret != UCODE_OK)
+ return;
+
+ apply_microcode_early(&uci, false);
}
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index e2b22df964cd..36d99a337b49 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -28,7 +28,7 @@ function dump_array()
# If the /* comment */ starts with a quote string, grab that.
VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
[ -z "$VALUE" ] && VALUE="\"$NAME\""
- [ "$VALUE" == '""' ] && continue
+ [ "$VALUE" = '""' ] && continue
# Name is uppercase, VALUE is all lowercase
VALUE="$(echo "$VALUE" | tr A-Z a-z)"
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f961de9964c7..ea5f363a1948 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -707,7 +707,7 @@ void __init mtrr_bp_init(void)
} else {
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
- if (cpu_has_k6_mtrr) {
+ if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) {
/* Pre-Athlon (K6) AMD CPU MTRRs */
mtrr_if = mtrr_ops[X86_VENDOR_AMD];
size_or_mask = SIZE_OR_MASK_BITS(32);
@@ -715,14 +715,14 @@ void __init mtrr_bp_init(void)
}
break;
case X86_VENDOR_CENTAUR:
- if (cpu_has_centaur_mcr) {
+ if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) {
mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR];
size_or_mask = SIZE_OR_MASK_BITS(32);
size_and_mask = 0;
}
break;
case X86_VENDOR_CYRIX:
- if (cpu_has_cyrix_arr) {
+ if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) {
mtrr_if = mtrr_ops[X86_VENDOR_CYRIX];
size_or_mask = SIZE_OR_MASK_BITS(32);
size_and_mask = 0;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2879ecdaac43..143e5f5dc855 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -243,7 +243,9 @@ static bool check_hw_exists(void)
msr_fail:
printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
- printk(KERN_ERR "Failed to access perfctr msr (MSR %x is %Lx)\n", reg, val_new);
+ printk("%sFailed to access perfctr msr (MSR %x is %Lx)\n",
+ boot_cpu_has(X86_FEATURE_HYPERVISOR) ? KERN_INFO : KERN_ERR,
+ reg, val_new);
return false;
}
@@ -387,7 +389,7 @@ int x86_pmu_hw_config(struct perf_event *event)
precise++;
/* Support for IP fixup */
- if (x86_pmu.lbr_nr)
+ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2)
precise++;
}
@@ -487,7 +489,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
void x86_pmu_disable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -505,7 +507,7 @@ void x86_pmu_disable_all(void)
static void x86_pmu_disable(struct pmu *pmu)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (!x86_pmu_initialized())
return;
@@ -522,7 +524,7 @@ static void x86_pmu_disable(struct pmu *pmu)
void x86_pmu_enable_all(int added)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -869,7 +871,7 @@ static void x86_pmu_start(struct perf_event *event, int flags);
static void x86_pmu_enable(struct pmu *pmu)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct perf_event *event;
struct hw_perf_event *hwc;
int i, added = cpuc->n_added;
@@ -1020,7 +1022,7 @@ void x86_pmu_enable_event(struct perf_event *event)
*/
static int x86_pmu_add(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc;
int assign[X86_PMC_IDX_MAX];
int n, n0, ret;
@@ -1071,7 +1073,7 @@ out:
static void x86_pmu_start(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx = event->hw.idx;
if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
@@ -1150,7 +1152,7 @@ void perf_event_print_debug(void)
void x86_pmu_stop(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
@@ -1172,7 +1174,7 @@ void x86_pmu_stop(struct perf_event *event, int flags)
static void x86_pmu_del(struct perf_event *event, int flags)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int i;
/*
@@ -1227,7 +1229,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
int idx, handled = 0;
u64 val;
- cpuc = &__get_cpu_var(cpu_hw_events);
+ cpuc = this_cpu_ptr(&cpu_hw_events);
/*
* Some chipsets need to unmask the LVTPC in a particular spot
@@ -1636,7 +1638,7 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
*/
static int x86_pmu_commit_txn(struct pmu *pmu)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int assign[X86_PMC_IDX_MAX];
int n, ret;
@@ -1995,7 +1997,7 @@ static unsigned long get_segment_base(unsigned int segment)
if (idx > GDT_ENTRIES)
return 0;
- desc = __this_cpu_ptr(&gdt_page.gdt[0]);
+ desc = raw_cpu_ptr(gdt_page.gdt);
}
return get_desc_base(desc + idx);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8ade93111e03..4e6cdb0ddc70 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -67,8 +67,10 @@ struct event_constraint {
*/
#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */
#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */
-#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style st data sampling */
+#define PERF_X86_EVENT_PEBS_ST_HSW 0x4 /* haswell style datala, store */
#define PERF_X86_EVENT_COMMITTED 0x8 /* event passed commit_txn */
+#define PERF_X86_EVENT_PEBS_LD_HSW 0x10 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW 0x20 /* haswell style datala, unknown */
struct amd_nb {
int nb_id; /* NorthBridge id */
@@ -251,19 +253,57 @@ struct cpu_hw_events {
#define INTEL_UEVENT_CONSTRAINT(c, n) \
EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
+/* Like UEVENT_CONSTRAINT, but match flags too */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
#define INTEL_PLD_CONSTRAINT(c, n) \
- __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
#define INTEL_PST_CONSTRAINT(c, n) \
- __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+ __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST)
-/* DataLA version of store sampling without extra enable bit. */
-#define INTEL_PST_HSW_CONSTRAINT(c, n) \
- __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \
+/* Event constraint, but match on all event flags too. */
+#define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
+ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
+/* Check only flags, but allow all event/umask */
+#define INTEL_ALL_EVENT_CONSTRAINT(code, n) \
+ EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
+
+/* Check flags and event code, and set the HSW store flag */
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_ST(code, n) \
+ __EVENT_CONSTRAINT(code, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
+/* Check flags and event code, and set the HSW load flag */
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(code, n) \
+ __EVENT_CONSTRAINT(code, n, \
+ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
+/* Check flags and event code/umask, and set the HSW store flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(code, n) \
+ __EVENT_CONSTRAINT(code, n, \
+ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST_HSW)
+
+/* Check flags and event code/umask, and set the HSW load flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(code, n) \
+ __EVENT_CONSTRAINT(code, n, \
+ INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
+/* Check flags and event code/umask, and set the HSW N/A flag */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
+ __EVENT_CONSTRAINT(code, n, \
+ INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
+
+
/*
* We define the end marker as having a weight of -1
* to enable blacklisting of events using a counter bitmask
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index beeb7cc07044..28926311aac1 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -699,7 +699,7 @@ __init int amd_pmu_init(void)
void amd_pmu_enable_virt(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
cpuc->perf_ctr_virt_mask = 0;
@@ -711,7 +711,7 @@ EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
void amd_pmu_disable_virt(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
/*
* We only mask out the Host-only bit so that host-only counting works
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index cbb1be3ed9e4..a61f5c6911da 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -565,6 +565,21 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
perf_ibs->offset_max,
offset + 1);
} while (offset < offset_max);
+ if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+ /*
+ * Read IbsBrTarget and IbsOpData4 separately
+ * depending on their availability.
+ * Can't add to offset_max as they are staggered
+ */
+ if (ibs_caps & IBS_CAPS_BRNTRGT) {
+ rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
+ size++;
+ }
+ if (ibs_caps & IBS_CAPS_OPDATA4) {
+ rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
+ size++;
+ }
+ }
ibs_data.size = sizeof(u64) * size;
regs = *iregs;
diff --git a/arch/x86/kernel/cpu/perf_event_amd_iommu.c b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
index 639d1289b1ba..97242a9242bd 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_iommu.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_iommu.c
@@ -130,10 +130,7 @@ static ssize_t _iommu_cpumask_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &iommu_cpumask);
- buf[n++] = '\n';
- buf[n] = '\0';
- return n;
+ return cpumap_print_to_pagebuf(true, buf, &iommu_cpumask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, _iommu_cpumask_show, NULL);
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 30790d798e6b..cc6cedb8f25d 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -219,7 +219,6 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- int n;
cpumask_t *active_mask;
struct pmu *pmu = dev_get_drvdata(dev);
@@ -230,10 +229,7 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
else
return 0;
- n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask);
- buf[n++] = '\n';
- buf[n] = '\0';
- return n;
+ return cpumap_print_to_pagebuf(true, buf, active_mask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2502d0d9d246..944bf019b74f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1045,7 +1045,7 @@ static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
static void intel_pmu_disable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
@@ -1058,7 +1058,7 @@ static void intel_pmu_disable_all(void)
static void intel_pmu_enable_all(int added)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
intel_pmu_pebs_enable_all();
intel_pmu_lbr_enable_all();
@@ -1092,7 +1092,7 @@ static void intel_pmu_enable_all(int added)
*/
static void intel_pmu_nhm_workaround(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
static const unsigned long nhm_magic[4] = {
0x4300B5,
0x4300D2,
@@ -1191,7 +1191,7 @@ static inline bool event_is_checkpointed(struct perf_event *event)
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
intel_pmu_disable_bts();
@@ -1255,7 +1255,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
static void intel_pmu_enable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (unlikely(hwc->idx == INTEL_PMC_IDX_FIXED_BTS)) {
if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -1349,7 +1349,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
u64 status;
int handled;
- cpuc = &__get_cpu_var(cpu_hw_events);
+ cpuc = this_cpu_ptr(&cpu_hw_events);
/*
* No known reason to not always do late ACK,
@@ -1781,7 +1781,7 @@ EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
@@ -1802,7 +1802,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
int idx;
@@ -1836,7 +1836,7 @@ static void core_pmu_enable_event(struct perf_event *event)
static void core_pmu_enable_all(int added)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -2367,15 +2367,15 @@ __init int intel_pmu_init(void)
* Install the hw-cache-events table:
*/
switch (boot_cpu_data.x86_model) {
- case 14: /* 65 nm core solo/duo, "Yonah" */
+ case 14: /* 65nm Core "Yonah" */
pr_cont("Core events, ");
break;
- case 15: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+ case 15: /* 65nm Core2 "Merom" */
x86_add_quirk(intel_clovertown_quirk);
- case 22: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
- case 23: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
- case 29: /* six-core 45 nm xeon "Dunnington" */
+ case 22: /* 65nm Core2 "Merom-L" */
+ case 23: /* 45nm Core2 "Penryn" */
+ case 29: /* 45nm Core2 "Dunnington (MP) */
memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2386,9 +2386,9 @@ __init int intel_pmu_init(void)
pr_cont("Core2 events, ");
break;
- case 26: /* 45 nm nehalem, "Bloomfield" */
- case 30: /* 45 nm nehalem, "Lynnfield" */
- case 46: /* 45 nm nehalem-ex, "Beckton" */
+ case 30: /* 45nm Nehalem */
+ case 26: /* 45nm Nehalem-EP */
+ case 46: /* 45nm Nehalem-EX */
memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -2415,11 +2415,11 @@ __init int intel_pmu_init(void)
pr_cont("Nehalem events, ");
break;
- case 28: /* Atom */
- case 38: /* Lincroft */
- case 39: /* Penwell */
- case 53: /* Cloverview */
- case 54: /* Cedarview */
+ case 28: /* 45nm Atom "Pineview" */
+ case 38: /* 45nm Atom "Lincroft" */
+ case 39: /* 32nm Atom "Penwell" */
+ case 53: /* 32nm Atom "Cloverview" */
+ case 54: /* 32nm Atom "Cedarview" */
memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2430,8 +2430,8 @@ __init int intel_pmu_init(void)
pr_cont("Atom events, ");
break;
- case 55: /* Atom 22nm "Silvermont" */
- case 77: /* Avoton "Silvermont" */
+ case 55: /* 22nm Atom "Silvermont" */
+ case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
@@ -2446,9 +2446,9 @@ __init int intel_pmu_init(void)
pr_cont("Silvermont events, ");
break;
- case 37: /* 32 nm nehalem, "Clarkdale" */
- case 44: /* 32 nm nehalem, "Gulftown" */
- case 47: /* 32 nm Xeon E7 */
+ case 37: /* 32nm Westmere */
+ case 44: /* 32nm Westmere-EP */
+ case 47: /* 32nm Westmere-EX */
memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
@@ -2474,8 +2474,8 @@ __init int intel_pmu_init(void)
pr_cont("Westmere events, ");
break;
- case 42: /* SandyBridge */
- case 45: /* SandyBridge, "Romely-EP" */
+ case 42: /* 32nm SandyBridge */
+ case 45: /* 32nm SandyBridge-E/EN/EP */
x86_add_quirk(intel_sandybridge_quirk);
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
@@ -2506,8 +2506,9 @@ __init int intel_pmu_init(void)
pr_cont("SandyBridge events, ");
break;
- case 58: /* IvyBridge */
- case 62: /* IvyBridge EP */
+
+ case 58: /* 22nm IvyBridge */
+ case 62: /* 22nm IvyBridge-EP/EX */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
/* dTLB-load-misses on IVB is different than SNB */
@@ -2539,11 +2540,10 @@ __init int intel_pmu_init(void)
break;
- case 60: /* Haswell Client */
- case 70:
- case 71:
- case 63:
- case 69:
+ case 60: /* 22nm Haswell Core */
+ case 63: /* 22nm Haswell Server */
+ case 69: /* 22nm Haswell ULT */
+ case 70: /* 22nm Haswell + GT3e (Intel Iris Pro graphics) */
x86_pmu.late_ack = true;
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
@@ -2552,7 +2552,7 @@ __init int intel_pmu_init(void)
x86_pmu.event_constraints = intel_hsw_event_constraints;
x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
- x86_pmu.extra_regs = intel_snb_extra_regs;
+ x86_pmu.extra_regs = intel_snbep_extra_regs;
x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
/* all extra regs are per-cpu when HT is on */
x86_pmu.er_flags |= ERF_HAS_RSP_1;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 696ade311ded..3c895d480cd7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -108,14 +108,16 @@ static u64 precise_store_data(u64 status)
return val;
}
-static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
+static u64 precise_datala_hsw(struct perf_event *event, u64 status)
{
union perf_mem_data_src dse;
- u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK;
- dse.val = 0;
- dse.mem_op = PERF_MEM_OP_STORE;
- dse.mem_lvl = PERF_MEM_LVL_NA;
+ dse.val = PERF_MEM_NA;
+
+ if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+ dse.mem_op = PERF_MEM_OP_STORE;
+ else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW)
+ dse.mem_op = PERF_MEM_OP_LOAD;
/*
* L1 info only valid for following events:
@@ -125,15 +127,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
* MEM_UOPS_RETIRED.SPLIT_STORES
* MEM_UOPS_RETIRED.ALL_STORES
*/
- if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0)
- return dse.mem_lvl;
-
- if (status & 1)
- dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
- else
- dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
-
- /* Nothing else supported. Sorry. */
+ if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) {
+ if (status & 1)
+ dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;
+ else
+ dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS;
+ }
return dse.val;
}
@@ -475,7 +474,7 @@ void intel_pmu_enable_bts(u64 config)
void intel_pmu_disable_bts(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
unsigned long debugctlmsr;
if (!cpuc->ds)
@@ -492,7 +491,7 @@ void intel_pmu_disable_bts(void)
int intel_pmu_drain_bts_buffer(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
struct bts_record {
u64 from;
@@ -553,141 +552,99 @@ int intel_pmu_drain_bts_buffer(void)
* PEBS
*/
struct event_constraint intel_core2_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
- INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
- INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
- INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
- INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_atom_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
- INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
- INTEL_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_slm_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */
- INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */
- INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */
- INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */
- INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */
- INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */
- INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */
- INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */
- INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */
- INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */
- INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */
- INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */
- INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */
- INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */
- INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */
- INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */
- INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */
- INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */
- INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */
- INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
- INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
- INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ /* Allow all events as PEBS with no flags */
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
EVENT_CONSTRAINT_END
};
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
- INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
- INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
- INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_westmere_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
- INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0xc2, 0xf), /* UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
- INTEL_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf), /* SSEX_UOPS_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf), /* MEM_LOAD_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf), /* FP_ASSIST.* */
EVENT_CONSTRAINT_END
};
struct event_constraint intel_snb_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
- INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
- INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
- INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
+ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ /* Allow all events as PEBS with no flags */
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
EVENT_CONSTRAINT_END
};
struct event_constraint intel_ivb_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
- INTEL_UEVENT_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
- INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */
- INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ /* Allow all events as PEBS with no flags */
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
EVENT_CONSTRAINT_END
};
struct event_constraint intel_hsw_pebs_event_constraints[] = {
- INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
- INTEL_PST_HSW_CONSTRAINT(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
- INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */
- INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */
- INTEL_UEVENT_CONSTRAINT(0x01c5, 0xf), /* BR_MISP_RETIRED.CONDITIONAL */
- INTEL_UEVENT_CONSTRAINT(0x04c5, 0xf), /* BR_MISP_RETIRED.ALL_BRANCHES */
- INTEL_UEVENT_CONSTRAINT(0x20c5, 0xf), /* BR_MISP_RETIRED.NEAR_TAKEN */
- INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.* */
- /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x11d0, 0xf),
- /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
- INTEL_UEVENT_CONSTRAINT(0x12d0, 0xf),
- INTEL_UEVENT_CONSTRAINT(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
- INTEL_UEVENT_CONSTRAINT(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
- /* MEM_UOPS_RETIRED.SPLIT_STORES */
- INTEL_UEVENT_CONSTRAINT(0x42d0, 0xf),
- INTEL_UEVENT_CONSTRAINT(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
- INTEL_PST_HSW_CONSTRAINT(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
- INTEL_UEVENT_CONSTRAINT(0x01d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L1_HIT */
- INTEL_UEVENT_CONSTRAINT(0x02d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L2_HIT */
- INTEL_UEVENT_CONSTRAINT(0x04d1, 0xf), /* MEM_LOAD_UOPS_RETIRED.L3_HIT */
- /* MEM_LOAD_UOPS_RETIRED.HIT_LFB */
- INTEL_UEVENT_CONSTRAINT(0x40d1, 0xf),
- /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS */
- INTEL_UEVENT_CONSTRAINT(0x01d2, 0xf),
- /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT */
- INTEL_UEVENT_CONSTRAINT(0x02d2, 0xf),
- /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.LOCAL_DRAM */
- INTEL_UEVENT_CONSTRAINT(0x01d3, 0xf),
- INTEL_UEVENT_CONSTRAINT(0x04c8, 0xf), /* HLE_RETIRED.Abort */
- INTEL_UEVENT_CONSTRAINT(0x04c9, 0xf), /* RTM_RETIRED.Abort */
-
+ INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+ INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */
+ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
+ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_UOPS_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_UOPS_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_UOPS_RETIRED.ALL_STORES */
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd2, 0xf), /* MEM_LOAD_UOPS_L3_HIT_RETIRED.* */
+ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD(0xd3, 0xf), /* MEM_LOAD_UOPS_L3_MISS_RETIRED.* */
+ /* Allow all events as PEBS with no flags */
+ INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
EVENT_CONSTRAINT_END
};
@@ -712,7 +669,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
void intel_pmu_pebs_enable(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
@@ -727,7 +684,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
void intel_pmu_pebs_disable(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -745,7 +702,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
void intel_pmu_pebs_enable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (cpuc->pebs_enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
@@ -753,7 +710,7 @@ void intel_pmu_pebs_enable_all(void)
void intel_pmu_pebs_disable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (cpuc->pebs_enabled)
wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
@@ -761,12 +718,13 @@ void intel_pmu_pebs_disable_all(void)
static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
unsigned long from = cpuc->lbr_entries[0].from;
unsigned long old_to, to = cpuc->lbr_entries[0].to;
unsigned long ip = regs->ip;
int is_64bit = 0;
void *kaddr;
+ int size;
/*
* We don't need to fixup if the PEBS assist is fault like
@@ -801,11 +759,12 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 1;
}
+ size = ip - to;
if (!kernel_ip(ip)) {
- int size, bytes;
+ int bytes;
u8 *buf = this_cpu_read(insn_buffer);
- size = ip - to; /* Must fit our buffer, see above */
+ /* 'size' must fit our buffer, see above */
bytes = copy_from_user_nmi(buf, (void __user *)to, size);
if (bytes != 0)
return 0;
@@ -823,11 +782,20 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
#ifdef CONFIG_X86_64
is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
- insn_init(&insn, kaddr, is_64bit);
+ insn_init(&insn, kaddr, size, is_64bit);
insn_get_length(&insn);
+ /*
+ * Make sure there was not a problem decoding the
+ * instruction and getting the length. This is
+ * doubly important because we have an infinite
+ * loop if insn.length=0.
+ */
+ if (!insn.length)
+ break;
to += insn.length;
kaddr += insn.length;
+ size -= insn.length;
} while (to < ip);
if (to == ip) {
@@ -864,51 +832,53 @@ static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs, void *__pebs)
{
+#define PERF_X86_EVENT_PEBS_HSW_PREC \
+ (PERF_X86_EVENT_PEBS_ST_HSW | \
+ PERF_X86_EVENT_PEBS_LD_HSW | \
+ PERF_X86_EVENT_PEBS_NA_HSW)
/*
* We cast to the biggest pebs_record but are careful not to
* unconditionally access the 'extra' entries.
*/
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct pebs_record_hsw *pebs = __pebs;
struct perf_sample_data data;
struct pt_regs regs;
u64 sample_type;
- int fll, fst;
+ int fll, fst, dsrc;
+ int fl = event->hw.flags;
if (!intel_pmu_save_and_restart(event))
return;
- fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
- fst = event->hw.flags & (PERF_X86_EVENT_PEBS_ST |
- PERF_X86_EVENT_PEBS_ST_HSW);
+ sample_type = event->attr.sample_type;
+ dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
+
+ fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
+ fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
perf_sample_data_init(&data, 0, event->hw.last_period);
data.period = event->hw.last_period;
- sample_type = event->attr.sample_type;
/*
- * if PEBS-LL or PreciseStore
+ * Use latency for weight (only avail with PEBS-LL)
*/
- if (fll || fst) {
- /*
- * Use latency for weight (only avail with PEBS-LL)
- */
- if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
- data.weight = pebs->lat;
+ if (fll && (sample_type & PERF_SAMPLE_WEIGHT))
+ data.weight = pebs->lat;
- /*
- * data.data_src encodes the data source
- */
- if (sample_type & PERF_SAMPLE_DATA_SRC) {
- if (fll)
- data.data_src.val = load_latency_data(pebs->dse);
- else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
- data.data_src.val =
- precise_store_data_hsw(event, pebs->dse);
- else
- data.data_src.val = precise_store_data(pebs->dse);
- }
+ /*
+ * data.data_src encodes the data source
+ */
+ if (dsrc) {
+ u64 val = PERF_MEM_NA;
+ if (fll)
+ val = load_latency_data(pebs->dse);
+ else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+ val = precise_datala_hsw(event, pebs->dse);
+ else if (fst)
+ val = precise_store_data(pebs->dse);
+ data.data_src.val = val;
}
/*
@@ -927,6 +897,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
regs.bp = pebs->bp;
regs.sp = pebs->sp;
+ if (sample_type & PERF_SAMPLE_REGS_INTR) {
+ regs.ax = pebs->ax;
+ regs.bx = pebs->bx;
+ regs.cx = pebs->cx;
+ regs.dx = pebs->dx;
+ regs.si = pebs->si;
+ regs.di = pebs->di;
+ regs.bp = pebs->bp;
+ regs.sp = pebs->sp;
+
+ regs.flags = pebs->flags;
+#ifndef CONFIG_X86_32
+ regs.r8 = pebs->r8;
+ regs.r9 = pebs->r9;
+ regs.r10 = pebs->r10;
+ regs.r11 = pebs->r11;
+ regs.r12 = pebs->r12;
+ regs.r13 = pebs->r13;
+ regs.r14 = pebs->r14;
+ regs.r15 = pebs->r15;
+#endif
+ }
+
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
regs.ip = pebs->real_ip;
regs.flags |= PERF_EFLAGS_EXACT;
@@ -935,16 +928,16 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
else
regs.flags &= ~PERF_EFLAGS_EXACT;
- if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
+ if ((sample_type & PERF_SAMPLE_ADDR) &&
x86_pmu.intel_cap.pebs_format >= 1)
data.addr = pebs->dla;
if (x86_pmu.intel_cap.pebs_format >= 2) {
/* Only set the TSX weight when no memory weight. */
- if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll)
+ if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
data.weight = intel_hsw_weight(pebs);
- if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION)
+ if (sample_type & PERF_SAMPLE_TRANSACTION)
data.txn = intel_hsw_transaction(pebs);
}
@@ -957,7 +950,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
struct perf_event *event = cpuc->events[0]; /* PMC0 only */
struct pebs_record_core *at, *top;
@@ -998,7 +991,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct debug_store *ds = cpuc->ds;
struct perf_event *event = NULL;
void *at, *top;
@@ -1055,7 +1048,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
* BTS, PEBS probe and setup
*/
-void intel_ds_init(void)
+void __init intel_ds_init(void)
{
/*
* No support for 32bit formats
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 9dd2459a4c73..58f1a94beaf0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -133,7 +133,7 @@ static void intel_pmu_lbr_filter(struct cpu_hw_events *cpuc);
static void __intel_pmu_lbr_enable(void)
{
u64 debugctl;
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (cpuc->lbr_sel)
wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
@@ -183,7 +183,7 @@ void intel_pmu_lbr_reset(void)
void intel_pmu_lbr_enable(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (!x86_pmu.lbr_nr)
return;
@@ -203,7 +203,7 @@ void intel_pmu_lbr_enable(struct perf_event *event)
void intel_pmu_lbr_disable(struct perf_event *event)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (!x86_pmu.lbr_nr)
return;
@@ -220,7 +220,7 @@ void intel_pmu_lbr_disable(struct perf_event *event)
void intel_pmu_lbr_enable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (cpuc->lbr_users)
__intel_pmu_lbr_enable();
@@ -228,7 +228,7 @@ void intel_pmu_lbr_enable_all(void)
void intel_pmu_lbr_disable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (cpuc->lbr_users)
__intel_pmu_lbr_disable();
@@ -332,7 +332,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
void intel_pmu_lbr_read(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (!cpuc->lbr_users)
return;
@@ -465,7 +465,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
{
struct insn insn;
void *addr;
- int bytes, size = MAX_INSN_SIZE;
+ int bytes_read, bytes_left;
int ret = X86_BR_NONE;
int ext, to_plm, from_plm;
u8 buf[MAX_INSN_SIZE];
@@ -493,8 +493,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
return X86_BR_NONE;
/* may fail if text not present */
- bytes = copy_from_user_nmi(buf, (void __user *)from, size);
- if (bytes != 0)
+ bytes_left = copy_from_user_nmi(buf, (void __user *)from,
+ MAX_INSN_SIZE);
+ bytes_read = MAX_INSN_SIZE - bytes_left;
+ if (!bytes_read)
return X86_BR_NONE;
addr = buf;
@@ -505,10 +507,19 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
* Ensure we don't blindy read any address by validating it is
* a known text address.
*/
- if (kernel_text_address(from))
+ if (kernel_text_address(from)) {
addr = (void *)from;
- else
+ /*
+ * Assume we can get the maximum possible size
+ * when grabbing kernel data. This is not
+ * _strictly_ true since we could possibly be
+ * executing up next to a memory hole, but
+ * it is very unlikely to be a problem.
+ */
+ bytes_read = MAX_INSN_SIZE;
+ } else {
return X86_BR_NONE;
+ }
}
/*
@@ -518,8 +529,10 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
#ifdef CONFIG_X86_64
is64 = kernel_ip((unsigned long)addr) || !test_thread_flag(TIF_IA32);
#endif
- insn_init(&insn, addr, is64);
+ insn_init(&insn, addr, bytes_read, is64);
insn_get_opcode(&insn);
+ if (!insn.opcode.got)
+ return X86_BR_ABORT;
switch (insn.opcode.bytes[0]) {
case 0xf:
@@ -697,7 +710,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
};
/* core */
-void intel_pmu_lbr_init_core(void)
+void __init intel_pmu_lbr_init_core(void)
{
x86_pmu.lbr_nr = 4;
x86_pmu.lbr_tos = MSR_LBR_TOS;
@@ -712,7 +725,7 @@ void intel_pmu_lbr_init_core(void)
}
/* nehalem/westmere */
-void intel_pmu_lbr_init_nhm(void)
+void __init intel_pmu_lbr_init_nhm(void)
{
x86_pmu.lbr_nr = 16;
x86_pmu.lbr_tos = MSR_LBR_TOS;
@@ -733,7 +746,7 @@ void intel_pmu_lbr_init_nhm(void)
}
/* sandy bridge */
-void intel_pmu_lbr_init_snb(void)
+void __init intel_pmu_lbr_init_snb(void)
{
x86_pmu.lbr_nr = 16;
x86_pmu.lbr_tos = MSR_LBR_TOS;
@@ -753,7 +766,7 @@ void intel_pmu_lbr_init_snb(void)
}
/* atom */
-void intel_pmu_lbr_init_atom(void)
+void __init intel_pmu_lbr_init_atom(void)
{
/*
* only models starting at stepping 10 seems
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 619f7699487a..673f930c700f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -135,7 +135,7 @@ static inline u64 rapl_scale(u64 v)
* or use ldexp(count, -32).
* Watts = Joules/Time delta
*/
- return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+ return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
}
static u64 rapl_event_update(struct perf_event *event)
@@ -187,7 +187,7 @@ static void rapl_stop_hrtimer(struct rapl_pmu *pmu)
static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
{
- struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
struct perf_event *event;
unsigned long flags;
@@ -234,7 +234,7 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
static void rapl_pmu_event_start(struct perf_event *event, int mode)
{
- struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
unsigned long flags;
spin_lock_irqsave(&pmu->lock, flags);
@@ -244,7 +244,7 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
static void rapl_pmu_event_stop(struct perf_event *event, int mode)
{
- struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
struct hw_perf_event *hwc = &event->hw;
unsigned long flags;
@@ -278,7 +278,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
static int rapl_pmu_event_add(struct perf_event *event, int mode)
{
- struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
struct hw_perf_event *hwc = &event->hw;
unsigned long flags;
@@ -365,11 +365,7 @@ static void rapl_pmu_event_read(struct perf_event *event)
static ssize_t rapl_get_attr_cpumask(struct device *dev,
struct device_attribute *attr, char *buf)
{
- int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask);
-
- buf[n++] = '\n';
- buf[n] = '\0';
- return n;
+ return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
@@ -696,7 +692,7 @@ static int __init rapl_pmu_init(void)
return -1;
}
- pmu = __get_cpu_var(rapl_pmu);
+ pmu = __this_cpu_read(rapl_pmu);
pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
" API unit is 2^-32 Joules,"
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 0939f86f543d..10b8d3eaaf15 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -1,83 +1,39 @@
#include "perf_event_intel_uncore.h"
static struct intel_uncore_type *empty_uncore[] = { NULL, };
-static struct intel_uncore_type **msr_uncores = empty_uncore;
-static struct intel_uncore_type **pci_uncores = empty_uncore;
-/* pci bus to socket mapping */
-static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+struct intel_uncore_type **uncore_msr_uncores = empty_uncore;
+struct intel_uncore_type **uncore_pci_uncores = empty_uncore;
-static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+static bool pcidrv_registered;
+struct pci_driver *uncore_pci_driver;
+/* pci bus to socket mapping */
+int uncore_pcibus_to_physid[256] = { [0 ... 255] = -1, };
+struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
static DEFINE_RAW_SPINLOCK(uncore_box_lock);
-
/* mask of cpus that collect uncore events */
static cpumask_t uncore_cpu_mask;
/* constraint for the fixed counter */
-static struct event_constraint constraint_fixed =
+static struct event_constraint uncore_constraint_fixed =
EVENT_CONSTRAINT(~0ULL, 1 << UNCORE_PMC_IDX_FIXED, ~0ULL);
-static struct event_constraint constraint_empty =
+struct event_constraint uncore_constraint_empty =
EVENT_CONSTRAINT(0, 0, 0);
-#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \
- ((1ULL << (n)) - 1)))
-
-DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
-DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
-DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
-DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
-DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
-DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
-DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
-DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
-DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
-DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
-DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
-DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
-DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
-DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
-DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
-DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
-DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
-DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
-DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
-DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
-DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
-DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
-DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
-DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
-DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
-DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
-DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
-DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
-DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
-DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
-
-static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
-static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
-static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
-static void uncore_pmu_event_read(struct perf_event *event);
-
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+ssize_t uncore_event_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct uncore_event_desc *event =
+ container_of(attr, struct uncore_event_desc, attr);
+ return sprintf(buf, "%s", event->config);
+}
+
+struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
{
return container_of(event->pmu, struct intel_uncore_pmu, pmu);
}
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
{
struct intel_uncore_box *box;
@@ -86,6 +42,9 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
return box;
raw_spin_lock(&uncore_box_lock);
+ /* Recheck in lock to handle races. */
+ if (*per_cpu_ptr(pmu->box, cpu))
+ goto out;
list_for_each_entry(box, &pmu->box_list, list) {
if (box->phys_id == topology_physical_package_id(cpu)) {
atomic_inc(&box->refcnt);
@@ -93,12 +52,13 @@ uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
break;
}
}
+out:
raw_spin_unlock(&uncore_box_lock);
return *per_cpu_ptr(pmu->box, cpu);
}
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
{
/*
* perf core schedules event on the basis of cpu, uncore events are
@@ -107,7 +67,7 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
}
-static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
{
u64 count;
@@ -119,7 +79,7 @@ static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_eve
/*
* generic get constraint function for shared match/mask registers.
*/
-static struct event_constraint *
+struct event_constraint *
uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
{
struct intel_uncore_extra_reg *er;
@@ -154,10 +114,10 @@ uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
return NULL;
}
- return &constraint_empty;
+ return &uncore_constraint_empty;
}
-static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
{
struct intel_uncore_extra_reg *er;
struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
@@ -178,7 +138,7 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even
reg1->alloc = 0;
}
-static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
+u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
{
struct intel_uncore_extra_reg *er;
unsigned long flags;
@@ -193,2936 +153,6 @@ static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx)
return config;
}
-/* Sandy Bridge-EP uncore support */
-static struct intel_uncore_type snbep_uncore_cbox;
-static struct intel_uncore_type snbep_uncore_pcu;
-
-static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
-{
- struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
- u32 config = 0;
-
- if (!pci_read_config_dword(pdev, box_ctl, &config)) {
- config |= SNBEP_PMON_BOX_CTL_FRZ;
- pci_write_config_dword(pdev, box_ctl, config);
- }
-}
-
-static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
-{
- struct pci_dev *pdev = box->pci_dev;
- int box_ctl = uncore_pci_box_ctl(box);
- u32 config = 0;
-
- if (!pci_read_config_dword(pdev, box_ctl, &config)) {
- config &= ~SNBEP_PMON_BOX_CTL_FRZ;
- pci_write_config_dword(pdev, box_ctl, config);
- }
-}
-
-static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
-
- pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
-
- pci_write_config_dword(pdev, hwc->config_base, hwc->config);
-}
-
-static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
- u64 count = 0;
-
- pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
- pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
-
- return count;
-}
-
-static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
-{
- struct pci_dev *pdev = box->pci_dev;
-
- pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
-}
-
-static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
- u64 config;
- unsigned msr;
-
- msr = uncore_msr_box_ctl(box);
- if (msr) {
- rdmsrl(msr, config);
- config |= SNBEP_PMON_BOX_CTL_FRZ;
- wrmsrl(msr, config);
- }
-}
-
-static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
- u64 config;
- unsigned msr;
-
- msr = uncore_msr_box_ctl(box);
- if (msr) {
- rdmsrl(msr, config);
- config &= ~SNBEP_PMON_BOX_CTL_FRZ;
- wrmsrl(msr, config);
- }
-}
-
-static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
- if (reg1->idx != EXTRA_REG_NONE)
- wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
-
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
- struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- wrmsrl(hwc->config_base, hwc->config);
-}
-
-static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
-{
- unsigned msr = uncore_msr_box_ctl(box);
-
- if (msr)
- wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
-}
-
-static struct attribute *snbep_uncore_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh8.attr,
- NULL,
-};
-
-static struct attribute *snbep_uncore_ubox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh5.attr,
- NULL,
-};
-
-static struct attribute *snbep_uncore_cbox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_tid_en.attr,
- &format_attr_inv.attr,
- &format_attr_thresh8.attr,
- &format_attr_filter_tid.attr,
- &format_attr_filter_nid.attr,
- &format_attr_filter_state.attr,
- &format_attr_filter_opc.attr,
- NULL,
-};
-
-static struct attribute *snbep_uncore_pcu_formats_attr[] = {
- &format_attr_event_ext.attr,
- &format_attr_occ_sel.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh5.attr,
- &format_attr_occ_invert.attr,
- &format_attr_occ_edge.attr,
- &format_attr_filter_band0.attr,
- &format_attr_filter_band1.attr,
- &format_attr_filter_band2.attr,
- &format_attr_filter_band3.attr,
- NULL,
-};
-
-static struct attribute *snbep_uncore_qpi_formats_attr[] = {
- &format_attr_event_ext.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh8.attr,
- &format_attr_match_rds.attr,
- &format_attr_match_rnid30.attr,
- &format_attr_match_rnid4.attr,
- &format_attr_match_dnid.attr,
- &format_attr_match_mc.attr,
- &format_attr_match_opc.attr,
- &format_attr_match_vnw.attr,
- &format_attr_match0.attr,
- &format_attr_match1.attr,
- &format_attr_mask_rds.attr,
- &format_attr_mask_rnid30.attr,
- &format_attr_mask_rnid4.attr,
- &format_attr_mask_dnid.attr,
- &format_attr_mask_mc.attr,
- &format_attr_mask_opc.attr,
- &format_attr_mask_vnw.attr,
- &format_attr_mask0.attr,
- &format_attr_mask1.attr,
- NULL,
-};
-
-static struct uncore_event_desc snbep_uncore_imc_events[] = {
- INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
- INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
- INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
- { /* end: all zeroes */ },
-};
-
-static struct uncore_event_desc snbep_uncore_qpi_events[] = {
- INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
- INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
- INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"),
- INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"),
- { /* end: all zeroes */ },
-};
-
-static struct attribute_group snbep_uncore_format_group = {
- .name = "format",
- .attrs = snbep_uncore_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_ubox_format_group = {
- .name = "format",
- .attrs = snbep_uncore_ubox_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_cbox_format_group = {
- .name = "format",
- .attrs = snbep_uncore_cbox_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_pcu_format_group = {
- .name = "format",
- .attrs = snbep_uncore_pcu_formats_attr,
-};
-
-static struct attribute_group snbep_uncore_qpi_format_group = {
- .name = "format",
- .attrs = snbep_uncore_qpi_formats_attr,
-};
-
-#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \
- .init_box = snbep_uncore_msr_init_box, \
- .disable_box = snbep_uncore_msr_disable_box, \
- .enable_box = snbep_uncore_msr_enable_box, \
- .disable_event = snbep_uncore_msr_disable_event, \
- .enable_event = snbep_uncore_msr_enable_event, \
- .read_counter = uncore_msr_read_counter
-
-static struct intel_uncore_ops snbep_uncore_msr_ops = {
- SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
-};
-
-#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \
- .init_box = snbep_uncore_pci_init_box, \
- .disable_box = snbep_uncore_pci_disable_box, \
- .enable_box = snbep_uncore_pci_enable_box, \
- .disable_event = snbep_uncore_pci_disable_event, \
- .read_counter = snbep_uncore_pci_read_counter
-
-static struct intel_uncore_ops snbep_uncore_pci_ops = {
- SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
- .enable_event = snbep_uncore_pci_enable_event, \
-};
-
-static struct event_constraint snbep_uncore_cbox_constraints[] = {
- UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
- UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
- UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
- UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
- UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
- UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
- EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
- UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
- UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
- EVENT_CONSTRAINT_END
-};
-
-static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
- UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
- UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
- EVENT_CONSTRAINT_END
-};
-
-static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
- UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
- UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
- UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
- EVENT_CONSTRAINT_END
-};
-
-static struct intel_uncore_type snbep_uncore_ubox = {
- .name = "ubox",
- .num_counters = 2,
- .num_boxes = 1,
- .perf_ctr_bits = 44,
- .fixed_ctr_bits = 48,
- .perf_ctr = SNBEP_U_MSR_PMON_CTR0,
- .event_ctl = SNBEP_U_MSR_PMON_CTL0,
- .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
- .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
- .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
- .ops = &snbep_uncore_msr_ops,
- .format_group = &snbep_uncore_ubox_format_group,
-};
-
-static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
- SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
- SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
- EVENT_EXTRA_END
-};
-
-static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct intel_uncore_extra_reg *er = &box->shared_regs[0];
- int i;
-
- if (uncore_box_is_fake(box))
- return;
-
- for (i = 0; i < 5; i++) {
- if (reg1->alloc & (0x1 << i))
- atomic_sub(1 << (i * 6), &er->ref);
- }
- reg1->alloc = 0;
-}
-
-static struct event_constraint *
-__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
- u64 (*cbox_filter_mask)(int fields))
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct intel_uncore_extra_reg *er = &box->shared_regs[0];
- int i, alloc = 0;
- unsigned long flags;
- u64 mask;
-
- if (reg1->idx == EXTRA_REG_NONE)
- return NULL;
-
- raw_spin_lock_irqsave(&er->lock, flags);
- for (i = 0; i < 5; i++) {
- if (!(reg1->idx & (0x1 << i)))
- continue;
- if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
- continue;
-
- mask = cbox_filter_mask(0x1 << i);
- if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
- !((reg1->config ^ er->config) & mask)) {
- atomic_add(1 << (i * 6), &er->ref);
- er->config &= ~mask;
- er->config |= reg1->config & mask;
- alloc |= (0x1 << i);
- } else {
- break;
- }
- }
- raw_spin_unlock_irqrestore(&er->lock, flags);
- if (i < 5)
- goto fail;
-
- if (!uncore_box_is_fake(box))
- reg1->alloc |= alloc;
-
- return NULL;
-fail:
- for (; i >= 0; i--) {
- if (alloc & (0x1 << i))
- atomic_sub(1 << (i * 6), &er->ref);
- }
- return &constraint_empty;
-}
-
-static u64 snbep_cbox_filter_mask(int fields)
-{
- u64 mask = 0;
-
- if (fields & 0x1)
- mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
- if (fields & 0x2)
- mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
- if (fields & 0x4)
- mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
- if (fields & 0x8)
- mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
-
- return mask;
-}
-
-static struct event_constraint *
-snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
-}
-
-static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct extra_reg *er;
- int idx = 0;
-
- for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
- if (er->event != (event->hw.config & er->config_mask))
- continue;
- idx |= er->idx;
- }
-
- if (idx) {
- reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
- SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
- reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
- reg1->idx = idx;
- }
- return 0;
-}
-
-static struct intel_uncore_ops snbep_uncore_cbox_ops = {
- SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
- .hw_config = snbep_cbox_hw_config,
- .get_constraint = snbep_cbox_get_constraint,
- .put_constraint = snbep_cbox_put_constraint,
-};
-
-static struct intel_uncore_type snbep_uncore_cbox = {
- .name = "cbox",
- .num_counters = 4,
- .num_boxes = 8,
- .perf_ctr_bits = 44,
- .event_ctl = SNBEP_C0_MSR_PMON_CTL0,
- .perf_ctr = SNBEP_C0_MSR_PMON_CTR0,
- .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL,
- .msr_offset = SNBEP_CBO_MSR_OFFSET,
- .num_shared_regs = 1,
- .constraints = snbep_uncore_cbox_constraints,
- .ops = &snbep_uncore_cbox_ops,
- .format_group = &snbep_uncore_cbox_format_group,
-};
-
-static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- u64 config = reg1->config;
-
- if (new_idx > reg1->idx)
- config <<= 8 * (new_idx - reg1->idx);
- else
- config >>= 8 * (reg1->idx - new_idx);
-
- if (modify) {
- hwc->config += new_idx - reg1->idx;
- reg1->config = config;
- reg1->idx = new_idx;
- }
- return config;
-}
-
-static struct event_constraint *
-snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct intel_uncore_extra_reg *er = &box->shared_regs[0];
- unsigned long flags;
- int idx = reg1->idx;
- u64 mask, config1 = reg1->config;
- bool ok = false;
-
- if (reg1->idx == EXTRA_REG_NONE ||
- (!uncore_box_is_fake(box) && reg1->alloc))
- return NULL;
-again:
- mask = 0xffULL << (idx * 8);
- raw_spin_lock_irqsave(&er->lock, flags);
- if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
- !((config1 ^ er->config) & mask)) {
- atomic_add(1 << (idx * 8), &er->ref);
- er->config &= ~mask;
- er->config |= config1 & mask;
- ok = true;
- }
- raw_spin_unlock_irqrestore(&er->lock, flags);
-
- if (!ok) {
- idx = (idx + 1) % 4;
- if (idx != reg1->idx) {
- config1 = snbep_pcu_alter_er(event, idx, false);
- goto again;
- }
- return &constraint_empty;
- }
-
- if (!uncore_box_is_fake(box)) {
- if (idx != reg1->idx)
- snbep_pcu_alter_er(event, idx, true);
- reg1->alloc = 1;
- }
- return NULL;
-}
-
-static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct intel_uncore_extra_reg *er = &box->shared_regs[0];
-
- if (uncore_box_is_fake(box) || !reg1->alloc)
- return;
-
- atomic_sub(1 << (reg1->idx * 8), &er->ref);
- reg1->alloc = 0;
-}
-
-static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
-
- if (ev_sel >= 0xb && ev_sel <= 0xe) {
- reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
- reg1->idx = ev_sel - 0xb;
- reg1->config = event->attr.config1 & (0xff << reg1->idx);
- }
- return 0;
-}
-
-static struct intel_uncore_ops snbep_uncore_pcu_ops = {
- SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
- .hw_config = snbep_pcu_hw_config,
- .get_constraint = snbep_pcu_get_constraint,
- .put_constraint = snbep_pcu_put_constraint,
-};
-
-static struct intel_uncore_type snbep_uncore_pcu = {
- .name = "pcu",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0,
- .event_ctl = SNBEP_PCU_MSR_PMON_CTL0,
- .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL,
- .num_shared_regs = 1,
- .ops = &snbep_uncore_pcu_ops,
- .format_group = &snbep_uncore_pcu_format_group,
-};
-
-static struct intel_uncore_type *snbep_msr_uncores[] = {
- &snbep_uncore_ubox,
- &snbep_uncore_cbox,
- &snbep_uncore_pcu,
- NULL,
-};
-
-enum {
- SNBEP_PCI_QPI_PORT0_FILTER,
- SNBEP_PCI_QPI_PORT1_FILTER,
-};
-
-static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
- if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
- reg1->idx = 0;
- reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
- reg1->config = event->attr.config1;
- reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
- reg2->config = event->attr.config2;
- }
- return 0;
-}
-
-static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
- if (reg1->idx != EXTRA_REG_NONE) {
- int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
- struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
- WARN_ON_ONCE(!filter_pdev);
- if (filter_pdev) {
- pci_write_config_dword(filter_pdev, reg1->reg,
- (u32)reg1->config);
- pci_write_config_dword(filter_pdev, reg1->reg + 4,
- (u32)(reg1->config >> 32));
- pci_write_config_dword(filter_pdev, reg2->reg,
- (u32)reg2->config);
- pci_write_config_dword(filter_pdev, reg2->reg + 4,
- (u32)(reg2->config >> 32));
- }
- }
-
- pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static struct intel_uncore_ops snbep_uncore_qpi_ops = {
- SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
- .enable_event = snbep_qpi_enable_event,
- .hw_config = snbep_qpi_hw_config,
- .get_constraint = uncore_get_constraint,
- .put_constraint = uncore_put_constraint,
-};
-
-#define SNBEP_UNCORE_PCI_COMMON_INIT() \
- .perf_ctr = SNBEP_PCI_PMON_CTR0, \
- .event_ctl = SNBEP_PCI_PMON_CTL0, \
- .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \
- .ops = &snbep_uncore_pci_ops, \
- .format_group = &snbep_uncore_format_group
-
-static struct intel_uncore_type snbep_uncore_ha = {
- .name = "ha",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_imc = {
- .name = "imc",
- .num_counters = 4,
- .num_boxes = 4,
- .perf_ctr_bits = 48,
- .fixed_ctr_bits = 48,
- .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
- .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
- .event_descs = snbep_uncore_imc_events,
- SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_qpi = {
- .name = "qpi",
- .num_counters = 4,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCI_PMON_CTR0,
- .event_ctl = SNBEP_PCI_PMON_CTL0,
- .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
- .num_shared_regs = 1,
- .ops = &snbep_uncore_qpi_ops,
- .event_descs = snbep_uncore_qpi_events,
- .format_group = &snbep_uncore_qpi_format_group,
-};
-
-
-static struct intel_uncore_type snbep_uncore_r2pcie = {
- .name = "r2pcie",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 44,
- .constraints = snbep_uncore_r2pcie_constraints,
- SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type snbep_uncore_r3qpi = {
- .name = "r3qpi",
- .num_counters = 3,
- .num_boxes = 2,
- .perf_ctr_bits = 44,
- .constraints = snbep_uncore_r3qpi_constraints,
- SNBEP_UNCORE_PCI_COMMON_INIT(),
-};
-
-enum {
- SNBEP_PCI_UNCORE_HA,
- SNBEP_PCI_UNCORE_IMC,
- SNBEP_PCI_UNCORE_QPI,
- SNBEP_PCI_UNCORE_R2PCIE,
- SNBEP_PCI_UNCORE_R3QPI,
-};
-
-static struct intel_uncore_type *snbep_pci_uncores[] = {
- [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha,
- [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc,
- [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi,
- [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie,
- [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi,
- NULL,
-};
-
-static const struct pci_device_id snbep_uncore_pci_ids[] = {
- { /* Home Agent */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
- },
- { /* MC Channel 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
- },
- { /* MC Channel 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
- },
- { /* MC Channel 2 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
- },
- { /* MC Channel 3 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
- },
- { /* QPI Port 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
- },
- { /* QPI Port 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
- },
- { /* R2PCIe */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
- },
- { /* R3QPI Link 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
- },
- { /* R3QPI Link 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
- .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
- },
- { /* QPI Port 0 filter */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
- SNBEP_PCI_QPI_PORT0_FILTER),
- },
- { /* QPI Port 0 filter */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
- SNBEP_PCI_QPI_PORT1_FILTER),
- },
- { /* end: all zeroes */ }
-};
-
-static struct pci_driver snbep_uncore_pci_driver = {
- .name = "snbep_uncore",
- .id_table = snbep_uncore_pci_ids,
-};
-
-/*
- * build pci bus to socket mapping
- */
-static int snbep_pci2phy_map_init(int devid)
-{
- struct pci_dev *ubox_dev = NULL;
- int i, bus, nodeid;
- int err = 0;
- u32 config = 0;
-
- while (1) {
- /* find the UBOX device */
- ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
- if (!ubox_dev)
- break;
- bus = ubox_dev->bus->number;
- /* get the Node ID of the local register */
- err = pci_read_config_dword(ubox_dev, 0x40, &config);
- if (err)
- break;
- nodeid = config;
- /* get the Node ID mapping */
- err = pci_read_config_dword(ubox_dev, 0x54, &config);
- if (err)
- break;
- /*
- * every three bits in the Node ID mapping register maps
- * to a particular node.
- */
- for (i = 0; i < 8; i++) {
- if (nodeid == ((config >> (3 * i)) & 0x7)) {
- pcibus_to_physid[bus] = i;
- break;
- }
- }
- }
-
- if (!err) {
- /*
- * For PCI bus with no UBOX device, find the next bus
- * that has UBOX device and use its mapping.
- */
- i = -1;
- for (bus = 255; bus >= 0; bus--) {
- if (pcibus_to_physid[bus] >= 0)
- i = pcibus_to_physid[bus];
- else
- pcibus_to_physid[bus] = i;
- }
- }
-
- if (ubox_dev)
- pci_dev_put(ubox_dev);
-
- return err ? pcibios_err_to_errno(err) : 0;
-}
-/* end of Sandy Bridge-EP uncore support */
-
-/* IvyTown uncore support */
-static void ivt_uncore_msr_init_box(struct intel_uncore_box *box)
-{
- unsigned msr = uncore_msr_box_ctl(box);
- if (msr)
- wrmsrl(msr, IVT_PMON_BOX_CTL_INT);
-}
-
-static void ivt_uncore_pci_init_box(struct intel_uncore_box *box)
-{
- struct pci_dev *pdev = box->pci_dev;
-
- pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT);
-}
-
-#define IVT_UNCORE_MSR_OPS_COMMON_INIT() \
- .init_box = ivt_uncore_msr_init_box, \
- .disable_box = snbep_uncore_msr_disable_box, \
- .enable_box = snbep_uncore_msr_enable_box, \
- .disable_event = snbep_uncore_msr_disable_event, \
- .enable_event = snbep_uncore_msr_enable_event, \
- .read_counter = uncore_msr_read_counter
-
-static struct intel_uncore_ops ivt_uncore_msr_ops = {
- IVT_UNCORE_MSR_OPS_COMMON_INIT(),
-};
-
-static struct intel_uncore_ops ivt_uncore_pci_ops = {
- .init_box = ivt_uncore_pci_init_box,
- .disable_box = snbep_uncore_pci_disable_box,
- .enable_box = snbep_uncore_pci_enable_box,
- .disable_event = snbep_uncore_pci_disable_event,
- .enable_event = snbep_uncore_pci_enable_event,
- .read_counter = snbep_uncore_pci_read_counter,
-};
-
-#define IVT_UNCORE_PCI_COMMON_INIT() \
- .perf_ctr = SNBEP_PCI_PMON_CTR0, \
- .event_ctl = SNBEP_PCI_PMON_CTL0, \
- .event_mask = IVT_PMON_RAW_EVENT_MASK, \
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \
- .ops = &ivt_uncore_pci_ops, \
- .format_group = &ivt_uncore_format_group
-
-static struct attribute *ivt_uncore_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh8.attr,
- NULL,
-};
-
-static struct attribute *ivt_uncore_ubox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh5.attr,
- NULL,
-};
-
-static struct attribute *ivt_uncore_cbox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_tid_en.attr,
- &format_attr_thresh8.attr,
- &format_attr_filter_tid.attr,
- &format_attr_filter_link.attr,
- &format_attr_filter_state2.attr,
- &format_attr_filter_nid2.attr,
- &format_attr_filter_opc2.attr,
- NULL,
-};
-
-static struct attribute *ivt_uncore_pcu_formats_attr[] = {
- &format_attr_event_ext.attr,
- &format_attr_occ_sel.attr,
- &format_attr_edge.attr,
- &format_attr_thresh5.attr,
- &format_attr_occ_invert.attr,
- &format_attr_occ_edge.attr,
- &format_attr_filter_band0.attr,
- &format_attr_filter_band1.attr,
- &format_attr_filter_band2.attr,
- &format_attr_filter_band3.attr,
- NULL,
-};
-
-static struct attribute *ivt_uncore_qpi_formats_attr[] = {
- &format_attr_event_ext.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_thresh8.attr,
- &format_attr_match_rds.attr,
- &format_attr_match_rnid30.attr,
- &format_attr_match_rnid4.attr,
- &format_attr_match_dnid.attr,
- &format_attr_match_mc.attr,
- &format_attr_match_opc.attr,
- &format_attr_match_vnw.attr,
- &format_attr_match0.attr,
- &format_attr_match1.attr,
- &format_attr_mask_rds.attr,
- &format_attr_mask_rnid30.attr,
- &format_attr_mask_rnid4.attr,
- &format_attr_mask_dnid.attr,
- &format_attr_mask_mc.attr,
- &format_attr_mask_opc.attr,
- &format_attr_mask_vnw.attr,
- &format_attr_mask0.attr,
- &format_attr_mask1.attr,
- NULL,
-};
-
-static struct attribute_group ivt_uncore_format_group = {
- .name = "format",
- .attrs = ivt_uncore_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_ubox_format_group = {
- .name = "format",
- .attrs = ivt_uncore_ubox_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_cbox_format_group = {
- .name = "format",
- .attrs = ivt_uncore_cbox_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_pcu_format_group = {
- .name = "format",
- .attrs = ivt_uncore_pcu_formats_attr,
-};
-
-static struct attribute_group ivt_uncore_qpi_format_group = {
- .name = "format",
- .attrs = ivt_uncore_qpi_formats_attr,
-};
-
-static struct intel_uncore_type ivt_uncore_ubox = {
- .name = "ubox",
- .num_counters = 2,
- .num_boxes = 1,
- .perf_ctr_bits = 44,
- .fixed_ctr_bits = 48,
- .perf_ctr = SNBEP_U_MSR_PMON_CTR0,
- .event_ctl = SNBEP_U_MSR_PMON_CTL0,
- .event_mask = IVT_U_MSR_PMON_RAW_EVENT_MASK,
- .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
- .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
- .ops = &ivt_uncore_msr_ops,
- .format_group = &ivt_uncore_ubox_format_group,
-};
-
-static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
- SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
- SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
- SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
-
- SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
- EVENT_EXTRA_END
-};
-
-static u64 ivt_cbox_filter_mask(int fields)
-{
- u64 mask = 0;
-
- if (fields & 0x1)
- mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID;
- if (fields & 0x2)
- mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK;
- if (fields & 0x4)
- mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE;
- if (fields & 0x8)
- mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID;
- if (fields & 0x10)
- mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC;
-
- return mask;
-}
-
-static struct event_constraint *
-ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask);
-}
-
-static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct extra_reg *er;
- int idx = 0;
-
- for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) {
- if (er->event != (event->hw.config & er->config_mask))
- continue;
- idx |= er->idx;
- }
-
- if (idx) {
- reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
- SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
- reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx);
- reg1->idx = idx;
- }
- return 0;
-}
-
-static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
- if (reg1->idx != EXTRA_REG_NONE) {
- u64 filter = uncore_shared_reg_config(box, 0);
- wrmsrl(reg1->reg, filter & 0xffffffff);
- wrmsrl(reg1->reg + 6, filter >> 32);
- }
-
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static struct intel_uncore_ops ivt_uncore_cbox_ops = {
- .init_box = ivt_uncore_msr_init_box,
- .disable_box = snbep_uncore_msr_disable_box,
- .enable_box = snbep_uncore_msr_enable_box,
- .disable_event = snbep_uncore_msr_disable_event,
- .enable_event = ivt_cbox_enable_event,
- .read_counter = uncore_msr_read_counter,
- .hw_config = ivt_cbox_hw_config,
- .get_constraint = ivt_cbox_get_constraint,
- .put_constraint = snbep_cbox_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_cbox = {
- .name = "cbox",
- .num_counters = 4,
- .num_boxes = 15,
- .perf_ctr_bits = 44,
- .event_ctl = SNBEP_C0_MSR_PMON_CTL0,
- .perf_ctr = SNBEP_C0_MSR_PMON_CTR0,
- .event_mask = IVT_CBO_MSR_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL,
- .msr_offset = SNBEP_CBO_MSR_OFFSET,
- .num_shared_regs = 1,
- .constraints = snbep_uncore_cbox_constraints,
- .ops = &ivt_uncore_cbox_ops,
- .format_group = &ivt_uncore_cbox_format_group,
-};
-
-static struct intel_uncore_ops ivt_uncore_pcu_ops = {
- IVT_UNCORE_MSR_OPS_COMMON_INIT(),
- .hw_config = snbep_pcu_hw_config,
- .get_constraint = snbep_pcu_get_constraint,
- .put_constraint = snbep_pcu_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_pcu = {
- .name = "pcu",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0,
- .event_ctl = SNBEP_PCU_MSR_PMON_CTL0,
- .event_mask = IVT_PCU_MSR_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL,
- .num_shared_regs = 1,
- .ops = &ivt_uncore_pcu_ops,
- .format_group = &ivt_uncore_pcu_format_group,
-};
-
-static struct intel_uncore_type *ivt_msr_uncores[] = {
- &ivt_uncore_ubox,
- &ivt_uncore_cbox,
- &ivt_uncore_pcu,
- NULL,
-};
-
-static struct intel_uncore_type ivt_uncore_ha = {
- .name = "ha",
- .num_counters = 4,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type ivt_uncore_imc = {
- .name = "imc",
- .num_counters = 4,
- .num_boxes = 8,
- .perf_ctr_bits = 48,
- .fixed_ctr_bits = 48,
- .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
- .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
- IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-/* registers in IRP boxes are not properly aligned */
-static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
-static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
-
-static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
-
- pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx],
- hwc->config | SNBEP_PMON_CTL_EN);
-}
-
-static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
-
- pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config);
-}
-
-static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct pci_dev *pdev = box->pci_dev;
- struct hw_perf_event *hwc = &event->hw;
- u64 count = 0;
-
- pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
- pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
-
- return count;
-}
-
-static struct intel_uncore_ops ivt_uncore_irp_ops = {
- .init_box = ivt_uncore_pci_init_box,
- .disable_box = snbep_uncore_pci_disable_box,
- .enable_box = snbep_uncore_pci_enable_box,
- .disable_event = ivt_uncore_irp_disable_event,
- .enable_event = ivt_uncore_irp_enable_event,
- .read_counter = ivt_uncore_irp_read_counter,
-};
-
-static struct intel_uncore_type ivt_uncore_irp = {
- .name = "irp",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .event_mask = IVT_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
- .ops = &ivt_uncore_irp_ops,
- .format_group = &ivt_uncore_format_group,
-};
-
-static struct intel_uncore_ops ivt_uncore_qpi_ops = {
- .init_box = ivt_uncore_pci_init_box,
- .disable_box = snbep_uncore_pci_disable_box,
- .enable_box = snbep_uncore_pci_enable_box,
- .disable_event = snbep_uncore_pci_disable_event,
- .enable_event = snbep_qpi_enable_event,
- .read_counter = snbep_uncore_pci_read_counter,
- .hw_config = snbep_qpi_hw_config,
- .get_constraint = uncore_get_constraint,
- .put_constraint = uncore_put_constraint,
-};
-
-static struct intel_uncore_type ivt_uncore_qpi = {
- .name = "qpi",
- .num_counters = 4,
- .num_boxes = 3,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCI_PMON_CTR0,
- .event_ctl = SNBEP_PCI_PMON_CTL0,
- .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
- .num_shared_regs = 1,
- .ops = &ivt_uncore_qpi_ops,
- .format_group = &ivt_uncore_qpi_format_group,
-};
-
-static struct intel_uncore_type ivt_uncore_r2pcie = {
- .name = "r2pcie",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 44,
- .constraints = snbep_uncore_r2pcie_constraints,
- IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-static struct intel_uncore_type ivt_uncore_r3qpi = {
- .name = "r3qpi",
- .num_counters = 3,
- .num_boxes = 2,
- .perf_ctr_bits = 44,
- .constraints = snbep_uncore_r3qpi_constraints,
- IVT_UNCORE_PCI_COMMON_INIT(),
-};
-
-enum {
- IVT_PCI_UNCORE_HA,
- IVT_PCI_UNCORE_IMC,
- IVT_PCI_UNCORE_IRP,
- IVT_PCI_UNCORE_QPI,
- IVT_PCI_UNCORE_R2PCIE,
- IVT_PCI_UNCORE_R3QPI,
-};
-
-static struct intel_uncore_type *ivt_pci_uncores[] = {
- [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha,
- [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc,
- [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp,
- [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi,
- [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie,
- [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi,
- NULL,
-};
-
-static const struct pci_device_id ivt_uncore_pci_ids[] = {
- { /* Home Agent 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
- },
- { /* Home Agent 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
- },
- { /* MC0 Channel 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
- },
- { /* MC0 Channel 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
- },
- { /* MC0 Channel 3 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
- },
- { /* MC0 Channel 4 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
- },
- { /* MC1 Channel 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
- },
- { /* MC1 Channel 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
- },
- { /* MC1 Channel 3 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
- },
- { /* MC1 Channel 4 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
- },
- { /* IRP */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0),
- },
- { /* QPI0 Port 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
- },
- { /* QPI0 Port 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
- },
- { /* QPI1 Port 2 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
- },
- { /* R2PCIe */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
- },
- { /* R3QPI0 Link 0 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
- },
- { /* R3QPI0 Link 1 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
- },
- { /* R3QPI1 Link 2 */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
- .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
- },
- { /* QPI Port 0 filter */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
- SNBEP_PCI_QPI_PORT0_FILTER),
- },
- { /* QPI Port 0 filter */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
- SNBEP_PCI_QPI_PORT1_FILTER),
- },
- { /* end: all zeroes */ }
-};
-
-static struct pci_driver ivt_uncore_pci_driver = {
- .name = "ivt_uncore",
- .id_table = ivt_uncore_pci_ids,
-};
-/* end of IvyTown uncore support */
-
-/* Sandy Bridge uncore support */
-static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- if (hwc->idx < UNCORE_PMC_IDX_FIXED)
- wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
- else
- wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
-}
-
-static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- wrmsrl(event->hw.config_base, 0);
-}
-
-static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
-{
- if (box->pmu->pmu_idx == 0) {
- wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
- SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
- }
-}
-
-static struct uncore_event_desc snb_uncore_events[] = {
- INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
- { /* end: all zeroes */ },
-};
-
-static struct attribute *snb_uncore_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_cmask5.attr,
- NULL,
-};
-
-static struct attribute_group snb_uncore_format_group = {
- .name = "format",
- .attrs = snb_uncore_formats_attr,
-};
-
-static struct intel_uncore_ops snb_uncore_msr_ops = {
- .init_box = snb_uncore_msr_init_box,
- .disable_event = snb_uncore_msr_disable_event,
- .enable_event = snb_uncore_msr_enable_event,
- .read_counter = uncore_msr_read_counter,
-};
-
-static struct event_constraint snb_uncore_cbox_constraints[] = {
- UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
- UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
- EVENT_CONSTRAINT_END
-};
-
-static struct intel_uncore_type snb_uncore_cbox = {
- .name = "cbox",
- .num_counters = 2,
- .num_boxes = 4,
- .perf_ctr_bits = 44,
- .fixed_ctr_bits = 48,
- .perf_ctr = SNB_UNC_CBO_0_PER_CTR0,
- .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
- .fixed_ctr = SNB_UNC_FIXED_CTR,
- .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
- .single_fixed = 1,
- .event_mask = SNB_UNC_RAW_EVENT_MASK,
- .msr_offset = SNB_UNC_CBO_MSR_OFFSET,
- .constraints = snb_uncore_cbox_constraints,
- .ops = &snb_uncore_msr_ops,
- .format_group = &snb_uncore_format_group,
- .event_descs = snb_uncore_events,
-};
-
-static struct intel_uncore_type *snb_msr_uncores[] = {
- &snb_uncore_cbox,
- NULL,
-};
-
-enum {
- SNB_PCI_UNCORE_IMC,
-};
-
-static struct uncore_event_desc snb_uncore_imc_events[] = {
- INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"),
- INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
- INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
-
- INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
- INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
- INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
-
- { /* end: all zeroes */ },
-};
-
-#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff
-#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48
-
-/* page size multiple covering all config regs */
-#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000
-
-#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1
-#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050
-#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2
-#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054
-#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE
-
-static struct attribute *snb_uncore_imc_formats_attr[] = {
- &format_attr_event.attr,
- NULL,
-};
-
-static struct attribute_group snb_uncore_imc_format_group = {
- .name = "format",
- .attrs = snb_uncore_imc_formats_attr,
-};
-
-static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
-{
- struct pci_dev *pdev = box->pci_dev;
- int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
- resource_size_t addr;
- u32 pci_dword;
-
- pci_read_config_dword(pdev, where, &pci_dword);
- addr = pci_dword;
-
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
- pci_read_config_dword(pdev, where + 4, &pci_dword);
- addr |= ((resource_size_t)pci_dword << 32);
-#endif
-
- addr &= ~(PAGE_SIZE - 1);
-
- box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
- box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
-}
-
-static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
-{}
-
-static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
-{}
-
-static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{}
-
-static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{}
-
-static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
-}
-
-/*
- * custom event_init() function because we define our own fixed, free
- * running counters, so we do not want to conflict with generic uncore
- * logic. Also simplifies processing
- */
-static int snb_uncore_imc_event_init(struct perf_event *event)
-{
- struct intel_uncore_pmu *pmu;
- struct intel_uncore_box *box;
- struct hw_perf_event *hwc = &event->hw;
- u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
- int idx, base;
-
- if (event->attr.type != event->pmu->type)
- return -ENOENT;
-
- pmu = uncore_event_to_pmu(event);
- /* no device found for this pmu */
- if (pmu->func_id < 0)
- return -ENOENT;
-
- /* Sampling not supported yet */
- if (hwc->sample_period)
- return -EINVAL;
-
- /* unsupported modes and filters */
- if (event->attr.exclude_user ||
- event->attr.exclude_kernel ||
- event->attr.exclude_hv ||
- event->attr.exclude_idle ||
- event->attr.exclude_host ||
- event->attr.exclude_guest ||
- event->attr.sample_period) /* no sampling */
- return -EINVAL;
-
- /*
- * Place all uncore events for a particular physical package
- * onto a single cpu
- */
- if (event->cpu < 0)
- return -EINVAL;
-
- /* check only supported bits are set */
- if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
- return -EINVAL;
-
- box = uncore_pmu_to_box(pmu, event->cpu);
- if (!box || box->cpu < 0)
- return -EINVAL;
-
- event->cpu = box->cpu;
-
- event->hw.idx = -1;
- event->hw.last_tag = ~0ULL;
- event->hw.extra_reg.idx = EXTRA_REG_NONE;
- event->hw.branch_reg.idx = EXTRA_REG_NONE;
- /*
- * check event is known (whitelist, determines counter)
- */
- switch (cfg) {
- case SNB_UNCORE_PCI_IMC_DATA_READS:
- base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
- idx = UNCORE_PMC_IDX_FIXED;
- break;
- case SNB_UNCORE_PCI_IMC_DATA_WRITES:
- base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
- idx = UNCORE_PMC_IDX_FIXED + 1;
- break;
- default:
- return -EINVAL;
- }
-
- /* must be done before validate_group */
- event->hw.event_base = base;
- event->hw.config = cfg;
- event->hw.idx = idx;
-
- /* no group validation needed, we have free running counters */
-
- return 0;
-}
-
-static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- return 0;
-}
-
-static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- u64 count;
-
- if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
- return;
-
- event->hw.state = 0;
- box->n_active++;
-
- list_add_tail(&event->active_entry, &box->active_list);
-
- count = snb_uncore_imc_read_counter(box, event);
- local64_set(&event->hw.prev_count, count);
-
- if (box->n_active == 1)
- uncore_pmu_start_hrtimer(box);
-}
-
-static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- struct hw_perf_event *hwc = &event->hw;
-
- if (!(hwc->state & PERF_HES_STOPPED)) {
- box->n_active--;
-
- WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
- hwc->state |= PERF_HES_STOPPED;
-
- list_del(&event->active_entry);
-
- if (box->n_active == 0)
- uncore_pmu_cancel_hrtimer(box);
- }
-
- if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
- /*
- * Drain the remaining delta count out of a event
- * that we are disabling:
- */
- uncore_perf_event_update(box, event);
- hwc->state |= PERF_HES_UPTODATE;
- }
-}
-
-static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- struct hw_perf_event *hwc = &event->hw;
-
- if (!box)
- return -ENODEV;
-
- hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
- if (!(flags & PERF_EF_START))
- hwc->state |= PERF_HES_ARCH;
-
- snb_uncore_imc_event_start(event, 0);
-
- box->n_events++;
-
- return 0;
-}
-
-static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
-{
- struct intel_uncore_box *box = uncore_event_to_box(event);
- int i;
-
- snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
- for (i = 0; i < box->n_events; i++) {
- if (event == box->event_list[i]) {
- --box->n_events;
- break;
- }
- }
-}
-
-static int snb_pci2phy_map_init(int devid)
-{
- struct pci_dev *dev = NULL;
- int bus;
-
- dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
- if (!dev)
- return -ENOTTY;
-
- bus = dev->bus->number;
-
- pcibus_to_physid[bus] = 0;
-
- pci_dev_put(dev);
-
- return 0;
-}
-
-static struct pmu snb_uncore_imc_pmu = {
- .task_ctx_nr = perf_invalid_context,
- .event_init = snb_uncore_imc_event_init,
- .add = snb_uncore_imc_event_add,
- .del = snb_uncore_imc_event_del,
- .start = snb_uncore_imc_event_start,
- .stop = snb_uncore_imc_event_stop,
- .read = uncore_pmu_event_read,
-};
-
-static struct intel_uncore_ops snb_uncore_imc_ops = {
- .init_box = snb_uncore_imc_init_box,
- .enable_box = snb_uncore_imc_enable_box,
- .disable_box = snb_uncore_imc_disable_box,
- .disable_event = snb_uncore_imc_disable_event,
- .enable_event = snb_uncore_imc_enable_event,
- .hw_config = snb_uncore_imc_hw_config,
- .read_counter = snb_uncore_imc_read_counter,
-};
-
-static struct intel_uncore_type snb_uncore_imc = {
- .name = "imc",
- .num_counters = 2,
- .num_boxes = 1,
- .fixed_ctr_bits = 32,
- .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE,
- .event_descs = snb_uncore_imc_events,
- .format_group = &snb_uncore_imc_format_group,
- .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
- .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK,
- .ops = &snb_uncore_imc_ops,
- .pmu = &snb_uncore_imc_pmu,
-};
-
-static struct intel_uncore_type *snb_pci_uncores[] = {
- [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc,
- NULL,
-};
-
-static const struct pci_device_id snb_uncore_pci_ids[] = {
- { /* IMC */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
- .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
- },
- { /* end: all zeroes */ },
-};
-
-static const struct pci_device_id ivb_uncore_pci_ids[] = {
- { /* IMC */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
- .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
- },
- { /* end: all zeroes */ },
-};
-
-static const struct pci_device_id hsw_uncore_pci_ids[] = {
- { /* IMC */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
- .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
- },
- { /* end: all zeroes */ },
-};
-
-static struct pci_driver snb_uncore_pci_driver = {
- .name = "snb_uncore",
- .id_table = snb_uncore_pci_ids,
-};
-
-static struct pci_driver ivb_uncore_pci_driver = {
- .name = "ivb_uncore",
- .id_table = ivb_uncore_pci_ids,
-};
-
-static struct pci_driver hsw_uncore_pci_driver = {
- .name = "hsw_uncore",
- .id_table = hsw_uncore_pci_ids,
-};
-
-/* end of Sandy Bridge uncore support */
-
-/* Nehalem uncore support */
-static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
- wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
-}
-
-static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
- wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
-}
-
-static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- if (hwc->idx < UNCORE_PMC_IDX_FIXED)
- wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
- else
- wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
-}
-
-static struct attribute *nhm_uncore_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_cmask8.attr,
- NULL,
-};
-
-static struct attribute_group nhm_uncore_format_group = {
- .name = "format",
- .attrs = nhm_uncore_formats_attr,
-};
-
-static struct uncore_event_desc nhm_uncore_events[] = {
- INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
- INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"),
- INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"),
- INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"),
- INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"),
- INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"),
- INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
- INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"),
- INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"),
- { /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhm_uncore_msr_ops = {
- .disable_box = nhm_uncore_msr_disable_box,
- .enable_box = nhm_uncore_msr_enable_box,
- .disable_event = snb_uncore_msr_disable_event,
- .enable_event = nhm_uncore_msr_enable_event,
- .read_counter = uncore_msr_read_counter,
-};
-
-static struct intel_uncore_type nhm_uncore = {
- .name = "",
- .num_counters = 8,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .fixed_ctr_bits = 48,
- .event_ctl = NHM_UNC_PERFEVTSEL0,
- .perf_ctr = NHM_UNC_UNCORE_PMC0,
- .fixed_ctr = NHM_UNC_FIXED_CTR,
- .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL,
- .event_mask = NHM_UNC_RAW_EVENT_MASK,
- .event_descs = nhm_uncore_events,
- .ops = &nhm_uncore_msr_ops,
- .format_group = &nhm_uncore_format_group,
-};
-
-static struct intel_uncore_type *nhm_msr_uncores[] = {
- &nhm_uncore,
- NULL,
-};
-/* end of Nehalem uncore support */
-
-/* Nehalem-EX uncore support */
-DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
-DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
-DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
-
-static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
-{
- wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
-}
-
-static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
-{
- unsigned msr = uncore_msr_box_ctl(box);
- u64 config;
-
- if (msr) {
- rdmsrl(msr, config);
- config &= ~((1ULL << uncore_num_counters(box)) - 1);
- /* WBox has a fixed counter */
- if (uncore_msr_fixed_ctl(box))
- config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
- wrmsrl(msr, config);
- }
-}
-
-static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
-{
- unsigned msr = uncore_msr_box_ctl(box);
- u64 config;
-
- if (msr) {
- rdmsrl(msr, config);
- config |= (1ULL << uncore_num_counters(box)) - 1;
- /* WBox has a fixed counter */
- if (uncore_msr_fixed_ctl(box))
- config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
- wrmsrl(msr, config);
- }
-}
-
-static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- wrmsrl(event->hw.config_base, 0);
-}
-
-static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
-
- if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
- wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
- else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
- else
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
-}
-
-#define NHMEX_UNCORE_OPS_COMMON_INIT() \
- .init_box = nhmex_uncore_msr_init_box, \
- .disable_box = nhmex_uncore_msr_disable_box, \
- .enable_box = nhmex_uncore_msr_enable_box, \
- .disable_event = nhmex_uncore_msr_disable_event, \
- .read_counter = uncore_msr_read_counter
-
-static struct intel_uncore_ops nhmex_uncore_ops = {
- NHMEX_UNCORE_OPS_COMMON_INIT(),
- .enable_event = nhmex_uncore_msr_enable_event,
-};
-
-static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_edge.attr,
- NULL,
-};
-
-static struct attribute_group nhmex_uncore_ubox_format_group = {
- .name = "format",
- .attrs = nhmex_uncore_ubox_formats_attr,
-};
-
-static struct intel_uncore_type nhmex_uncore_ubox = {
- .name = "ubox",
- .num_counters = 1,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_U_MSR_PMON_EV_SEL,
- .perf_ctr = NHMEX_U_MSR_PMON_CTR,
- .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL,
- .ops = &nhmex_uncore_ops,
- .format_group = &nhmex_uncore_ubox_format_group
-};
-
-static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh8.attr,
- NULL,
-};
-
-static struct attribute_group nhmex_uncore_cbox_format_group = {
- .name = "format",
- .attrs = nhmex_uncore_cbox_formats_attr,
-};
-
-/* msr offset for each instance of cbox */
-static unsigned nhmex_cbox_msr_offsets[] = {
- 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
-};
-
-static struct intel_uncore_type nhmex_uncore_cbox = {
- .name = "cbox",
- .num_counters = 6,
- .num_boxes = 10,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0,
- .perf_ctr = NHMEX_C0_MSR_PMON_CTR0,
- .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL,
- .msr_offsets = nhmex_cbox_msr_offsets,
- .pair_ctr_ctl = 1,
- .ops = &nhmex_uncore_ops,
- .format_group = &nhmex_uncore_cbox_format_group
-};
-
-static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
- INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
- { /* end: all zeroes */ },
-};
-
-static struct intel_uncore_type nhmex_uncore_wbox = {
- .name = "wbox",
- .num_counters = 4,
- .num_boxes = 1,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_W_MSR_PMON_CNT0,
- .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0,
- .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR,
- .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL,
- .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_W_MSR_GLOBAL_CTL,
- .pair_ctr_ctl = 1,
- .event_descs = nhmex_uncore_wbox_events,
- .ops = &nhmex_uncore_ops,
- .format_group = &nhmex_uncore_cbox_format_group
-};
-
-static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
- int ctr, ev_sel;
-
- ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
- NHMEX_B_PMON_CTR_SHIFT;
- ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
- NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
-
- /* events that do not use the match/mask registers */
- if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
- (ctr == 2 && ev_sel != 0x4) || ctr == 3)
- return 0;
-
- if (box->pmu->pmu_idx == 0)
- reg1->reg = NHMEX_B0_MSR_MATCH;
- else
- reg1->reg = NHMEX_B1_MSR_MATCH;
- reg1->idx = 0;
- reg1->config = event->attr.config1;
- reg2->config = event->attr.config2;
- return 0;
-}
-
-static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
- if (reg1->idx != EXTRA_REG_NONE) {
- wrmsrl(reg1->reg, reg1->config);
- wrmsrl(reg1->reg + 1, reg2->config);
- }
- wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
- (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
-}
-
-/*
- * The Bbox has 4 counters, but each counter monitors different events.
- * Use bits 6-7 in the event config to select counter.
- */
-static struct event_constraint nhmex_uncore_bbox_constraints[] = {
- EVENT_CONSTRAINT(0 , 1, 0xc0),
- EVENT_CONSTRAINT(0x40, 2, 0xc0),
- EVENT_CONSTRAINT(0x80, 4, 0xc0),
- EVENT_CONSTRAINT(0xc0, 8, 0xc0),
- EVENT_CONSTRAINT_END,
-};
-
-static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
- &format_attr_event5.attr,
- &format_attr_counter.attr,
- &format_attr_match.attr,
- &format_attr_mask.attr,
- NULL,
-};
-
-static struct attribute_group nhmex_uncore_bbox_format_group = {
- .name = "format",
- .attrs = nhmex_uncore_bbox_formats_attr,
-};
-
-static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
- NHMEX_UNCORE_OPS_COMMON_INIT(),
- .enable_event = nhmex_bbox_msr_enable_event,
- .hw_config = nhmex_bbox_hw_config,
- .get_constraint = uncore_get_constraint,
- .put_constraint = uncore_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_bbox = {
- .name = "bbox",
- .num_counters = 4,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_B0_MSR_PMON_CTL0,
- .perf_ctr = NHMEX_B0_MSR_PMON_CTR0,
- .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL,
- .msr_offset = NHMEX_B_MSR_OFFSET,
- .pair_ctr_ctl = 1,
- .num_shared_regs = 1,
- .constraints = nhmex_uncore_bbox_constraints,
- .ops = &nhmex_uncore_bbox_ops,
- .format_group = &nhmex_uncore_bbox_format_group
-};
-
-static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
- /* only TO_R_PROG_EV event uses the match/mask register */
- if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
- NHMEX_S_EVENT_TO_R_PROG_EV)
- return 0;
-
- if (box->pmu->pmu_idx == 0)
- reg1->reg = NHMEX_S0_MSR_MM_CFG;
- else
- reg1->reg = NHMEX_S1_MSR_MM_CFG;
- reg1->idx = 0;
- reg1->config = event->attr.config1;
- reg2->config = event->attr.config2;
- return 0;
-}
-
-static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
-
- if (reg1->idx != EXTRA_REG_NONE) {
- wrmsrl(reg1->reg, 0);
- wrmsrl(reg1->reg + 1, reg1->config);
- wrmsrl(reg1->reg + 2, reg2->config);
- wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
- }
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
-}
-
-static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
- &format_attr_event.attr,
- &format_attr_umask.attr,
- &format_attr_edge.attr,
- &format_attr_inv.attr,
- &format_attr_thresh8.attr,
- &format_attr_match.attr,
- &format_attr_mask.attr,
- NULL,
-};
-
-static struct attribute_group nhmex_uncore_sbox_format_group = {
- .name = "format",
- .attrs = nhmex_uncore_sbox_formats_attr,
-};
-
-static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
- NHMEX_UNCORE_OPS_COMMON_INIT(),
- .enable_event = nhmex_sbox_msr_enable_event,
- .hw_config = nhmex_sbox_hw_config,
- .get_constraint = uncore_get_constraint,
- .put_constraint = uncore_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_sbox = {
- .name = "sbox",
- .num_counters = 4,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_S0_MSR_PMON_CTL0,
- .perf_ctr = NHMEX_S0_MSR_PMON_CTR0,
- .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL,
- .msr_offset = NHMEX_S_MSR_OFFSET,
- .pair_ctr_ctl = 1,
- .num_shared_regs = 1,
- .ops = &nhmex_uncore_sbox_ops,
- .format_group = &nhmex_uncore_sbox_format_group
-};
-
-enum {
- EXTRA_REG_NHMEX_M_FILTER,
- EXTRA_REG_NHMEX_M_DSP,
- EXTRA_REG_NHMEX_M_ISS,
- EXTRA_REG_NHMEX_M_MAP,
- EXTRA_REG_NHMEX_M_MSC_THR,
- EXTRA_REG_NHMEX_M_PGT,
- EXTRA_REG_NHMEX_M_PLD,
- EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
-};
-
-static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
- MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
- MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
- MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
- MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
- /* event 0xa uses two extra registers */
- MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
- MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
- MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
- /* events 0xd ~ 0x10 use the same extra register */
- MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
- MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
- MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
- MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
- MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
- MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
- MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
- MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
- MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
- EVENT_EXTRA_END
-};
-
-/* Nehalem-EX or Westmere-EX ? */
-static bool uncore_nhmex;
-
-static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
-{
- struct intel_uncore_extra_reg *er;
- unsigned long flags;
- bool ret = false;
- u64 mask;
-
- if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
- er = &box->shared_regs[idx];
- raw_spin_lock_irqsave(&er->lock, flags);
- if (!atomic_read(&er->ref) || er->config == config) {
- atomic_inc(&er->ref);
- er->config = config;
- ret = true;
- }
- raw_spin_unlock_irqrestore(&er->lock, flags);
-
- return ret;
- }
- /*
- * The ZDP_CTL_FVC MSR has 4 fields which are used to control
- * events 0xd ~ 0x10. Besides these 4 fields, there are additional
- * fields which are shared.
- */
- idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
- if (WARN_ON_ONCE(idx >= 4))
- return false;
-
- /* mask of the shared fields */
- if (uncore_nhmex)
- mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
- else
- mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
- er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
-
- raw_spin_lock_irqsave(&er->lock, flags);
- /* add mask of the non-shared field if it's in use */
- if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
- if (uncore_nhmex)
- mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
- else
- mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
- }
-
- if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
- atomic_add(1 << (idx * 8), &er->ref);
- if (uncore_nhmex)
- mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
- NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
- else
- mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
- WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
- er->config &= ~mask;
- er->config |= (config & mask);
- ret = true;
- }
- raw_spin_unlock_irqrestore(&er->lock, flags);
-
- return ret;
-}
-
-static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
-{
- struct intel_uncore_extra_reg *er;
-
- if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
- er = &box->shared_regs[idx];
- atomic_dec(&er->ref);
- return;
- }
-
- idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
- er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
- atomic_sub(1 << (idx * 8), &er->ref);
-}
-
-static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
- u64 config = reg1->config;
-
- /* get the non-shared control bits and shift them */
- idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
- if (uncore_nhmex)
- config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
- else
- config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
- if (new_idx > orig_idx) {
- idx = new_idx - orig_idx;
- config <<= 3 * idx;
- } else {
- idx = orig_idx - new_idx;
- config >>= 3 * idx;
- }
-
- /* add the shared control bits back */
- if (uncore_nhmex)
- config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
- else
- config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
- config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
- if (modify) {
- /* adjust the main event selector */
- if (new_idx > orig_idx)
- hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
- else
- hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
- reg1->config = config;
- reg1->idx = ~0xff | new_idx;
- }
- return config;
-}
-
-static struct event_constraint *
-nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
- int i, idx[2], alloc = 0;
- u64 config1 = reg1->config;
-
- idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
- idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
-again:
- for (i = 0; i < 2; i++) {
- if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
- idx[i] = 0xff;
-
- if (idx[i] == 0xff)
- continue;
-
- if (!nhmex_mbox_get_shared_reg(box, idx[i],
- __BITS_VALUE(config1, i, 32)))
- goto fail;
- alloc |= (0x1 << i);
- }
-
- /* for the match/mask registers */
- if (reg2->idx != EXTRA_REG_NONE &&
- (uncore_box_is_fake(box) || !reg2->alloc) &&
- !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
- goto fail;
-
- /*
- * If it's a fake box -- as per validate_{group,event}() we
- * shouldn't touch event state and we can avoid doing so
- * since both will only call get_event_constraints() once
- * on each event, this avoids the need for reg->alloc.
- */
- if (!uncore_box_is_fake(box)) {
- if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
- nhmex_mbox_alter_er(event, idx[0], true);
- reg1->alloc |= alloc;
- if (reg2->idx != EXTRA_REG_NONE)
- reg2->alloc = 1;
- }
- return NULL;
-fail:
- if (idx[0] != 0xff && !(alloc & 0x1) &&
- idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
- /*
- * events 0xd ~ 0x10 are functional identical, but are
- * controlled by different fields in the ZDP_CTL_FVC
- * register. If we failed to take one field, try the
- * rest 3 choices.
- */
- BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
- idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
- idx[0] = (idx[0] + 1) % 4;
- idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
- if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
- config1 = nhmex_mbox_alter_er(event, idx[0], false);
- goto again;
- }
- }
-
- if (alloc & 0x1)
- nhmex_mbox_put_shared_reg(box, idx[0]);
- if (alloc & 0x2)
- nhmex_mbox_put_shared_reg(box, idx[1]);
- return &constraint_empty;
-}
-
-static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
-
- if (uncore_box_is_fake(box))
- return;
-
- if (reg1->alloc & 0x1)
- nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
- if (reg1->alloc & 0x2)
- nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
- reg1->alloc = 0;
-
- if (reg2->alloc) {
- nhmex_mbox_put_shared_reg(box, reg2->idx);
- reg2->alloc = 0;
- }
-}
-
-static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
-{
- if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
- return er->idx;
- return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
-}
-
-static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct intel_uncore_type *type = box->pmu->type;
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
- struct extra_reg *er;
- unsigned msr;
- int reg_idx = 0;
- /*
- * The mbox events may require 2 extra MSRs at the most. But only
- * the lower 32 bits in these MSRs are significant, so we can use
- * config1 to pass two MSRs' config.
- */
- for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
- if (er->event != (event->hw.config & er->config_mask))
- continue;
- if (event->attr.config1 & ~er->valid_mask)
- return -EINVAL;
-
- msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
- if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
- return -EINVAL;
-
- /* always use the 32~63 bits to pass the PLD config */
- if (er->idx == EXTRA_REG_NHMEX_M_PLD)
- reg_idx = 1;
- else if (WARN_ON_ONCE(reg_idx > 0))
- return -EINVAL;
-
- reg1->idx &= ~(0xff << (reg_idx * 8));
- reg1->reg &= ~(0xffff << (reg_idx * 16));
- reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
- reg1->reg |= msr << (reg_idx * 16);
- reg1->config = event->attr.config1;
- reg_idx++;
- }
- /*
- * The mbox only provides ability to perform address matching
- * for the PLD events.
- */
- if (reg_idx == 2) {
- reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
- if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
- reg2->config = event->attr.config2;
- else
- reg2->config = ~0ULL;
- if (box->pmu->pmu_idx == 0)
- reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
- else
- reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
- }
- return 0;
-}
-
-static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
-{
- struct intel_uncore_extra_reg *er;
- unsigned long flags;
- u64 config;
-
- if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
- return box->shared_regs[idx].config;
-
- er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
- raw_spin_lock_irqsave(&er->lock, flags);
- config = er->config;
- raw_spin_unlock_irqrestore(&er->lock, flags);
- return config;
-}
-
-static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
- int idx;
-
- idx = __BITS_VALUE(reg1->idx, 0, 8);
- if (idx != 0xff)
- wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
- nhmex_mbox_shared_reg_config(box, idx));
- idx = __BITS_VALUE(reg1->idx, 1, 8);
- if (idx != 0xff)
- wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
- nhmex_mbox_shared_reg_config(box, idx));
-
- if (reg2->idx != EXTRA_REG_NONE) {
- wrmsrl(reg2->reg, 0);
- if (reg2->config != ~0ULL) {
- wrmsrl(reg2->reg + 1,
- reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
- wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
- (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
- wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
- }
- }
-
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
-}
-
-DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3");
-DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5");
-DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6");
-DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7");
-DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13");
-DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21");
-DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63");
-DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33");
-DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61");
-DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31");
-DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63");
-
-static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
- &format_attr_count_mode.attr,
- &format_attr_storage_mode.attr,
- &format_attr_wrap_mode.attr,
- &format_attr_flag_mode.attr,
- &format_attr_inc_sel.attr,
- &format_attr_set_flag_sel.attr,
- &format_attr_filter_cfg_en.attr,
- &format_attr_filter_match.attr,
- &format_attr_filter_mask.attr,
- &format_attr_dsp.attr,
- &format_attr_thr.attr,
- &format_attr_fvc.attr,
- &format_attr_pgt.attr,
- &format_attr_map.attr,
- &format_attr_iss.attr,
- &format_attr_pld.attr,
- NULL,
-};
-
-static struct attribute_group nhmex_uncore_mbox_format_group = {
- .name = "format",
- .attrs = nhmex_uncore_mbox_formats_attr,
-};
-
-static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
- INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
- INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
- { /* end: all zeroes */ },
-};
-
-static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
- INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
- INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
- { /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
- NHMEX_UNCORE_OPS_COMMON_INIT(),
- .enable_event = nhmex_mbox_msr_enable_event,
- .hw_config = nhmex_mbox_hw_config,
- .get_constraint = nhmex_mbox_get_constraint,
- .put_constraint = nhmex_mbox_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_mbox = {
- .name = "mbox",
- .num_counters = 6,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_M0_MSR_PMU_CTL0,
- .perf_ctr = NHMEX_M0_MSR_PMU_CNT0,
- .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL,
- .msr_offset = NHMEX_M_MSR_OFFSET,
- .pair_ctr_ctl = 1,
- .num_shared_regs = 8,
- .event_descs = nhmex_uncore_mbox_events,
- .ops = &nhmex_uncore_mbox_ops,
- .format_group = &nhmex_uncore_mbox_format_group,
-};
-
-static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
-
- /* adjust the main event selector and extra register index */
- if (reg1->idx % 2) {
- reg1->idx--;
- hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
- } else {
- reg1->idx++;
- hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
- }
-
- /* adjust extra register config */
- switch (reg1->idx % 6) {
- case 2:
- /* shift the 8~15 bits to the 0~7 bits */
- reg1->config >>= 8;
- break;
- case 3:
- /* shift the 0~7 bits to the 8~15 bits */
- reg1->config <<= 8;
- break;
- };
-}
-
-/*
- * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
- * An event set consists of 6 events, the 3rd and 4th events in
- * an event set use the same extra register. So an event set uses
- * 5 extra registers.
- */
-static struct event_constraint *
-nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
- struct intel_uncore_extra_reg *er;
- unsigned long flags;
- int idx, er_idx;
- u64 config1;
- bool ok = false;
-
- if (!uncore_box_is_fake(box) && reg1->alloc)
- return NULL;
-
- idx = reg1->idx % 6;
- config1 = reg1->config;
-again:
- er_idx = idx;
- /* the 3rd and 4th events use the same extra register */
- if (er_idx > 2)
- er_idx--;
- er_idx += (reg1->idx / 6) * 5;
-
- er = &box->shared_regs[er_idx];
- raw_spin_lock_irqsave(&er->lock, flags);
- if (idx < 2) {
- if (!atomic_read(&er->ref) || er->config == reg1->config) {
- atomic_inc(&er->ref);
- er->config = reg1->config;
- ok = true;
- }
- } else if (idx == 2 || idx == 3) {
- /*
- * these two events use different fields in a extra register,
- * the 0~7 bits and the 8~15 bits respectively.
- */
- u64 mask = 0xff << ((idx - 2) * 8);
- if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
- !((er->config ^ config1) & mask)) {
- atomic_add(1 << ((idx - 2) * 8), &er->ref);
- er->config &= ~mask;
- er->config |= config1 & mask;
- ok = true;
- }
- } else {
- if (!atomic_read(&er->ref) ||
- (er->config == (hwc->config >> 32) &&
- er->config1 == reg1->config &&
- er->config2 == reg2->config)) {
- atomic_inc(&er->ref);
- er->config = (hwc->config >> 32);
- er->config1 = reg1->config;
- er->config2 = reg2->config;
- ok = true;
- }
- }
- raw_spin_unlock_irqrestore(&er->lock, flags);
-
- if (!ok) {
- /*
- * The Rbox events are always in pairs. The paired
- * events are functional identical, but use different
- * extra registers. If we failed to take an extra
- * register, try the alternative.
- */
- idx ^= 1;
- if (idx != reg1->idx % 6) {
- if (idx == 2)
- config1 >>= 8;
- else if (idx == 3)
- config1 <<= 8;
- goto again;
- }
- } else {
- if (!uncore_box_is_fake(box)) {
- if (idx != reg1->idx % 6)
- nhmex_rbox_alter_er(box, event);
- reg1->alloc = 1;
- }
- return NULL;
- }
- return &constraint_empty;
-}
-
-static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct intel_uncore_extra_reg *er;
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- int idx, er_idx;
-
- if (uncore_box_is_fake(box) || !reg1->alloc)
- return;
-
- idx = reg1->idx % 6;
- er_idx = idx;
- if (er_idx > 2)
- er_idx--;
- er_idx += (reg1->idx / 6) * 5;
-
- er = &box->shared_regs[er_idx];
- if (idx == 2 || idx == 3)
- atomic_sub(1 << ((idx - 2) * 8), &er->ref);
- else
- atomic_dec(&er->ref);
-
- reg1->alloc = 0;
-}
-
-static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
- struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
- int idx;
-
- idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
- NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
- if (idx >= 0x18)
- return -EINVAL;
-
- reg1->idx = idx;
- reg1->config = event->attr.config1;
-
- switch (idx % 6) {
- case 4:
- case 5:
- hwc->config |= event->attr.config & (~0ULL << 32);
- reg2->config = event->attr.config2;
- break;
- };
- return 0;
-}
-
-static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
-{
- struct hw_perf_event *hwc = &event->hw;
- struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
- struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
- int idx, port;
-
- idx = reg1->idx;
- port = idx / 6 + box->pmu->pmu_idx * 4;
-
- switch (idx % 6) {
- case 0:
- wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
- break;
- case 1:
- wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
- break;
- case 2:
- case 3:
- wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
- uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
- break;
- case 4:
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
- hwc->config >> 32);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
- break;
- case 5:
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
- hwc->config >> 32);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
- break;
- };
-
- wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
- (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
-}
-
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
-DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
-DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
-
-static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
- &format_attr_event5.attr,
- &format_attr_xbr_mm_cfg.attr,
- &format_attr_xbr_match.attr,
- &format_attr_xbr_mask.attr,
- &format_attr_qlx_cfg.attr,
- &format_attr_iperf_cfg.attr,
- NULL,
-};
-
-static struct attribute_group nhmex_uncore_rbox_format_group = {
- .name = "format",
- .attrs = nhmex_uncore_rbox_formats_attr,
-};
-
-static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
- INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"),
- INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"),
- INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"),
- INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"),
- INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"),
- INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"),
- { /* end: all zeroes */ },
-};
-
-static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
- NHMEX_UNCORE_OPS_COMMON_INIT(),
- .enable_event = nhmex_rbox_msr_enable_event,
- .hw_config = nhmex_rbox_hw_config,
- .get_constraint = nhmex_rbox_get_constraint,
- .put_constraint = nhmex_rbox_put_constraint,
-};
-
-static struct intel_uncore_type nhmex_uncore_rbox = {
- .name = "rbox",
- .num_counters = 8,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .event_ctl = NHMEX_R_MSR_PMON_CTL0,
- .perf_ctr = NHMEX_R_MSR_PMON_CNT0,
- .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK,
- .box_ctl = NHMEX_R_MSR_GLOBAL_CTL,
- .msr_offset = NHMEX_R_MSR_OFFSET,
- .pair_ctr_ctl = 1,
- .num_shared_regs = 20,
- .event_descs = nhmex_uncore_rbox_events,
- .ops = &nhmex_uncore_rbox_ops,
- .format_group = &nhmex_uncore_rbox_format_group
-};
-
-static struct intel_uncore_type *nhmex_msr_uncores[] = {
- &nhmex_uncore_ubox,
- &nhmex_uncore_cbox,
- &nhmex_uncore_bbox,
- &nhmex_uncore_sbox,
- &nhmex_uncore_mbox,
- &nhmex_uncore_rbox,
- &nhmex_uncore_wbox,
- NULL,
-};
-/* end of Nehalem-EX uncore support */
-
static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
{
struct hw_perf_event *hwc = &event->hw;
@@ -3140,7 +170,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_eve
hwc->event_base = uncore_perf_ctr(box, hwc->idx);
}
-static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
+void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
{
u64 prev_count, new_count, delta;
int shift;
@@ -3201,14 +231,14 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
return HRTIMER_RESTART;
}
-static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
+void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
__hrtimer_start_range_ns(&box->hrtimer,
ns_to_ktime(box->hrtimer_duration), 0,
HRTIMER_MODE_REL_PINNED, 0);
}
-static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
+void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
{
hrtimer_cancel(&box->hrtimer);
}
@@ -3246,6 +276,17 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
return box;
}
+/*
+ * Using uncore_pmu_event_init pmu event_init callback
+ * as a detection point for uncore events.
+ */
+static int uncore_pmu_event_init(struct perf_event *event);
+
+static bool is_uncore_event(struct perf_event *event)
+{
+ return event->pmu->event_init == uncore_pmu_event_init;
+}
+
static int
uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
{
@@ -3260,13 +301,18 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, b
return -EINVAL;
n = box->n_events;
- box->event_list[n] = leader;
- n++;
+
+ if (is_uncore_event(leader)) {
+ box->event_list[n] = leader;
+ n++;
+ }
+
if (!dogrp)
return n;
list_for_each_entry(event, &leader->sibling_list, group_entry) {
- if (event->state <= PERF_EVENT_STATE_OFF)
+ if (!is_uncore_event(event) ||
+ event->state <= PERF_EVENT_STATE_OFF)
continue;
if (n >= max_count)
@@ -3291,7 +337,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
}
if (event->attr.config == UNCORE_FIXED_EVENT)
- return &constraint_fixed;
+ return &uncore_constraint_fixed;
if (type->constraints) {
for_each_event_constraint(c, type->constraints) {
@@ -3496,7 +542,7 @@ static void uncore_pmu_event_del(struct perf_event *event, int flags)
event->hw.last_tag = ~0ULL;
}
-static void uncore_pmu_event_read(struct perf_event *event)
+void uncore_pmu_event_read(struct perf_event *event)
{
struct intel_uncore_box *box = uncore_event_to_box(event);
uncore_perf_event_update(box, event);
@@ -3617,11 +663,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
static ssize_t uncore_get_attr_cpumask(struct device *dev,
struct device_attribute *attr, char *buf)
{
- int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &uncore_cpu_mask);
-
- buf[n++] = '\n';
- buf[n] = '\0';
- return n;
+ return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
@@ -3635,7 +677,7 @@ static struct attribute_group uncore_pmu_attr_group = {
.attrs = uncore_pmu_attrs,
};
-static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
+static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
{
int ret;
@@ -3758,9 +800,6 @@ fail:
return ret;
}
-static struct pci_driver *uncore_pci_driver;
-static bool pcidrv_registered;
-
/*
* add a pci uncore device
*/
@@ -3770,18 +809,20 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
struct intel_uncore_box *box;
struct intel_uncore_type *type;
int phys_id;
+ bool first_box = false;
- phys_id = pcibus_to_physid[pdev->bus->number];
+ phys_id = uncore_pcibus_to_physid[pdev->bus->number];
if (phys_id < 0)
return -ENODEV;
if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
- extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+ int idx = UNCORE_PCI_DEV_IDX(id->driver_data);
+ uncore_extra_pci_dev[phys_id][idx] = pdev;
pci_set_drvdata(pdev, NULL);
return 0;
}
- type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+ type = uncore_pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
box = uncore_alloc_box(type, NUMA_NO_NODE);
if (!box)
return -ENOMEM;
@@ -3803,9 +844,13 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
pci_set_drvdata(pdev, box);
raw_spin_lock(&uncore_box_lock);
+ if (list_empty(&pmu->box_list))
+ first_box = true;
list_add_tail(&box->list, &pmu->box_list);
raw_spin_unlock(&uncore_box_lock);
+ if (first_box)
+ uncore_pmu_register(pmu);
return 0;
}
@@ -3813,13 +858,14 @@ static void uncore_pci_remove(struct pci_dev *pdev)
{
struct intel_uncore_box *box = pci_get_drvdata(pdev);
struct intel_uncore_pmu *pmu;
- int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+ int i, cpu, phys_id = uncore_pcibus_to_physid[pdev->bus->number];
+ bool last_box = false;
box = pci_get_drvdata(pdev);
if (!box) {
for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
- if (extra_pci_dev[phys_id][i] == pdev) {
- extra_pci_dev[phys_id][i] = NULL;
+ if (uncore_extra_pci_dev[phys_id][i] == pdev) {
+ uncore_extra_pci_dev[phys_id][i] = NULL;
break;
}
}
@@ -3835,6 +881,8 @@ static void uncore_pci_remove(struct pci_dev *pdev)
raw_spin_lock(&uncore_box_lock);
list_del(&box->list);
+ if (list_empty(&pmu->box_list))
+ last_box = true;
raw_spin_unlock(&uncore_box_lock);
for_each_possible_cpu(cpu) {
@@ -3846,6 +894,9 @@ static void uncore_pci_remove(struct pci_dev *pdev)
WARN_ON_ONCE(atomic_read(&box->refcnt) != 1);
kfree(box);
+
+ if (last_box)
+ perf_pmu_unregister(&pmu->pmu);
}
static int __init uncore_pci_init(void)
@@ -3854,46 +905,32 @@ static int __init uncore_pci_init(void)
switch (boot_cpu_data.x86_model) {
case 45: /* Sandy Bridge-EP */
- ret = snbep_pci2phy_map_init(0x3ce0);
- if (ret)
- return ret;
- pci_uncores = snbep_pci_uncores;
- uncore_pci_driver = &snbep_uncore_pci_driver;
+ ret = snbep_uncore_pci_init();
break;
- case 62: /* IvyTown */
- ret = snbep_pci2phy_map_init(0x0e1e);
- if (ret)
- return ret;
- pci_uncores = ivt_pci_uncores;
- uncore_pci_driver = &ivt_uncore_pci_driver;
+ case 62: /* Ivy Bridge-EP */
+ ret = ivbep_uncore_pci_init();
+ break;
+ case 63: /* Haswell-EP */
+ ret = hswep_uncore_pci_init();
break;
case 42: /* Sandy Bridge */
- ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
- if (ret)
- return ret;
- pci_uncores = snb_pci_uncores;
- uncore_pci_driver = &snb_uncore_pci_driver;
+ ret = snb_uncore_pci_init();
break;
case 58: /* Ivy Bridge */
- ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
- if (ret)
- return ret;
- pci_uncores = snb_pci_uncores;
- uncore_pci_driver = &ivb_uncore_pci_driver;
+ ret = ivb_uncore_pci_init();
break;
case 60: /* Haswell */
case 69: /* Haswell Celeron */
- ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
- if (ret)
- return ret;
- pci_uncores = snb_pci_uncores;
- uncore_pci_driver = &hsw_uncore_pci_driver;
+ ret = hsw_uncore_pci_init();
break;
default:
return 0;
}
- ret = uncore_types_init(pci_uncores);
+ if (ret)
+ return ret;
+
+ ret = uncore_types_init(uncore_pci_uncores);
if (ret)
return ret;
@@ -3904,7 +941,7 @@ static int __init uncore_pci_init(void)
if (ret == 0)
pcidrv_registered = true;
else
- uncore_types_exit(pci_uncores);
+ uncore_types_exit(uncore_pci_uncores);
return ret;
}
@@ -3914,7 +951,7 @@ static void __init uncore_pci_exit(void)
if (pcidrv_registered) {
pcidrv_registered = false;
pci_unregister_driver(uncore_pci_driver);
- uncore_types_exit(pci_uncores);
+ uncore_types_exit(uncore_pci_uncores);
}
}
@@ -3940,8 +977,8 @@ static void uncore_cpu_dying(int cpu)
struct intel_uncore_box *box;
int i, j;
- for (i = 0; msr_uncores[i]; i++) {
- type = msr_uncores[i];
+ for (i = 0; uncore_msr_uncores[i]; i++) {
+ type = uncore_msr_uncores[i];
for (j = 0; j < type->num_boxes; j++) {
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
@@ -3961,8 +998,8 @@ static int uncore_cpu_starting(int cpu)
phys_id = topology_physical_package_id(cpu);
- for (i = 0; msr_uncores[i]; i++) {
- type = msr_uncores[i];
+ for (i = 0; uncore_msr_uncores[i]; i++) {
+ type = uncore_msr_uncores[i];
for (j = 0; j < type->num_boxes; j++) {
pmu = &type->pmus[j];
box = *per_cpu_ptr(pmu->box, cpu);
@@ -4002,8 +1039,8 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
struct intel_uncore_box *box;
int i, j;
- for (i = 0; msr_uncores[i]; i++) {
- type = msr_uncores[i];
+ for (i = 0; uncore_msr_uncores[i]; i++) {
+ type = uncore_msr_uncores[i];
for (j = 0; j < type->num_boxes; j++) {
pmu = &type->pmus[j];
if (pmu->func_id < 0)
@@ -4083,8 +1120,8 @@ static void uncore_event_exit_cpu(int cpu)
if (target >= 0)
cpumask_set_cpu(target, &uncore_cpu_mask);
- uncore_change_context(msr_uncores, cpu, target);
- uncore_change_context(pci_uncores, cpu, target);
+ uncore_change_context(uncore_msr_uncores, cpu, target);
+ uncore_change_context(uncore_pci_uncores, cpu, target);
}
static void uncore_event_init_cpu(int cpu)
@@ -4099,8 +1136,8 @@ static void uncore_event_init_cpu(int cpu)
cpumask_set_cpu(cpu, &uncore_cpu_mask);
- uncore_change_context(msr_uncores, -1, cpu);
- uncore_change_context(pci_uncores, -1, cpu);
+ uncore_change_context(uncore_msr_uncores, -1, cpu);
+ uncore_change_context(uncore_pci_uncores, -1, cpu);
}
static int uncore_cpu_notifier(struct notifier_block *self,
@@ -4160,47 +1197,37 @@ static void __init uncore_cpu_setup(void *dummy)
static int __init uncore_cpu_init(void)
{
- int ret, max_cores;
+ int ret;
- max_cores = boot_cpu_data.x86_max_cores;
switch (boot_cpu_data.x86_model) {
case 26: /* Nehalem */
case 30:
case 37: /* Westmere */
case 44:
- msr_uncores = nhm_msr_uncores;
+ nhm_uncore_cpu_init();
break;
case 42: /* Sandy Bridge */
case 58: /* Ivy Bridge */
- if (snb_uncore_cbox.num_boxes > max_cores)
- snb_uncore_cbox.num_boxes = max_cores;
- msr_uncores = snb_msr_uncores;
+ snb_uncore_cpu_init();
break;
case 45: /* Sandy Bridge-EP */
- if (snbep_uncore_cbox.num_boxes > max_cores)
- snbep_uncore_cbox.num_boxes = max_cores;
- msr_uncores = snbep_msr_uncores;
+ snbep_uncore_cpu_init();
break;
case 46: /* Nehalem-EX */
- uncore_nhmex = true;
case 47: /* Westmere-EX aka. Xeon E7 */
- if (!uncore_nhmex)
- nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
- if (nhmex_uncore_cbox.num_boxes > max_cores)
- nhmex_uncore_cbox.num_boxes = max_cores;
- msr_uncores = nhmex_msr_uncores;
+ nhmex_uncore_cpu_init();
break;
- case 62: /* IvyTown */
- if (ivt_uncore_cbox.num_boxes > max_cores)
- ivt_uncore_cbox.num_boxes = max_cores;
- msr_uncores = ivt_msr_uncores;
+ case 62: /* Ivy Bridge-EP */
+ ivbep_uncore_cpu_init();
+ break;
+ case 63: /* Haswell-EP */
+ hswep_uncore_cpu_init();
break;
-
default:
return 0;
}
- ret = uncore_types_init(msr_uncores);
+ ret = uncore_types_init(uncore_msr_uncores);
if (ret)
return ret;
@@ -4213,16 +1240,8 @@ static int __init uncore_pmus_register(void)
struct intel_uncore_type *type;
int i, j;
- for (i = 0; msr_uncores[i]; i++) {
- type = msr_uncores[i];
- for (j = 0; j < type->num_boxes; j++) {
- pmu = &type->pmus[j];
- uncore_pmu_register(pmu);
- }
- }
-
- for (i = 0; pci_uncores[i]; i++) {
- type = pci_uncores[i];
+ for (i = 0; uncore_msr_uncores[i]; i++) {
+ type = uncore_msr_uncores[i];
for (j = 0; j < type->num_boxes; j++) {
pmu = &type->pmus[j];
uncore_pmu_register(pmu);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 90236f0c94a9..863d9b02563e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,402 +17,13 @@
#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff)
#define UNCORE_PCI_DEV_IDX(data) (data & 0xff)
#define UNCORE_EXTRA_PCI_DEV 0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX 2
+#define UNCORE_EXTRA_PCI_DEV_MAX 3
/* support up to 8 sockets */
#define UNCORE_SOCKET_MAX 8
#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
-/* SNB event control */
-#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
-#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
-#define SNB_UNC_CTL_EDGE_DET (1 << 18)
-#define SNB_UNC_CTL_EN (1 << 22)
-#define SNB_UNC_CTL_INVERT (1 << 23)
-#define SNB_UNC_CTL_CMASK_MASK 0x1f000000
-#define NHM_UNC_CTL_CMASK_MASK 0xff000000
-#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0)
-
-#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
- SNB_UNC_CTL_UMASK_MASK | \
- SNB_UNC_CTL_EDGE_DET | \
- SNB_UNC_CTL_INVERT | \
- SNB_UNC_CTL_CMASK_MASK)
-
-#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
- SNB_UNC_CTL_UMASK_MASK | \
- SNB_UNC_CTL_EDGE_DET | \
- SNB_UNC_CTL_INVERT | \
- NHM_UNC_CTL_CMASK_MASK)
-
-/* SNB global control register */
-#define SNB_UNC_PERF_GLOBAL_CTL 0x391
-#define SNB_UNC_FIXED_CTR_CTRL 0x394
-#define SNB_UNC_FIXED_CTR 0x395
-
-/* SNB uncore global control */
-#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1)
-#define SNB_UNC_GLOBAL_CTL_EN (1 << 29)
-
-/* SNB Cbo register */
-#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700
-#define SNB_UNC_CBO_0_PER_CTR0 0x706
-#define SNB_UNC_CBO_MSR_OFFSET 0x10
-
-/* NHM global control register */
-#define NHM_UNC_PERF_GLOBAL_CTL 0x391
-#define NHM_UNC_FIXED_CTR 0x394
-#define NHM_UNC_FIXED_CTR_CTRL 0x395
-
-/* NHM uncore global control */
-#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1)
-#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32)
-
-/* NHM uncore register */
-#define NHM_UNC_PERFEVTSEL0 0x3c0
-#define NHM_UNC_UNCORE_PMC0 0x3b0
-
-/* SNB-EP Box level control */
-#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0)
-#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1)
-#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8)
-#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16)
-#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \
- SNBEP_PMON_BOX_CTL_RST_CTRS | \
- SNBEP_PMON_BOX_CTL_FRZ_EN)
-/* SNB-EP event control */
-#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff
-#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00
-#define SNBEP_PMON_CTL_RST (1 << 17)
-#define SNBEP_PMON_CTL_EDGE_DET (1 << 18)
-#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21)
-#define SNBEP_PMON_CTL_EN (1 << 22)
-#define SNBEP_PMON_CTL_INVERT (1 << 23)
-#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000
-#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
- SNBEP_PMON_CTL_UMASK_MASK | \
- SNBEP_PMON_CTL_EDGE_DET | \
- SNBEP_PMON_CTL_INVERT | \
- SNBEP_PMON_CTL_TRESH_MASK)
-
-/* SNB-EP Ubox event control */
-#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000
-#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \
- (SNBEP_PMON_CTL_EV_SEL_MASK | \
- SNBEP_PMON_CTL_UMASK_MASK | \
- SNBEP_PMON_CTL_EDGE_DET | \
- SNBEP_PMON_CTL_INVERT | \
- SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
-
-#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19)
-#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
- SNBEP_CBO_PMON_CTL_TID_EN)
-
-/* SNB-EP PCU event control */
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000
-#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30)
-#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31)
-#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \
- (SNBEP_PMON_CTL_EV_SEL_MASK | \
- SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
- SNBEP_PMON_CTL_EDGE_DET | \
- SNBEP_PMON_CTL_EV_SEL_EXT | \
- SNBEP_PMON_CTL_INVERT | \
- SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
- SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
- SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
-
-#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \
- (SNBEP_PMON_RAW_EVENT_MASK | \
- SNBEP_PMON_CTL_EV_SEL_EXT)
-
-/* SNB-EP pci control register */
-#define SNBEP_PCI_PMON_BOX_CTL 0xf4
-#define SNBEP_PCI_PMON_CTL0 0xd8
-/* SNB-EP pci counter register */
-#define SNBEP_PCI_PMON_CTR0 0xa0
-
-/* SNB-EP home agent register */
-#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40
-#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44
-#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48
-/* SNB-EP memory controller register */
-#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0
-#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0
-/* SNB-EP QPI register */
-#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228
-#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c
-#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238
-#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c
-
-/* SNB-EP Ubox register */
-#define SNBEP_U_MSR_PMON_CTR0 0xc16
-#define SNBEP_U_MSR_PMON_CTL0 0xc10
-
-#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08
-#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09
-
-/* SNB-EP Cbo register */
-#define SNBEP_C0_MSR_PMON_CTR0 0xd16
-#define SNBEP_C0_MSR_PMON_CTL0 0xd10
-#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04
-#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14
-#define SNBEP_CBO_MSR_OFFSET 0x20
-
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000
-#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000
-
-#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \
- .event = (e), \
- .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \
- .config_mask = (m), \
- .idx = (i) \
-}
-
-/* SNB-EP PCU register */
-#define SNBEP_PCU_MSR_PMON_CTR0 0xc36
-#define SNBEP_PCU_MSR_PMON_CTL0 0xc30
-#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24
-#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34
-#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff
-#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc
-#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd
-
-/* IVT event control */
-#define IVT_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \
- SNBEP_PMON_BOX_CTL_RST_CTRS)
-#define IVT_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
- SNBEP_PMON_CTL_UMASK_MASK | \
- SNBEP_PMON_CTL_EDGE_DET | \
- SNBEP_PMON_CTL_TRESH_MASK)
-/* IVT Ubox */
-#define IVT_U_MSR_PMON_GLOBAL_CTL 0xc00
-#define IVT_U_PMON_GLOBAL_FRZ_ALL (1 << 31)
-#define IVT_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29)
-
-#define IVT_U_MSR_PMON_RAW_EVENT_MASK \
- (SNBEP_PMON_CTL_EV_SEL_MASK | \
- SNBEP_PMON_CTL_UMASK_MASK | \
- SNBEP_PMON_CTL_EDGE_DET | \
- SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
-/* IVT Cbo */
-#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK (IVT_PMON_RAW_EVENT_MASK | \
- SNBEP_CBO_PMON_CTL_TID_EN)
-
-#define IVT_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62)
-#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC (0x1ULL << 63)
-
-/* IVT home agent */
-#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16)
-#define IVT_HA_PCI_PMON_RAW_EVENT_MASK \
- (IVT_PMON_RAW_EVENT_MASK | \
- IVT_HA_PCI_PMON_CTL_Q_OCC_RST)
-/* IVT PCU */
-#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \
- (SNBEP_PMON_CTL_EV_SEL_MASK | \
- SNBEP_PMON_CTL_EV_SEL_EXT | \
- SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
- SNBEP_PMON_CTL_EDGE_DET | \
- SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
- SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
- SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
-/* IVT QPI */
-#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \
- (IVT_PMON_RAW_EVENT_MASK | \
- SNBEP_PMON_CTL_EV_SEL_EXT)
-
-/* NHM-EX event control */
-#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff
-#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00
-#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0)
-#define NHMEX_PMON_CTL_EDGE_DET (1 << 18)
-#define NHMEX_PMON_CTL_PMI_EN (1 << 20)
-#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22)
-#define NHMEX_PMON_CTL_INVERT (1 << 23)
-#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000
-#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \
- NHMEX_PMON_CTL_UMASK_MASK | \
- NHMEX_PMON_CTL_EDGE_DET | \
- NHMEX_PMON_CTL_INVERT | \
- NHMEX_PMON_CTL_TRESH_MASK)
-
-/* NHM-EX Ubox */
-#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00
-#define NHMEX_U_MSR_PMON_CTR 0xc11
-#define NHMEX_U_MSR_PMON_EV_SEL 0xc10
-
-#define NHMEX_U_PMON_GLOBAL_EN (1 << 0)
-#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e
-#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28)
-#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29)
-#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31)
-
-#define NHMEX_U_PMON_RAW_EVENT_MASK \
- (NHMEX_PMON_CTL_EV_SEL_MASK | \
- NHMEX_PMON_CTL_EDGE_DET)
-
-/* NHM-EX Cbox */
-#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00
-#define NHMEX_C0_MSR_PMON_CTR0 0xd11
-#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10
-#define NHMEX_C_MSR_OFFSET 0x20
-
-/* NHM-EX Bbox */
-#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20
-#define NHMEX_B0_MSR_PMON_CTR0 0xc31
-#define NHMEX_B0_MSR_PMON_CTL0 0xc30
-#define NHMEX_B_MSR_OFFSET 0x40
-#define NHMEX_B0_MSR_MATCH 0xe45
-#define NHMEX_B0_MSR_MASK 0xe46
-#define NHMEX_B1_MSR_MATCH 0xe4d
-#define NHMEX_B1_MSR_MASK 0xe4e
-
-#define NHMEX_B_PMON_CTL_EN (1 << 0)
-#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1
-#define NHMEX_B_PMON_CTL_EV_SEL_MASK \
- (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
-#define NHMEX_B_PMON_CTR_SHIFT 6
-#define NHMEX_B_PMON_CTR_MASK \
- (0x3 << NHMEX_B_PMON_CTR_SHIFT)
-#define NHMEX_B_PMON_RAW_EVENT_MASK \
- (NHMEX_B_PMON_CTL_EV_SEL_MASK | \
- NHMEX_B_PMON_CTR_MASK)
-
-/* NHM-EX Sbox */
-#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40
-#define NHMEX_S0_MSR_PMON_CTR0 0xc51
-#define NHMEX_S0_MSR_PMON_CTL0 0xc50
-#define NHMEX_S_MSR_OFFSET 0x80
-#define NHMEX_S0_MSR_MM_CFG 0xe48
-#define NHMEX_S0_MSR_MATCH 0xe49
-#define NHMEX_S0_MSR_MASK 0xe4a
-#define NHMEX_S1_MSR_MM_CFG 0xe58
-#define NHMEX_S1_MSR_MATCH 0xe59
-#define NHMEX_S1_MSR_MASK 0xe5a
-
-#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63)
-#define NHMEX_S_EVENT_TO_R_PROG_EV 0
-
-/* NHM-EX Mbox */
-#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0
-#define NHMEX_M0_MSR_PMU_DSP 0xca5
-#define NHMEX_M0_MSR_PMU_ISS 0xca6
-#define NHMEX_M0_MSR_PMU_MAP 0xca7
-#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8
-#define NHMEX_M0_MSR_PMU_PGT 0xca9
-#define NHMEX_M0_MSR_PMU_PLD 0xcaa
-#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab
-#define NHMEX_M0_MSR_PMU_CTL0 0xcb0
-#define NHMEX_M0_MSR_PMU_CNT0 0xcb1
-#define NHMEX_M_MSR_OFFSET 0x40
-#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54
-#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c
-
-#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63)
-#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL
-#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL
-#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34
-
-#define NHMEX_M_PMON_CTL_EN (1 << 0)
-#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1)
-#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2
-#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \
- (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
-#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4
-#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \
- (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
-#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6)
-#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7)
-#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9
-#define NHMEX_M_PMON_CTL_INC_SEL_MASK \
- (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
-#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19
-#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \
- (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
-#define NHMEX_M_PMON_RAW_EVENT_MASK \
- (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \
- NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \
- NHMEX_M_PMON_CTL_WRAP_MODE | \
- NHMEX_M_PMON_CTL_FLAG_MODE | \
- NHMEX_M_PMON_CTL_INC_SEL_MASK | \
- NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
-
-#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23))
-#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n)))
-
-#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24))
-#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n)))
-
-/*
- * use the 9~13 bits to select event If the 7th bit is not set,
- * otherwise use the 19~21 bits to select event.
- */
-#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
-#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
- NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
- NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
- NHMEX_M_PMON_CTL_FLAG_MODE)
-#define MBOX_INC_SEL_EXTAR_REG(c, r) \
- EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
- MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
-#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
- EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
- MBOX_SET_FLAG_SEL_MASK, \
- (u64)-1, NHMEX_M_##r)
-
-/* NHM-EX Rbox */
-#define NHMEX_R_MSR_GLOBAL_CTL 0xe00
-#define NHMEX_R_MSR_PMON_CTL0 0xe10
-#define NHMEX_R_MSR_PMON_CNT0 0xe11
-#define NHMEX_R_MSR_OFFSET 0x20
-
-#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \
- ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
-#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n))
-#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n))
-#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \
- (((n) < 4 ? 0 : 0x10) + (n) * 4)
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \
- (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \
- (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
-#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \
- (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \
- (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \
- (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
-#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \
- (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
-
-#define NHMEX_R_PMON_CTL_EN (1 << 0)
-#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1
-#define NHMEX_R_PMON_CTL_EV_SEL_MASK \
- (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
-#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6)
-#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK
-
-/* NHM-EX Wbox */
-#define NHMEX_W_MSR_GLOBAL_CTL 0xc80
-#define NHMEX_W_MSR_PMON_CNT0 0xc90
-#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91
-#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394
-#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395
-
-#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31)
-
struct intel_uncore_ops;
struct intel_uncore_pmu;
struct intel_uncore_box;
@@ -505,6 +116,9 @@ struct uncore_event_desc {
const char *config;
};
+ssize_t uncore_event_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf);
+
#define INTEL_UNCORE_EVENT_DESC(_name, _config) \
{ \
.attr = __ATTR(_name, 0444, uncore_event_show, NULL), \
@@ -522,15 +136,6 @@ static ssize_t __uncore_##_var##_show(struct kobject *kobj, \
static struct kobj_attribute format_attr_##_var = \
__ATTR(_name, 0444, __uncore_##_var##_show, NULL)
-
-static ssize_t uncore_event_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct uncore_event_desc *event =
- container_of(attr, struct uncore_event_desc, attr);
- return sprintf(buf, "%s", event->config);
-}
-
static inline unsigned uncore_pci_box_ctl(struct intel_uncore_box *box)
{
return box->pmu->type->box_ctl;
@@ -694,3 +299,41 @@ static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
{
return (box->phys_id < 0);
}
+
+struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event);
+struct intel_uncore_box *uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu);
+struct intel_uncore_box *uncore_event_to_box(struct perf_event *event);
+u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+void uncore_pmu_event_read(struct perf_event *event);
+void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+struct event_constraint *
+uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event);
+void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event);
+u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx);
+
+extern struct intel_uncore_type **uncore_msr_uncores;
+extern struct intel_uncore_type **uncore_pci_uncores;
+extern struct pci_driver *uncore_pci_driver;
+extern int uncore_pcibus_to_physid[256];
+extern struct pci_dev *uncore_extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+extern struct event_constraint uncore_constraint_empty;
+
+/* perf_event_intel_uncore_snb.c */
+int snb_uncore_pci_init(void);
+int ivb_uncore_pci_init(void);
+int hsw_uncore_pci_init(void);
+void snb_uncore_cpu_init(void);
+void nhm_uncore_cpu_init(void);
+
+/* perf_event_intel_uncore_snbep.c */
+int snbep_uncore_pci_init(void);
+void snbep_uncore_cpu_init(void);
+int ivbep_uncore_pci_init(void);
+void ivbep_uncore_cpu_init(void);
+int hswep_uncore_pci_init(void);
+void hswep_uncore_cpu_init(void);
+
+/* perf_event_intel_uncore_nhmex.c */
+void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
new file mode 100644
index 000000000000..2749965afed0
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_nhmex.c
@@ -0,0 +1,1221 @@
+/* Nehalem-EX/Westmere-EX uncore support */
+#include "perf_event_intel_uncore.h"
+
+/* NHM-EX event control */
+#define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff
+#define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00
+#define NHMEX_PMON_CTL_EN_BIT0 (1 << 0)
+#define NHMEX_PMON_CTL_EDGE_DET (1 << 18)
+#define NHMEX_PMON_CTL_PMI_EN (1 << 20)
+#define NHMEX_PMON_CTL_EN_BIT22 (1 << 22)
+#define NHMEX_PMON_CTL_INVERT (1 << 23)
+#define NHMEX_PMON_CTL_TRESH_MASK 0xff000000
+#define NHMEX_PMON_RAW_EVENT_MASK (NHMEX_PMON_CTL_EV_SEL_MASK | \
+ NHMEX_PMON_CTL_UMASK_MASK | \
+ NHMEX_PMON_CTL_EDGE_DET | \
+ NHMEX_PMON_CTL_INVERT | \
+ NHMEX_PMON_CTL_TRESH_MASK)
+
+/* NHM-EX Ubox */
+#define NHMEX_U_MSR_PMON_GLOBAL_CTL 0xc00
+#define NHMEX_U_MSR_PMON_CTR 0xc11
+#define NHMEX_U_MSR_PMON_EV_SEL 0xc10
+
+#define NHMEX_U_PMON_GLOBAL_EN (1 << 0)
+#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL 0x0000001e
+#define NHMEX_U_PMON_GLOBAL_EN_ALL (1 << 28)
+#define NHMEX_U_PMON_GLOBAL_RST_ALL (1 << 29)
+#define NHMEX_U_PMON_GLOBAL_FRZ_ALL (1 << 31)
+
+#define NHMEX_U_PMON_RAW_EVENT_MASK \
+ (NHMEX_PMON_CTL_EV_SEL_MASK | \
+ NHMEX_PMON_CTL_EDGE_DET)
+
+/* NHM-EX Cbox */
+#define NHMEX_C0_MSR_PMON_GLOBAL_CTL 0xd00
+#define NHMEX_C0_MSR_PMON_CTR0 0xd11
+#define NHMEX_C0_MSR_PMON_EV_SEL0 0xd10
+#define NHMEX_C_MSR_OFFSET 0x20
+
+/* NHM-EX Bbox */
+#define NHMEX_B0_MSR_PMON_GLOBAL_CTL 0xc20
+#define NHMEX_B0_MSR_PMON_CTR0 0xc31
+#define NHMEX_B0_MSR_PMON_CTL0 0xc30
+#define NHMEX_B_MSR_OFFSET 0x40
+#define NHMEX_B0_MSR_MATCH 0xe45
+#define NHMEX_B0_MSR_MASK 0xe46
+#define NHMEX_B1_MSR_MATCH 0xe4d
+#define NHMEX_B1_MSR_MASK 0xe4e
+
+#define NHMEX_B_PMON_CTL_EN (1 << 0)
+#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT 1
+#define NHMEX_B_PMON_CTL_EV_SEL_MASK \
+ (0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_B_PMON_CTR_SHIFT 6
+#define NHMEX_B_PMON_CTR_MASK \
+ (0x3 << NHMEX_B_PMON_CTR_SHIFT)
+#define NHMEX_B_PMON_RAW_EVENT_MASK \
+ (NHMEX_B_PMON_CTL_EV_SEL_MASK | \
+ NHMEX_B_PMON_CTR_MASK)
+
+/* NHM-EX Sbox */
+#define NHMEX_S0_MSR_PMON_GLOBAL_CTL 0xc40
+#define NHMEX_S0_MSR_PMON_CTR0 0xc51
+#define NHMEX_S0_MSR_PMON_CTL0 0xc50
+#define NHMEX_S_MSR_OFFSET 0x80
+#define NHMEX_S0_MSR_MM_CFG 0xe48
+#define NHMEX_S0_MSR_MATCH 0xe49
+#define NHMEX_S0_MSR_MASK 0xe4a
+#define NHMEX_S1_MSR_MM_CFG 0xe58
+#define NHMEX_S1_MSR_MATCH 0xe59
+#define NHMEX_S1_MSR_MASK 0xe5a
+
+#define NHMEX_S_PMON_MM_CFG_EN (0x1ULL << 63)
+#define NHMEX_S_EVENT_TO_R_PROG_EV 0
+
+/* NHM-EX Mbox */
+#define NHMEX_M0_MSR_GLOBAL_CTL 0xca0
+#define NHMEX_M0_MSR_PMU_DSP 0xca5
+#define NHMEX_M0_MSR_PMU_ISS 0xca6
+#define NHMEX_M0_MSR_PMU_MAP 0xca7
+#define NHMEX_M0_MSR_PMU_MSC_THR 0xca8
+#define NHMEX_M0_MSR_PMU_PGT 0xca9
+#define NHMEX_M0_MSR_PMU_PLD 0xcaa
+#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC 0xcab
+#define NHMEX_M0_MSR_PMU_CTL0 0xcb0
+#define NHMEX_M0_MSR_PMU_CNT0 0xcb1
+#define NHMEX_M_MSR_OFFSET 0x40
+#define NHMEX_M0_MSR_PMU_MM_CFG 0xe54
+#define NHMEX_M1_MSR_PMU_MM_CFG 0xe5c
+
+#define NHMEX_M_PMON_MM_CFG_EN (1ULL << 63)
+#define NHMEX_M_PMON_ADDR_MATCH_MASK 0x3ffffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_MASK 0x7ffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_SHIFT 34
+
+#define NHMEX_M_PMON_CTL_EN (1 << 0)
+#define NHMEX_M_PMON_CTL_PMI_EN (1 << 1)
+#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT 2
+#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK \
+ (0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT 4
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK \
+ (0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_WRAP_MODE (1 << 6)
+#define NHMEX_M_PMON_CTL_FLAG_MODE (1 << 7)
+#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT 9
+#define NHMEX_M_PMON_CTL_INC_SEL_MASK \
+ (0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT 19
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK \
+ (0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
+#define NHMEX_M_PMON_RAW_EVENT_MASK \
+ (NHMEX_M_PMON_CTL_COUNT_MODE_MASK | \
+ NHMEX_M_PMON_CTL_STORAGE_MODE_MASK | \
+ NHMEX_M_PMON_CTL_WRAP_MODE | \
+ NHMEX_M_PMON_CTL_FLAG_MODE | \
+ NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+ NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
+
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 11) - 1) | (1 << 23))
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (11 + 3 * (n)))
+
+#define WSMEX_M_PMON_ZDP_CTL_FVC_MASK (((1 << 12) - 1) | (1 << 24))
+#define WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n) (0x7ULL << (12 + 3 * (n)))
+
+/*
+ * use the 9~13 bits to select event If the 7th bit is not set,
+ * otherwise use the 19~21 bits to select event.
+ */
+#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
+ NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+ NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
+ NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_EXTAR_REG(c, r) \
+ EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+ MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
+#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
+ EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+ MBOX_SET_FLAG_SEL_MASK, \
+ (u64)-1, NHMEX_M_##r)
+
+/* NHM-EX Rbox */
+#define NHMEX_R_MSR_GLOBAL_CTL 0xe00
+#define NHMEX_R_MSR_PMON_CTL0 0xe10
+#define NHMEX_R_MSR_PMON_CNT0 0xe11
+#define NHMEX_R_MSR_OFFSET 0x20
+
+#define NHMEX_R_MSR_PORTN_QLX_CFG(n) \
+ ((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n) (0xe04 + (n))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n) (0xe24 + (n))
+#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n) \
+ (((n) < 4 ? 0 : 0x10) + (n) * 4)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) \
+ (0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) \
+ (0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n) \
+ (NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
+
+#define NHMEX_R_PMON_CTL_EN (1 << 0)
+#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT 1
+#define NHMEX_R_PMON_CTL_EV_SEL_MASK \
+ (0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_R_PMON_CTL_PMI_EN (1 << 6)
+#define NHMEX_R_PMON_RAW_EVENT_MASK NHMEX_R_PMON_CTL_EV_SEL_MASK
+
+/* NHM-EX Wbox */
+#define NHMEX_W_MSR_GLOBAL_CTL 0xc80
+#define NHMEX_W_MSR_PMON_CNT0 0xc90
+#define NHMEX_W_MSR_PMON_EVT_SEL0 0xc91
+#define NHMEX_W_MSR_PMON_FIXED_CTR 0x394
+#define NHMEX_W_MSR_PMON_FIXED_CTL 0x395
+
+#define NHMEX_W_PMON_GLOBAL_FIXED_EN (1ULL << 31)
+
+#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \
+ ((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
+DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
+
+static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+}
+
+static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+ u64 config;
+
+ if (msr) {
+ rdmsrl(msr, config);
+ config &= ~((1ULL << uncore_num_counters(box)) - 1);
+ /* WBox has a fixed counter */
+ if (uncore_msr_fixed_ctl(box))
+ config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
+ wrmsrl(msr, config);
+ }
+}
+
+static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+ u64 config;
+
+ if (msr) {
+ rdmsrl(msr, config);
+ config |= (1ULL << uncore_num_counters(box)) - 1;
+ /* WBox has a fixed counter */
+ if (uncore_msr_fixed_ctl(box))
+ config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
+ wrmsrl(msr, config);
+ }
+}
+
+static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ wrmsrl(event->hw.config_base, 0);
+}
+
+static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+ else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+ else
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+#define NHMEX_UNCORE_OPS_COMMON_INIT() \
+ .init_box = nhmex_uncore_msr_init_box, \
+ .disable_box = nhmex_uncore_msr_disable_box, \
+ .enable_box = nhmex_uncore_msr_enable_box, \
+ .disable_event = nhmex_uncore_msr_disable_event, \
+ .read_counter = uncore_msr_read_counter
+
+static struct intel_uncore_ops nhmex_uncore_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_uncore_msr_enable_event,
+};
+
+static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_edge.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 1,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_U_MSR_PMON_EV_SEL,
+ .perf_ctr = NHMEX_U_MSR_PMON_CTR,
+ .event_mask = NHMEX_U_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_U_MSR_PMON_GLOBAL_CTL,
+ .ops = &nhmex_uncore_ops,
+ .format_group = &nhmex_uncore_ubox_format_group
+};
+
+static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_cbox_formats_attr,
+};
+
+/* msr offset for each instance of cbox */
+static unsigned nhmex_cbox_msr_offsets[] = {
+ 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0,
+};
+
+static struct intel_uncore_type nhmex_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 6,
+ .num_boxes = 10,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_C0_MSR_PMON_EV_SEL0,
+ .perf_ctr = NHMEX_C0_MSR_PMON_CTR0,
+ .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_C0_MSR_PMON_GLOBAL_CTL,
+ .msr_offsets = nhmex_cbox_msr_offsets,
+ .pair_ctr_ctl = 1,
+ .ops = &nhmex_uncore_ops,
+ .format_group = &nhmex_uncore_cbox_format_group
+};
+
+static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type nhmex_uncore_wbox = {
+ .name = "wbox",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_W_MSR_PMON_CNT0,
+ .perf_ctr = NHMEX_W_MSR_PMON_EVT_SEL0,
+ .fixed_ctr = NHMEX_W_MSR_PMON_FIXED_CTR,
+ .fixed_ctl = NHMEX_W_MSR_PMON_FIXED_CTL,
+ .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_W_MSR_GLOBAL_CTL,
+ .pair_ctr_ctl = 1,
+ .event_descs = nhmex_uncore_wbox_events,
+ .ops = &nhmex_uncore_ops,
+ .format_group = &nhmex_uncore_cbox_format_group
+};
+
+static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ int ctr, ev_sel;
+
+ ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
+ NHMEX_B_PMON_CTR_SHIFT;
+ ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
+ NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
+
+ /* events that do not use the match/mask registers */
+ if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
+ (ctr == 2 && ev_sel != 0x4) || ctr == 3)
+ return 0;
+
+ if (box->pmu->pmu_idx == 0)
+ reg1->reg = NHMEX_B0_MSR_MATCH;
+ else
+ reg1->reg = NHMEX_B1_MSR_MATCH;
+ reg1->idx = 0;
+ reg1->config = event->attr.config1;
+ reg2->config = event->attr.config2;
+ return 0;
+}
+
+static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ wrmsrl(reg1->reg, reg1->config);
+ wrmsrl(reg1->reg + 1, reg2->config);
+ }
+ wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+ (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
+}
+
+/*
+ * The Bbox has 4 counters, but each counter monitors different events.
+ * Use bits 6-7 in the event config to select counter.
+ */
+static struct event_constraint nhmex_uncore_bbox_constraints[] = {
+ EVENT_CONSTRAINT(0 , 1, 0xc0),
+ EVENT_CONSTRAINT(0x40, 2, 0xc0),
+ EVENT_CONSTRAINT(0x80, 4, 0xc0),
+ EVENT_CONSTRAINT(0xc0, 8, 0xc0),
+ EVENT_CONSTRAINT_END,
+};
+
+static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
+ &format_attr_event5.attr,
+ &format_attr_counter.attr,
+ &format_attr_match.attr,
+ &format_attr_mask.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_bbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_bbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_bbox_msr_enable_event,
+ .hw_config = nhmex_bbox_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_bbox = {
+ .name = "bbox",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_B0_MSR_PMON_CTL0,
+ .perf_ctr = NHMEX_B0_MSR_PMON_CTR0,
+ .event_mask = NHMEX_B_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_B0_MSR_PMON_GLOBAL_CTL,
+ .msr_offset = NHMEX_B_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 1,
+ .constraints = nhmex_uncore_bbox_constraints,
+ .ops = &nhmex_uncore_bbox_ops,
+ .format_group = &nhmex_uncore_bbox_format_group
+};
+
+static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ /* only TO_R_PROG_EV event uses the match/mask register */
+ if ((hwc->config & NHMEX_PMON_CTL_EV_SEL_MASK) !=
+ NHMEX_S_EVENT_TO_R_PROG_EV)
+ return 0;
+
+ if (box->pmu->pmu_idx == 0)
+ reg1->reg = NHMEX_S0_MSR_MM_CFG;
+ else
+ reg1->reg = NHMEX_S1_MSR_MM_CFG;
+ reg1->idx = 0;
+ reg1->config = event->attr.config1;
+ reg2->config = event->attr.config2;
+ return 0;
+}
+
+static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ wrmsrl(reg1->reg, 0);
+ wrmsrl(reg1->reg + 1, reg1->config);
+ wrmsrl(reg1->reg + 2, reg2->config);
+ wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+ }
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+}
+
+static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_match.attr,
+ &format_attr_mask.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_sbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_sbox_msr_enable_event,
+ .hw_config = nhmex_sbox_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_sbox = {
+ .name = "sbox",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_S0_MSR_PMON_CTL0,
+ .perf_ctr = NHMEX_S0_MSR_PMON_CTR0,
+ .event_mask = NHMEX_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_S0_MSR_PMON_GLOBAL_CTL,
+ .msr_offset = NHMEX_S_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 1,
+ .ops = &nhmex_uncore_sbox_ops,
+ .format_group = &nhmex_uncore_sbox_format_group
+};
+
+enum {
+ EXTRA_REG_NHMEX_M_FILTER,
+ EXTRA_REG_NHMEX_M_DSP,
+ EXTRA_REG_NHMEX_M_ISS,
+ EXTRA_REG_NHMEX_M_MAP,
+ EXTRA_REG_NHMEX_M_MSC_THR,
+ EXTRA_REG_NHMEX_M_PGT,
+ EXTRA_REG_NHMEX_M_PLD,
+ EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
+};
+
+static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
+ MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
+ MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
+ MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
+ MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
+ /* event 0xa uses two extra registers */
+ MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
+ MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
+ MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
+ /* events 0xd ~ 0x10 use the same extra register */
+ MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
+ MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
+ MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
+ EVENT_EXTRA_END
+};
+
+/* Nehalem-EX or Westmere-EX ? */
+static bool uncore_nhmex;
+
+static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
+{
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ bool ret = false;
+ u64 mask;
+
+ if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+ er = &box->shared_regs[idx];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (!atomic_read(&er->ref) || er->config == config) {
+ atomic_inc(&er->ref);
+ er->config = config;
+ ret = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ return ret;
+ }
+ /*
+ * The ZDP_CTL_FVC MSR has 4 fields which are used to control
+ * events 0xd ~ 0x10. Besides these 4 fields, there are additional
+ * fields which are shared.
+ */
+ idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ if (WARN_ON_ONCE(idx >= 4))
+ return false;
+
+ /* mask of the shared fields */
+ if (uncore_nhmex)
+ mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+ else
+ mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK;
+ er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+
+ raw_spin_lock_irqsave(&er->lock, flags);
+ /* add mask of the non-shared field if it's in use */
+ if (__BITS_VALUE(atomic_read(&er->ref), idx, 8)) {
+ if (uncore_nhmex)
+ mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ else
+ mask |= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ }
+
+ if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
+ atomic_add(1 << (idx * 8), &er->ref);
+ if (uncore_nhmex)
+ mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+ NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ else
+ mask = WSMEX_M_PMON_ZDP_CTL_FVC_MASK |
+ WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ er->config &= ~mask;
+ er->config |= (config & mask);
+ ret = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ return ret;
+}
+
+static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
+{
+ struct intel_uncore_extra_reg *er;
+
+ if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+ er = &box->shared_regs[idx];
+ atomic_dec(&er->ref);
+ return;
+ }
+
+ idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+ atomic_sub(1 << (idx * 8), &er->ref);
+}
+
+static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ u64 idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+ u64 config = reg1->config;
+
+ /* get the non-shared control bits and shift them */
+ idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ if (uncore_nhmex)
+ config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ else
+ config &= WSMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+ if (new_idx > orig_idx) {
+ idx = new_idx - orig_idx;
+ config <<= 3 * idx;
+ } else {
+ idx = orig_idx - new_idx;
+ config >>= 3 * idx;
+ }
+
+ /* add the shared control bits back */
+ if (uncore_nhmex)
+ config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+ else
+ config |= WSMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+ config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+ if (modify) {
+ /* adjust the main event selector */
+ if (new_idx > orig_idx)
+ hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+ else
+ hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+ reg1->config = config;
+ reg1->idx = ~0xff | new_idx;
+ }
+ return config;
+}
+
+static struct event_constraint *
+nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ int i, idx[2], alloc = 0;
+ u64 config1 = reg1->config;
+
+ idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
+ idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
+again:
+ for (i = 0; i < 2; i++) {
+ if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+ idx[i] = 0xff;
+
+ if (idx[i] == 0xff)
+ continue;
+
+ if (!nhmex_mbox_get_shared_reg(box, idx[i],
+ __BITS_VALUE(config1, i, 32)))
+ goto fail;
+ alloc |= (0x1 << i);
+ }
+
+ /* for the match/mask registers */
+ if (reg2->idx != EXTRA_REG_NONE &&
+ (uncore_box_is_fake(box) || !reg2->alloc) &&
+ !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
+ goto fail;
+
+ /*
+ * If it's a fake box -- as per validate_{group,event}() we
+ * shouldn't touch event state and we can avoid doing so
+ * since both will only call get_event_constraints() once
+ * on each event, this avoids the need for reg->alloc.
+ */
+ if (!uncore_box_is_fake(box)) {
+ if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
+ nhmex_mbox_alter_er(event, idx[0], true);
+ reg1->alloc |= alloc;
+ if (reg2->idx != EXTRA_REG_NONE)
+ reg2->alloc = 1;
+ }
+ return NULL;
+fail:
+ if (idx[0] != 0xff && !(alloc & 0x1) &&
+ idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+ /*
+ * events 0xd ~ 0x10 are functional identical, but are
+ * controlled by different fields in the ZDP_CTL_FVC
+ * register. If we failed to take one field, try the
+ * rest 3 choices.
+ */
+ BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
+ idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ idx[0] = (idx[0] + 1) % 4;
+ idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+ if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
+ config1 = nhmex_mbox_alter_er(event, idx[0], false);
+ goto again;
+ }
+ }
+
+ if (alloc & 0x1)
+ nhmex_mbox_put_shared_reg(box, idx[0]);
+ if (alloc & 0x2)
+ nhmex_mbox_put_shared_reg(box, idx[1]);
+ return &uncore_constraint_empty;
+}
+
+static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+ if (uncore_box_is_fake(box))
+ return;
+
+ if (reg1->alloc & 0x1)
+ nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
+ if (reg1->alloc & 0x2)
+ nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
+ reg1->alloc = 0;
+
+ if (reg2->alloc) {
+ nhmex_mbox_put_shared_reg(box, reg2->idx);
+ reg2->alloc = 0;
+ }
+}
+
+static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
+{
+ if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+ return er->idx;
+ return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
+}
+
+static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_type *type = box->pmu->type;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ struct extra_reg *er;
+ unsigned msr;
+ int reg_idx = 0;
+ /*
+ * The mbox events may require 2 extra MSRs at the most. But only
+ * the lower 32 bits in these MSRs are significant, so we can use
+ * config1 to pass two MSRs' config.
+ */
+ for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
+ if (er->event != (event->hw.config & er->config_mask))
+ continue;
+ if (event->attr.config1 & ~er->valid_mask)
+ return -EINVAL;
+
+ msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
+ if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
+ return -EINVAL;
+
+ /* always use the 32~63 bits to pass the PLD config */
+ if (er->idx == EXTRA_REG_NHMEX_M_PLD)
+ reg_idx = 1;
+ else if (WARN_ON_ONCE(reg_idx > 0))
+ return -EINVAL;
+
+ reg1->idx &= ~(0xff << (reg_idx * 8));
+ reg1->reg &= ~(0xffff << (reg_idx * 16));
+ reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
+ reg1->reg |= msr << (reg_idx * 16);
+ reg1->config = event->attr.config1;
+ reg_idx++;
+ }
+ /*
+ * The mbox only provides ability to perform address matching
+ * for the PLD events.
+ */
+ if (reg_idx == 2) {
+ reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+ if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+ reg2->config = event->attr.config2;
+ else
+ reg2->config = ~0ULL;
+ if (box->pmu->pmu_idx == 0)
+ reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+ else
+ reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+ }
+ return 0;
+}
+
+static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ u64 config;
+
+ if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+ return box->shared_regs[idx].config;
+
+ er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ config = er->config;
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+ return config;
+}
+
+static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ int idx;
+
+ idx = __BITS_VALUE(reg1->idx, 0, 8);
+ if (idx != 0xff)
+ wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+ nhmex_mbox_shared_reg_config(box, idx));
+ idx = __BITS_VALUE(reg1->idx, 1, 8);
+ if (idx != 0xff)
+ wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+ nhmex_mbox_shared_reg_config(box, idx));
+
+ if (reg2->idx != EXTRA_REG_NONE) {
+ wrmsrl(reg2->reg, 0);
+ if (reg2->config != ~0ULL) {
+ wrmsrl(reg2->reg + 1,
+ reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+ wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+ (reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+ wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+ }
+ }
+
+ wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode, "config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode, wrap_mode, "config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode, flag_mode, "config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel, inc_sel, "config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel, set_flag_sel, "config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg_en, filter_cfg_en, "config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match, filter_match, "config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask, filter_mask, "config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp, dsp, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr, thr, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc, fvc, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt, pgt, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map, map, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss, iss, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld, pld, "config1:32-63");
+
+static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
+ &format_attr_count_mode.attr,
+ &format_attr_storage_mode.attr,
+ &format_attr_wrap_mode.attr,
+ &format_attr_flag_mode.attr,
+ &format_attr_inc_sel.attr,
+ &format_attr_set_flag_sel.attr,
+ &format_attr_filter_cfg_en.attr,
+ &format_attr_filter_match.attr,
+ &format_attr_filter_mask.attr,
+ &format_attr_dsp.attr,
+ &format_attr_thr.attr,
+ &format_attr_fvc.attr,
+ &format_attr_pgt.attr,
+ &format_attr_map.attr,
+ &format_attr_iss.attr,
+ &format_attr_pld.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_mbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_mbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
+ { /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc wsmex_uncore_mbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x5000"),
+ INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x5040"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_mbox_msr_enable_event,
+ .hw_config = nhmex_mbox_hw_config,
+ .get_constraint = nhmex_mbox_get_constraint,
+ .put_constraint = nhmex_mbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_mbox = {
+ .name = "mbox",
+ .num_counters = 6,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_M0_MSR_PMU_CTL0,
+ .perf_ctr = NHMEX_M0_MSR_PMU_CNT0,
+ .event_mask = NHMEX_M_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_M0_MSR_GLOBAL_CTL,
+ .msr_offset = NHMEX_M_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 8,
+ .event_descs = nhmex_uncore_mbox_events,
+ .ops = &nhmex_uncore_mbox_ops,
+ .format_group = &nhmex_uncore_mbox_format_group,
+};
+
+static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ /* adjust the main event selector and extra register index */
+ if (reg1->idx % 2) {
+ reg1->idx--;
+ hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+ } else {
+ reg1->idx++;
+ hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+ }
+
+ /* adjust extra register config */
+ switch (reg1->idx % 6) {
+ case 2:
+ /* shift the 8~15 bits to the 0~7 bits */
+ reg1->config >>= 8;
+ break;
+ case 3:
+ /* shift the 0~7 bits to the 8~15 bits */
+ reg1->config <<= 8;
+ break;
+ }
+}
+
+/*
+ * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
+ * An event set consists of 6 events, the 3rd and 4th events in
+ * an event set use the same extra register. So an event set uses
+ * 5 extra registers.
+ */
+static struct event_constraint *
+nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ struct intel_uncore_extra_reg *er;
+ unsigned long flags;
+ int idx, er_idx;
+ u64 config1;
+ bool ok = false;
+
+ if (!uncore_box_is_fake(box) && reg1->alloc)
+ return NULL;
+
+ idx = reg1->idx % 6;
+ config1 = reg1->config;
+again:
+ er_idx = idx;
+ /* the 3rd and 4th events use the same extra register */
+ if (er_idx > 2)
+ er_idx--;
+ er_idx += (reg1->idx / 6) * 5;
+
+ er = &box->shared_regs[er_idx];
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (idx < 2) {
+ if (!atomic_read(&er->ref) || er->config == reg1->config) {
+ atomic_inc(&er->ref);
+ er->config = reg1->config;
+ ok = true;
+ }
+ } else if (idx == 2 || idx == 3) {
+ /*
+ * these two events use different fields in a extra register,
+ * the 0~7 bits and the 8~15 bits respectively.
+ */
+ u64 mask = 0xff << ((idx - 2) * 8);
+ if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
+ !((er->config ^ config1) & mask)) {
+ atomic_add(1 << ((idx - 2) * 8), &er->ref);
+ er->config &= ~mask;
+ er->config |= config1 & mask;
+ ok = true;
+ }
+ } else {
+ if (!atomic_read(&er->ref) ||
+ (er->config == (hwc->config >> 32) &&
+ er->config1 == reg1->config &&
+ er->config2 == reg2->config)) {
+ atomic_inc(&er->ref);
+ er->config = (hwc->config >> 32);
+ er->config1 = reg1->config;
+ er->config2 = reg2->config;
+ ok = true;
+ }
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ if (!ok) {
+ /*
+ * The Rbox events are always in pairs. The paired
+ * events are functional identical, but use different
+ * extra registers. If we failed to take an extra
+ * register, try the alternative.
+ */
+ idx ^= 1;
+ if (idx != reg1->idx % 6) {
+ if (idx == 2)
+ config1 >>= 8;
+ else if (idx == 3)
+ config1 <<= 8;
+ goto again;
+ }
+ } else {
+ if (!uncore_box_is_fake(box)) {
+ if (idx != reg1->idx % 6)
+ nhmex_rbox_alter_er(box, event);
+ reg1->alloc = 1;
+ }
+ return NULL;
+ }
+ return &uncore_constraint_empty;
+}
+
+static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct intel_uncore_extra_reg *er;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ int idx, er_idx;
+
+ if (uncore_box_is_fake(box) || !reg1->alloc)
+ return;
+
+ idx = reg1->idx % 6;
+ er_idx = idx;
+ if (er_idx > 2)
+ er_idx--;
+ er_idx += (reg1->idx / 6) * 5;
+
+ er = &box->shared_regs[er_idx];
+ if (idx == 2 || idx == 3)
+ atomic_sub(1 << ((idx - 2) * 8), &er->ref);
+ else
+ atomic_dec(&er->ref);
+
+ reg1->alloc = 0;
+}
+
+static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+ int idx;
+
+ idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
+ NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+ if (idx >= 0x18)
+ return -EINVAL;
+
+ reg1->idx = idx;
+ reg1->config = event->attr.config1;
+
+ switch (idx % 6) {
+ case 4:
+ case 5:
+ hwc->config |= event->attr.config & (~0ULL << 32);
+ reg2->config = event->attr.config2;
+ break;
+ }
+ return 0;
+}
+
+static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+ int idx, port;
+
+ idx = reg1->idx;
+ port = idx / 6 + box->pmu->pmu_idx * 4;
+
+ switch (idx % 6) {
+ case 0:
+ wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+ break;
+ case 1:
+ wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
+ break;
+ case 2:
+ case 3:
+ wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+ uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
+ break;
+ case 4:
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+ hwc->config >> 32);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+ break;
+ case 5:
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+ hwc->config >> 32);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+ wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
+ break;
+ }
+
+ wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+ (hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
+DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
+
+static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
+ &format_attr_event5.attr,
+ &format_attr_xbr_mm_cfg.attr,
+ &format_attr_xbr_match.attr,
+ &format_attr_xbr_mask.attr,
+ &format_attr_qlx_cfg.attr,
+ &format_attr_iperf_cfg.attr,
+ NULL,
+};
+
+static struct attribute_group nhmex_uncore_rbox_format_group = {
+ .name = "format",
+ .attrs = nhmex_uncore_rbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
+ INTEL_UNCORE_EVENT_DESC(qpi0_flit_send, "event=0x0,iperf_cfg=0x80000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi1_filt_send, "event=0x6,iperf_cfg=0x80000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt, "event=0x0,iperf_cfg=0x40000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt, "event=0x6,iperf_cfg=0x40000000"),
+ INTEL_UNCORE_EVENT_DESC(qpi0_date_response, "event=0x0,iperf_cfg=0xc4"),
+ INTEL_UNCORE_EVENT_DESC(qpi1_date_response, "event=0x6,iperf_cfg=0xc4"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
+ NHMEX_UNCORE_OPS_COMMON_INIT(),
+ .enable_event = nhmex_rbox_msr_enable_event,
+ .hw_config = nhmex_rbox_hw_config,
+ .get_constraint = nhmex_rbox_get_constraint,
+ .put_constraint = nhmex_rbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_rbox = {
+ .name = "rbox",
+ .num_counters = 8,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .event_ctl = NHMEX_R_MSR_PMON_CTL0,
+ .perf_ctr = NHMEX_R_MSR_PMON_CNT0,
+ .event_mask = NHMEX_R_PMON_RAW_EVENT_MASK,
+ .box_ctl = NHMEX_R_MSR_GLOBAL_CTL,
+ .msr_offset = NHMEX_R_MSR_OFFSET,
+ .pair_ctr_ctl = 1,
+ .num_shared_regs = 20,
+ .event_descs = nhmex_uncore_rbox_events,
+ .ops = &nhmex_uncore_rbox_ops,
+ .format_group = &nhmex_uncore_rbox_format_group
+};
+
+static struct intel_uncore_type *nhmex_msr_uncores[] = {
+ &nhmex_uncore_ubox,
+ &nhmex_uncore_cbox,
+ &nhmex_uncore_bbox,
+ &nhmex_uncore_sbox,
+ &nhmex_uncore_mbox,
+ &nhmex_uncore_rbox,
+ &nhmex_uncore_wbox,
+ NULL,
+};
+
+void nhmex_uncore_cpu_init(void)
+{
+ if (boot_cpu_data.x86_model == 46)
+ uncore_nhmex = true;
+ else
+ nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events;
+ if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+ nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+ uncore_msr_uncores = nhmex_msr_uncores;
+}
+/* end of Nehalem-EX uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
new file mode 100644
index 000000000000..3001015b755c
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c
@@ -0,0 +1,636 @@
+/* Nehalem/SandBridge/Haswell uncore support */
+#include "perf_event_intel_uncore.h"
+
+/* SNB event control */
+#define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff
+#define SNB_UNC_CTL_UMASK_MASK 0x0000ff00
+#define SNB_UNC_CTL_EDGE_DET (1 << 18)
+#define SNB_UNC_CTL_EN (1 << 22)
+#define SNB_UNC_CTL_INVERT (1 << 23)
+#define SNB_UNC_CTL_CMASK_MASK 0x1f000000
+#define NHM_UNC_CTL_CMASK_MASK 0xff000000
+#define NHM_UNC_FIXED_CTR_CTL_EN (1 << 0)
+
+#define SNB_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
+ SNB_UNC_CTL_UMASK_MASK | \
+ SNB_UNC_CTL_EDGE_DET | \
+ SNB_UNC_CTL_INVERT | \
+ SNB_UNC_CTL_CMASK_MASK)
+
+#define NHM_UNC_RAW_EVENT_MASK (SNB_UNC_CTL_EV_SEL_MASK | \
+ SNB_UNC_CTL_UMASK_MASK | \
+ SNB_UNC_CTL_EDGE_DET | \
+ SNB_UNC_CTL_INVERT | \
+ NHM_UNC_CTL_CMASK_MASK)
+
+/* SNB global control register */
+#define SNB_UNC_PERF_GLOBAL_CTL 0x391
+#define SNB_UNC_FIXED_CTR_CTRL 0x394
+#define SNB_UNC_FIXED_CTR 0x395
+
+/* SNB uncore global control */
+#define SNB_UNC_GLOBAL_CTL_CORE_ALL ((1 << 4) - 1)
+#define SNB_UNC_GLOBAL_CTL_EN (1 << 29)
+
+/* SNB Cbo register */
+#define SNB_UNC_CBO_0_PERFEVTSEL0 0x700
+#define SNB_UNC_CBO_0_PER_CTR0 0x706
+#define SNB_UNC_CBO_MSR_OFFSET 0x10
+
+/* NHM global control register */
+#define NHM_UNC_PERF_GLOBAL_CTL 0x391
+#define NHM_UNC_FIXED_CTR 0x394
+#define NHM_UNC_FIXED_CTR_CTRL 0x395
+
+/* NHM uncore global control */
+#define NHM_UNC_GLOBAL_CTL_EN_PC_ALL ((1ULL << 8) - 1)
+#define NHM_UNC_GLOBAL_CTL_EN_FC (1ULL << 32)
+
+/* NHM uncore register */
+#define NHM_UNC_PERFEVTSEL0 0x3c0
+#define NHM_UNC_UNCORE_PMC0 0x3b0
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(cmask5, cmask, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(cmask8, cmask, "config:24-31");
+
+/* Sandy Bridge uncore support */
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ else
+ wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+}
+
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ wrmsrl(event->hw.config_base, 0);
+}
+
+static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ if (box->pmu->pmu_idx == 0) {
+ wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
+ }
+}
+
+static struct uncore_event_desc snb_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute *snb_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask5.attr,
+ NULL,
+};
+
+static struct attribute_group snb_uncore_format_group = {
+ .name = "format",
+ .attrs = snb_uncore_formats_attr,
+};
+
+static struct intel_uncore_ops snb_uncore_msr_ops = {
+ .init_box = snb_uncore_msr_init_box,
+ .disable_event = snb_uncore_msr_disable_event,
+ .enable_event = snb_uncore_msr_enable_event,
+ .read_counter = uncore_msr_read_counter,
+};
+
+static struct event_constraint snb_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x80, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x83, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snb_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 2,
+ .num_boxes = 4,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNB_UNC_CBO_0_PER_CTR0,
+ .event_ctl = SNB_UNC_CBO_0_PERFEVTSEL0,
+ .fixed_ctr = SNB_UNC_FIXED_CTR,
+ .fixed_ctl = SNB_UNC_FIXED_CTR_CTRL,
+ .single_fixed = 1,
+ .event_mask = SNB_UNC_RAW_EVENT_MASK,
+ .msr_offset = SNB_UNC_CBO_MSR_OFFSET,
+ .constraints = snb_uncore_cbox_constraints,
+ .ops = &snb_uncore_msr_ops,
+ .format_group = &snb_uncore_format_group,
+ .event_descs = snb_uncore_events,
+};
+
+static struct intel_uncore_type *snb_msr_uncores[] = {
+ &snb_uncore_cbox,
+ NULL,
+};
+
+void snb_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = snb_msr_uncores;
+ if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+ snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+}
+
+enum {
+ SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(data_reads, "event=0x01"),
+ INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+ INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+ INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+ { /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK 0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET 0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE 0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS 0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE 0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES 0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+ .name = "format",
+ .attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
+ resource_size_t addr;
+ u32 pci_dword;
+
+ pci_read_config_dword(pdev, where, &pci_dword);
+ addr = pci_dword;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ pci_read_config_dword(pdev, where + 4, &pci_dword);
+ addr |= ((resource_size_t)pci_dword << 32);
+#endif
+
+ addr &= ~(PAGE_SIZE - 1);
+
+ box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+ box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+ struct intel_uncore_pmu *pmu;
+ struct intel_uncore_box *box;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+ int idx, base;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ pmu = uncore_event_to_pmu(event);
+ /* no device found for this pmu */
+ if (pmu->func_id < 0)
+ return -ENOENT;
+
+ /* Sampling not supported yet */
+ if (hwc->sample_period)
+ return -EINVAL;
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ event->attr.sample_period) /* no sampling */
+ return -EINVAL;
+
+ /*
+ * Place all uncore events for a particular physical package
+ * onto a single cpu
+ */
+ if (event->cpu < 0)
+ return -EINVAL;
+
+ /* check only supported bits are set */
+ if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+ return -EINVAL;
+
+ box = uncore_pmu_to_box(pmu, event->cpu);
+ if (!box || box->cpu < 0)
+ return -EINVAL;
+
+ event->cpu = box->cpu;
+
+ event->hw.idx = -1;
+ event->hw.last_tag = ~0ULL;
+ event->hw.extra_reg.idx = EXTRA_REG_NONE;
+ event->hw.branch_reg.idx = EXTRA_REG_NONE;
+ /*
+ * check event is known (whitelist, determines counter)
+ */
+ switch (cfg) {
+ case SNB_UNCORE_PCI_IMC_DATA_READS:
+ base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+ idx = UNCORE_PMC_IDX_FIXED;
+ break;
+ case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+ base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+ idx = UNCORE_PMC_IDX_FIXED + 1;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ /* must be done before validate_group */
+ event->hw.event_base = base;
+ event->hw.config = cfg;
+ event->hw.idx = idx;
+
+ /* no group validation needed, we have free running counters */
+
+ return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ u64 count;
+
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ event->hw.state = 0;
+ box->n_active++;
+
+ list_add_tail(&event->active_entry, &box->active_list);
+
+ count = snb_uncore_imc_read_counter(box, event);
+ local64_set(&event->hw.prev_count, count);
+
+ if (box->n_active == 1)
+ uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!(hwc->state & PERF_HES_STOPPED)) {
+ box->n_active--;
+
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+
+ list_del(&event->active_entry);
+
+ if (box->n_active == 0)
+ uncore_pmu_cancel_hrtimer(box);
+ }
+
+ if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ /*
+ * Drain the remaining delta count out of a event
+ * that we are disabling:
+ */
+ uncore_perf_event_update(box, event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!box)
+ return -ENODEV;
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+ if (!(flags & PERF_EF_START))
+ hwc->state |= PERF_HES_ARCH;
+
+ snb_uncore_imc_event_start(event, 0);
+
+ box->n_events++;
+
+ return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+ struct intel_uncore_box *box = uncore_event_to_box(event);
+ int i;
+
+ snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+ for (i = 0; i < box->n_events; i++) {
+ if (event == box->event_list[i]) {
+ --box->n_events;
+ break;
+ }
+ }
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+ struct pci_dev *dev = NULL;
+ int bus;
+
+ dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+ if (!dev)
+ return -ENOTTY;
+
+ bus = dev->bus->number;
+
+ uncore_pcibus_to_physid[bus] = 0;
+
+ pci_dev_put(dev);
+
+ return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = snb_uncore_imc_event_init,
+ .add = snb_uncore_imc_event_add,
+ .del = snb_uncore_imc_event_del,
+ .start = snb_uncore_imc_event_start,
+ .stop = snb_uncore_imc_event_stop,
+ .read = uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+ .init_box = snb_uncore_imc_init_box,
+ .enable_box = snb_uncore_imc_enable_box,
+ .disable_box = snb_uncore_imc_disable_box,
+ .disable_event = snb_uncore_imc_disable_event,
+ .enable_event = snb_uncore_imc_enable_event,
+ .hw_config = snb_uncore_imc_hw_config,
+ .read_counter = snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+ .name = "imc",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .fixed_ctr_bits = 32,
+ .fixed_ctr = SNB_UNCORE_PCI_IMC_CTR_BASE,
+ .event_descs = snb_uncore_imc_events,
+ .format_group = &snb_uncore_imc_format_group,
+ .perf_ctr = SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+ .event_mask = SNB_UNCORE_PCI_IMC_EVENT_MASK,
+ .ops = &snb_uncore_imc_ops,
+ .pmu = &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+ [SNB_PCI_UNCORE_IMC] = &snb_uncore_imc,
+ NULL,
+};
+
+static const struct pci_device_id snb_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static const struct pci_device_id ivb_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_E3_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static const struct pci_device_id hsw_uncore_pci_ids[] = {
+ { /* IMC */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+ },
+ { /* end: all zeroes */ },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+ .name = "snb_uncore",
+ .id_table = snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+ .name = "ivb_uncore",
+ .id_table = ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+ .name = "hsw_uncore",
+ .id_table = hsw_uncore_pci_ids,
+};
+
+struct imc_uncore_pci_dev {
+ __u32 pci_id;
+ struct pci_driver *driver;
+};
+#define IMC_DEV(a, d) \
+ { .pci_id = PCI_DEVICE_ID_INTEL_##a, .driver = (d) }
+
+static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
+ IMC_DEV(SNB_IMC, &snb_uncore_pci_driver),
+ IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver), /* 3rd Gen Core processor */
+ IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */
+ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */
+ { /* end marker */ }
+};
+
+
+#define for_each_imc_pci_id(x, t) \
+ for (x = (t); (x)->pci_id; x++)
+
+static struct pci_driver *imc_uncore_find_dev(void)
+{
+ const struct imc_uncore_pci_dev *p;
+ int ret;
+
+ for_each_imc_pci_id(p, desktop_imc_pci_ids) {
+ ret = snb_pci2phy_map_init(p->pci_id);
+ if (ret == 0)
+ return p->driver;
+ }
+ return NULL;
+}
+
+static int imc_uncore_pci_init(void)
+{
+ struct pci_driver *imc_drv = imc_uncore_find_dev();
+
+ if (!imc_drv)
+ return -ENODEV;
+
+ uncore_pci_uncores = snb_pci_uncores;
+ uncore_pci_driver = imc_drv;
+
+ return 0;
+}
+
+int snb_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
+int ivb_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+int hsw_uncore_pci_init(void)
+{
+ return imc_uncore_pci_init();
+}
+
+/* end of Sandy Bridge uncore support */
+
+/* Nehalem uncore support */
+static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+}
+
+static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+}
+
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (hwc->idx < UNCORE_PMC_IDX_FIXED)
+ wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ else
+ wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+}
+
+static struct attribute *nhm_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_cmask8.attr,
+ NULL,
+};
+
+static struct attribute_group nhm_uncore_format_group = {
+ .name = "format",
+ .attrs = nhm_uncore_formats_attr,
+};
+
+static struct uncore_event_desc nhm_uncore_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(qmc_writes_full_any, "event=0x2f,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(qmc_normal_reads_any, "event=0x2c,umask=0x0f"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_reads, "event=0x20,umask=0x01"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_ioh_writes, "event=0x20,umask=0x02"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_remote_reads, "event=0x20,umask=0x04"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_remote_writes, "event=0x20,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_local_reads, "event=0x20,umask=0x10"),
+ INTEL_UNCORE_EVENT_DESC(qhl_request_local_writes, "event=0x20,umask=0x20"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhm_uncore_msr_ops = {
+ .disable_box = nhm_uncore_msr_disable_box,
+ .enable_box = nhm_uncore_msr_enable_box,
+ .disable_event = snb_uncore_msr_disable_event,
+ .enable_event = nhm_uncore_msr_enable_event,
+ .read_counter = uncore_msr_read_counter,
+};
+
+static struct intel_uncore_type nhm_uncore = {
+ .name = "",
+ .num_counters = 8,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .event_ctl = NHM_UNC_PERFEVTSEL0,
+ .perf_ctr = NHM_UNC_UNCORE_PMC0,
+ .fixed_ctr = NHM_UNC_FIXED_CTR,
+ .fixed_ctl = NHM_UNC_FIXED_CTR_CTRL,
+ .event_mask = NHM_UNC_RAW_EVENT_MASK,
+ .event_descs = nhm_uncore_events,
+ .ops = &nhm_uncore_msr_ops,
+ .format_group = &nhm_uncore_format_group,
+};
+
+static struct intel_uncore_type *nhm_msr_uncores[] = {
+ &nhm_uncore,
+ NULL,
+};
+
+void nhm_uncore_cpu_init(void)
+{
+ uncore_msr_uncores = nhm_msr_uncores;
+}
+
+/* end of Nehalem uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
new file mode 100644
index 000000000000..21af6149edf2
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -0,0 +1,2324 @@
+/* SandyBridge-EP/IvyTown uncore support */
+#include "perf_event_intel_uncore.h"
+
+
+/* SNB-EP Box level control */
+#define SNBEP_PMON_BOX_CTL_RST_CTRL (1 << 0)
+#define SNBEP_PMON_BOX_CTL_RST_CTRS (1 << 1)
+#define SNBEP_PMON_BOX_CTL_FRZ (1 << 8)
+#define SNBEP_PMON_BOX_CTL_FRZ_EN (1 << 16)
+#define SNBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \
+ SNBEP_PMON_BOX_CTL_RST_CTRS | \
+ SNBEP_PMON_BOX_CTL_FRZ_EN)
+/* SNB-EP event control */
+#define SNBEP_PMON_CTL_EV_SEL_MASK 0x000000ff
+#define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00
+#define SNBEP_PMON_CTL_RST (1 << 17)
+#define SNBEP_PMON_CTL_EDGE_DET (1 << 18)
+#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21)
+#define SNBEP_PMON_CTL_EN (1 << 22)
+#define SNBEP_PMON_CTL_INVERT (1 << 23)
+#define SNBEP_PMON_CTL_TRESH_MASK 0xff000000
+#define SNBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_PMON_CTL_TRESH_MASK)
+
+/* SNB-EP Ubox event control */
+#define SNBEP_U_MSR_PMON_CTL_TRESH_MASK 0x1f000000
+#define SNBEP_U_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+
+#define SNBEP_CBO_PMON_CTL_TID_EN (1 << 19)
+#define SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* SNB-EP PCU event control */
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK 0x0000c000
+#define SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK 0x1f000000
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT (1 << 30)
+#define SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET (1 << 31)
+#define SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_EV_SEL_EXT | \
+ SNBEP_PMON_CTL_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+
+#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_PMON_CTL_EV_SEL_EXT)
+
+/* SNB-EP pci control register */
+#define SNBEP_PCI_PMON_BOX_CTL 0xf4
+#define SNBEP_PCI_PMON_CTL0 0xd8
+/* SNB-EP pci counter register */
+#define SNBEP_PCI_PMON_CTR0 0xa0
+
+/* SNB-EP home agent register */
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH0 0x40
+#define SNBEP_HA_PCI_PMON_BOX_ADDRMATCH1 0x44
+#define SNBEP_HA_PCI_PMON_BOX_OPCODEMATCH 0x48
+/* SNB-EP memory controller register */
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTL 0xf0
+#define SNBEP_MC_CHy_PCI_PMON_FIXED_CTR 0xd0
+/* SNB-EP QPI register */
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH0 0x228
+#define SNBEP_Q_Py_PCI_PMON_PKT_MATCH1 0x22c
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK0 0x238
+#define SNBEP_Q_Py_PCI_PMON_PKT_MASK1 0x23c
+
+/* SNB-EP Ubox register */
+#define SNBEP_U_MSR_PMON_CTR0 0xc16
+#define SNBEP_U_MSR_PMON_CTL0 0xc10
+
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTL 0xc08
+#define SNBEP_U_MSR_PMON_UCLK_FIXED_CTR 0xc09
+
+/* SNB-EP Cbo register */
+#define SNBEP_C0_MSR_PMON_CTR0 0xd16
+#define SNBEP_C0_MSR_PMON_CTL0 0xd10
+#define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04
+#define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14
+#define SNBEP_CBO_MSR_OFFSET 0x20
+
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000
+#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000
+
+#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \
+ .event = (e), \
+ .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \
+ .config_mask = (m), \
+ .idx = (i) \
+}
+
+/* SNB-EP PCU register */
+#define SNBEP_PCU_MSR_PMON_CTR0 0xc36
+#define SNBEP_PCU_MSR_PMON_CTL0 0xc30
+#define SNBEP_PCU_MSR_PMON_BOX_CTL 0xc24
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER 0xc34
+#define SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK 0xffffffff
+#define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc
+#define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd
+
+/* IVBEP event control */
+#define IVBEP_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \
+ SNBEP_PMON_BOX_CTL_RST_CTRS)
+#define IVBEP_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_TRESH_MASK)
+/* IVBEP Ubox */
+#define IVBEP_U_MSR_PMON_GLOBAL_CTL 0xc00
+#define IVBEP_U_PMON_GLOBAL_FRZ_ALL (1 << 31)
+#define IVBEP_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29)
+
+#define IVBEP_U_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_UMASK_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_U_MSR_PMON_CTL_TRESH_MASK)
+/* IVBEP Cbo */
+#define IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK (IVBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_CBO_PMON_CTL_TID_EN)
+
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62)
+#define IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63)
+
+/* IVBEP home agent */
+#define IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16)
+#define IVBEP_HA_PCI_PMON_RAW_EVENT_MASK \
+ (IVBEP_PMON_RAW_EVENT_MASK | \
+ IVBEP_HA_PCI_PMON_CTL_Q_OCC_RST)
+/* IVBEP PCU */
+#define IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK \
+ (SNBEP_PMON_CTL_EV_SEL_MASK | \
+ SNBEP_PMON_CTL_EV_SEL_EXT | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
+ SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
+ SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
+/* IVBEP QPI */
+#define IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK \
+ (IVBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_PMON_CTL_EV_SEL_EXT)
+
+#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \
+ ((1ULL << (n)) - 1)))
+
+/* Haswell-EP Ubox */
+#define HSWEP_U_MSR_PMON_CTR0 0x705
+#define HSWEP_U_MSR_PMON_CTL0 0x709
+#define HSWEP_U_MSR_PMON_FILTER 0x707
+
+#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTL 0x703
+#define HSWEP_U_MSR_PMON_UCLK_FIXED_CTR 0x704
+
+#define HSWEP_U_MSR_PMON_BOX_FILTER_TID (0x1 << 0)
+#define HSWEP_U_MSR_PMON_BOX_FILTER_CID (0x1fULL << 1)
+#define HSWEP_U_MSR_PMON_BOX_FILTER_MASK \
+ (HSWEP_U_MSR_PMON_BOX_FILTER_TID | \
+ HSWEP_U_MSR_PMON_BOX_FILTER_CID)
+
+/* Haswell-EP CBo */
+#define HSWEP_C0_MSR_PMON_CTR0 0xe08
+#define HSWEP_C0_MSR_PMON_CTL0 0xe01
+#define HSWEP_C0_MSR_PMON_BOX_CTL 0xe00
+#define HSWEP_C0_MSR_PMON_BOX_FILTER0 0xe05
+#define HSWEP_CBO_MSR_OFFSET 0x10
+
+
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_TID (0x3fULL << 0)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 6)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE (0x7fULL << 17)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62)
+#define HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC (0x1ULL << 63)
+
+
+/* Haswell-EP Sbox */
+#define HSWEP_S0_MSR_PMON_CTR0 0x726
+#define HSWEP_S0_MSR_PMON_CTL0 0x721
+#define HSWEP_S0_MSR_PMON_BOX_CTL 0x720
+#define HSWEP_SBOX_MSR_OFFSET 0xa
+#define HSWEP_S_MSR_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
+ SNBEP_CBO_PMON_CTL_TID_EN)
+
+/* Haswell-EP PCU */
+#define HSWEP_PCU_MSR_PMON_CTR0 0x717
+#define HSWEP_PCU_MSR_PMON_CTL0 0x711
+#define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710
+#define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715
+
+
+DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
+DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23");
+DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28");
+DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15");
+DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30");
+DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0");
+DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22");
+DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60");
+DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62");
+DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61");
+DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
+
+static void snbep_uncore_pci_disable_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+ u32 config = 0;
+
+ if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+ }
+}
+
+static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ int box_ctl = uncore_pci_box_ctl(box);
+ u32 config = 0;
+
+ if (!pci_read_config_dword(pdev, box_ctl, &config)) {
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ pci_write_config_dword(pdev, box_ctl, config);
+ }
+}
+
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config);
+}
+
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count = 0;
+
+ pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
+ pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+
+ return count;
+}
+
+static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+
+ pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+ u64 config;
+ unsigned msr;
+
+ msr = uncore_msr_box_ctl(box);
+ if (msr) {
+ rdmsrl(msr, config);
+ config |= SNBEP_PMON_BOX_CTL_FRZ;
+ wrmsrl(msr, config);
+ }
+}
+
+static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+ u64 config;
+ unsigned msr;
+
+ msr = uncore_msr_box_ctl(box);
+ if (msr) {
+ rdmsrl(msr, config);
+ config &= ~SNBEP_PMON_BOX_CTL_FRZ;
+ wrmsrl(msr, config);
+ }
+}
+
+static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE)
+ wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ wrmsrl(hwc->config_base, hwc->config);
+}
+
+static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+
+ if (msr)
+ wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+}
+
+static struct attribute *snbep_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid.attr,
+ &format_attr_filter_nid.attr,
+ &format_attr_filter_state.attr,
+ &format_attr_filter_opc.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_pcu_formats_attr[] = {
+ &format_attr_event_ext.attr,
+ &format_attr_occ_sel.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ &format_attr_occ_invert.attr,
+ &format_attr_occ_edge.attr,
+ &format_attr_filter_band0.attr,
+ &format_attr_filter_band1.attr,
+ &format_attr_filter_band2.attr,
+ &format_attr_filter_band3.attr,
+ NULL,
+};
+
+static struct attribute *snbep_uncore_qpi_formats_attr[] = {
+ &format_attr_event_ext.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_match_rds.attr,
+ &format_attr_match_rnid30.attr,
+ &format_attr_match_rnid4.attr,
+ &format_attr_match_dnid.attr,
+ &format_attr_match_mc.attr,
+ &format_attr_match_opc.attr,
+ &format_attr_match_vnw.attr,
+ &format_attr_match0.attr,
+ &format_attr_match1.attr,
+ &format_attr_mask_rds.attr,
+ &format_attr_mask_rnid30.attr,
+ &format_attr_mask_rnid4.attr,
+ &format_attr_mask_dnid.attr,
+ &format_attr_mask_mc.attr,
+ &format_attr_mask_opc.attr,
+ &format_attr_mask_vnw.attr,
+ &format_attr_mask0.attr,
+ &format_attr_mask1.attr,
+ NULL,
+};
+
+static struct uncore_event_desc snbep_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct uncore_event_desc snbep_uncore_qpi_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x14"),
+ INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
+ INTEL_UNCORE_EVENT_DESC(drs_data, "event=0x102,umask=0x08"),
+ INTEL_UNCORE_EVENT_DESC(ncb_data, "event=0x103,umask=0x04"),
+ { /* end: all zeroes */ },
+};
+
+static struct attribute_group snbep_uncore_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_pcu_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group snbep_uncore_qpi_format_group = {
+ .name = "format",
+ .attrs = snbep_uncore_qpi_formats_attr,
+};
+
+#define __SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \
+ .disable_box = snbep_uncore_msr_disable_box, \
+ .enable_box = snbep_uncore_msr_enable_box, \
+ .disable_event = snbep_uncore_msr_disable_event, \
+ .enable_event = snbep_uncore_msr_enable_event, \
+ .read_counter = uncore_msr_read_counter
+
+#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \
+ __SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), \
+ .init_box = snbep_uncore_msr_init_box \
+
+static struct intel_uncore_ops snbep_uncore_msr_ops = {
+ SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \
+ .init_box = snbep_uncore_pci_init_box, \
+ .disable_box = snbep_uncore_pci_disable_box, \
+ .enable_box = snbep_uncore_pci_enable_box, \
+ .disable_event = snbep_uncore_pci_disable_event, \
+ .read_counter = snbep_uncore_pci_read_counter
+
+static struct intel_uncore_ops snbep_uncore_pci_ops = {
+ SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+ .enable_event = snbep_uncore_pci_enable_event, \
+};
+
+static struct event_constraint snbep_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x02, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x04, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x05, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x07, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x09, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x1b, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1c, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1d, 0xc),
+ UNCORE_EVENT_CONSTRAINT(0x1e, 0xc),
+ EVENT_CONSTRAINT_OVERLAP(0x1f, 0xe, 0xff),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r2pcie_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint snbep_uncore_r3qpi_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2a, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x30, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type snbep_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNBEP_U_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &snbep_uncore_msr_ops,
+ .format_group = &snbep_uncore_ubox_format_group,
+};
+
+static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
+ SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+ SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2),
+ EVENT_EXTRA_END
+};
+
+static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+ int i;
+
+ if (uncore_box_is_fake(box))
+ return;
+
+ for (i = 0; i < 5; i++) {
+ if (reg1->alloc & (0x1 << i))
+ atomic_sub(1 << (i * 6), &er->ref);
+ }
+ reg1->alloc = 0;
+}
+
+static struct event_constraint *
+__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event,
+ u64 (*cbox_filter_mask)(int fields))
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+ int i, alloc = 0;
+ unsigned long flags;
+ u64 mask;
+
+ if (reg1->idx == EXTRA_REG_NONE)
+ return NULL;
+
+ raw_spin_lock_irqsave(&er->lock, flags);
+ for (i = 0; i < 5; i++) {
+ if (!(reg1->idx & (0x1 << i)))
+ continue;
+ if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+ continue;
+
+ mask = cbox_filter_mask(0x1 << i);
+ if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) ||
+ !((reg1->config ^ er->config) & mask)) {
+ atomic_add(1 << (i * 6), &er->ref);
+ er->config &= ~mask;
+ er->config |= reg1->config & mask;
+ alloc |= (0x1 << i);
+ } else {
+ break;
+ }
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+ if (i < 5)
+ goto fail;
+
+ if (!uncore_box_is_fake(box))
+ reg1->alloc |= alloc;
+
+ return NULL;
+fail:
+ for (; i >= 0; i--) {
+ if (alloc & (0x1 << i))
+ atomic_sub(1 << (i * 6), &er->ref);
+ }
+ return &uncore_constraint_empty;
+}
+
+static u64 snbep_cbox_filter_mask(int fields)
+{
+ u64 mask = 0;
+
+ if (fields & 0x1)
+ mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+ if (fields & 0x2)
+ mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+ if (fields & 0x4)
+ mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+ if (fields & 0x8)
+ mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+
+ return mask;
+}
+
+static struct event_constraint *
+snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask);
+}
+
+static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct extra_reg *er;
+ int idx = 0;
+
+ for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) {
+ if (er->event != (event->hw.config & er->config_mask))
+ continue;
+ idx |= er->idx;
+ }
+
+ if (idx) {
+ reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+ SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx);
+ reg1->idx = idx;
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_cbox_ops = {
+ SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = snbep_cbox_hw_config,
+ .get_constraint = snbep_cbox_get_constraint,
+ .put_constraint = snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type snbep_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .num_boxes = 8,
+ .perf_ctr_bits = 44,
+ .event_ctl = SNBEP_C0_MSR_PMON_CTL0,
+ .perf_ctr = SNBEP_C0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNBEP_CBO_MSR_OFFSET,
+ .num_shared_regs = 1,
+ .constraints = snbep_uncore_cbox_constraints,
+ .ops = &snbep_uncore_cbox_ops,
+ .format_group = &snbep_uncore_cbox_format_group,
+};
+
+static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ u64 config = reg1->config;
+
+ if (new_idx > reg1->idx)
+ config <<= 8 * (new_idx - reg1->idx);
+ else
+ config >>= 8 * (reg1->idx - new_idx);
+
+ if (modify) {
+ hwc->config += new_idx - reg1->idx;
+ reg1->config = config;
+ reg1->idx = new_idx;
+ }
+ return config;
+}
+
+static struct event_constraint *
+snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+ unsigned long flags;
+ int idx = reg1->idx;
+ u64 mask, config1 = reg1->config;
+ bool ok = false;
+
+ if (reg1->idx == EXTRA_REG_NONE ||
+ (!uncore_box_is_fake(box) && reg1->alloc))
+ return NULL;
+again:
+ mask = 0xffULL << (idx * 8);
+ raw_spin_lock_irqsave(&er->lock, flags);
+ if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) ||
+ !((config1 ^ er->config) & mask)) {
+ atomic_add(1 << (idx * 8), &er->ref);
+ er->config &= ~mask;
+ er->config |= config1 & mask;
+ ok = true;
+ }
+ raw_spin_unlock_irqrestore(&er->lock, flags);
+
+ if (!ok) {
+ idx = (idx + 1) % 4;
+ if (idx != reg1->idx) {
+ config1 = snbep_pcu_alter_er(event, idx, false);
+ goto again;
+ }
+ return &uncore_constraint_empty;
+ }
+
+ if (!uncore_box_is_fake(box)) {
+ if (idx != reg1->idx)
+ snbep_pcu_alter_er(event, idx, true);
+ reg1->alloc = 1;
+ }
+ return NULL;
+}
+
+static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct intel_uncore_extra_reg *er = &box->shared_regs[0];
+
+ if (uncore_box_is_fake(box) || !reg1->alloc)
+ return;
+
+ atomic_sub(1 << (reg1->idx * 8), &er->ref);
+ reg1->alloc = 0;
+}
+
+static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+ if (ev_sel >= 0xb && ev_sel <= 0xe) {
+ reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+ reg1->idx = ev_sel - 0xb;
+ reg1->config = event->attr.config1 & (0xff << (reg1->idx * 8));
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops snbep_uncore_pcu_ops = {
+ SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = snbep_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type snbep_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_pcu_ops,
+ .format_group = &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *snbep_msr_uncores[] = {
+ &snbep_uncore_ubox,
+ &snbep_uncore_cbox,
+ &snbep_uncore_pcu,
+ NULL,
+};
+
+void snbep_uncore_cpu_init(void)
+{
+ if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+ snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+ uncore_msr_uncores = snbep_msr_uncores;
+}
+
+enum {
+ SNBEP_PCI_QPI_PORT0_FILTER,
+ SNBEP_PCI_QPI_PORT1_FILTER,
+ HSWEP_PCI_PCU_3,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+ reg1->idx = 0;
+ reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+ reg1->config = event->attr.config1;
+ reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+ reg2->config = event->attr.config2;
+ }
+ return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+ struct pci_dev *filter_pdev = uncore_extra_pci_dev[box->phys_id][idx];
+ if (filter_pdev) {
+ pci_write_config_dword(filter_pdev, reg1->reg,
+ (u32)reg1->config);
+ pci_write_config_dword(filter_pdev, reg1->reg + 4,
+ (u32)(reg1->config >> 32));
+ pci_write_config_dword(filter_pdev, reg2->reg,
+ (u32)reg2->config);
+ pci_write_config_dword(filter_pdev, reg2->reg + 4,
+ (u32)(reg2->config >> 32));
+ }
+ }
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+ SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+ .enable_event = snbep_qpi_enable_event,
+ .hw_config = snbep_qpi_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+#define SNBEP_UNCORE_PCI_COMMON_INIT() \
+ .perf_ctr = SNBEP_PCI_PMON_CTR0, \
+ .event_ctl = SNBEP_PCI_PMON_CTL0, \
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK, \
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \
+ .ops = &snbep_uncore_pci_ops, \
+ .format_group = &snbep_uncore_format_group
+
+static struct intel_uncore_type snbep_uncore_ha = {
+ .name = "ha",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+ .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+ .event_descs = snbep_uncore_imc_events,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_qpi = {
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_qpi_ops,
+ .event_descs = snbep_uncore_qpi_events,
+ .format_group = &snbep_uncore_qpi_format_group,
+};
+
+
+static struct intel_uncore_type snbep_uncore_r2pcie = {
+ .name = "r2pcie",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r2pcie_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type snbep_uncore_r3qpi = {
+ .name = "r3qpi",
+ .num_counters = 3,
+ .num_boxes = 2,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r3qpi_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+ SNBEP_PCI_UNCORE_HA,
+ SNBEP_PCI_UNCORE_IMC,
+ SNBEP_PCI_UNCORE_QPI,
+ SNBEP_PCI_UNCORE_R2PCIE,
+ SNBEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *snbep_pci_uncores[] = {
+ [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha,
+ [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc,
+ [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi,
+ [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie,
+ [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi,
+ NULL,
+};
+
+static const struct pci_device_id snbep_uncore_pci_ids[] = {
+ { /* Home Agent */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
+ },
+ { /* MC Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
+ },
+ { /* MC Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
+ },
+ { /* MC Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
+ },
+ { /* MC Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
+ },
+ { /* QPI Port 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
+ },
+ { /* QPI Port 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
+ },
+ { /* R2PCIe */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
+ },
+ { /* R3QPI Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
+ },
+ { /* R3QPI Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver snbep_uncore_pci_driver = {
+ .name = "snbep_uncore",
+ .id_table = snbep_uncore_pci_ids,
+};
+
+/*
+ * build pci bus to socket mapping
+ */
+static int snbep_pci2phy_map_init(int devid)
+{
+ struct pci_dev *ubox_dev = NULL;
+ int i, bus, nodeid;
+ int err = 0;
+ u32 config = 0;
+
+ while (1) {
+ /* find the UBOX device */
+ ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev);
+ if (!ubox_dev)
+ break;
+ bus = ubox_dev->bus->number;
+ /* get the Node ID of the local register */
+ err = pci_read_config_dword(ubox_dev, 0x40, &config);
+ if (err)
+ break;
+ nodeid = config;
+ /* get the Node ID mapping */
+ err = pci_read_config_dword(ubox_dev, 0x54, &config);
+ if (err)
+ break;
+ /*
+ * every three bits in the Node ID mapping register maps
+ * to a particular node.
+ */
+ for (i = 0; i < 8; i++) {
+ if (nodeid == ((config >> (3 * i)) & 0x7)) {
+ uncore_pcibus_to_physid[bus] = i;
+ break;
+ }
+ }
+ }
+
+ if (!err) {
+ /*
+ * For PCI bus with no UBOX device, find the next bus
+ * that has UBOX device and use its mapping.
+ */
+ i = -1;
+ for (bus = 255; bus >= 0; bus--) {
+ if (uncore_pcibus_to_physid[bus] >= 0)
+ i = uncore_pcibus_to_physid[bus];
+ else
+ uncore_pcibus_to_physid[bus] = i;
+ }
+ }
+
+ if (ubox_dev)
+ pci_dev_put(ubox_dev);
+
+ return err ? pcibios_err_to_errno(err) : 0;
+}
+
+int snbep_uncore_pci_init(void)
+{
+ int ret = snbep_pci2phy_map_init(0x3ce0);
+ if (ret)
+ return ret;
+ uncore_pci_uncores = snbep_pci_uncores;
+ uncore_pci_driver = &snbep_uncore_pci_driver;
+ return 0;
+}
+/* end of Sandy Bridge-EP uncore support */
+
+/* IvyTown uncore support */
+static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+ if (msr)
+ wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT);
+}
+
+static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box)
+{
+ struct pci_dev *pdev = box->pci_dev;
+
+ pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVBEP_PMON_BOX_CTL_INT);
+}
+
+#define IVBEP_UNCORE_MSR_OPS_COMMON_INIT() \
+ .init_box = ivbep_uncore_msr_init_box, \
+ .disable_box = snbep_uncore_msr_disable_box, \
+ .enable_box = snbep_uncore_msr_enable_box, \
+ .disable_event = snbep_uncore_msr_disable_event, \
+ .enable_event = snbep_uncore_msr_enable_event, \
+ .read_counter = uncore_msr_read_counter
+
+static struct intel_uncore_ops ivbep_uncore_msr_ops = {
+ IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+};
+
+static struct intel_uncore_ops ivbep_uncore_pci_ops = {
+ .init_box = ivbep_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_uncore_pci_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+};
+
+#define IVBEP_UNCORE_PCI_COMMON_INIT() \
+ .perf_ctr = SNBEP_PCI_PMON_CTR0, \
+ .event_ctl = SNBEP_PCI_PMON_CTL0, \
+ .event_mask = IVBEP_PMON_RAW_EVENT_MASK, \
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \
+ .ops = &ivbep_uncore_pci_ops, \
+ .format_group = &ivbep_uncore_format_group
+
+static struct attribute *ivbep_uncore_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute *ivbep_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ NULL,
+};
+
+static struct attribute *ivbep_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid.attr,
+ &format_attr_filter_link.attr,
+ &format_attr_filter_state2.attr,
+ &format_attr_filter_nid2.attr,
+ &format_attr_filter_opc2.attr,
+ &format_attr_filter_nc.attr,
+ &format_attr_filter_c6.attr,
+ &format_attr_filter_isoc.attr,
+ NULL,
+};
+
+static struct attribute *ivbep_uncore_pcu_formats_attr[] = {
+ &format_attr_event_ext.attr,
+ &format_attr_occ_sel.attr,
+ &format_attr_edge.attr,
+ &format_attr_thresh5.attr,
+ &format_attr_occ_invert.attr,
+ &format_attr_occ_edge.attr,
+ &format_attr_filter_band0.attr,
+ &format_attr_filter_band1.attr,
+ &format_attr_filter_band2.attr,
+ &format_attr_filter_band3.attr,
+ NULL,
+};
+
+static struct attribute *ivbep_uncore_qpi_formats_attr[] = {
+ &format_attr_event_ext.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_match_rds.attr,
+ &format_attr_match_rnid30.attr,
+ &format_attr_match_rnid4.attr,
+ &format_attr_match_dnid.attr,
+ &format_attr_match_mc.attr,
+ &format_attr_match_opc.attr,
+ &format_attr_match_vnw.attr,
+ &format_attr_match0.attr,
+ &format_attr_match1.attr,
+ &format_attr_mask_rds.attr,
+ &format_attr_mask_rnid30.attr,
+ &format_attr_mask_rnid4.attr,
+ &format_attr_mask_dnid.attr,
+ &format_attr_mask_mc.attr,
+ &format_attr_mask_opc.attr,
+ &format_attr_mask_vnw.attr,
+ &format_attr_mask0.attr,
+ &format_attr_mask1.attr,
+ NULL,
+};
+
+static struct attribute_group ivbep_uncore_format_group = {
+ .name = "format",
+ .attrs = ivbep_uncore_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = ivbep_uncore_ubox_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = ivbep_uncore_cbox_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_pcu_format_group = {
+ .name = "format",
+ .attrs = ivbep_uncore_pcu_formats_attr,
+};
+
+static struct attribute_group ivbep_uncore_qpi_format_group = {
+ .name = "format",
+ .attrs = ivbep_uncore_qpi_formats_attr,
+};
+
+static struct intel_uncore_type ivbep_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = SNBEP_U_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_U_MSR_PMON_CTL0,
+ .event_mask = IVBEP_U_MSR_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL,
+ .ops = &ivbep_uncore_msr_ops,
+ .format_group = &ivbep_uncore_ubox_format_group,
+};
+
+static struct extra_reg ivbep_uncore_cbox_extra_regs[] = {
+ SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+ SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+ EVENT_EXTRA_END
+};
+
+static u64 ivbep_cbox_filter_mask(int fields)
+{
+ u64 mask = 0;
+
+ if (fields & 0x1)
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_TID;
+ if (fields & 0x2)
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_LINK;
+ if (fields & 0x4)
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+ if (fields & 0x8)
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NID;
+ if (fields & 0x10) {
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_NC;
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_C6;
+ mask |= IVBEP_CB0_MSR_PMON_BOX_FILTER_ISOC;
+ }
+
+ return mask;
+}
+
+static struct event_constraint *
+ivbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ return __snbep_cbox_get_constraint(box, event, ivbep_cbox_filter_mask);
+}
+
+static int ivbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct extra_reg *er;
+ int idx = 0;
+
+ for (er = ivbep_uncore_cbox_extra_regs; er->msr; er++) {
+ if (er->event != (event->hw.config & er->config_mask))
+ continue;
+ idx |= er->idx;
+ }
+
+ if (idx) {
+ reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER +
+ SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & ivbep_cbox_filter_mask(idx);
+ reg1->idx = idx;
+ }
+ return 0;
+}
+
+static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ u64 filter = uncore_shared_reg_config(box, 0);
+ wrmsrl(reg1->reg, filter & 0xffffffff);
+ wrmsrl(reg1->reg + 6, filter >> 32);
+ }
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops ivbep_uncore_cbox_ops = {
+ .init_box = ivbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = ivbep_cbox_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = ivbep_cbox_hw_config,
+ .get_constraint = ivbep_cbox_get_constraint,
+ .put_constraint = snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .num_boxes = 15,
+ .perf_ctr_bits = 44,
+ .event_ctl = SNBEP_C0_MSR_PMON_CTL0,
+ .perf_ctr = SNBEP_C0_MSR_PMON_CTR0,
+ .event_mask = IVBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL,
+ .msr_offset = SNBEP_CBO_MSR_OFFSET,
+ .num_shared_regs = 1,
+ .constraints = snbep_uncore_cbox_constraints,
+ .ops = &ivbep_uncore_cbox_ops,
+ .format_group = &ivbep_uncore_cbox_format_group,
+};
+
+static struct intel_uncore_ops ivbep_uncore_pcu_ops = {
+ IVBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = snbep_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0,
+ .event_ctl = SNBEP_PCU_MSR_PMON_CTL0,
+ .event_mask = IVBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &ivbep_uncore_pcu_ops,
+ .format_group = &ivbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *ivbep_msr_uncores[] = {
+ &ivbep_uncore_ubox,
+ &ivbep_uncore_cbox,
+ &ivbep_uncore_pcu,
+ NULL,
+};
+
+void ivbep_uncore_cpu_init(void)
+{
+ if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+ ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+ uncore_msr_uncores = ivbep_msr_uncores;
+}
+
+static struct intel_uncore_type ivbep_uncore_ha = {
+ .name = "ha",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivbep_uncore_imc = {
+ .name = "imc",
+ .num_counters = 4,
+ .num_boxes = 8,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+ .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+ .event_descs = snbep_uncore_imc_events,
+ IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+/* registers in IRP boxes are not properly aligned */
+static unsigned ivbep_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
+static unsigned ivbep_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
+
+static void ivbep_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx],
+ hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void ivbep_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, ivbep_uncore_irp_ctls[hwc->idx], hwc->config);
+}
+
+static u64 ivbep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count = 0;
+
+ pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+ pci_read_config_dword(pdev, ivbep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+ return count;
+}
+
+static struct intel_uncore_ops ivbep_uncore_irp_ops = {
+ .init_box = ivbep_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = ivbep_uncore_irp_disable_event,
+ .enable_event = ivbep_uncore_irp_enable_event,
+ .read_counter = ivbep_uncore_irp_read_counter,
+};
+
+static struct intel_uncore_type ivbep_uncore_irp = {
+ .name = "irp",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_mask = IVBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &ivbep_uncore_irp_ops,
+ .format_group = &ivbep_uncore_format_group,
+};
+
+static struct intel_uncore_ops ivbep_uncore_qpi_ops = {
+ .init_box = ivbep_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_qpi_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+ .hw_config = snbep_qpi_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct intel_uncore_type ivbep_uncore_qpi = {
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 3,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = IVBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &ivbep_uncore_qpi_ops,
+ .format_group = &ivbep_uncore_qpi_format_group,
+};
+
+static struct intel_uncore_type ivbep_uncore_r2pcie = {
+ .name = "r2pcie",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r2pcie_constraints,
+ IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct intel_uncore_type ivbep_uncore_r3qpi = {
+ .name = "r3qpi",
+ .num_counters = 3,
+ .num_boxes = 2,
+ .perf_ctr_bits = 44,
+ .constraints = snbep_uncore_r3qpi_constraints,
+ IVBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+ IVBEP_PCI_UNCORE_HA,
+ IVBEP_PCI_UNCORE_IMC,
+ IVBEP_PCI_UNCORE_IRP,
+ IVBEP_PCI_UNCORE_QPI,
+ IVBEP_PCI_UNCORE_R2PCIE,
+ IVBEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *ivbep_pci_uncores[] = {
+ [IVBEP_PCI_UNCORE_HA] = &ivbep_uncore_ha,
+ [IVBEP_PCI_UNCORE_IMC] = &ivbep_uncore_imc,
+ [IVBEP_PCI_UNCORE_IRP] = &ivbep_uncore_irp,
+ [IVBEP_PCI_UNCORE_QPI] = &ivbep_uncore_qpi,
+ [IVBEP_PCI_UNCORE_R2PCIE] = &ivbep_uncore_r2pcie,
+ [IVBEP_PCI_UNCORE_R3QPI] = &ivbep_uncore_r3qpi,
+ NULL,
+};
+
+static const struct pci_device_id ivbep_uncore_pci_ids[] = {
+ { /* Home Agent 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 0),
+ },
+ { /* Home Agent 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_HA, 1),
+ },
+ { /* MC0 Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 0),
+ },
+ { /* MC0 Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 1),
+ },
+ { /* MC0 Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 2),
+ },
+ { /* MC0 Channel 4 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 3),
+ },
+ { /* MC1 Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 4),
+ },
+ { /* MC1 Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 5),
+ },
+ { /* MC1 Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 6),
+ },
+ { /* MC1 Channel 4 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IMC, 7),
+ },
+ { /* IRP */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_IRP, 0),
+ },
+ { /* QPI0 Port 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 0),
+ },
+ { /* QPI0 Port 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 1),
+ },
+ { /* QPI1 Port 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_QPI, 2),
+ },
+ { /* R2PCIe */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R2PCIE, 0),
+ },
+ { /* R3QPI0 Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 0),
+ },
+ { /* R3QPI0 Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 1),
+ },
+ { /* R3QPI1 Link 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVBEP_PCI_UNCORE_R3QPI, 2),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver ivbep_uncore_pci_driver = {
+ .name = "ivbep_uncore",
+ .id_table = ivbep_uncore_pci_ids,
+};
+
+int ivbep_uncore_pci_init(void)
+{
+ int ret = snbep_pci2phy_map_init(0x0e1e);
+ if (ret)
+ return ret;
+ uncore_pci_uncores = ivbep_pci_uncores;
+ uncore_pci_driver = &ivbep_uncore_pci_driver;
+ return 0;
+}
+/* end of IvyTown uncore support */
+
+/* Haswell-EP uncore support */
+static struct attribute *hswep_uncore_ubox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh5.attr,
+ &format_attr_filter_tid2.attr,
+ &format_attr_filter_cid.attr,
+ NULL,
+};
+
+static struct attribute_group hswep_uncore_ubox_format_group = {
+ .name = "format",
+ .attrs = hswep_uncore_ubox_formats_attr,
+};
+
+static int hswep_ubox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ reg1->reg = HSWEP_U_MSR_PMON_FILTER;
+ reg1->config = event->attr.config1 & HSWEP_U_MSR_PMON_BOX_FILTER_MASK;
+ reg1->idx = 0;
+ return 0;
+}
+
+static struct intel_uncore_ops hswep_uncore_ubox_ops = {
+ SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = hswep_ubox_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
+static struct intel_uncore_type hswep_uncore_ubox = {
+ .name = "ubox",
+ .num_counters = 2,
+ .num_boxes = 1,
+ .perf_ctr_bits = 44,
+ .fixed_ctr_bits = 48,
+ .perf_ctr = HSWEP_U_MSR_PMON_CTR0,
+ .event_ctl = HSWEP_U_MSR_PMON_CTL0,
+ .event_mask = SNBEP_U_MSR_PMON_RAW_EVENT_MASK,
+ .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR,
+ .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL,
+ .num_shared_regs = 1,
+ .ops = &hswep_uncore_ubox_ops,
+ .format_group = &hswep_uncore_ubox_format_group,
+};
+
+static struct attribute *hswep_uncore_cbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_thresh8.attr,
+ &format_attr_filter_tid3.attr,
+ &format_attr_filter_link2.attr,
+ &format_attr_filter_state3.attr,
+ &format_attr_filter_nid2.attr,
+ &format_attr_filter_opc2.attr,
+ &format_attr_filter_nc.attr,
+ &format_attr_filter_c6.attr,
+ &format_attr_filter_isoc.attr,
+ NULL,
+};
+
+static struct attribute_group hswep_uncore_cbox_format_group = {
+ .name = "format",
+ .attrs = hswep_uncore_cbox_formats_attr,
+};
+
+static struct event_constraint hswep_uncore_cbox_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x01, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x09, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x3b, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x3e, 0x1),
+ EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg hswep_uncore_cbox_extra_regs[] = {
+ SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
+ SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x4),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4028, 0x40ff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4032, 0x40ff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4029, 0x40ff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4033, 0x40ff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x402A, 0x40ff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x12),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8),
+ EVENT_EXTRA_END
+};
+
+static u64 hswep_cbox_filter_mask(int fields)
+{
+ u64 mask = 0;
+ if (fields & 0x1)
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_TID;
+ if (fields & 0x2)
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_LINK;
+ if (fields & 0x4)
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_STATE;
+ if (fields & 0x8)
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NID;
+ if (fields & 0x10) {
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_OPC;
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_NC;
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_C6;
+ mask |= HSWEP_CB0_MSR_PMON_BOX_FILTER_ISOC;
+ }
+ return mask;
+}
+
+static struct event_constraint *
+hswep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+ return __snbep_cbox_get_constraint(box, event, hswep_cbox_filter_mask);
+}
+
+static int hswep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+ struct extra_reg *er;
+ int idx = 0;
+
+ for (er = hswep_uncore_cbox_extra_regs; er->msr; er++) {
+ if (er->event != (event->hw.config & er->config_mask))
+ continue;
+ idx |= er->idx;
+ }
+
+ if (idx) {
+ reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 +
+ HSWEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
+ reg1->config = event->attr.config1 & hswep_cbox_filter_mask(idx);
+ reg1->idx = idx;
+ }
+ return 0;
+}
+
+static void hswep_cbox_enable_event(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ u64 filter = uncore_shared_reg_config(box, 0);
+ wrmsrl(reg1->reg, filter & 0xffffffff);
+ wrmsrl(reg1->reg + 1, filter >> 32);
+ }
+
+ wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops hswep_uncore_cbox_ops = {
+ .init_box = snbep_uncore_msr_init_box,
+ .disable_box = snbep_uncore_msr_disable_box,
+ .enable_box = snbep_uncore_msr_enable_box,
+ .disable_event = snbep_uncore_msr_disable_event,
+ .enable_event = hswep_cbox_enable_event,
+ .read_counter = uncore_msr_read_counter,
+ .hw_config = hswep_cbox_hw_config,
+ .get_constraint = hswep_cbox_get_constraint,
+ .put_constraint = snbep_cbox_put_constraint,
+};
+
+static struct intel_uncore_type hswep_uncore_cbox = {
+ .name = "cbox",
+ .num_counters = 4,
+ .num_boxes = 18,
+ .perf_ctr_bits = 44,
+ .event_ctl = HSWEP_C0_MSR_PMON_CTL0,
+ .perf_ctr = HSWEP_C0_MSR_PMON_CTR0,
+ .event_mask = SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_CBO_MSR_OFFSET,
+ .num_shared_regs = 1,
+ .constraints = hswep_uncore_cbox_constraints,
+ .ops = &hswep_uncore_cbox_ops,
+ .format_group = &hswep_uncore_cbox_format_group,
+};
+
+/*
+ * Write SBOX Initialization register bit by bit to avoid spurious #GPs
+ */
+static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box)
+{
+ unsigned msr = uncore_msr_box_ctl(box);
+
+ if (msr) {
+ u64 init = SNBEP_PMON_BOX_CTL_INT;
+ u64 flags = 0;
+ int i;
+
+ for_each_set_bit(i, (unsigned long *)&init, 64) {
+ flags |= (1ULL << i);
+ wrmsrl(msr, flags);
+ }
+ }
+}
+
+static struct intel_uncore_ops hswep_uncore_sbox_msr_ops = {
+ __SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .init_box = hswep_uncore_sbox_msr_init_box
+};
+
+static struct attribute *hswep_uncore_sbox_formats_attr[] = {
+ &format_attr_event.attr,
+ &format_attr_umask.attr,
+ &format_attr_edge.attr,
+ &format_attr_tid_en.attr,
+ &format_attr_inv.attr,
+ &format_attr_thresh8.attr,
+ NULL,
+};
+
+static struct attribute_group hswep_uncore_sbox_format_group = {
+ .name = "format",
+ .attrs = hswep_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_type hswep_uncore_sbox = {
+ .name = "sbox",
+ .num_counters = 4,
+ .num_boxes = 4,
+ .perf_ctr_bits = 44,
+ .event_ctl = HSWEP_S0_MSR_PMON_CTL0,
+ .perf_ctr = HSWEP_S0_MSR_PMON_CTR0,
+ .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL,
+ .msr_offset = HSWEP_SBOX_MSR_OFFSET,
+ .ops = &hswep_uncore_sbox_msr_ops,
+ .format_group = &hswep_uncore_sbox_format_group,
+};
+
+static int hswep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK;
+
+ if (ev_sel >= 0xb && ev_sel <= 0xe) {
+ reg1->reg = HSWEP_PCU_MSR_PMON_BOX_FILTER;
+ reg1->idx = ev_sel - 0xb;
+ reg1->config = event->attr.config1 & (0xff << reg1->idx);
+ }
+ return 0;
+}
+
+static struct intel_uncore_ops hswep_uncore_pcu_ops = {
+ SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
+ .hw_config = hswep_pcu_hw_config,
+ .get_constraint = snbep_pcu_get_constraint,
+ .put_constraint = snbep_pcu_put_constraint,
+};
+
+static struct intel_uncore_type hswep_uncore_pcu = {
+ .name = "pcu",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0,
+ .event_ctl = HSWEP_PCU_MSR_PMON_CTL0,
+ .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK,
+ .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &hswep_uncore_pcu_ops,
+ .format_group = &snbep_uncore_pcu_format_group,
+};
+
+static struct intel_uncore_type *hswep_msr_uncores[] = {
+ &hswep_uncore_ubox,
+ &hswep_uncore_cbox,
+ &hswep_uncore_sbox,
+ &hswep_uncore_pcu,
+ NULL,
+};
+
+void hswep_uncore_cpu_init(void)
+{
+ if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
+ hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+ /* Detect 6-8 core systems with only two SBOXes */
+ if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+ u32 capid4;
+
+ pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+ 0x94, &capid4);
+ if (((capid4 >> 6) & 0x3) == 0)
+ hswep_uncore_sbox.num_boxes = 2;
+ }
+
+ uncore_msr_uncores = hswep_msr_uncores;
+}
+
+static struct intel_uncore_type hswep_uncore_ha = {
+ .name = "ha",
+ .num_counters = 5,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct uncore_event_desc hswep_uncore_imc_events[] = {
+ INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x00,umask=0x00"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read, "event=0x04,umask=0x03"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+ INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
+ { /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type hswep_uncore_imc = {
+ .name = "imc",
+ .num_counters = 5,
+ .num_boxes = 8,
+ .perf_ctr_bits = 48,
+ .fixed_ctr_bits = 48,
+ .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR,
+ .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL,
+ .event_descs = hswep_uncore_imc_events,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static unsigned hswep_uncore_irp_ctrs[] = {0xa0, 0xa8, 0xb0, 0xb8};
+
+static u64 hswep_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count = 0;
+
+ pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+ pci_read_config_dword(pdev, hswep_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+ return count;
+}
+
+static struct intel_uncore_ops hswep_uncore_irp_ops = {
+ .init_box = snbep_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = ivbep_uncore_irp_disable_event,
+ .enable_event = ivbep_uncore_irp_enable_event,
+ .read_counter = hswep_uncore_irp_read_counter,
+};
+
+static struct intel_uncore_type hswep_uncore_irp = {
+ .name = "irp",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_mask = SNBEP_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &hswep_uncore_irp_ops,
+ .format_group = &snbep_uncore_format_group,
+};
+
+static struct intel_uncore_type hswep_uncore_qpi = {
+ .name = "qpi",
+ .num_counters = 5,
+ .num_boxes = 3,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_qpi_ops,
+ .format_group = &snbep_uncore_qpi_format_group,
+};
+
+static struct event_constraint hswep_uncore_r2pcie_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x24, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x27, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2a, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x2b, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x35, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type hswep_uncore_r2pcie = {
+ .name = "r2pcie",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .constraints = hswep_uncore_r2pcie_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+static struct event_constraint hswep_uncore_r3qpi_constraints[] = {
+ UNCORE_EVENT_CONSTRAINT(0x01, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x07, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x08, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x09, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x0a, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x0e, 0x7),
+ UNCORE_EVENT_CONSTRAINT(0x10, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x11, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x12, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x13, 0x1),
+ UNCORE_EVENT_CONSTRAINT(0x14, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x15, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x1f, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x20, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x21, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x22, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x23, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x25, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x26, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x28, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x29, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2c, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2d, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2e, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x2f, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x31, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x32, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x33, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x34, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x36, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x37, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x38, 0x3),
+ UNCORE_EVENT_CONSTRAINT(0x39, 0x3),
+ EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type hswep_uncore_r3qpi = {
+ .name = "r3qpi",
+ .num_counters = 4,
+ .num_boxes = 3,
+ .perf_ctr_bits = 44,
+ .constraints = hswep_uncore_r3qpi_constraints,
+ SNBEP_UNCORE_PCI_COMMON_INIT(),
+};
+
+enum {
+ HSWEP_PCI_UNCORE_HA,
+ HSWEP_PCI_UNCORE_IMC,
+ HSWEP_PCI_UNCORE_IRP,
+ HSWEP_PCI_UNCORE_QPI,
+ HSWEP_PCI_UNCORE_R2PCIE,
+ HSWEP_PCI_UNCORE_R3QPI,
+};
+
+static struct intel_uncore_type *hswep_pci_uncores[] = {
+ [HSWEP_PCI_UNCORE_HA] = &hswep_uncore_ha,
+ [HSWEP_PCI_UNCORE_IMC] = &hswep_uncore_imc,
+ [HSWEP_PCI_UNCORE_IRP] = &hswep_uncore_irp,
+ [HSWEP_PCI_UNCORE_QPI] = &hswep_uncore_qpi,
+ [HSWEP_PCI_UNCORE_R2PCIE] = &hswep_uncore_r2pcie,
+ [HSWEP_PCI_UNCORE_R3QPI] = &hswep_uncore_r3qpi,
+ NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
+ { /* Home Agent 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f30),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 0),
+ },
+ { /* Home Agent 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f38),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_HA, 1),
+ },
+ { /* MC0 Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb0),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 0),
+ },
+ { /* MC0 Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb1),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 1),
+ },
+ { /* MC0 Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb4),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 2),
+ },
+ { /* MC0 Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fb5),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 3),
+ },
+ { /* MC1 Channel 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd0),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 4),
+ },
+ { /* MC1 Channel 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd1),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 5),
+ },
+ { /* MC1 Channel 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd4),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 6),
+ },
+ { /* MC1 Channel 3 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fd5),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IMC, 7),
+ },
+ { /* IRP */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f39),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_IRP, 0),
+ },
+ { /* QPI0 Port 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f32),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 0),
+ },
+ { /* QPI0 Port 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f33),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 1),
+ },
+ { /* QPI1 Port 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3a),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_QPI, 2),
+ },
+ { /* R2PCIe */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f34),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R2PCIE, 0),
+ },
+ { /* R3QPI0 Link 0 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f36),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 0),
+ },
+ { /* R3QPI0 Link 1 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f37),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 1),
+ },
+ { /* R3QPI1 Link 2 */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f3e),
+ .driver_data = UNCORE_PCI_DEV_DATA(HSWEP_PCI_UNCORE_R3QPI, 2),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f86),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
+ },
+ { /* QPI Port 1 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2f96),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
+ },
+ { /* PCU.3 (for Capability registers) */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ HSWEP_PCI_PCU_3),
+ },
+ { /* end: all zeroes */ }
+};
+
+static struct pci_driver hswep_uncore_pci_driver = {
+ .name = "hswep_uncore",
+ .id_table = hswep_uncore_pci_ids,
+};
+
+int hswep_uncore_pci_init(void)
+{
+ int ret = snbep_pci2phy_map_init(0x2f1e);
+ if (ret)
+ return ret;
+ uncore_pci_uncores = hswep_pci_uncores;
+ uncore_pci_driver = &hswep_uncore_pci_driver;
+ return 0;
+}
+/* end of Haswell-EP uncore support */
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
index 838fa8772c62..5b0c232d1ee6 100644
--- a/arch/x86/kernel/cpu/perf_event_knc.c
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -217,7 +217,7 @@ static int knc_pmu_handle_irq(struct pt_regs *regs)
int bit, loops;
u64 status;
- cpuc = &__get_cpu_var(cpu_hw_events);
+ cpuc = this_cpu_ptr(&cpu_hw_events);
knc_pmu_disable_all();
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 5d466b7d8609..f2e56783af3d 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -915,7 +915,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
static void p4_pmu_disable_all(void)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -984,7 +984,7 @@ static void p4_pmu_enable_event(struct perf_event *event)
static void p4_pmu_enable_all(int added)
{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
@@ -1004,7 +1004,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
int idx, handled = 0;
u64 val;
- cpuc = &__get_cpu_var(cpu_hw_events);
+ cpuc = this_cpu_ptr(&cpu_hw_events);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
int overflow;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 5433658e598d..e7d8c7608471 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -72,7 +72,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
if (c->x86_mask || c->cpuid_level >= 0)
seq_printf(m, "stepping\t: %d\n", c->x86_mask);
else
- seq_printf(m, "stepping\t: unknown\n");
+ seq_puts(m, "stepping\t: unknown\n");
if (c->microcode)
seq_printf(m, "microcode\t: 0x%x\n", c->microcode);
@@ -92,12 +92,12 @@ static int show_cpuinfo(struct seq_file *m, void *v)
show_cpuinfo_core(m, c, cpu);
show_cpuinfo_misc(m, c);
- seq_printf(m, "flags\t\t:");
+ seq_puts(m, "flags\t\t:");
for (i = 0; i < 32*NCAPINTS; i++)
if (cpu_has(c, i) && x86_cap_flags[i] != NULL)
seq_printf(m, " %s", x86_cap_flags[i]);
- seq_printf(m, "\nbugs\t\t:");
+ seq_puts(m, "\nbugs\t\t:");
for (i = 0; i < 32*NBUGINTS; i++) {
unsigned int bug_bit = 32*NCAPINTS + i;
@@ -118,7 +118,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n",
c->x86_phys_bits, c->x86_virt_bits);
- seq_printf(m, "power management:");
+ seq_puts(m, "power management:");
for (i = 0; i < 32; i++) {
if (c->x86_power & (1 << i)) {
if (i < ARRAY_SIZE(x86_power_flags) &&
@@ -131,7 +131,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
}
}
- seq_printf(m, "\n\n");
+ seq_puts(m, "\n\n");
return 0;
}
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 4a8013d55947..60639093d536 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -36,6 +36,11 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
{ X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 },
{ X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 },
{ X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 },
+ { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 },
+ { X86_FEATURE_HWP_NOITFY, CR_EAX, 8, 0x00000006, 0 },
+ { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 },
+ { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 },
+ { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 },
{ X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 },
{ X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 },
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 3225ae6c5180..83741a71558f 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -143,7 +143,7 @@ static int cpuid_device_create(int cpu)
dev = device_create(cpuid_class, NULL, MKDEV(CPUID_MAJOR, cpu), NULL,
"cpu%d", cpu);
- return IS_ERR(dev) ? PTR_ERR(dev) : 0;
+ return PTR_ERR_OR_ZERO(dev);
}
static void cpuid_device_destroy(int cpu)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a618fcd2c07d..aceb2f90c716 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -28,6 +28,7 @@
#include <asm/nmi.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
#include <asm/cpu.h>
@@ -237,7 +238,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
ced->max_nr_ranges++;
/* If crashk_low_res is not 0, another range split possible */
- if (crashk_low_res.end != 0)
+ if (crashk_low_res.end)
ced->max_nr_ranges++;
}
@@ -335,9 +336,11 @@ static int elf_header_exclude_ranges(struct crash_elf_data *ced,
if (ret)
return ret;
- ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
- if (ret)
- return ret;
+ if (crashk_low_res.end) {
+ ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
+ if (ret)
+ return ret;
+ }
/* Exclude GART region */
if (ced->gart_end) {
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 1abcb50b48ae..ff86f19b5758 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = {
[ DEBUG_STACK-1 ] = "#DB",
[ NMI_STACK-1 ] = "NMI",
[ DOUBLEFAULT_STACK-1 ] = "#DF",
- [ STACKFAULT_STACK-1 ] = "#SS",
[ MCE_STACK-1 ] = "#MC",
#if DEBUG_STKSZ > EXCEPTION_STKSZ
[ N_EXCEPTION_STACKS ...
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 988c00a1f60d..dd2f07ae9d0c 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -682,15 +682,14 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len)
* hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
*
* This function requires the e820 map to be sorted and without any
- * overlapping entries and assumes the first e820 area to be RAM.
+ * overlapping entries.
*/
void __init e820_mark_nosave_regions(unsigned long limit_pfn)
{
int i;
- unsigned long pfn;
+ unsigned long pfn = 0;
- pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
- for (i = 1; i < e820.nr_map; i++) {
+ for (i = 0; i < e820.nr_map; i++) {
struct e820entry *ei = &e820.map[i];
if (pfn < PFN_UP(ei->addr))
@@ -1115,8 +1114,8 @@ void __init memblock_find_dma_reserve(void)
* at first, and assume boot_mem will not take below MAX_DMA_PFN
*/
for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
- start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN);
- end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN);
+ start_pfn = min(start_pfn, MAX_DMA_PFN);
+ end_pfn = min(end_pfn, MAX_DMA_PFN);
nr_pages += end_pfn - start_pfn;
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 2e1a6853e00c..fe9f0b79a18b 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -455,6 +455,23 @@ struct intel_stolen_funcs {
u32 (*base)(int num, int slot, int func, size_t size);
};
+static size_t __init gen9_stolen_size(int num, int slot, int func)
+{
+ u16 gmch_ctrl;
+
+ gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
+ gmch_ctrl >>= BDW_GMCH_GMS_SHIFT;
+ gmch_ctrl &= BDW_GMCH_GMS_MASK;
+
+ if (gmch_ctrl < 0xf0)
+ return gmch_ctrl << 25; /* 32 MB units */
+ else
+ /* 4MB increments starting at 0xf0 for 4MB */
+ return (gmch_ctrl - 0xf0 + 1) << 22;
+}
+
+typedef size_t (*stolen_size_fn)(int num, int slot, int func);
+
static const struct intel_stolen_funcs i830_stolen_funcs __initconst = {
.base = i830_stolen_base,
.size = i830_stolen_size,
@@ -490,6 +507,11 @@ static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = {
.size = gen8_stolen_size,
};
+static const struct intel_stolen_funcs gen9_stolen_funcs __initconst = {
+ .base = intel_stolen_base,
+ .size = gen9_stolen_size,
+};
+
static const struct intel_stolen_funcs chv_stolen_funcs __initconst = {
.base = intel_stolen_base,
.size = chv_stolen_size,
@@ -523,6 +545,7 @@ static const struct pci_device_id intel_stolen_ids[] __initconst = {
INTEL_BDW_M_IDS(&gen8_stolen_funcs),
INTEL_BDW_D_IDS(&gen8_stolen_funcs),
INTEL_CHV_IDS(&chv_stolen_funcs),
+ INTEL_SKL_IDS(&gen9_stolen_funcs),
};
static void __init intel_graphics_stolen(int num, int slot, int func)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 4b0e1dfa2226..000d4199b03e 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -447,16 +447,14 @@ sysenter_exit:
sysenter_audit:
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp)
jnz syscall_trace_entry
- addl $4,%esp
- CFI_ADJUST_CFA_OFFSET -4
- /* %esi already in 8(%esp) 6th arg: 4th syscall arg */
- /* %edx already in 4(%esp) 5th arg: 3rd syscall arg */
- /* %ecx already in 0(%esp) 4th arg: 2nd syscall arg */
- movl %ebx,%ecx /* 3rd arg: 1st syscall arg */
- movl %eax,%edx /* 2nd arg: syscall number */
- movl $AUDIT_ARCH_I386,%eax /* 1st arg: audit arch */
+ /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */
+ movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */
+ /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */
+ pushl_cfi PT_ESI(%esp) /* a3: 5th arg */
+ pushl_cfi PT_EDX+4(%esp) /* a2: 4th arg */
call __audit_syscall_entry
- pushl_cfi %ebx
+ popl_cfi %ecx /* get that remapped edx off the stack */
+ popl_cfi %ecx /* get that remapped esi off the stack */
movl PT_EAX(%esp),%eax /* reload syscall number */
jmp sysenter_do_call
@@ -734,10 +732,10 @@ ENTRY(interrupt)
ENTRY(irq_entries_start)
RING0_INT_FRAME
vector=FIRST_EXTERNAL_VECTOR
-.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
.balign 32
.rept 7
- .if vector < NR_VECTORS
+ .if vector < FIRST_SYSTEM_VECTOR
.if vector <> FIRST_EXTERNAL_VECTOR
CFI_ADJUST_CFA_OFFSET -4
.endif
@@ -1193,10 +1191,10 @@ ENTRY(ftrace_graph_caller)
pushl %eax
pushl %ecx
pushl %edx
- movl 0xc(%esp), %edx
- lea 0x4(%ebp), %eax
+ movl 0xc(%esp), %eax
+ lea 0x4(%ebp), %edx
movl (%ebp), %ecx
- subl $MCOUNT_INSN_SIZE, %edx
+ subl $MCOUNT_INSN_SIZE, %eax
call prepare_ftrace_return
popl %edx
popl %ecx
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2fac1343a90b..9ebaf63ba182 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -404,8 +404,8 @@ GLOBAL(system_call_after_swapgs)
* and short:
*/
ENABLE_INTERRUPTS(CLBR_NONE)
- SAVE_ARGS 8,0
- movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
+ SAVE_ARGS 8, 0, rax_enosys=1
+ movq_cfi rax,(ORIG_RAX-ARGOFFSET)
movq %rcx,RIP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rip,RIP-ARGOFFSET
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
@@ -417,7 +417,7 @@ system_call_fastpath:
andl $__SYSCALL_MASK,%eax
cmpl $__NR_syscall_max,%eax
#endif
- ja badsys
+ ja ret_from_sys_call /* and return regs->ax */
movq %r10,%rcx
call *sys_call_table(,%rax,8) # XXX: rip relative
movq %rax,RAX-ARGOFFSET(%rsp)
@@ -476,28 +476,8 @@ sysret_signal:
FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
jmp int_check_syscall_exit_work
-badsys:
- movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
- jmp ret_from_sys_call
-
#ifdef CONFIG_AUDITSYSCALL
/*
- * Fast path for syscall audit without full syscall trace.
- * We just call __audit_syscall_entry() directly, and then
- * jump back to the normal fast path.
- */
-auditsys:
- movq %r10,%r9 /* 6th arg: 4th syscall arg */
- movq %rdx,%r8 /* 5th arg: 3rd syscall arg */
- movq %rsi,%rcx /* 4th arg: 2nd syscall arg */
- movq %rdi,%rdx /* 3rd arg: 1st syscall arg */
- movq %rax,%rsi /* 2nd arg: syscall number */
- movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */
- call __audit_syscall_entry
- LOAD_ARGS 0 /* reload call-clobbered registers */
- jmp system_call_fastpath
-
- /*
* Return fast path for syscall audit. Call __audit_syscall_exit()
* directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
* masked off.
@@ -514,18 +494,25 @@ sysret_audit:
/* Do syscall tracing */
tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
- jz auditsys
-#endif
+ leaq -REST_SKIP(%rsp), %rdi
+ movq $AUDIT_ARCH_X86_64, %rsi
+ call syscall_trace_enter_phase1
+ test %rax, %rax
+ jnz tracesys_phase2 /* if needed, run the slow path */
+ LOAD_ARGS 0 /* else restore clobbered regs */
+ jmp system_call_fastpath /* and return to the fast path */
+
+tracesys_phase2:
SAVE_REST
- movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
FIXUP_TOP_OF_STACK %rdi
- movq %rsp,%rdi
- call syscall_trace_enter
+ movq %rsp, %rdi
+ movq $AUDIT_ARCH_X86_64, %rsi
+ movq %rax,%rdx
+ call syscall_trace_enter_phase2
+
/*
* Reload arg registers from stack in case ptrace changed them.
- * We don't reload %rax because syscall_trace_enter() returned
+ * We don't reload %rax because syscall_trace_entry_phase2() returned
* the value it wants us to use in the table lookup.
*/
LOAD_ARGS ARGOFFSET, 1
@@ -536,7 +523,7 @@ tracesys:
andl $__SYSCALL_MASK,%eax
cmpl $__NR_syscall_max,%eax
#endif
- ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */
+ ja int_ret_from_sys_call /* RAX(%rsp) is already set */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
movq %rax,RAX-ARGOFFSET(%rsp)
@@ -665,6 +652,20 @@ ENTRY(stub_execve)
CFI_ENDPROC
END(stub_execve)
+ENTRY(stub_execveat)
+ CFI_STARTPROC
+ addq $8, %rsp
+ PARTIAL_FRAME 0
+ SAVE_REST
+ FIXUP_TOP_OF_STACK %r11
+ call sys_execveat
+ RESTORE_TOP_OF_STACK %r11
+ movq %rax,RAX(%rsp)
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+END(stub_execveat)
+
/*
* sigreturn is special because it needs to restore all registers on return.
* This cannot be done with SYSRET, so use the IRET return path instead.
@@ -710,6 +711,20 @@ ENTRY(stub_x32_execve)
CFI_ENDPROC
END(stub_x32_execve)
+ENTRY(stub_x32_execveat)
+ CFI_STARTPROC
+ addq $8, %rsp
+ PARTIAL_FRAME 0
+ SAVE_REST
+ FIXUP_TOP_OF_STACK %r11
+ call compat_sys_execveat
+ RESTORE_TOP_OF_STACK %r11
+ movq %rax,RAX(%rsp)
+ RESTORE_REST
+ jmp int_ret_from_sys_call
+ CFI_ENDPROC
+END(stub_x32_execveat)
+
#endif
/*
@@ -725,10 +740,10 @@ ENTRY(interrupt)
ENTRY(irq_entries_start)
INTR_FRAME
vector=FIRST_EXTERNAL_VECTOR
-.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+.rept (FIRST_SYSTEM_VECTOR-FIRST_EXTERNAL_VECTOR+6)/7
.balign 32
.rept 7
- .if vector < NR_VECTORS
+ .if vector < FIRST_SYSTEM_VECTOR
.if vector <> FIRST_EXTERNAL_VECTOR
CFI_ADJUST_CFA_OFFSET -8
.endif
@@ -841,9 +856,15 @@ ENTRY(native_iret)
jnz native_irq_return_ldt
#endif
+.global native_irq_return_iret
native_irq_return_iret:
+ /*
+ * This may fault. Non-paranoid faults on return to userspace are
+ * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
+ * Double-faults due to espfix64 are handled in do_double_fault.
+ * Other faults here are fatal.
+ */
iretq
- _ASM_EXTABLE(native_irq_return_iret, bad_iret)
#ifdef CONFIG_X86_ESPFIX64
native_irq_return_ldt:
@@ -871,25 +892,6 @@ native_irq_return_ldt:
jmp native_irq_return_iret
#endif
- .section .fixup,"ax"
-bad_iret:
- /*
- * The iret traps when the %cs or %ss being restored is bogus.
- * We've lost the original trap vector and error code.
- * #GPF is the most likely one to get for an invalid selector.
- * So pretend we completed the iret and took the #GPF in user mode.
- *
- * We are now running with the kernel GS after exception recovery.
- * But error_entry expects us to have user GS to match the user %cs,
- * so swap back.
- */
- pushq $0
-
- SWAPGS
- jmp general_protection
-
- .previous
-
/* edi: workmask, edx: work */
retint_careful:
CFI_RESTORE_STATE
@@ -935,37 +937,6 @@ ENTRY(retint_kernel)
CFI_ENDPROC
END(common_interrupt)
- /*
- * If IRET takes a fault on the espfix stack, then we
- * end up promoting it to a doublefault. In that case,
- * modify the stack to make it look like we just entered
- * the #GP handler from user space, similar to bad_iret.
- */
-#ifdef CONFIG_X86_ESPFIX64
- ALIGN
-__do_double_fault:
- XCPT_FRAME 1 RDI+8
- movq RSP(%rdi),%rax /* Trap on the espfix stack? */
- sarq $PGDIR_SHIFT,%rax
- cmpl $ESPFIX_PGD_ENTRY,%eax
- jne do_double_fault /* No, just deliver the fault */
- cmpl $__KERNEL_CS,CS(%rdi)
- jne do_double_fault
- movq RIP(%rdi),%rax
- cmpq $native_irq_return_iret,%rax
- jne do_double_fault /* This shouldn't happen... */
- movq PER_CPU_VAR(kernel_stack),%rax
- subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */
- movq %rax,RSP(%rdi)
- movq $0,(%rax) /* Missing (lost) #GP error code */
- movq $general_protection,RIP(%rdi)
- retq
- CFI_ENDPROC
-END(__do_double_fault)
-#else
-# define __do_double_fault do_double_fault
-#endif
-
/*
* APIC interrupts.
*/
@@ -1137,7 +1108,7 @@ idtentry overflow do_overflow has_error_code=0
idtentry bounds do_bounds has_error_code=0
idtentry invalid_op do_invalid_op has_error_code=0
idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault __do_double_fault has_error_code=1 paranoid=1
+idtentry double_fault do_double_fault has_error_code=1 paranoid=1
idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
idtentry invalid_TSS do_invalid_TSS has_error_code=1
idtentry segment_not_present do_segment_not_present has_error_code=1
@@ -1302,7 +1273,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1
+idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN
idtentry xen_debug do_debug has_error_code=0
idtentry xen_int3 do_int3 has_error_code=0
@@ -1412,17 +1383,16 @@ error_sti:
/*
* There are two places in the kernel that can potentially fault with
- * usergs. Handle them here. The exception handlers after iret run with
- * kernel gs again, so don't set the user space flag. B stepping K8s
- * sometimes report an truncated RIP for IRET exceptions returning to
- * compat mode. Check for these here too.
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
*/
error_kernelspace:
CFI_REL_OFFSET rcx, RCX+8
incl %ebx
leaq native_irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
- je error_swapgs
+ je error_bad_iret
movl %ecx,%eax /* zero extend */
cmpq %rax,RIP+8(%rsp)
je bstep_iret
@@ -1433,7 +1403,15 @@ error_kernelspace:
bstep_iret:
/* Fix truncated RIP */
movq %rcx,RIP+8(%rsp)
- jmp error_swapgs
+ /* fall through */
+
+error_bad_iret:
+ SWAPGS
+ mov %rsp,%rdi
+ call fixup_bad_iret
+ mov %rax,%rsp
+ decl %ebx /* Return to usergs */
+ jmp error_sti
CFI_ENDPROC
END(error_entry)
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index 94d857fb1033..f5d0730e7b08 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -122,9 +122,6 @@ static void init_espfix_random(void)
void __init init_espfix_bsp(void)
{
pgd_t *pgd_p;
- pteval_t ptemask;
-
- ptemask = __supported_pte_mask;
/* Install the espfix pud into the kernel page directory */
pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 3386dc9aa333..2142376dc8c6 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -17,6 +17,7 @@
#include <linux/ftrace.h>
#include <linux/percpu.h>
#include <linux/sched.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/module.h>
@@ -47,7 +48,7 @@ int ftrace_arch_code_modify_post_process(void)
union ftrace_code_union {
char code[MCOUNT_INSN_SIZE];
struct {
- char e8;
+ unsigned char e8;
int offset;
} __attribute__((packed));
};
@@ -582,7 +583,7 @@ void ftrace_replace_code(int enable)
remove_breakpoints:
pr_warn("Failed on %s (%d):\n", report, count);
- ftrace_bug(ret, rec ? rec->ip : 0);
+ ftrace_bug(ret, rec);
for_ftrace_rec_iter(iter) {
rec = ftrace_rec_iter_record(iter);
/*
@@ -644,13 +645,8 @@ int __init ftrace_dyn_arch_init(void)
{
return 0;
}
-#endif
-
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-
-#ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
+#if defined(CONFIG_X86_64) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
{
static union ftrace_code_union calc;
@@ -664,6 +660,280 @@ static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
*/
return calc.code;
}
+#endif
+
+/* Currently only x86_64 supports dynamic trampolines */
+#ifdef CONFIG_X86_64
+
+#ifdef CONFIG_MODULES
+#include <linux/moduleloader.h>
+/* Module allocation simplifies allocating memory for code */
+static inline void *alloc_tramp(unsigned long size)
+{
+ return module_alloc(size);
+}
+static inline void tramp_free(void *tramp)
+{
+ module_free(NULL, tramp);
+}
+#else
+/* Trampolines can only be created if modules are supported */
+static inline void *alloc_tramp(unsigned long size)
+{
+ return NULL;
+}
+static inline void tramp_free(void *tramp) { }
+#endif
+
+/* Defined as markers to the end of the ftrace default trampolines */
+extern void ftrace_caller_end(void);
+extern void ftrace_regs_caller_end(void);
+extern void ftrace_return(void);
+extern void ftrace_caller_op_ptr(void);
+extern void ftrace_regs_caller_op_ptr(void);
+
+/* movq function_trace_op(%rip), %rdx */
+/* 0x48 0x8b 0x15 <offset-to-ftrace_trace_op (4 bytes)> */
+#define OP_REF_SIZE 7
+
+/*
+ * The ftrace_ops is passed to the function callback. Since the
+ * trampoline only services a single ftrace_ops, we can pass in
+ * that ops directly.
+ *
+ * The ftrace_op_code_union is used to create a pointer to the
+ * ftrace_ops that will be passed to the callback function.
+ */
+union ftrace_op_code_union {
+ char code[OP_REF_SIZE];
+ struct {
+ char op[3];
+ int offset;
+ } __attribute__((packed));
+};
+
+static unsigned long
+create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
+{
+ unsigned const char *jmp;
+ unsigned long start_offset;
+ unsigned long end_offset;
+ unsigned long op_offset;
+ unsigned long offset;
+ unsigned long size;
+ unsigned long ip;
+ unsigned long *ptr;
+ void *trampoline;
+ /* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */
+ unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
+ union ftrace_op_code_union op_ptr;
+ int ret;
+
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
+ start_offset = (unsigned long)ftrace_regs_caller;
+ end_offset = (unsigned long)ftrace_regs_caller_end;
+ op_offset = (unsigned long)ftrace_regs_caller_op_ptr;
+ } else {
+ start_offset = (unsigned long)ftrace_caller;
+ end_offset = (unsigned long)ftrace_caller_end;
+ op_offset = (unsigned long)ftrace_caller_op_ptr;
+ }
+
+ size = end_offset - start_offset;
+
+ /*
+ * Allocate enough size to store the ftrace_caller code,
+ * the jmp to ftrace_return, as well as the address of
+ * the ftrace_ops this trampoline is used for.
+ */
+ trampoline = alloc_tramp(size + MCOUNT_INSN_SIZE + sizeof(void *));
+ if (!trampoline)
+ return 0;
+
+ *tramp_size = size + MCOUNT_INSN_SIZE + sizeof(void *);
+
+ /* Copy ftrace_caller onto the trampoline memory */
+ ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+ if (WARN_ON(ret < 0)) {
+ tramp_free(trampoline);
+ return 0;
+ }
+
+ ip = (unsigned long)trampoline + size;
+
+ /* The trampoline ends with a jmp to ftrace_return */
+ jmp = ftrace_jmp_replace(ip, (unsigned long)ftrace_return);
+ memcpy(trampoline + size, jmp, MCOUNT_INSN_SIZE);
+
+ /*
+ * The address of the ftrace_ops that is used for this trampoline
+ * is stored at the end of the trampoline. This will be used to
+ * load the third parameter for the callback. Basically, that
+ * location at the end of the trampoline takes the place of
+ * the global function_trace_op variable.
+ */
+
+ ptr = (unsigned long *)(trampoline + size + MCOUNT_INSN_SIZE);
+ *ptr = (unsigned long)ops;
+
+ op_offset -= start_offset;
+ memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
+
+ /* Are we pointing to the reference? */
+ if (WARN_ON(memcmp(op_ptr.op, op_ref, 3) != 0)) {
+ tramp_free(trampoline);
+ return 0;
+ }
+
+ /* Load the contents of ptr into the callback parameter */
+ offset = (unsigned long)ptr;
+ offset -= (unsigned long)trampoline + op_offset + OP_REF_SIZE;
+
+ op_ptr.offset = offset;
+
+ /* put in the new offset to the ftrace_ops */
+ memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+
+ /* ALLOC_TRAMP flags lets us know we created it */
+ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
+
+ return (unsigned long)trampoline;
+}
+
+static unsigned long calc_trampoline_call_offset(bool save_regs)
+{
+ unsigned long start_offset;
+ unsigned long call_offset;
+
+ if (save_regs) {
+ start_offset = (unsigned long)ftrace_regs_caller;
+ call_offset = (unsigned long)ftrace_regs_call;
+ } else {
+ start_offset = (unsigned long)ftrace_caller;
+ call_offset = (unsigned long)ftrace_call;
+ }
+
+ return call_offset - start_offset;
+}
+
+void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
+{
+ ftrace_func_t func;
+ unsigned char *new;
+ unsigned long offset;
+ unsigned long ip;
+ unsigned int size;
+ int ret;
+
+ if (ops->trampoline) {
+ /*
+ * The ftrace_ops caller may set up its own trampoline.
+ * In such a case, this code must not modify it.
+ */
+ if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+ return;
+ } else {
+ ops->trampoline = create_trampoline(ops, &size);
+ if (!ops->trampoline)
+ return;
+ ops->trampoline_size = size;
+ }
+
+ offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
+ ip = ops->trampoline + offset;
+
+ func = ftrace_ops_get_func(ops);
+
+ /* Do a safe modify in case the trampoline is executing */
+ new = ftrace_call_replace(ip, (unsigned long)func);
+ ret = update_ftrace_func(ip, new);
+
+ /* The update should never fail */
+ WARN_ON(ret);
+}
+
+/* Return the address of the function the trampoline calls */
+static void *addr_from_call(void *ptr)
+{
+ union ftrace_code_union calc;
+ int ret;
+
+ ret = probe_kernel_read(&calc, ptr, MCOUNT_INSN_SIZE);
+ if (WARN_ON_ONCE(ret < 0))
+ return NULL;
+
+ /* Make sure this is a call */
+ if (WARN_ON_ONCE(calc.e8 != 0xe8)) {
+ pr_warn("Expected e8, got %x\n", calc.e8);
+ return NULL;
+ }
+
+ return ptr + MCOUNT_INSN_SIZE + calc.offset;
+}
+
+void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
+ unsigned long frame_pointer);
+
+/*
+ * If the ops->trampoline was not allocated, then it probably
+ * has a static trampoline func, or is the ftrace caller itself.
+ */
+static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
+{
+ unsigned long offset;
+ bool save_regs = rec->flags & FTRACE_FL_REGS_EN;
+ void *ptr;
+
+ if (ops && ops->trampoline) {
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ /*
+ * We only know about function graph tracer setting as static
+ * trampoline.
+ */
+ if (ops->trampoline == FTRACE_GRAPH_ADDR)
+ return (void *)prepare_ftrace_return;
+#endif
+ return NULL;
+ }
+
+ offset = calc_trampoline_call_offset(save_regs);
+
+ if (save_regs)
+ ptr = (void *)FTRACE_REGS_ADDR + offset;
+ else
+ ptr = (void *)FTRACE_ADDR + offset;
+
+ return addr_from_call(ptr);
+}
+
+void *arch_ftrace_trampoline_func(struct ftrace_ops *ops, struct dyn_ftrace *rec)
+{
+ unsigned long offset;
+
+ /* If we didn't allocate this trampoline, consider it static */
+ if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+ return static_tramp_func(ops, rec);
+
+ offset = calc_trampoline_call_offset(ops->flags & FTRACE_OPS_FL_SAVE_REGS);
+ return addr_from_call((void *)ops->trampoline + offset);
+}
+
+void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
+{
+ if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
+ return;
+
+ tramp_free((void *)ops->trampoline);
+ ops->trampoline = 0;
+}
+
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
static int ftrace_mod_jmp(unsigned long ip, void *func)
{
@@ -694,7 +964,7 @@ int ftrace_disable_ftrace_graph_caller(void)
* Hook the return address and push it in the stack of return addrs
* in current thread info.
*/
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
unsigned long frame_pointer)
{
unsigned long old;
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 5f9cf20cdb68..3d5fb509bdeb 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -108,7 +108,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
int i;
for (i = 0; i < HBP_NUM; i++) {
- struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+ struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
if (!*slot) {
*slot = bp;
@@ -122,7 +122,7 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
set_debugreg(info->address, i);
__this_cpu_write(cpu_debugreg[i], info->address);
- dr7 = &__get_cpu_var(cpu_dr7);
+ dr7 = this_cpu_ptr(&cpu_dr7);
*dr7 |= encode_dr7(i, info->len, info->type);
set_debugreg(*dr7, 7);
@@ -146,7 +146,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
int i;
for (i = 0; i < HBP_NUM; i++) {
- struct perf_event **slot = &__get_cpu_var(bp_per_reg[i]);
+ struct perf_event **slot = this_cpu_ptr(&bp_per_reg[i]);
if (*slot == bp) {
*slot = NULL;
@@ -157,7 +157,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
if (WARN_ONCE(i == HBP_NUM, "Can't find any breakpoint slot"))
return;
- dr7 = &__get_cpu_var(cpu_dr7);
+ dr7 = this_cpu_ptr(&cpu_dr7);
*dr7 &= ~__encode_dr7(i, info->len, info->type);
set_debugreg(*dr7, 7);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 8af817105e29..e7cc5370cd2f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -111,8 +111,7 @@ static void make_8259A_irq(unsigned int irq)
{
disable_irq_nosync(irq);
io_apic_irqs &= ~(1<<irq);
- irq_set_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
- i8259A_chip.name);
+ irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
enable_irq(irq);
}
diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c
index 9030e83db6ee..82f8d02f0df2 100644
--- a/arch/x86/kernel/iosf_mbi.c
+++ b/arch/x86/kernel/iosf_mbi.c
@@ -22,10 +22,13 @@
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/capability.h>
#include <asm/iosf_mbi.h>
#define PCI_DEVICE_ID_BAYTRAIL 0x0F00
+#define PCI_DEVICE_ID_BRASWELL 0x2280
#define PCI_DEVICE_ID_QUARK_X1000 0x0958
static DEFINE_SPINLOCK(iosf_mbi_lock);
@@ -187,6 +190,89 @@ bool iosf_mbi_available(void)
}
EXPORT_SYMBOL(iosf_mbi_available);
+#ifdef CONFIG_IOSF_MBI_DEBUG
+static u32 dbg_mdr;
+static u32 dbg_mcr;
+static u32 dbg_mcrx;
+
+static int mcr_get(void *data, u64 *val)
+{
+ *val = *(u32 *)data;
+ return 0;
+}
+
+static int mcr_set(void *data, u64 val)
+{
+ u8 command = ((u32)val & 0xFF000000) >> 24,
+ port = ((u32)val & 0x00FF0000) >> 16,
+ offset = ((u32)val & 0x0000FF00) >> 8;
+ int err;
+
+ *(u32 *)data = val;
+
+ if (!capable(CAP_SYS_RAWIO))
+ return -EACCES;
+
+ if (command & 1u)
+ err = iosf_mbi_write(port,
+ command,
+ dbg_mcrx | offset,
+ dbg_mdr);
+ else
+ err = iosf_mbi_read(port,
+ command,
+ dbg_mcrx | offset,
+ &dbg_mdr);
+
+ return err;
+}
+DEFINE_SIMPLE_ATTRIBUTE(iosf_mcr_fops, mcr_get, mcr_set , "%llx\n");
+
+static struct dentry *iosf_dbg;
+
+static void iosf_sideband_debug_init(void)
+{
+ struct dentry *d;
+
+ iosf_dbg = debugfs_create_dir("iosf_sb", NULL);
+ if (IS_ERR_OR_NULL(iosf_dbg))
+ return;
+
+ /* mdr */
+ d = debugfs_create_x32("mdr", 0660, iosf_dbg, &dbg_mdr);
+ if (IS_ERR_OR_NULL(d))
+ goto cleanup;
+
+ /* mcrx */
+ debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx);
+ if (IS_ERR_OR_NULL(d))
+ goto cleanup;
+
+ /* mcr - initiates mailbox tranaction */
+ debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops);
+ if (IS_ERR_OR_NULL(d))
+ goto cleanup;
+
+ return;
+
+cleanup:
+ debugfs_remove_recursive(d);
+}
+
+static void iosf_debugfs_init(void)
+{
+ iosf_sideband_debug_init();
+}
+
+static void iosf_debugfs_remove(void)
+{
+ debugfs_remove_recursive(iosf_dbg);
+}
+#else
+static inline void iosf_debugfs_init(void) { }
+static inline void iosf_debugfs_remove(void) { }
+#endif /* CONFIG_IOSF_MBI_DEBUG */
+
static int iosf_mbi_probe(struct pci_dev *pdev,
const struct pci_device_id *unused)
{
@@ -204,6 +290,7 @@ static int iosf_mbi_probe(struct pci_dev *pdev,
static const struct pci_device_id iosf_mbi_pci_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BRASWELL) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) },
{ 0, },
};
@@ -217,11 +304,15 @@ static struct pci_driver iosf_mbi_pci_driver = {
static int __init iosf_mbi_init(void)
{
+ iosf_debugfs_init();
+
return pci_register_driver(&iosf_mbi_pci_driver);
}
static void __exit iosf_mbi_exit(void)
{
+ iosf_debugfs_remove();
+
pci_unregister_driver(&iosf_mbi_pci_driver);
if (mbi_pdev) {
pci_dev_put(mbi_pdev);
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 922d28581024..6307a0f0cf17 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -59,78 +59,78 @@ int arch_show_interrupts(struct seq_file *p, int prec)
seq_printf(p, "%*s: ", prec, "NMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->__nmi_count);
- seq_printf(p, " Non-maskable interrupts\n");
+ seq_puts(p, " Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
seq_printf(p, "%*s: ", prec, "LOC");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
- seq_printf(p, " Local timer interrupts\n");
+ seq_puts(p, " Local timer interrupts\n");
seq_printf(p, "%*s: ", prec, "SPU");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
- seq_printf(p, " Spurious interrupts\n");
+ seq_puts(p, " Spurious interrupts\n");
seq_printf(p, "%*s: ", prec, "PMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
- seq_printf(p, " Performance monitoring interrupts\n");
+ seq_puts(p, " Performance monitoring interrupts\n");
seq_printf(p, "%*s: ", prec, "IWI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
- seq_printf(p, " IRQ work interrupts\n");
+ seq_puts(p, " IRQ work interrupts\n");
seq_printf(p, "%*s: ", prec, "RTR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
- seq_printf(p, " APIC ICR read retries\n");
+ seq_puts(p, " APIC ICR read retries\n");
#endif
if (x86_platform_ipi_callback) {
seq_printf(p, "%*s: ", prec, "PLT");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis);
- seq_printf(p, " Platform interrupts\n");
+ seq_puts(p, " Platform interrupts\n");
}
#ifdef CONFIG_SMP
seq_printf(p, "%*s: ", prec, "RES");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
- seq_printf(p, " Rescheduling interrupts\n");
+ seq_puts(p, " Rescheduling interrupts\n");
seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
irq_stats(j)->irq_tlb_count);
- seq_printf(p, " Function call interrupts\n");
+ seq_puts(p, " Function call interrupts\n");
seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
- seq_printf(p, " TLB shootdowns\n");
+ seq_puts(p, " TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
seq_printf(p, "%*s: ", prec, "TRM");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
- seq_printf(p, " Thermal event interrupts\n");
+ seq_puts(p, " Thermal event interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
seq_printf(p, "%*s: ", prec, "THR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
- seq_printf(p, " Threshold APIC interrupts\n");
+ seq_puts(p, " Threshold APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE
seq_printf(p, "%*s: ", prec, "MCE");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(mce_exception_count, j));
- seq_printf(p, " Machine check exceptions\n");
+ seq_puts(p, " Machine check exceptions\n");
seq_printf(p, "%*s: ", prec, "MCP");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
- seq_printf(p, " Machine check polls\n");
+ seq_puts(p, " Machine check polls\n");
#endif
#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
seq_printf(p, "%*s: ", prec, "THR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
- seq_printf(p, " Hypervisor callback interrupts\n");
+ seq_puts(p, " Hypervisor callback interrupts\n");
#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 4d1c746892eb..e4b503d5558c 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -52,13 +52,13 @@ static inline void stack_overflow_check(struct pt_regs *regs)
regs->sp <= curbase + THREAD_SIZE)
return;
- irq_stack_top = (u64)__get_cpu_var(irq_stack_union.irq_stack) +
+ irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
STACK_TOP_MARGIN;
- irq_stack_bottom = (u64)__get_cpu_var(irq_stack_ptr);
+ irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
return;
- oist = &__get_cpu_var(orig_ist);
+ oist = this_cpu_ptr(&orig_ist);
estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
if (regs->sp >= estack_top && regs->sp <= estack_bottom)
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 1de84e3ab4e0..15d741ddfeeb 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -41,7 +41,7 @@ __visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
void arch_irq_work_raise(void)
{
#ifdef CONFIG_X86_LOCAL_APIC
- if (!cpu_has_apic)
+ if (!arch_irq_work_has_interrupt())
return;
apic->send_IPI_self(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 44f1ed42fdf2..70e181ea1eac 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -70,7 +70,6 @@ int vector_used_by_percpu_irq(unsigned int vector)
void __init init_ISA_irqs(void)
{
struct irq_chip *chip = legacy_pic->chip;
- const char *name = chip->name;
int i;
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
@@ -79,7 +78,7 @@ void __init init_ISA_irqs(void)
legacy_pic->init(0);
for (i = 0; i < nr_legacy_irqs(); i++)
- irq_set_chip_and_handler_name(i, chip, handle_level_irq, name);
+ irq_set_chip_and_handler(i, chip, handle_level_irq);
}
void __init init_IRQ(void)
@@ -100,32 +99,9 @@ void __init init_IRQ(void)
x86_init.irqs.intr_init();
}
-/*
- * Setup the vector to irq mappings.
- */
-void setup_vector_irq(int cpu)
-{
-#ifndef CONFIG_X86_IO_APIC
- int irq;
-
- /*
- * On most of the platforms, legacy PIC delivers the interrupts on the
- * boot cpu. But there are certain platforms where PIC interrupts are
- * delivered to multiple cpu's. If the legacy IRQ is handled by the
- * legacy PIC, for the new cpu that is coming online, setup the static
- * legacy vector to irq mapping:
- */
- for (irq = 0; irq < nr_legacy_irqs(); irq++)
- per_cpu(vector_irq, cpu)[IRQ0_VECTOR + irq] = irq;
-#endif
-
- __setup_vector_irq(cpu);
-}
-
static void __init smp_intr_init(void)
{
#ifdef CONFIG_SMP
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
/*
* The reschedule interrupt is a CPU-to-CPU reschedule-helper
* IPI, driven by wakeup.
@@ -145,7 +121,6 @@ static void __init smp_intr_init(void)
/* IPI used for rebooting/stopping */
alloc_intr_gate(REBOOT_VECTOR, reboot_interrupt);
-#endif
#endif /* CONFIG_SMP */
}
@@ -160,7 +135,7 @@ static void __init apic_intr_init(void)
alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
#endif
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+#ifdef CONFIG_X86_LOCAL_APIC
/* self generated IPI for local APIC timer */
alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
@@ -198,10 +173,17 @@ void __init native_init_IRQ(void)
* 'special' SMP interrupts)
*/
i = FIRST_EXTERNAL_VECTOR;
- for_each_clear_bit_from(i, used_vectors, NR_VECTORS) {
+#ifndef CONFIG_X86_LOCAL_APIC
+#define first_system_vector NR_VECTORS
+#endif
+ for_each_clear_bit_from(i, used_vectors, first_system_vector) {
/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
set_intr_gate(i, interrupt[i - FIRST_EXTERNAL_VECTOR]);
}
+#ifdef CONFIG_X86_LOCAL_APIC
+ for_each_clear_bit_from(i, used_vectors, NR_VECTORS)
+ set_intr_gate(i, spurious_interrupt);
+#endif
if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
setup_irq(2, &irq2);
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 9642b9b33655..ca05f86481aa 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -26,6 +26,7 @@
#include <asm/setup.h>
#include <asm/crash.h>
#include <asm/efi.h>
+#include <asm/kexec-bzimage64.h>
#define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */
@@ -267,7 +268,7 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
return ret;
}
-int bzImage64_probe(const char *buf, unsigned long len)
+static int bzImage64_probe(const char *buf, unsigned long len)
{
int ret = -ENOEXEC;
struct setup_header *header;
@@ -325,10 +326,10 @@ int bzImage64_probe(const char *buf, unsigned long len)
return ret;
}
-void *bzImage64_load(struct kimage *image, char *kernel,
- unsigned long kernel_len, char *initrd,
- unsigned long initrd_len, char *cmdline,
- unsigned long cmdline_len)
+static void *bzImage64_load(struct kimage *image, char *kernel,
+ unsigned long kernel_len, char *initrd,
+ unsigned long initrd_len, char *cmdline,
+ unsigned long cmdline_len)
{
struct setup_header *header;
@@ -514,7 +515,7 @@ out_free_params:
}
/* This cleanup function is called after various segments have been loaded */
-int bzImage64_cleanup(void *loader_data)
+static int bzImage64_cleanup(void *loader_data)
{
struct bzimage64_data *ldata = loader_data;
@@ -528,7 +529,7 @@ int bzImage64_cleanup(void *loader_data)
}
#ifdef CONFIG_KEXEC_BZIMAGE_VERIFY_SIG
-int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
+static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
{
bool trusted;
int ret;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 67e6d19ef1be..f7e3cd50ece0 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -285,7 +285,7 @@ static int can_probe(unsigned long paddr)
* normally used, we just go through if there is no kprobe.
*/
__addr = recover_probed_instruction(buf, addr);
- kernel_insn_init(&insn, (void *)__addr);
+ kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
insn_get_length(&insn);
/*
@@ -330,8 +330,10 @@ int __copy_instruction(u8 *dest, u8 *src)
{
struct insn insn;
kprobe_opcode_t buf[MAX_INSN_SIZE];
+ unsigned long recovered_insn =
+ recover_probed_instruction(buf, (unsigned long)src);
- kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, (unsigned long)src));
+ kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
insn_get_length(&insn);
/* Another subsystem puts a breakpoint, failed to recover */
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
@@ -342,7 +344,7 @@ int __copy_instruction(u8 *dest, u8 *src)
if (insn_rip_relative(&insn)) {
s64 newdisp;
u8 *disp;
- kernel_insn_init(&insn, dest);
+ kernel_insn_init(&insn, dest, insn.length);
insn_get_displacement(&insn);
/*
* The copied instruction uses the %rip-relative addressing
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 717b02a22e67..5f8f0b3cc674 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -27,7 +27,7 @@
static nokprobe_inline
int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
- struct kprobe_ctlblk *kcb)
+ struct kprobe_ctlblk *kcb, unsigned long orig_ip)
{
/*
* Emulate singlestep (and also recover regs->ip)
@@ -39,6 +39,8 @@ int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
p->post_handler(p, regs, 0);
}
__this_cpu_write(current_kprobe, NULL);
+ if (orig_ip)
+ regs->ip = orig_ip;
return 1;
}
@@ -46,7 +48,7 @@ int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
struct kprobe_ctlblk *kcb)
{
if (kprobe_ftrace(p))
- return __skip_singlestep(p, regs, kcb);
+ return __skip_singlestep(p, regs, kcb, 0);
else
return 0;
}
@@ -71,13 +73,14 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
if (kprobe_running()) {
kprobes_inc_nmissed_count(p);
} else {
+ unsigned long orig_ip = regs->ip;
/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
regs->ip = ip + sizeof(kprobe_opcode_t);
__this_cpu_write(current_kprobe, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
if (!p->pre_handler || !p->pre_handler(p, regs))
- __skip_singlestep(p, regs, kcb);
+ __skip_singlestep(p, regs, kcb, orig_ip);
/*
* If pre_handler returns !0, it sets regs->ip and
* resets current kprobe.
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index f1314d0bcf0a..7c523bbf3dc8 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -251,13 +251,15 @@ static int can_optimize(unsigned long paddr)
/* Decode instructions */
addr = paddr - offset;
while (addr < paddr - offset + size) { /* Decode until function end */
+ unsigned long recovered_insn;
if (search_exception_tables(addr))
/*
* Since some fixup code will jumps into this function,
* we can't optimize kprobe in this function.
*/
return 0;
- kernel_insn_init(&insn, (void *)recover_probed_instruction(buf, addr));
+ recovered_insn = recover_probed_instruction(buf, addr);
+ kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
insn_get_length(&insn);
/* Another subsystem puts a breakpoint */
if (insn.opcode.bytes[0] == BREAKPOINT_INSTRUCTION)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 3dd8e2c4d74a..94f643484300 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -35,6 +35,7 @@
#include <linux/slab.h>
#include <linux/kprobes.h>
#include <linux/debugfs.h>
+#include <linux/nmi.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
@@ -243,9 +244,9 @@ u32 kvm_read_and_reset_pf_reason(void)
{
u32 reason = 0;
- if (__get_cpu_var(apf_reason).enabled) {
- reason = __get_cpu_var(apf_reason).reason;
- __get_cpu_var(apf_reason).reason = 0;
+ if (__this_cpu_read(apf_reason.enabled)) {
+ reason = __this_cpu_read(apf_reason.reason);
+ __this_cpu_write(apf_reason.reason, 0);
}
return reason;
@@ -282,7 +283,14 @@ NOKPROBE_SYMBOL(do_async_page_fault);
static void __init paravirt_ops_setup(void)
{
pv_info.name = "KVM";
- pv_info.paravirt_enabled = 1;
+
+ /*
+ * KVM isn't paravirt in the sense of paravirt_enabled. A KVM
+ * guest kernel works like a bare metal kernel with additional
+ * features, and paravirt_enabled is about features that are
+ * missing.
+ */
+ pv_info.paravirt_enabled = 0;
if (kvm_para_has_feature(KVM_FEATURE_NOP_IO_DELAY))
pv_cpu_ops.io_delay = kvm_io_delay;
@@ -318,7 +326,7 @@ static void kvm_guest_apic_eoi_write(u32 reg, u32 val)
* there's no need for lock or memory barriers.
* An optimization barrier is implied in apic write.
*/
- if (__test_and_clear_bit(KVM_PV_EOI_BIT, &__get_cpu_var(kvm_apic_eoi)))
+ if (__test_and_clear_bit(KVM_PV_EOI_BIT, this_cpu_ptr(&kvm_apic_eoi)))
return;
apic_write(APIC_EOI, APIC_EOI_ACK);
}
@@ -329,13 +337,13 @@ void kvm_guest_cpu_init(void)
return;
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) && kvmapf) {
- u64 pa = slow_virt_to_phys(&__get_cpu_var(apf_reason));
+ u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
#ifdef CONFIG_PREEMPT
pa |= KVM_ASYNC_PF_SEND_ALWAYS;
#endif
wrmsrl(MSR_KVM_ASYNC_PF_EN, pa | KVM_ASYNC_PF_ENABLED);
- __get_cpu_var(apf_reason).enabled = 1;
+ __this_cpu_write(apf_reason.enabled, 1);
printk(KERN_INFO"KVM setup async PF for cpu %d\n",
smp_processor_id());
}
@@ -344,8 +352,8 @@ void kvm_guest_cpu_init(void)
unsigned long pa;
/* Size alignment is implied but just to make it explicit. */
BUILD_BUG_ON(__alignof__(kvm_apic_eoi) < 4);
- __get_cpu_var(kvm_apic_eoi) = 0;
- pa = slow_virt_to_phys(&__get_cpu_var(kvm_apic_eoi))
+ __this_cpu_write(kvm_apic_eoi, 0);
+ pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
| KVM_MSR_ENABLED;
wrmsrl(MSR_KVM_PV_EOI_EN, pa);
}
@@ -356,11 +364,11 @@ void kvm_guest_cpu_init(void)
static void kvm_pv_disable_apf(void)
{
- if (!__get_cpu_var(apf_reason).enabled)
+ if (!__this_cpu_read(apf_reason.enabled))
return;
wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
- __get_cpu_var(apf_reason).enabled = 0;
+ __this_cpu_write(apf_reason.enabled, 0);
printk(KERN_INFO"Unregister pv shared memory for cpu %d\n",
smp_processor_id());
@@ -499,6 +507,13 @@ void __init kvm_guest_init(void)
#else
kvm_guest_cpu_init();
#endif
+
+ /*
+ * Hard lockup detection is enabled by default. Disable it, as guests
+ * can get false positives too easily, for example if the host is
+ * overcommitted.
+ */
+ watchdog_enable_hardlockup_detector(false);
}
static noinline uint32_t __kvm_cpuid_base(void)
@@ -716,7 +731,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
if (in_nmi())
return;
- w = &__get_cpu_var(klock_waiting);
+ w = this_cpu_ptr(&klock_waiting);
cpu = smp_processor_id();
start = spin_time_start();
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d9156ceecdff..42caaef897c8 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -59,13 +59,12 @@ static void kvm_get_wallclock(struct timespec *now)
native_write_msr(msr_kvm_wall_clock, low, high);
- preempt_disable();
- cpu = smp_processor_id();
+ cpu = get_cpu();
vcpu_time = &hv_clock[cpu].pvti;
pvclock_read_wallclock(&wall_clock, vcpu_time, now);
- preempt_enable();
+ put_cpu();
}
static int kvm_set_wallclock(const struct timespec *now)
@@ -107,11 +106,10 @@ static unsigned long kvm_get_tsc_khz(void)
int cpu;
unsigned long tsc_khz;
- preempt_disable();
- cpu = smp_processor_id();
+ cpu = get_cpu();
src = &hv_clock[cpu].pvti;
tsc_khz = pvclock_tsc_khz(src);
- preempt_enable();
+ put_cpu();
return tsc_khz;
}
@@ -263,7 +261,6 @@ void __init kvmclock_init(void)
#endif
kvm_get_preset_lpj();
clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
- pv_info.paravirt_enabled = 1;
pv_info.name = "KVM";
if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
@@ -284,23 +281,22 @@ int __init kvm_setup_vsyscall_timeinfo(void)
size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
- preempt_disable();
- cpu = smp_processor_id();
+ cpu = get_cpu();
vcpu_time = &hv_clock[cpu].pvti;
flags = pvclock_read_flags(vcpu_time);
if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
- preempt_enable();
+ put_cpu();
return 1;
}
if ((ret = pvclock_init_vsyscall(hv_clock, size))) {
- preempt_enable();
+ put_cpu();
return ret;
}
- preempt_enable();
+ put_cpu();
kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
#endif
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 1667b1de8d5d..469b23d6acc2 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -20,6 +20,7 @@
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/cpufeature.h>
#include <asm/desc.h>
#include <asm/cacheflush.h>
@@ -247,7 +248,8 @@ void machine_kexec(struct kimage *image)
/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
(unsigned long)page_list,
- image->start, cpu_has_pae,
+ image->start,
+ boot_cpu_has(X86_FEATURE_PAE),
image->preserve_context);
#ifdef CONFIG_KEXEC_JUMP
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 485981059a40..415480d3ea84 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -22,6 +22,7 @@
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
+#include <asm/io_apic.h>
#include <asm/debugreg.h>
#include <asm/kexec-bzimage64.h>
diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index c73aecf10d34..94ea120fa21f 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -21,40 +21,159 @@
# define function_hook mcount
#endif
+/* All cases save the original rbp (8 bytes) */
+#ifdef CONFIG_FRAME_POINTER
+# ifdef CC_USING_FENTRY
+/* Save parent and function stack frames (rip and rbp) */
+# define MCOUNT_FRAME_SIZE (8+16*2)
+# else
+/* Save just function stack frame (rip and rbp) */
+# define MCOUNT_FRAME_SIZE (8+16)
+# endif
+#else
+/* No need to save a stack frame */
+# define MCOUNT_FRAME_SIZE 8
+#endif /* CONFIG_FRAME_POINTER */
+
+/* Size of stack used to save mcount regs in save_mcount_regs */
+#define MCOUNT_REG_SIZE (SS+8 + MCOUNT_FRAME_SIZE)
+
+/*
+ * gcc -pg option adds a call to 'mcount' in most functions.
+ * When -mfentry is used, the call is to 'fentry' and not 'mcount'
+ * and is done before the function's stack frame is set up.
+ * They both require a set of regs to be saved before calling
+ * any C code and restored before returning back to the function.
+ *
+ * On boot up, all these calls are converted into nops. When tracing
+ * is enabled, the call can jump to either ftrace_caller or
+ * ftrace_regs_caller. Callbacks (tracing functions) that require
+ * ftrace_regs_caller (like kprobes) need to have pt_regs passed to
+ * it. For this reason, the size of the pt_regs structure will be
+ * allocated on the stack and the required mcount registers will
+ * be saved in the locations that pt_regs has them in.
+ */
+
+/*
+ * @added: the amount of stack added before calling this
+ *
+ * After this is called, the following registers contain:
+ *
+ * %rdi - holds the address that called the trampoline
+ * %rsi - holds the parent function (traced function's return address)
+ * %rdx - holds the original %rbp
+ */
+.macro save_mcount_regs added=0
+
+ /* Always save the original rbp */
+ pushq %rbp
+
+#ifdef CONFIG_FRAME_POINTER
+ /*
+ * Stack traces will stop at the ftrace trampoline if the frame pointer
+ * is not set up properly. If fentry is used, we need to save a frame
+ * pointer for the parent as well as the function traced, because the
+ * fentry is called before the stack frame is set up, where as mcount
+ * is called afterward.
+ */
+#ifdef CC_USING_FENTRY
+ /* Save the parent pointer (skip orig rbp and our return address) */
+ pushq \added+8*2(%rsp)
+ pushq %rbp
+ movq %rsp, %rbp
+ /* Save the return address (now skip orig rbp, rbp and parent) */
+ pushq \added+8*3(%rsp)
+#else
+ /* Can't assume that rip is before this (unless added was zero) */
+ pushq \added+8(%rsp)
+#endif
+ pushq %rbp
+ movq %rsp, %rbp
+#endif /* CONFIG_FRAME_POINTER */
+
+ /*
+ * We add enough stack to save all regs.
+ */
+ subq $(MCOUNT_REG_SIZE - MCOUNT_FRAME_SIZE), %rsp
+ movq %rax, RAX(%rsp)
+ movq %rcx, RCX(%rsp)
+ movq %rdx, RDX(%rsp)
+ movq %rsi, RSI(%rsp)
+ movq %rdi, RDI(%rsp)
+ movq %r8, R8(%rsp)
+ movq %r9, R9(%rsp)
+ /*
+ * Save the original RBP. Even though the mcount ABI does not
+ * require this, it helps out callers.
+ */
+ movq MCOUNT_REG_SIZE-8(%rsp), %rdx
+ movq %rdx, RBP(%rsp)
+
+ /* Copy the parent address into %rsi (second parameter) */
+#ifdef CC_USING_FENTRY
+ movq MCOUNT_REG_SIZE+8+\added(%rsp), %rsi
+#else
+ /* %rdx contains original %rbp */
+ movq 8(%rdx), %rsi
+#endif
+
+ /* Move RIP to its proper location */
+ movq MCOUNT_REG_SIZE+\added(%rsp), %rdi
+ movq %rdi, RIP(%rsp)
+
+ /*
+ * Now %rdi (the first parameter) has the return address of
+ * where ftrace_call returns. But the callbacks expect the
+ * address of the call itself.
+ */
+ subq $MCOUNT_INSN_SIZE, %rdi
+ .endm
+
+.macro restore_mcount_regs
+ movq R9(%rsp), %r9
+ movq R8(%rsp), %r8
+ movq RDI(%rsp), %rdi
+ movq RSI(%rsp), %rsi
+ movq RDX(%rsp), %rdx
+ movq RCX(%rsp), %rcx
+ movq RAX(%rsp), %rax
+
+ /* ftrace_regs_caller can modify %rbp */
+ movq RBP(%rsp), %rbp
+
+ addq $MCOUNT_REG_SIZE, %rsp
+
+ .endm
+
#ifdef CONFIG_DYNAMIC_FTRACE
ENTRY(function_hook)
retq
END(function_hook)
-/* skip is set if stack has been adjusted */
-.macro ftrace_caller_setup skip=0
- MCOUNT_SAVE_FRAME \skip
+ENTRY(ftrace_caller)
+ /* save_mcount_regs fills in first two parameters */
+ save_mcount_regs
+GLOBAL(ftrace_caller_op_ptr)
/* Load the ftrace_ops into the 3rd parameter */
movq function_trace_op(%rip), %rdx
- /* Load ip into the first parameter */
- movq RIP(%rsp), %rdi
- subq $MCOUNT_INSN_SIZE, %rdi
- /* Load the parent_ip into the second parameter */
-#ifdef CC_USING_FENTRY
- movq SS+16(%rsp), %rsi
-#else
- movq 8(%rbp), %rsi
-#endif
-.endm
-
-ENTRY(ftrace_caller)
- ftrace_caller_setup
/* regs go into 4th parameter (but make it NULL) */
movq $0, %rcx
GLOBAL(ftrace_call)
call ftrace_stub
- MCOUNT_RESTORE_FRAME
-ftrace_return:
+ restore_mcount_regs
+
+ /*
+ * The copied trampoline must call ftrace_return as it
+ * still may need to call the function graph tracer.
+ */
+GLOBAL(ftrace_caller_end)
+
+GLOBAL(ftrace_return)
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
GLOBAL(ftrace_graph_call)
@@ -66,11 +185,16 @@ GLOBAL(ftrace_stub)
END(ftrace_caller)
ENTRY(ftrace_regs_caller)
- /* Save the current flags before compare (in SS location)*/
+ /* Save the current flags before any operations that can change them */
pushfq
- /* skip=8 to skip flags saved in SS */
- ftrace_caller_setup 8
+ /* added 8 bytes to save flags */
+ save_mcount_regs 8
+ /* save_mcount_regs fills in first two parameters */
+
+GLOBAL(ftrace_regs_caller_op_ptr)
+ /* Load the ftrace_ops into the 3rd parameter */
+ movq function_trace_op(%rip), %rdx
/* Save the rest of pt_regs */
movq %r15, R15(%rsp)
@@ -79,18 +203,17 @@ ENTRY(ftrace_regs_caller)
movq %r12, R12(%rsp)
movq %r11, R11(%rsp)
movq %r10, R10(%rsp)
- movq %rbp, RBP(%rsp)
movq %rbx, RBX(%rsp)
/* Copy saved flags */
- movq SS(%rsp), %rcx
+ movq MCOUNT_REG_SIZE(%rsp), %rcx
movq %rcx, EFLAGS(%rsp)
/* Kernel segments */
movq $__KERNEL_DS, %rcx
movq %rcx, SS(%rsp)
movq $__KERNEL_CS, %rcx
movq %rcx, CS(%rsp)
- /* Stack - skipping return address */
- leaq SS+16(%rsp), %rcx
+ /* Stack - skipping return address and flags */
+ leaq MCOUNT_REG_SIZE+8*2(%rsp), %rcx
movq %rcx, RSP(%rsp)
/* regs go into 4th parameter */
@@ -101,11 +224,11 @@ GLOBAL(ftrace_regs_call)
/* Copy flags back to SS, to restore them */
movq EFLAGS(%rsp), %rax
- movq %rax, SS(%rsp)
+ movq %rax, MCOUNT_REG_SIZE(%rsp)
/* Handlers can change the RIP */
movq RIP(%rsp), %rax
- movq %rax, SS+8(%rsp)
+ movq %rax, MCOUNT_REG_SIZE+8(%rsp)
/* restore the rest of pt_regs */
movq R15(%rsp), %r15
@@ -113,19 +236,22 @@ GLOBAL(ftrace_regs_call)
movq R13(%rsp), %r13
movq R12(%rsp), %r12
movq R10(%rsp), %r10
- movq RBP(%rsp), %rbp
movq RBX(%rsp), %rbx
- /* skip=8 to skip flags saved in SS */
- MCOUNT_RESTORE_FRAME 8
+ restore_mcount_regs
/* Restore flags */
popfq
- jmp ftrace_return
+ /*
+ * As this jmp to ftrace_return can be a short jump
+ * it must not be copied into the trampoline.
+ * The trampoline will add the code to jump
+ * to the return.
+ */
+GLOBAL(ftrace_regs_caller_end)
- popfq
- jmp ftrace_stub
+ jmp ftrace_return
END(ftrace_regs_caller)
@@ -136,6 +262,7 @@ ENTRY(function_hook)
cmpq $ftrace_stub, ftrace_trace_function
jnz trace
+fgraph_trace:
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
cmpq $ftrace_stub, ftrace_graph_return
jnz ftrace_graph_caller
@@ -148,42 +275,35 @@ GLOBAL(ftrace_stub)
retq
trace:
- MCOUNT_SAVE_FRAME
-
- movq RIP(%rsp), %rdi
-#ifdef CC_USING_FENTRY
- movq SS+16(%rsp), %rsi
-#else
- movq 8(%rbp), %rsi
-#endif
- subq $MCOUNT_INSN_SIZE, %rdi
+ /* save_mcount_regs fills in first two parameters */
+ save_mcount_regs
call *ftrace_trace_function
- MCOUNT_RESTORE_FRAME
+ restore_mcount_regs
- jmp ftrace_stub
+ jmp fgraph_trace
END(function_hook)
#endif /* CONFIG_DYNAMIC_FTRACE */
#endif /* CONFIG_FUNCTION_TRACER */
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
ENTRY(ftrace_graph_caller)
- MCOUNT_SAVE_FRAME
+ /* Saves rbp into %rdx and fills first parameter */
+ save_mcount_regs
#ifdef CC_USING_FENTRY
- leaq SS+16(%rsp), %rdi
+ leaq MCOUNT_REG_SIZE+8(%rsp), %rsi
movq $0, %rdx /* No framepointers needed */
#else
- leaq 8(%rbp), %rdi
- movq (%rbp), %rdx
+ /* Save address of the return address of traced function */
+ leaq 8(%rdx), %rsi
+ /* ftrace does sanity checks against frame pointers */
+ movq (%rdx), %rdx
#endif
- movq RIP(%rsp), %rsi
- subq $MCOUNT_INSN_SIZE, %rsi
-
call prepare_ftrace_return
- MCOUNT_RESTORE_FRAME
+ restore_mcount_regs
retq
END(ftrace_graph_caller)
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index c9603ac80de5..113e70784854 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -22,6 +22,8 @@
* an SMP box will direct the access to CPU %d.
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/module.h>
#include <linux/types.h>
@@ -50,11 +52,11 @@ static loff_t msr_seek(struct file *file, loff_t offset, int orig)
mutex_lock(&inode->i_mutex);
switch (orig) {
- case 0:
+ case SEEK_SET:
file->f_pos = offset;
ret = file->f_pos;
break;
- case 1:
+ case SEEK_CUR:
file->f_pos += offset;
ret = file->f_pos;
break;
@@ -206,7 +208,7 @@ static int msr_device_create(int cpu)
dev = device_create(msr_class, NULL, MKDEV(MSR_MAJOR, cpu), NULL,
"msr%d", cpu);
- return IS_ERR(dev) ? PTR_ERR(dev) : 0;
+ return PTR_ERR_OR_ZERO(dev);
}
static void msr_device_destroy(int cpu)
@@ -248,8 +250,7 @@ static int __init msr_init(void)
i = 0;
if (__register_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr", &msr_fops)) {
- printk(KERN_ERR "msr: unable to get major %d for msr\n",
- MSR_MAJOR);
+ pr_err("unable to get major %d for msr\n", MSR_MAJOR);
err = -EBUSY;
goto out;
}
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..781861cc5ee8 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
{
return PERF_SAMPLE_REGS_ABI_32;
}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ regs_user->regs = task_pt_regs(current);
+ regs_user->abi = perf_reg_abi(current);
+}
#else /* CONFIG_X86_64 */
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
(1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task)
else
return PERF_SAMPLE_REGS_ABI_64;
}
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+ struct pt_regs *regs,
+ struct pt_regs *regs_user_copy)
+{
+ struct pt_regs *user_regs = task_pt_regs(current);
+
+ /*
+ * If we're in an NMI that interrupted task_pt_regs setup, then
+ * we can't sample user regs at all. This check isn't really
+ * sufficient, though, as we could be in an NMI inside an interrupt
+ * that happened during task_pt_regs setup.
+ */
+ if (regs->sp > (unsigned long)&user_regs->r11 &&
+ regs->sp <= (unsigned long)(user_regs + 1)) {
+ regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+ regs_user->regs = NULL;
+ return;
+ }
+
+ /*
+ * RIP, flags, and the argument registers are usually saved.
+ * orig_ax is probably okay, too.
+ */
+ regs_user_copy->ip = user_regs->ip;
+ regs_user_copy->cx = user_regs->cx;
+ regs_user_copy->dx = user_regs->dx;
+ regs_user_copy->si = user_regs->si;
+ regs_user_copy->di = user_regs->di;
+ regs_user_copy->r8 = user_regs->r8;
+ regs_user_copy->r9 = user_regs->r9;
+ regs_user_copy->r10 = user_regs->r10;
+ regs_user_copy->r11 = user_regs->r11;
+ regs_user_copy->orig_ax = user_regs->orig_ax;
+ regs_user_copy->flags = user_regs->flags;
+
+ /*
+ * Don't even try to report the "rest" regs.
+ */
+ regs_user_copy->bx = -1;
+ regs_user_copy->bp = -1;
+ regs_user_copy->r12 = -1;
+ regs_user_copy->r13 = -1;
+ regs_user_copy->r14 = -1;
+ regs_user_copy->r15 = -1;
+
+ /*
+ * For this to be at all useful, we need a reasonable guess for
+ * sp and the ABI. Be careful: we're in NMI context, and we're
+ * considering current to be the current task, so we should
+ * be careful not to look at any other percpu variables that might
+ * change during context switches.
+ */
+ if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+ task_thread_info(current)->status & TS_COMPAT) {
+ /* Easy case: we're in a compat syscall. */
+ regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
+ regs_user_copy->sp = user_regs->sp;
+ regs_user_copy->cs = user_regs->cs;
+ regs_user_copy->ss = user_regs->ss;
+ } else if (user_regs->orig_ax != -1) {
+ /*
+ * We're probably in a 64-bit syscall.
+ * Warning: this code is severely racy. At least it's better
+ * than just blindly copying user_regs.
+ */
+ regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
+ regs_user_copy->sp = this_cpu_read(old_rsp);
+ regs_user_copy->cs = __USER_CS;
+ regs_user_copy->ss = __USER_DS;
+ regs_user_copy->cx = -1; /* usually contains garbage */
+ } else {
+ /* We're probably in an interrupt or exception. */
+ regs_user->abi = user_64bit_mode(user_regs) ?
+ PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
+ regs_user_copy->sp = user_regs->sp;
+ regs_user_copy->cs = user_regs->cs;
+ regs_user_copy->ss = user_regs->ss;
+ }
+
+ regs_user->regs = regs_user_copy;
+}
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/pmc_atom.c b/arch/x86/kernel/pmc_atom.c
index 0c424a67985d..0ee5025e0fa4 100644
--- a/arch/x86/kernel/pmc_atom.c
+++ b/arch/x86/kernel/pmc_atom.c
@@ -235,6 +235,11 @@ err:
pmc_dbgfs_unregister(pmc);
return -ENODEV;
}
+#else
+static int pmc_dbgfs_register(struct pmc_dev *pmc, struct pci_dev *pdev)
+{
+ return 0;
+}
#endif /* CONFIG_DEBUG_FS */
static int pmc_setup_dev(struct pci_dev *pdev)
@@ -262,14 +267,12 @@ static int pmc_setup_dev(struct pci_dev *pdev)
/* PMC hardware registers setup */
pmc_hw_reg_setup(pmc);
-#ifdef CONFIG_DEBUG_FS
ret = pmc_dbgfs_register(pmc, pdev);
if (ret) {
iounmap(pmc->regmap);
- return ret;
}
-#endif /* CONFIG_DEBUG_FS */
- return 0;
+
+ return ret;
}
/*
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
deleted file mode 100644
index ca7f0d58a87d..000000000000
--- a/arch/x86/kernel/preempt.S
+++ /dev/null
@@ -1,25 +0,0 @@
-
-#include <linux/linkage.h>
-#include <asm/dwarf2.h>
-#include <asm/asm.h>
-#include <asm/calling.h>
-
-ENTRY(___preempt_schedule)
- CFI_STARTPROC
- SAVE_ALL
- call preempt_schedule
- RESTORE_ALL
- ret
- CFI_ENDPROC
-
-#ifdef CONFIG_CONTEXT_TRACKING
-
-ENTRY(___preempt_schedule_context)
- CFI_STARTPROC
- SAVE_ALL
- call preempt_schedule_context
- RESTORE_ALL
- ret
- CFI_ENDPROC
-
-#endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f804dc935d2a..e127ddaa2d5a 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -64,14 +64,16 @@ EXPORT_SYMBOL_GPL(task_xstate_cachep);
*/
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- int ret;
-
*dst = *src;
- if (fpu_allocated(&src->thread.fpu)) {
- memset(&dst->thread.fpu, 0, sizeof(dst->thread.fpu));
- ret = fpu_alloc(&dst->thread.fpu);
- if (ret)
- return ret;
+
+ dst->thread.fpu_counter = 0;
+ dst->thread.fpu.has_fpu = 0;
+ dst->thread.fpu.last_cpu = ~0;
+ dst->thread.fpu.state = NULL;
+ if (tsk_used_math(src)) {
+ int err = fpu_alloc(&dst->thread.fpu);
+ if (err)
+ return err;
fpu_copy(dst, src);
}
return 0;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 7bc86bbe7485..8f3ebfe710d0 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -138,6 +138,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp = (unsigned long) childregs;
p->thread.sp0 = (unsigned long) (childregs+1);
+ memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
if (unlikely(p->flags & PF_KTHREAD)) {
/* kernel thread */
@@ -152,9 +153,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
childregs->orig_ax = -1;
childregs->cs = __KERNEL_CS | get_kernel_rpl();
childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED;
- p->thread.fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
- memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
return 0;
}
*childregs = *current_pt_regs();
@@ -165,13 +164,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.ip = (unsigned long) ret_from_fork;
task_user_gs(p) = get_user_gs(current_pt_regs());
- p->thread.fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
tsk = current;
err = -ENOMEM;
- memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
IO_BITMAP_BYTES, GFP_KERNEL);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index ca5b02d405c3..5a2c02913af3 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -163,7 +163,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
p->thread.sp = (unsigned long) childregs;
p->thread.usersp = me->thread.usersp;
set_tsk_thread_flag(p, TIF_FORK);
- p->thread.fpu_counter = 0;
p->thread.io_bitmap_ptr = NULL;
savesegment(gs, p->thread.gsindex);
@@ -193,8 +192,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
childregs->sp = sp;
err = -ENOMEM;
- memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
-
if (unlikely(test_tsk_thread_flag(me, TIF_IO_BITMAP))) {
p->thread.io_bitmap_ptr = kmemdup(me->thread.io_bitmap_ptr,
IO_BITMAP_BYTES, GFP_KERNEL);
@@ -286,24 +283,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
fpu = switch_fpu_prepare(prev_p, next_p, cpu);
- /*
- * Reload esp0, LDT and the page table pointer:
- */
+ /* Reload esp0 and ss1. */
load_sp0(tss, next);
- /*
- * Switch DS and ES.
- * This won't pick up thread selector changes, but I guess that is ok.
- */
- savesegment(es, prev->es);
- if (unlikely(next->es | prev->es))
- loadsegment(es, next->es);
-
- savesegment(ds, prev->ds);
- if (unlikely(next->ds | prev->ds))
- loadsegment(ds, next->ds);
-
-
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
*
@@ -312,41 +294,101 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
savesegment(fs, fsindex);
savesegment(gs, gsindex);
+ /*
+ * Load TLS before restoring any segments so that segment loads
+ * reference the correct GDT entries.
+ */
load_TLS(next, cpu);
/*
- * Leave lazy mode, flushing any hypercalls made here.
- * This must be done before restoring TLS segments so
- * the GDT and LDT are properly updated, and must be
- * done before math_state_restore, so the TS bit is up
- * to date.
+ * Leave lazy mode, flushing any hypercalls made here. This
+ * must be done after loading TLS entries in the GDT but before
+ * loading segments that might reference them, and and it must
+ * be done before math_state_restore, so the TS bit is up to
+ * date.
*/
arch_end_context_switch(next_p);
+ /* Switch DS and ES.
+ *
+ * Reading them only returns the selectors, but writing them (if
+ * nonzero) loads the full descriptor from the GDT or LDT. The
+ * LDT for next is loaded in switch_mm, and the GDT is loaded
+ * above.
+ *
+ * We therefore need to write new values to the segment
+ * registers on every context switch unless both the new and old
+ * values are zero.
+ *
+ * Note that we don't need to do anything for CS and SS, as
+ * those are saved and restored as part of pt_regs.
+ */
+ savesegment(es, prev->es);
+ if (unlikely(next->es | prev->es))
+ loadsegment(es, next->es);
+
+ savesegment(ds, prev->ds);
+ if (unlikely(next->ds | prev->ds))
+ loadsegment(ds, next->ds);
+
/*
* Switch FS and GS.
*
- * Segment register != 0 always requires a reload. Also
- * reload when it has changed. When prev process used 64bit
- * base always reload to avoid an information leak.
+ * These are even more complicated than FS and GS: they have
+ * 64-bit bases are that controlled by arch_prctl. Those bases
+ * only differ from the values in the GDT or LDT if the selector
+ * is 0.
+ *
+ * Loading the segment register resets the hidden base part of
+ * the register to 0 or the value from the GDT / LDT. If the
+ * next base address zero, writing 0 to the segment register is
+ * much faster than using wrmsr to explicitly zero the base.
+ *
+ * The thread_struct.fs and thread_struct.gs values are 0
+ * if the fs and gs bases respectively are not overridden
+ * from the values implied by fsindex and gsindex. They
+ * are nonzero, and store the nonzero base addresses, if
+ * the bases are overridden.
+ *
+ * (fs != 0 && fsindex != 0) || (gs != 0 && gsindex != 0) should
+ * be impossible.
+ *
+ * Therefore we need to reload the segment registers if either
+ * the old or new selector is nonzero, and we need to override
+ * the base address if next thread expects it to be overridden.
+ *
+ * This code is unnecessarily slow in the case where the old and
+ * new indexes are zero and the new base is nonzero -- it will
+ * unnecessarily write 0 to the selector before writing the new
+ * base address.
+ *
+ * Note: This all depends on arch_prctl being the only way that
+ * user code can override the segment base. Once wrfsbase and
+ * wrgsbase are enabled, most of this code will need to change.
*/
if (unlikely(fsindex | next->fsindex | prev->fs)) {
loadsegment(fs, next->fsindex);
+
/*
- * Check if the user used a selector != 0; if yes
- * clear 64bit base, since overloaded base is always
- * mapped to the Null selector
+ * If user code wrote a nonzero value to FS, then it also
+ * cleared the overridden base address.
+ *
+ * XXX: if user code wrote 0 to FS and cleared the base
+ * address itself, we won't notice and we'll incorrectly
+ * restore the prior base address next time we reschdule
+ * the process.
*/
if (fsindex)
prev->fs = 0;
}
- /* when next process has a 64bit base use it */
if (next->fs)
wrmsrl(MSR_FS_BASE, next->fs);
prev->fsindex = fsindex;
if (unlikely(gsindex | next->gsindex | prev->gs)) {
load_gs_index(next->gsindex);
+
+ /* This works (and fails) the same way as fsindex above. */
if (gsindex)
prev->gs = 0;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 678c0ada3b3c..e510618b2e91 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1441,24 +1441,126 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
force_sig_info(SIGTRAP, &info, tsk);
}
-
-#ifdef CONFIG_X86_32
-# define IS_IA32 1
-#elif defined CONFIG_IA32_EMULATION
-# define IS_IA32 is_compat_task()
-#else
-# define IS_IA32 0
+static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
+{
+#ifdef CONFIG_X86_64
+ if (arch == AUDIT_ARCH_X86_64) {
+ audit_syscall_entry(regs->orig_ax, regs->di,
+ regs->si, regs->dx, regs->r10);
+ } else
#endif
+ {
+ audit_syscall_entry(regs->orig_ax, regs->bx,
+ regs->cx, regs->dx, regs->si);
+ }
+}
/*
- * We must return the syscall number to actually look up in the table.
- * This can be -1L to skip running any syscall at all.
+ * We can return 0 to resume the syscall or anything else to go to phase
+ * 2. If we resume the syscall, we need to put something appropriate in
+ * regs->orig_ax.
+ *
+ * NB: We don't have full pt_regs here, but regs->orig_ax and regs->ax
+ * are fully functional.
+ *
+ * For phase 2's benefit, our return value is:
+ * 0: resume the syscall
+ * 1: go to phase 2; no seccomp phase 2 needed
+ * anything else: go to phase 2; pass return value to seccomp
*/
-long syscall_trace_enter(struct pt_regs *regs)
+unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
+{
+ unsigned long ret = 0;
+ u32 work;
+
+ BUG_ON(regs != task_pt_regs(current));
+
+ work = ACCESS_ONCE(current_thread_info()->flags) &
+ _TIF_WORK_SYSCALL_ENTRY;
+
+ /*
+ * If TIF_NOHZ is set, we are required to call user_exit() before
+ * doing anything that could touch RCU.
+ */
+ if (work & _TIF_NOHZ) {
+ user_exit();
+ work &= ~_TIF_NOHZ;
+ }
+
+#ifdef CONFIG_SECCOMP
+ /*
+ * Do seccomp first -- it should minimize exposure of other
+ * code, and keeping seccomp fast is probably more valuable
+ * than the rest of this.
+ */
+ if (work & _TIF_SECCOMP) {
+ struct seccomp_data sd;
+
+ sd.arch = arch;
+ sd.nr = regs->orig_ax;
+ sd.instruction_pointer = regs->ip;
+#ifdef CONFIG_X86_64
+ if (arch == AUDIT_ARCH_X86_64) {
+ sd.args[0] = regs->di;
+ sd.args[1] = regs->si;
+ sd.args[2] = regs->dx;
+ sd.args[3] = regs->r10;
+ sd.args[4] = regs->r8;
+ sd.args[5] = regs->r9;
+ } else
+#endif
+ {
+ sd.args[0] = regs->bx;
+ sd.args[1] = regs->cx;
+ sd.args[2] = regs->dx;
+ sd.args[3] = regs->si;
+ sd.args[4] = regs->di;
+ sd.args[5] = regs->bp;
+ }
+
+ BUILD_BUG_ON(SECCOMP_PHASE1_OK != 0);
+ BUILD_BUG_ON(SECCOMP_PHASE1_SKIP != 1);
+
+ ret = seccomp_phase1(&sd);
+ if (ret == SECCOMP_PHASE1_SKIP) {
+ regs->orig_ax = -1;
+ ret = 0;
+ } else if (ret != SECCOMP_PHASE1_OK) {
+ return ret; /* Go directly to phase 2 */
+ }
+
+ work &= ~_TIF_SECCOMP;
+ }
+#endif
+
+ /* Do our best to finish without phase 2. */
+ if (work == 0)
+ return ret; /* seccomp and/or nohz only (ret == 0 here) */
+
+#ifdef CONFIG_AUDITSYSCALL
+ if (work == _TIF_SYSCALL_AUDIT) {
+ /*
+ * If there is no more work to be done except auditing,
+ * then audit in phase 1. Phase 2 always audits, so, if
+ * we audit here, then we can't go on to phase 2.
+ */
+ do_audit_syscall_entry(regs, arch);
+ return 0;
+ }
+#endif
+
+ return 1; /* Something is enabled that we can't handle in phase 1 */
+}
+
+/* Returns the syscall nr to run (which should match regs->orig_ax). */
+long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
+ unsigned long phase1_result)
{
long ret = 0;
+ u32 work = ACCESS_ONCE(current_thread_info()->flags) &
+ _TIF_WORK_SYSCALL_ENTRY;
- user_exit();
+ BUG_ON(regs != task_pt_regs(current));
/*
* If we stepped into a sysenter/syscall insn, it trapped in
@@ -1467,17 +1569,21 @@ long syscall_trace_enter(struct pt_regs *regs)
* do_debug() and we need to set it again to restore the user
* state. If we entered on the slow path, TF was already set.
*/
- if (test_thread_flag(TIF_SINGLESTEP))
+ if (work & _TIF_SINGLESTEP)
regs->flags |= X86_EFLAGS_TF;
- /* do the secure computing check first */
- if (secure_computing(regs->orig_ax)) {
+#ifdef CONFIG_SECCOMP
+ /*
+ * Call seccomp_phase2 before running the other hooks so that
+ * they can see any changes made by a seccomp tracer.
+ */
+ if (phase1_result > 1 && seccomp_phase2(phase1_result)) {
/* seccomp failures shouldn't expose any additional code. */
- ret = -1L;
- goto out;
+ return -1;
}
+#endif
- if (unlikely(test_thread_flag(TIF_SYSCALL_EMU)))
+ if (unlikely(work & _TIF_SYSCALL_EMU))
ret = -1L;
if ((ret || test_thread_flag(TIF_SYSCALL_TRACE)) &&
@@ -1487,23 +1593,22 @@ long syscall_trace_enter(struct pt_regs *regs)
if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
trace_sys_enter(regs, regs->orig_ax);
- if (IS_IA32)
- audit_syscall_entry(AUDIT_ARCH_I386,
- regs->orig_ax,
- regs->bx, regs->cx,
- regs->dx, regs->si);
-#ifdef CONFIG_X86_64
- else
- audit_syscall_entry(AUDIT_ARCH_X86_64,
- regs->orig_ax,
- regs->di, regs->si,
- regs->dx, regs->r10);
-#endif
+ do_audit_syscall_entry(regs, arch);
-out:
return ret ?: regs->orig_ax;
}
+long syscall_trace_enter(struct pt_regs *regs)
+{
+ u32 arch = is_ia32_task() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+ unsigned long phase1_result = syscall_trace_enter_phase1(regs, arch);
+
+ if (phase1_result == 0)
+ return regs->orig_ax;
+ else
+ return syscall_trace_enter_phase2(regs, arch, phase1_result);
+}
+
void syscall_trace_leave(struct pt_regs *regs)
{
bool step;
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index ff898bbf579d..176a0f99d4da 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -498,6 +498,24 @@ void force_hpet_resume(void)
}
/*
+ * According to the datasheet e6xx systems have the HPET hardwired to
+ * 0xfed00000
+ */
+static void e6xx_force_enable_hpet(struct pci_dev *dev)
+{
+ if (hpet_address || force_hpet_address)
+ return;
+
+ force_hpet_address = 0xFED00000;
+ force_hpet_resume_type = NONE_FORCE_HPET_RESUME;
+ dev_printk(KERN_DEBUG, &dev->dev, "Force enabled HPET at "
+ "0x%lx\n", force_hpet_address);
+ return;
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_E6XX_CU,
+ e6xx_force_enable_hpet);
+
+/*
* HPET MSI on some boards (ATI SB700/SB800) has side effect on
* floppy DMA. Disable HPET MSI on such platforms.
* See erratum #27 (Misinterpreted MSI Requests May Result in
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 17962e667a91..bae6c609888e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,7 @@
#include <acpi/reboot.h>
#include <asm/io.h>
#include <asm/apic.h>
+#include <asm/io_apic.h>
#include <asm/desc.h>
#include <asm/hpet.h>
#include <asm/pgtable.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 41ead8d3bc0b..ab4734e5411d 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -879,6 +879,15 @@ void __init setup_arch(char **cmdline_p)
KERNEL_PGD_PTRS);
load_cr3(swapper_pg_dir);
+ /*
+ * Note: Quark X1000 CPUs advertise PGE incorrectly and require
+ * a cr3 based tlb flush, so the following __flush_tlb_all()
+ * will not flush anything because the cpu quirk which clears
+ * X86_FEATURE_PGE has not been invoked yet. Though due to the
+ * load_cr3() above the TLB has been flushed already. The
+ * quirk is invoked before subsequent calls to __flush_tlb_all()
+ * so proper operation is guaranteed.
+ */
__flush_tlb_all();
#else
printk(KERN_INFO "Command line: %s\n", boot_command_line);
@@ -951,6 +960,8 @@ void __init setup_arch(char **cmdline_p)
init_mm.end_data = (unsigned long) _edata;
init_mm.brk = _brk_end;
+ mpx_mm_init(&init_mm);
+
code_resource.start = __pa_symbol(_text);
code_resource.end = __pa_symbol(_etext)-1;
data_resource.start = __pa_symbol(_etext);
@@ -1119,7 +1130,6 @@ void __init setup_arch(char **cmdline_p)
setup_real_mode();
memblock_set_current_limit(get_max_mapped());
- dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
/*
* NOTE: On x86-32, only from this point on, fixmaps are ready for use.
@@ -1150,6 +1160,7 @@ void __init setup_arch(char **cmdline_p)
early_acpi_boot_init();
initmem_init();
+ dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
/*
* Reserve memory for crash kernel after SRAT is parsed so that it
@@ -1181,9 +1192,7 @@ void __init setup_arch(char **cmdline_p)
tboot_probe();
-#ifdef CONFIG_X86_64
map_vsyscall();
-#endif
generic_apic_probe();
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 5cdff0357746..e4fcb87ba7a6 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -30,7 +30,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number);
#define BOOT_PERCPU_OFFSET 0
#endif
-DEFINE_PER_CPU(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 2851d63c1202..ed37a768d0fc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -675,6 +675,11 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
* handler too.
*/
regs->flags &= ~(X86_EFLAGS_DF|X86_EFLAGS_RF|X86_EFLAGS_TF);
+ /*
+ * Ensure the signal handler starts with the new fpu state.
+ */
+ if (used_math())
+ drop_init_fpu(current);
}
signal_setup_done(failed, ksig, test_thread_flag(TIF_SINGLESTEP));
}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 42a2dca984b3..6d7022c683e3 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -99,7 +99,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map);
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
/* Per CPU bogomips and other parameters */
-DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
+DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
atomic_t init_deasserted;
@@ -111,7 +111,6 @@ atomic_t init_deasserted;
static void smp_callin(void)
{
int cpuid, phys_id;
- unsigned long timeout;
/*
* If waken up by an INIT in an 82489DX configuration
@@ -130,37 +129,6 @@ static void smp_callin(void)
* (This works even if the APIC is not enabled.)
*/
phys_id = read_apic_id();
- if (cpumask_test_cpu(cpuid, cpu_callin_mask)) {
- panic("%s: phys CPU#%d, CPU#%d already present??\n", __func__,
- phys_id, cpuid);
- }
- pr_debug("CPU#%d (phys ID: %d) waiting for CALLOUT\n", cpuid, phys_id);
-
- /*
- * STARTUP IPIs are fragile beasts as they might sometimes
- * trigger some glue motherboard logic. Complete APIC bus
- * silence for 1 second, this overestimates the time the
- * boot CPU is spending to send the up to 2 STARTUP IPIs
- * by a factor of two. This should be enough.
- */
-
- /*
- * Waiting 2s total for startup (udelay is not yet working)
- */
- timeout = jiffies + 2*HZ;
- while (time_before(jiffies, timeout)) {
- /*
- * Has the boot CPU finished it's STARTUP sequence?
- */
- if (cpumask_test_cpu(cpuid, cpu_callout_mask))
- break;
- cpu_relax();
- }
-
- if (!time_before(jiffies, timeout)) {
- panic("%s: CPU%d started up but did not get a callout!\n",
- __func__, cpuid);
- }
/*
* the boot CPU has finished the init stage and is spinning
@@ -296,11 +264,19 @@ void smp_store_cpu_info(int id)
}
static bool
+topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+{
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+ return (cpu_to_node(cpu1) == cpu_to_node(cpu2));
+}
+
+static bool
topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
{
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2),
+ return !WARN_ONCE(!topology_same_node(c, o),
"sched: CPU #%d's %s-sibling CPU #%d is not on the same node! "
"[node: %d != %d]. Ignoring dependency.\n",
cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
@@ -341,17 +317,44 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
return false;
}
-static bool match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+/*
+ * Unlike the other levels, we do not enforce keeping a
+ * multicore group inside a NUMA node. If this happens, we will
+ * discard the MC level of the topology later.
+ */
+static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (c->phys_proc_id == o->phys_proc_id) {
- if (cpu_has(c, X86_FEATURE_AMD_DCM))
- return true;
-
- return topology_sane(c, o, "mc");
- }
+ if (c->phys_proc_id == o->phys_proc_id)
+ return true;
return false;
}
+static struct sched_domain_topology_level numa_inside_package_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+ { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+#endif
+ { NULL, },
+};
+/*
+ * set_sched_topology() sets the topology internal to a CPU. The
+ * NUMA topologies are layered on top of it to build the full
+ * system topology.
+ *
+ * If NUMA nodes are observed to occur within a CPU package, this
+ * function should be called. It forces the sched domain code to
+ * only use the SMT level for the CPU portion of the topology.
+ * This essentially falls back to relying on NUMA information
+ * from the SRAT table to describe the entire system topology
+ * (except for hyperthreads).
+ */
+static void primarily_use_numa_for_topology(void)
+{
+ set_sched_topology(numa_inside_package_topology);
+}
+
void set_cpu_sibling_map(int cpu)
{
bool has_smt = smp_num_siblings > 1;
@@ -388,7 +391,7 @@ void set_cpu_sibling_map(int cpu)
for_each_cpu(i, cpu_sibling_setup_mask) {
o = &cpu_data(i);
- if ((i == cpu) || (has_mp && match_mc(c, o))) {
+ if ((i == cpu) || (has_mp && match_die(c, o))) {
link_mask(core, cpu, i);
/*
@@ -410,6 +413,8 @@ void set_cpu_sibling_map(int cpu)
} else if (i != cpu && !c->booted_cores)
c->booted_cores = cpu_data(i).booted_cores;
}
+ if (match_die(c, o) && !topology_same_node(c, o))
+ primarily_use_numa_for_topology();
}
}
@@ -753,8 +758,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
unsigned long start_ip = real_mode_header->trampoline_start;
unsigned long boot_error = 0;
- int timeout;
int cpu0_nmi_registered = 0;
+ unsigned long timeout;
/* Just in case we booted with a single CPU. */
alternatives_enable_smp();
@@ -802,6 +807,15 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
}
/*
+ * AP might wait on cpu_callout_mask in cpu_init() with
+ * cpu_initialized_mask set if previous attempt to online
+ * it timed-out. Clear cpu_initialized_mask so that after
+ * INIT/SIPI it could start with a clean state.
+ */
+ cpumask_clear_cpu(cpu, cpu_initialized_mask);
+ smp_mb();
+
+ /*
* Wake up a CPU in difference cases:
* - Use the method in the APIC driver if it's defined
* Otherwise,
@@ -815,53 +829,38 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
if (!boot_error) {
/*
- * allow APs to start initializing.
+ * Wait 10s total for a response from AP
*/
- pr_debug("Before Callout %d\n", cpu);
- cpumask_set_cpu(cpu, cpu_callout_mask);
- pr_debug("After Callout %d\n", cpu);
+ boot_error = -1;
+ timeout = jiffies + 10*HZ;
+ while (time_before(jiffies, timeout)) {
+ if (cpumask_test_cpu(cpu, cpu_initialized_mask)) {
+ /*
+ * Tell AP to proceed with initialization
+ */
+ cpumask_set_cpu(cpu, cpu_callout_mask);
+ boot_error = 0;
+ break;
+ }
+ udelay(100);
+ schedule();
+ }
+ }
+ if (!boot_error) {
/*
- * Wait 5s total for a response
+ * Wait till AP completes initial initialization
*/
- for (timeout = 0; timeout < 50000; timeout++) {
- if (cpumask_test_cpu(cpu, cpu_callin_mask))
- break; /* It has booted */
- udelay(100);
+ while (!cpumask_test_cpu(cpu, cpu_callin_mask)) {
/*
* Allow other tasks to run while we wait for the
* AP to come online. This also gives a chance
* for the MTRR work(triggered by the AP coming online)
* to be completed in the stop machine context.
*/
+ udelay(100);
schedule();
}
-
- if (cpumask_test_cpu(cpu, cpu_callin_mask)) {
- print_cpu_msr(&cpu_data(cpu));
- pr_debug("CPU%d: has booted.\n", cpu);
- } else {
- boot_error = 1;
- if (*trampoline_status == 0xA5A5A5A5)
- /* trampoline started but...? */
- pr_err("CPU%d: Stuck ??\n", cpu);
- else
- /* trampoline code not run */
- pr_err("CPU%d: Not responding\n", cpu);
- if (apic->inquire_remote_apic)
- apic->inquire_remote_apic(apicid);
- }
- }
-
- if (boot_error) {
- /* Try to put things back the way they were before ... */
- numa_remove_cpu(cpu); /* was set by numa_add_cpu */
-
- /* was set by do_boot_cpu() */
- cpumask_clear_cpu(cpu, cpu_callout_mask);
-
- /* was set by cpu_init() */
- cpumask_clear_cpu(cpu, cpu_initialized_mask);
}
/* mark "stuck" area as not stuck */
@@ -1085,7 +1084,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int i;
- preempt_disable();
smp_cpu_index_default();
/*
@@ -1103,22 +1101,19 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
}
set_cpu_sibling_map(0);
-
if (smp_sanity_check(max_cpus) < 0) {
pr_info("SMP disabled\n");
disable_smp();
- goto out;
+ return;
}
default_setup_apic_routing();
- preempt_disable();
if (read_apic_id() != boot_cpu_physical_apicid) {
panic("Boot APIC ID in local APIC unexpected (%d vs %d)",
read_apic_id(), boot_cpu_physical_apicid);
/* Or can we switch back to PIC here? */
}
- preempt_enable();
connect_bsp_APIC();
@@ -1152,8 +1147,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
uv_system_init();
set_mtrr_aps_delayed_init();
-out:
- preempt_enable();
}
void arch_enable_nonboot_cpus_begin(void)
@@ -1304,10 +1297,14 @@ static void __ref remove_cpu_from_maps(int cpu)
numa_remove_cpu(cpu);
}
+static DEFINE_PER_CPU(struct completion, die_complete);
+
void cpu_disable_common(void)
{
int cpu = smp_processor_id();
+ init_completion(&per_cpu(die_complete, smp_processor_id()));
+
remove_siblinginfo(cpu);
/* It's now safe to remove this processor from the online map */
@@ -1326,26 +1323,29 @@ int native_cpu_disable(void)
return ret;
clear_local_APIC();
-
cpu_disable_common();
+
return 0;
}
+void cpu_die_common(unsigned int cpu)
+{
+ wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+}
+
void native_cpu_die(unsigned int cpu)
{
/* We don't do anything here: idle task is faking death itself. */
- unsigned int i;
- for (i = 0; i < 10; i++) {
- /* They ack this in play_dead by setting CPU_DEAD */
- if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
- if (system_state == SYSTEM_RUNNING)
- pr_info("CPU %u is now offline\n", cpu);
- return;
- }
- msleep(100);
+ cpu_die_common(cpu);
+
+ /* They ack this in play_dead() by setting CPU_DEAD */
+ if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
+ if (system_state == SYSTEM_RUNNING)
+ pr_info("CPU %u is now offline\n", cpu);
+ } else {
+ pr_err("CPU %u didn't die...\n", cpu);
}
- pr_err("CPU %u didn't die...\n", cpu);
}
void play_dead_common(void)
@@ -1357,6 +1357,7 @@ void play_dead_common(void)
mb();
/* Ack it */
__this_cpu_write(cpu_state, CPU_DEAD);
+ complete(&per_cpu(die_complete, smp_processor_id()));
/*
* With physical CPU hotplug, we should halt the cpu
diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c
index 193ec2ce46c7..160386e9fc17 100644
--- a/arch/x86/kernel/sysfb.c
+++ b/arch/x86/kernel/sysfb.c
@@ -67,7 +67,7 @@ static __init int sysfb_init(void)
pd = platform_device_register_resndata(NULL, name, 0,
NULL, 0, si, sizeof(*si));
- return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+ return PTR_ERR_OR_ZERO(pd);
}
/* must execute after PCI subsystem for EFI quirks */
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
index 86179d409893..764a29f84de7 100644
--- a/arch/x86/kernel/sysfb_simplefb.c
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -88,8 +88,5 @@ __init int create_simplefb(const struct screen_info *si,
pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0,
&res, 1, mode, sizeof(*mode));
- if (IS_ERR(pd))
- return PTR_ERR(pd);
-
- return 0;
+ return PTR_ERR_OR_ZERO(pd);
}
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 0fa29609b2c4..25adc0e16eaa 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
#include <asm/time.h>
#ifdef CONFIG_X86_64
-__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
+__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES;
#endif
unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index f7fec09e3e3a..4e942f31b1a7 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -27,6 +27,37 @@ static int get_free_idx(void)
return -ESRCH;
}
+static bool tls_desc_okay(const struct user_desc *info)
+{
+ if (LDT_empty(info))
+ return true;
+
+ /*
+ * espfix is required for 16-bit data segments, but espfix
+ * only works for LDT segments.
+ */
+ if (!info->seg_32bit)
+ return false;
+
+ /* Only allow data segments in the TLS array. */
+ if (info->contents > 1)
+ return false;
+
+ /*
+ * Non-present segments with DPL 3 present an interesting attack
+ * surface. The kernel should handle such segments correctly,
+ * but TLS is very difficult to protect in a sandbox, so prevent
+ * such segments from being created.
+ *
+ * If userspace needs to remove a TLS entry, it can still delete
+ * it outright.
+ */
+ if (info->seg_not_present)
+ return false;
+
+ return true;
+}
+
static void set_tls_desc(struct task_struct *p, int idx,
const struct user_desc *info, int n)
{
@@ -66,6 +97,9 @@ int do_set_thread_area(struct task_struct *p, int idx,
if (copy_from_user(&info, u_info, sizeof(info)))
return -EFAULT;
+ if (!tls_desc_okay(&info))
+ return -EINVAL;
+
if (idx == -1)
idx = info.entry_number;
@@ -192,6 +226,7 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
{
struct user_desc infobuf[GDT_ENTRY_TLS_ENTRIES];
const struct user_desc *info;
+ int i;
if (pos >= GDT_ENTRY_TLS_ENTRIES * sizeof(struct user_desc) ||
(pos % sizeof(struct user_desc)) != 0 ||
@@ -205,6 +240,10 @@ int regset_tls_set(struct task_struct *target, const struct user_regset *regset,
else
info = infobuf;
+ for (i = 0; i < count / sizeof(struct user_desc); i++)
+ if (!tls_desc_okay(info + i))
+ return -EINVAL;
+
set_tls_desc(target,
GDT_ENTRY_TLS_MIN + (pos / sizeof(struct user_desc)),
info, count / sizeof(struct user_desc));
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 0d0e922fafc1..88900e288021 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -60,6 +60,7 @@
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
#include <asm/alternative.h>
+#include <asm/mpx.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -228,37 +229,44 @@ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \
DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error)
DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow)
-DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds)
DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op)
DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun)
DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
-#ifdef CONFIG_X86_32
DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
-#endif
DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check)
#ifdef CONFIG_X86_64
/* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
- enum ctx_state prev_state;
-
- prev_state = exception_enter();
- if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
- X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
- preempt_conditional_sti(regs);
- do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
- preempt_conditional_cli(regs);
- }
- exception_exit(prev_state);
-}
-
dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
{
static const char str[] = "double fault";
struct task_struct *tsk = current;
+#ifdef CONFIG_X86_ESPFIX64
+ extern unsigned char native_irq_return_iret[];
+
+ /*
+ * If IRET takes a non-IST fault on the espfix64 stack, then we
+ * end up promoting it to a doublefault. In that case, modify
+ * the stack to make it look like we just entered the #GP
+ * handler from user space, similar to bad_iret.
+ */
+ if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ regs->cs == __KERNEL_CS &&
+ regs->ip == (unsigned long)native_irq_return_iret)
+ {
+ struct pt_regs *normal_regs = task_pt_regs(current);
+
+ /* Fake a #GP(0) from userspace. */
+ memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+ normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */
+ regs->ip = (unsigned long)general_protection;
+ regs->sp = (unsigned long)&normal_regs->orig_ax;
+ return;
+ }
+#endif
+
exception_enter();
/* Return not checked because double check cannot be ignored */
notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -278,6 +286,89 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
}
#endif
+dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
+{
+ struct task_struct *tsk = current;
+ struct xsave_struct *xsave_buf;
+ enum ctx_state prev_state;
+ struct bndcsr *bndcsr;
+ siginfo_t *info;
+
+ prev_state = exception_enter();
+ if (notify_die(DIE_TRAP, "bounds", regs, error_code,
+ X86_TRAP_BR, SIGSEGV) == NOTIFY_STOP)
+ goto exit;
+ conditional_sti(regs);
+
+ if (!user_mode(regs))
+ die("bounds", regs, error_code);
+
+ if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
+ /* The exception is not from Intel MPX */
+ goto exit_trap;
+ }
+
+ /*
+ * We need to look at BNDSTATUS to resolve this exception.
+ * It is not directly accessible, though, so we need to
+ * do an xsave and then pull it out of the xsave buffer.
+ */
+ fpu_save_init(&tsk->thread.fpu);
+ xsave_buf = &(tsk->thread.fpu.state->xsave);
+ bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ if (!bndcsr)
+ goto exit_trap;
+
+ /*
+ * The error code field of the BNDSTATUS register communicates status
+ * information of a bound range exception #BR or operation involving
+ * bound directory.
+ */
+ switch (bndcsr->bndstatus & MPX_BNDSTA_ERROR_CODE) {
+ case 2: /* Bound directory has invalid entry. */
+ if (mpx_handle_bd_fault(xsave_buf))
+ goto exit_trap;
+ break; /* Success, it was handled */
+ case 1: /* Bound violation. */
+ info = mpx_generate_siginfo(regs, xsave_buf);
+ if (IS_ERR(info)) {
+ /*
+ * We failed to decode the MPX instruction. Act as if
+ * the exception was not caused by MPX.
+ */
+ goto exit_trap;
+ }
+ /*
+ * Success, we decoded the instruction and retrieved
+ * an 'info' containing the address being accessed
+ * which caused the exception. This information
+ * allows and application to possibly handle the
+ * #BR exception itself.
+ */
+ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, info);
+ kfree(info);
+ break;
+ case 0: /* No exception caused by Intel MPX operations. */
+ goto exit_trap;
+ default:
+ die("bounds", regs, error_code);
+ }
+
+exit:
+ exception_exit(prev_state);
+ return;
+exit_trap:
+ /*
+ * This path out is for all the cases where we could not
+ * handle the exception in some way (like allocating a
+ * table or telling userspace about it. We will also end
+ * up here if the kernel has MPX turned off at compile
+ * time..
+ */
+ do_trap(X86_TRAP_BR, SIGSEGV, "bounds", regs, error_code, NULL);
+ exception_exit(prev_state);
+}
+
dotraplinkage void
do_general_protection(struct pt_regs *regs, long error_code)
{
@@ -379,7 +470,7 @@ NOKPROBE_SYMBOL(do_int3);
* for scheduling or signal handling. The actual stack switch is done in
* entry.S
*/
-asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs)
{
struct pt_regs *regs = eregs;
/* Did already sync */
@@ -399,6 +490,36 @@ asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
return regs;
}
NOKPROBE_SYMBOL(sync_regs);
+
+struct bad_iret_stack {
+ void *error_entry_ret;
+ struct pt_regs regs;
+};
+
+asmlinkage __visible notrace
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+ /*
+ * This is called from entry_64.S early in handling a fault
+ * caused by a bad iret to user mode. To handle the fault
+ * correctly, we want move our stack frame to task_pt_regs
+ * and we want to pretend that the exception came from the
+ * iret target.
+ */
+ struct bad_iret_stack *new_stack =
+ container_of(task_pt_regs(current),
+ struct bad_iret_stack, regs);
+
+ /* Copy the IRET target to the new stack. */
+ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+ /* Copy the remainder of the stack from the current stack. */
+ memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+ BUG_ON(!user_mode_vm(&new_stack->regs));
+ return new_stack;
+}
+NOKPROBE_SYMBOL(fixup_bad_iret);
#endif
/*
@@ -778,7 +899,7 @@ void __init trap_init(void)
set_intr_gate(X86_TRAP_OLD_MF, coprocessor_segment_overrun);
set_intr_gate(X86_TRAP_TS, invalid_TSS);
set_intr_gate(X86_TRAP_NP, segment_not_present);
- set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+ set_intr_gate(X86_TRAP_SS, stack_segment);
set_intr_gate(X86_TRAP_GP, general_protection);
set_intr_gate(X86_TRAP_SPURIOUS, spurious_interrupt_bug);
set_intr_gate(X86_TRAP_MF, coprocessor_error);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b6025f9e36c6..b7e50bba3bbb 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1166,14 +1166,17 @@ void __init tsc_init(void)
x86_init.timers.tsc_pre_init();
- if (!cpu_has_tsc)
+ if (!cpu_has_tsc) {
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
+ }
tsc_khz = x86_platform.calibrate_tsc();
cpu_khz = tsc_khz;
if (!tsc_khz) {
mark_tsc_unstable("could not calculate TSC khz");
+ setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
return;
}
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 5d1cbfe4ae58..8b96a947021f 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -219,7 +219,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
{
u32 volatile *good_insns;
- insn_init(insn, auprobe->insn, x86_64);
+ insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
/* has the side-effect of processing the entire instruction */
insn_get_length(insn);
if (WARN_ON_ONCE(!insn_complete(insn)))
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 49edf2dd3613..00bf300fd846 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -186,6 +186,8 @@ SECTIONS
* start another segment - init.
*/
PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
+ ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
+ "per-CPU data too large - increase CONFIG_PHYSICAL_START")
#endif
INIT_TEXT_SECTION(PAGE_SIZE)
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index e1e1e80fc6a6..2dcc6ff6fdcc 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -1,59 +1,43 @@
/*
+ * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
+ *
+ * Based on the original implementation which is:
* Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
* Copyright 2003 Andi Kleen, SuSE Labs.
*
- * [ NOTE: this mechanism is now deprecated in favor of the vDSO. ]
+ * Parts of the original code have been moved to arch/x86/vdso/vma.c
+ *
+ * This file implements vsyscall emulation. vsyscalls are a legacy ABI:
+ * Userspace can request certain kernel services by calling fixed
+ * addresses. This concept is problematic:
*
- * Thanks to hpa@transmeta.com for some useful hint.
- * Special thanks to Ingo Molnar for his early experience with
- * a different vsyscall implementation for Linux/IA32 and for the name.
+ * - It interferes with ASLR.
+ * - It's awkward to write code that lives in kernel addresses but is
+ * callable by userspace at fixed addresses.
+ * - The whole concept is impossible for 32-bit compat userspace.
+ * - UML cannot easily virtualize a vsyscall.
*
- * vsyscall 1 is located at -10Mbyte, vsyscall 2 is located
- * at virtual address -10Mbyte+1024bytes etc... There are at max 4
- * vsyscalls. One vsyscall can reserve more than 1 slot to avoid
- * jumping out of line if necessary. We cannot add more with this
- * mechanism because older kernels won't return -ENOSYS.
+ * As of mid-2014, I believe that there is no new userspace code that
+ * will use a vsyscall if the vDSO is present. I hope that there will
+ * soon be no new userspace code that will ever use a vsyscall.
*
- * Note: the concept clashes with user mode linux. UML users should
- * use the vDSO.
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
*/
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/time.h>
-#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/timer.h>
-#include <linux/seqlock.h>
-#include <linux/jiffies.h>
-#include <linux/sysctl.h>
-#include <linux/topology.h>
-#include <linux/timekeeper_internal.h>
-#include <linux/getcpu.h>
-#include <linux/cpu.h>
-#include <linux/smp.h>
-#include <linux/notifier.h>
#include <linux/syscalls.h>
#include <linux/ratelimit.h>
#include <asm/vsyscall.h>
-#include <asm/pgtable.h>
-#include <asm/compat.h>
-#include <asm/page.h>
#include <asm/unistd.h>
#include <asm/fixmap.h>
-#include <asm/errno.h>
-#include <asm/io.h>
-#include <asm/segment.h>
-#include <asm/desc.h>
-#include <asm/topology.h>
#include <asm/traps.h>
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"
-DEFINE_VVAR(int, vgetcpu_mode);
-
static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
static int __init vsyscall_setup(char *str)
@@ -216,12 +200,13 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
*/
regs->orig_ax = syscall_nr;
regs->ax = -ENOSYS;
- tmp = secure_computing(syscall_nr);
+ tmp = secure_computing();
if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
warn_bad_vsyscall(KERN_DEBUG, regs,
"seccomp tried to change syscall nr or ip");
do_exit(SIGSYS);
}
+ regs->orig_ax = -1;
if (tmp)
goto do_ret; /* skip requested */
@@ -284,46 +269,54 @@ sigsegv:
}
/*
- * Assume __initcall executes before all user space. Hopefully kmod
- * doesn't violate that. We'll find out if it does.
+ * A pseudo VMA to allow ptrace access for the vsyscall page. This only
+ * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
+ * not need special handling anymore:
*/
-static void vsyscall_set_cpu(int cpu)
+static const char *gate_vma_name(struct vm_area_struct *vma)
{
- unsigned long d;
- unsigned long node = 0;
-#ifdef CONFIG_NUMA
- node = cpu_to_node(cpu);
-#endif
- if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
- write_rdtscp_aux((node << 12) | cpu);
-
- /*
- * Store cpu number in limit so that it can be loaded quickly
- * in user space in vgetcpu. (12 bits for the CPU and 8 bits for the node)
- */
- d = 0x0f40000000000ULL;
- d |= cpu;
- d |= (node & 0xf) << 12;
- d |= (node >> 4) << 48;
-
- write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+ return "[vsyscall]";
}
-
-static void cpu_vsyscall_init(void *arg)
+static struct vm_operations_struct gate_vma_ops = {
+ .name = gate_vma_name,
+};
+static struct vm_area_struct gate_vma = {
+ .vm_start = VSYSCALL_ADDR,
+ .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
+ .vm_page_prot = PAGE_READONLY_EXEC,
+ .vm_flags = VM_READ | VM_EXEC,
+ .vm_ops = &gate_vma_ops,
+};
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
- /* preemption should be already off */
- vsyscall_set_cpu(raw_smp_processor_id());
+#ifdef CONFIG_IA32_EMULATION
+ if (!mm || mm->context.ia32_compat)
+ return NULL;
+#endif
+ if (vsyscall_mode == NONE)
+ return NULL;
+ return &gate_vma;
}
-static int
-cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
- long cpu = (long)arg;
+ struct vm_area_struct *vma = get_gate_vma(mm);
+
+ if (!vma)
+ return 0;
- if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
- smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 1);
+ return (addr >= vma->vm_start) && (addr < vma->vm_end);
+}
- return NOTIFY_DONE;
+/*
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
+ */
+int in_gate_area_no_mm(unsigned long addr)
+{
+ return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
}
void __init map_vsyscall(void)
@@ -331,24 +324,12 @@ void __init map_vsyscall(void)
extern char __vsyscall_page;
unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
- __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
- vsyscall_mode == NATIVE
- ? PAGE_KERNEL_VSYSCALL
- : PAGE_KERNEL_VVAR);
+ if (vsyscall_mode != NONE)
+ __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
+ vsyscall_mode == NATIVE
+ ? PAGE_KERNEL_VSYSCALL
+ : PAGE_KERNEL_VVAR);
+
BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
(unsigned long)VSYSCALL_ADDR);
}
-
-static int __init vsyscall_init(void)
-{
- cpu_notifier_register_begin();
-
- on_each_cpu(cpu_vsyscall_init, NULL, 1);
- /* notifier priority > KVM */
- __hotcpu_notifier(cpu_vsyscall_notifier, 30);
-
- cpu_notifier_register_done();
-
- return 0;
-}
-__initcall(vsyscall_init);
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e48b674639cc..234b0722de53 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -116,8 +116,6 @@ struct x86_msi_ops x86_msi = {
.teardown_msi_irqs = default_teardown_msi_irqs,
.restore_msi_irqs = default_restore_msi_irqs,
.setup_hpet_msi = default_setup_hpet_msi,
- .msi_mask_irq = default_msi_mask_irq,
- .msix_mask_irq = default_msix_mask_irq,
};
/* MSI arch specific hooks */
@@ -140,14 +138,6 @@ void arch_restore_msi_irqs(struct pci_dev *dev)
{
x86_msi.restore_msi_irqs(dev);
}
-u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
-{
- return x86_msi.msi_mask_irq(desc, mask, flag);
-}
-u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag)
-{
- return x86_msi.msix_mask_irq(desc, flag);
-}
#endif
struct x86_io_apic_ops x86_io_apic_ops = {
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 940b142cc11f..0de1fae2bdf0 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -271,8 +271,6 @@ int save_xstate_sig(void __user *buf, void __user *buf_fx, int size)
if (use_fxsr() && save_xstate_epilog(buf_fx, ia32_fxstate))
return -1;
- drop_init_fpu(tsk); /* trigger finit */
-
return 0;
}
@@ -402,8 +400,11 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
set_used_math();
}
- if (use_eager_fpu())
+ if (use_eager_fpu()) {
+ preempt_disable();
math_state_restore();
+ preempt_enable();
+ }
return err;
} else {
@@ -737,3 +738,4 @@ void *get_xsave_addr(struct xsave_struct *xsave, int xstate)
return (void *)xsave + xstate_comp_offsets[feature];
}
+EXPORT_SYMBOL_GPL(get_xsave_addr);
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 25d22b2d6509..08f790dfadc9 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -7,14 +7,13 @@ CFLAGS_vmx.o := -I.
KVM := ../../../virt/kvm
-kvm-y += $(KVM)/kvm_main.o $(KVM)/ioapic.o \
- $(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
+kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
-kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += $(KVM)/assigned-dev.o $(KVM)/iommu.o
kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o
kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
- i8254.o cpuid.o pmu.o
+ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o
+kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT) += assigned-dev.o iommu.o
kvm-intel-y += vmx.o
kvm-amd-y += svm.o
diff --git a/arch/x86/kvm/assigned-dev.c b/arch/x86/kvm/assigned-dev.c
new file mode 100644
index 000000000000..6eb5c20ee373
--- /dev/null
+++ b/arch/x86/kvm/assigned-dev.c
@@ -0,0 +1,1052 @@
+/*
+ * Kernel-based Virtual Machine - device assignment support
+ *
+ * Copyright (C) 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2. See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/errno.h>
+#include <linux/spinlock.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/namei.h>
+#include <linux/fs.h>
+#include "irq.h"
+#include "assigned-dev.h"
+
+struct kvm_assigned_dev_kernel {
+ struct kvm_irq_ack_notifier ack_notifier;
+ struct list_head list;
+ int assigned_dev_id;
+ int host_segnr;
+ int host_busnr;
+ int host_devfn;
+ unsigned int entries_nr;
+ int host_irq;
+ bool host_irq_disabled;
+ bool pci_2_3;
+ struct msix_entry *host_msix_entries;
+ int guest_irq;
+ struct msix_entry *guest_msix_entries;
+ unsigned long irq_requested_type;
+ int irq_source_id;
+ int flags;
+ struct pci_dev *dev;
+ struct kvm *kvm;
+ spinlock_t intx_lock;
+ spinlock_t intx_mask_lock;
+ char irq_name[32];
+ struct pci_saved_state *pci_saved_state;
+};
+
+static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
+ int assigned_dev_id)
+{
+ struct list_head *ptr;
+ struct kvm_assigned_dev_kernel *match;
+
+ list_for_each(ptr, head) {
+ match = list_entry(ptr, struct kvm_assigned_dev_kernel, list);
+ if (match->assigned_dev_id == assigned_dev_id)
+ return match;
+ }
+ return NULL;
+}
+
+static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
+ *assigned_dev, int irq)
+{
+ int i, index;
+ struct msix_entry *host_msix_entries;
+
+ host_msix_entries = assigned_dev->host_msix_entries;
+
+ index = -1;
+ for (i = 0; i < assigned_dev->entries_nr; i++)
+ if (irq == host_msix_entries[i].vector) {
+ index = i;
+ break;
+ }
+ if (index < 0)
+ printk(KERN_WARNING "Fail to find correlated MSI-X entry!\n");
+
+ return index;
+}
+
+static irqreturn_t kvm_assigned_dev_intx(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+ int ret;
+
+ spin_lock(&assigned_dev->intx_lock);
+ if (pci_check_and_mask_intx(assigned_dev->dev)) {
+ assigned_dev->host_irq_disabled = true;
+ ret = IRQ_WAKE_THREAD;
+ } else
+ ret = IRQ_NONE;
+ spin_unlock(&assigned_dev->intx_lock);
+
+ return ret;
+}
+
+static void
+kvm_assigned_dev_raise_guest_irq(struct kvm_assigned_dev_kernel *assigned_dev,
+ int vector)
+{
+ if (unlikely(assigned_dev->irq_requested_type &
+ KVM_DEV_IRQ_GUEST_INTX)) {
+ spin_lock(&assigned_dev->intx_mask_lock);
+ if (!(assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX))
+ kvm_set_irq(assigned_dev->kvm,
+ assigned_dev->irq_source_id, vector, 1,
+ false);
+ spin_unlock(&assigned_dev->intx_mask_lock);
+ } else
+ kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+ vector, 1, false);
+}
+
+static irqreturn_t kvm_assigned_dev_thread_intx(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+ if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+ spin_lock_irq(&assigned_dev->intx_lock);
+ disable_irq_nosync(irq);
+ assigned_dev->host_irq_disabled = true;
+ spin_unlock_irq(&assigned_dev->intx_lock);
+ }
+
+ kvm_assigned_dev_raise_guest_irq(assigned_dev,
+ assigned_dev->guest_irq);
+
+ return IRQ_HANDLED;
+}
+
+#ifdef __KVM_HAVE_MSI
+static irqreturn_t kvm_assigned_dev_msi(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+ int ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+ assigned_dev->irq_source_id,
+ assigned_dev->guest_irq, 1);
+ return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
+static irqreturn_t kvm_assigned_dev_thread_msi(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+
+ kvm_assigned_dev_raise_guest_irq(assigned_dev,
+ assigned_dev->guest_irq);
+
+ return IRQ_HANDLED;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static irqreturn_t kvm_assigned_dev_msix(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+ int index = find_index_from_host_irq(assigned_dev, irq);
+ u32 vector;
+ int ret = 0;
+
+ if (index >= 0) {
+ vector = assigned_dev->guest_msix_entries[index].vector;
+ ret = kvm_set_irq_inatomic(assigned_dev->kvm,
+ assigned_dev->irq_source_id,
+ vector, 1);
+ }
+
+ return unlikely(ret == -EWOULDBLOCK) ? IRQ_WAKE_THREAD : IRQ_HANDLED;
+}
+
+static irqreturn_t kvm_assigned_dev_thread_msix(int irq, void *dev_id)
+{
+ struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+ int index = find_index_from_host_irq(assigned_dev, irq);
+ u32 vector;
+
+ if (index >= 0) {
+ vector = assigned_dev->guest_msix_entries[index].vector;
+ kvm_assigned_dev_raise_guest_irq(assigned_dev, vector);
+ }
+
+ return IRQ_HANDLED;
+}
+#endif
+
+/* Ack the irq line for an assigned device */
+static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
+{
+ struct kvm_assigned_dev_kernel *dev =
+ container_of(kian, struct kvm_assigned_dev_kernel,
+ ack_notifier);
+
+ kvm_set_irq(dev->kvm, dev->irq_source_id, dev->guest_irq, 0, false);
+
+ spin_lock(&dev->intx_mask_lock);
+
+ if (!(dev->flags & KVM_DEV_ASSIGN_MASK_INTX)) {
+ bool reassert = false;
+
+ spin_lock_irq(&dev->intx_lock);
+ /*
+ * The guest IRQ may be shared so this ack can come from an
+ * IRQ for another guest device.
+ */
+ if (dev->host_irq_disabled) {
+ if (!(dev->flags & KVM_DEV_ASSIGN_PCI_2_3))
+ enable_irq(dev->host_irq);
+ else if (!pci_check_and_unmask_intx(dev->dev))
+ reassert = true;
+ dev->host_irq_disabled = reassert;
+ }
+ spin_unlock_irq(&dev->intx_lock);
+
+ if (reassert)
+ kvm_set_irq(dev->kvm, dev->irq_source_id,
+ dev->guest_irq, 1, false);
+ }
+
+ spin_unlock(&dev->intx_mask_lock);
+}
+
+static void deassign_guest_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
+{
+ if (assigned_dev->ack_notifier.gsi != -1)
+ kvm_unregister_irq_ack_notifier(kvm,
+ &assigned_dev->ack_notifier);
+
+ kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+ assigned_dev->guest_irq, 0, false);
+
+ if (assigned_dev->irq_source_id != -1)
+ kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
+ assigned_dev->irq_source_id = -1;
+ assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_GUEST_MASK);
+}
+
+/* The function implicit hold kvm->lock mutex due to cancel_work_sync() */
+static void deassign_host_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
+{
+ /*
+ * We disable irq here to prevent further events.
+ *
+ * Notice this maybe result in nested disable if the interrupt type is
+ * INTx, but it's OK for we are going to free it.
+ *
+ * If this function is a part of VM destroy, please ensure that till
+ * now, the kvm state is still legal for probably we also have to wait
+ * on a currently running IRQ handler.
+ */
+ if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
+ int i;
+ for (i = 0; i < assigned_dev->entries_nr; i++)
+ disable_irq(assigned_dev->host_msix_entries[i].vector);
+
+ for (i = 0; i < assigned_dev->entries_nr; i++)
+ free_irq(assigned_dev->host_msix_entries[i].vector,
+ assigned_dev);
+
+ assigned_dev->entries_nr = 0;
+ kfree(assigned_dev->host_msix_entries);
+ kfree(assigned_dev->guest_msix_entries);
+ pci_disable_msix(assigned_dev->dev);
+ } else {
+ /* Deal with MSI and INTx */
+ if ((assigned_dev->irq_requested_type &
+ KVM_DEV_IRQ_HOST_INTX) &&
+ (assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+ spin_lock_irq(&assigned_dev->intx_lock);
+ pci_intx(assigned_dev->dev, false);
+ spin_unlock_irq(&assigned_dev->intx_lock);
+ synchronize_irq(assigned_dev->host_irq);
+ } else
+ disable_irq(assigned_dev->host_irq);
+
+ free_irq(assigned_dev->host_irq, assigned_dev);
+
+ if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSI)
+ pci_disable_msi(assigned_dev->dev);
+ }
+
+ assigned_dev->irq_requested_type &= ~(KVM_DEV_IRQ_HOST_MASK);
+}
+
+static int kvm_deassign_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev,
+ unsigned long irq_requested_type)
+{
+ unsigned long guest_irq_type, host_irq_type;
+
+ if (!irqchip_in_kernel(kvm))
+ return -EINVAL;
+ /* no irq assignment to deassign */
+ if (!assigned_dev->irq_requested_type)
+ return -ENXIO;
+
+ host_irq_type = irq_requested_type & KVM_DEV_IRQ_HOST_MASK;
+ guest_irq_type = irq_requested_type & KVM_DEV_IRQ_GUEST_MASK;
+
+ if (host_irq_type)
+ deassign_host_irq(kvm, assigned_dev);
+ if (guest_irq_type)
+ deassign_guest_irq(kvm, assigned_dev);
+
+ return 0;
+}
+
+static void kvm_free_assigned_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *assigned_dev)
+{
+ kvm_deassign_irq(kvm, assigned_dev, assigned_dev->irq_requested_type);
+}
+
+static void kvm_free_assigned_device(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel
+ *assigned_dev)
+{
+ kvm_free_assigned_irq(kvm, assigned_dev);
+
+ pci_reset_function(assigned_dev->dev);
+ if (pci_load_and_free_saved_state(assigned_dev->dev,
+ &assigned_dev->pci_saved_state))
+ printk(KERN_INFO "%s: Couldn't reload %s saved state\n",
+ __func__, dev_name(&assigned_dev->dev->dev));
+ else
+ pci_restore_state(assigned_dev->dev);
+
+ pci_clear_dev_assigned(assigned_dev->dev);
+
+ pci_release_regions(assigned_dev->dev);
+ pci_disable_device(assigned_dev->dev);
+ pci_dev_put(assigned_dev->dev);
+
+ list_del(&assigned_dev->list);
+ kfree(assigned_dev);
+}
+
+void kvm_free_all_assigned_devices(struct kvm *kvm)
+{
+ struct list_head *ptr, *ptr2;
+ struct kvm_assigned_dev_kernel *assigned_dev;
+
+ list_for_each_safe(ptr, ptr2, &kvm->arch.assigned_dev_head) {
+ assigned_dev = list_entry(ptr,
+ struct kvm_assigned_dev_kernel,
+ list);
+
+ kvm_free_assigned_device(kvm, assigned_dev);
+ }
+}
+
+static int assigned_device_enable_host_intx(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev)
+{
+ irq_handler_t irq_handler;
+ unsigned long flags;
+
+ dev->host_irq = dev->dev->irq;
+
+ /*
+ * We can only share the IRQ line with other host devices if we are
+ * able to disable the IRQ source at device-level - independently of
+ * the guest driver. Otherwise host devices may suffer from unbounded
+ * IRQ latencies when the guest keeps the line asserted.
+ */
+ if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+ irq_handler = kvm_assigned_dev_intx;
+ flags = IRQF_SHARED;
+ } else {
+ irq_handler = NULL;
+ flags = IRQF_ONESHOT;
+ }
+ if (request_threaded_irq(dev->host_irq, irq_handler,
+ kvm_assigned_dev_thread_intx, flags,
+ dev->irq_name, dev))
+ return -EIO;
+
+ if (dev->flags & KVM_DEV_ASSIGN_PCI_2_3) {
+ spin_lock_irq(&dev->intx_lock);
+ pci_intx(dev->dev, true);
+ spin_unlock_irq(&dev->intx_lock);
+ }
+ return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_host_msi(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev)
+{
+ int r;
+
+ if (!dev->dev->msi_enabled) {
+ r = pci_enable_msi(dev->dev);
+ if (r)
+ return r;
+ }
+
+ dev->host_irq = dev->dev->irq;
+ if (request_threaded_irq(dev->host_irq, kvm_assigned_dev_msi,
+ kvm_assigned_dev_thread_msi, 0,
+ dev->irq_name, dev)) {
+ pci_disable_msi(dev->dev);
+ return -EIO;
+ }
+
+ return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_host_msix(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev)
+{
+ int i, r = -EINVAL;
+
+ /* host_msix_entries and guest_msix_entries should have been
+ * initialized */
+ if (dev->entries_nr == 0)
+ return r;
+
+ r = pci_enable_msix_exact(dev->dev,
+ dev->host_msix_entries, dev->entries_nr);
+ if (r)
+ return r;
+
+ for (i = 0; i < dev->entries_nr; i++) {
+ r = request_threaded_irq(dev->host_msix_entries[i].vector,
+ kvm_assigned_dev_msix,
+ kvm_assigned_dev_thread_msix,
+ 0, dev->irq_name, dev);
+ if (r)
+ goto err;
+ }
+
+ return 0;
+err:
+ for (i -= 1; i >= 0; i--)
+ free_irq(dev->host_msix_entries[i].vector, dev);
+ pci_disable_msix(dev->dev);
+ return r;
+}
+
+#endif
+
+static int assigned_device_enable_guest_intx(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq)
+{
+ dev->guest_irq = irq->guest_irq;
+ dev->ack_notifier.gsi = irq->guest_irq;
+ return 0;
+}
+
+#ifdef __KVM_HAVE_MSI
+static int assigned_device_enable_guest_msi(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq)
+{
+ dev->guest_irq = irq->guest_irq;
+ dev->ack_notifier.gsi = -1;
+ return 0;
+}
+#endif
+
+#ifdef __KVM_HAVE_MSIX
+static int assigned_device_enable_guest_msix(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq)
+{
+ dev->guest_irq = irq->guest_irq;
+ dev->ack_notifier.gsi = -1;
+ return 0;
+}
+#endif
+
+static int assign_host_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ __u32 host_irq_type)
+{
+ int r = -EEXIST;
+
+ if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
+ return r;
+
+ snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s",
+ pci_name(dev->dev));
+
+ switch (host_irq_type) {
+ case KVM_DEV_IRQ_HOST_INTX:
+ r = assigned_device_enable_host_intx(kvm, dev);
+ break;
+#ifdef __KVM_HAVE_MSI
+ case KVM_DEV_IRQ_HOST_MSI:
+ r = assigned_device_enable_host_msi(kvm, dev);
+ break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+ case KVM_DEV_IRQ_HOST_MSIX:
+ r = assigned_device_enable_host_msix(kvm, dev);
+ break;
+#endif
+ default:
+ r = -EINVAL;
+ }
+ dev->host_irq_disabled = false;
+
+ if (!r)
+ dev->irq_requested_type |= host_irq_type;
+
+ return r;
+}
+
+static int assign_guest_irq(struct kvm *kvm,
+ struct kvm_assigned_dev_kernel *dev,
+ struct kvm_assigned_irq *irq,
+ unsigned long guest_irq_type)
+{
+ int id;
+ int r = -EEXIST;
+
+ if (dev->irq_requested_type & KVM_DEV_IRQ_GUEST_MASK)
+ return r;
+
+ id = kvm_request_irq_source_id(kvm);
+ if (id < 0)
+ return id;
+
+ dev->irq_source_id = id;
+
+ switch (guest_irq_type) {
+ case KVM_DEV_IRQ_GUEST_INTX:
+ r = assigned_device_enable_guest_intx(kvm, dev, irq);
+ break;
+#ifdef __KVM_HAVE_MSI
+ case KVM_DEV_IRQ_GUEST_MSI:
+ r = assigned_device_enable_guest_msi(kvm, dev, irq);
+ break;
+#endif
+#ifdef __KVM_HAVE_MSIX
+ case KVM_DEV_IRQ_GUEST_MSIX:
+ r = assigned_device_enable_guest_msix(kvm, dev, irq);
+ break;
+#endif
+ default:
+ r = -EINVAL;
+ }
+
+ if (!r) {
+ dev->irq_requested_type |= guest_irq_type;
+ if (dev->ack_notifier.gsi != -1)
+ kvm_register_irq_ack_notifier(kvm, &dev->ack_notifier);
+ } else {
+ kvm_free_irq_source_id(kvm, dev->irq_source_id);
+ dev->irq_source_id = -1;
+ }
+
+ return r;
+}
+
+/* TODO Deal with KVM_DEV_IRQ_ASSIGNED_MASK_MSIX */
+static int kvm_vm_ioctl_assign_irq(struct kvm *kvm,
+ struct kvm_assigned_irq *assigned_irq)
+{
+ int r = -EINVAL;
+ struct kvm_assigned_dev_kernel *match;
+ unsigned long host_irq_type, guest_irq_type;
+
+ if (!irqchip_in_kernel(kvm))
+ return r;
+
+ mutex_lock(&kvm->lock);
+ r = -ENODEV;
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_irq->assigned_dev_id);
+ if (!match)
+ goto out;
+
+ host_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_HOST_MASK);
+ guest_irq_type = (assigned_irq->flags & KVM_DEV_IRQ_GUEST_MASK);
+
+ r = -EINVAL;
+ /* can only assign one type at a time */
+ if (hweight_long(host_irq_type) > 1)
+ goto out;
+ if (hweight_long(guest_irq_type) > 1)
+ goto out;
+ if (host_irq_type == 0 && guest_irq_type == 0)
+ goto out;
+
+ r = 0;
+ if (host_irq_type)
+ r = assign_host_irq(kvm, match, host_irq_type);
+ if (r)
+ goto out;
+
+ if (guest_irq_type)
+ r = assign_guest_irq(kvm, match, assigned_irq, guest_irq_type);
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_deassign_dev_irq(struct kvm *kvm,
+ struct kvm_assigned_irq
+ *assigned_irq)
+{
+ int r = -ENODEV;
+ struct kvm_assigned_dev_kernel *match;
+ unsigned long irq_type;
+
+ mutex_lock(&kvm->lock);
+
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_irq->assigned_dev_id);
+ if (!match)
+ goto out;
+
+ irq_type = assigned_irq->flags & (KVM_DEV_IRQ_HOST_MASK |
+ KVM_DEV_IRQ_GUEST_MASK);
+ r = kvm_deassign_irq(kvm, match, irq_type);
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+/*
+ * We want to test whether the caller has been granted permissions to
+ * use this device. To be able to configure and control the device,
+ * the user needs access to PCI configuration space and BAR resources.
+ * These are accessed through PCI sysfs. PCI config space is often
+ * passed to the process calling this ioctl via file descriptor, so we
+ * can't rely on access to that file. We can check for permissions
+ * on each of the BAR resource files, which is a pretty clear
+ * indicator that the user has been granted access to the device.
+ */
+static int probe_sysfs_permissions(struct pci_dev *dev)
+{
+#ifdef CONFIG_SYSFS
+ int i;
+ bool bar_found = false;
+
+ for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) {
+ char *kpath, *syspath;
+ struct path path;
+ struct inode *inode;
+ int r;
+
+ if (!pci_resource_len(dev, i))
+ continue;
+
+ kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL);
+ if (!kpath)
+ return -ENOMEM;
+
+ /* Per sysfs-rules, sysfs is always at /sys */
+ syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i);
+ kfree(kpath);
+ if (!syspath)
+ return -ENOMEM;
+
+ r = kern_path(syspath, LOOKUP_FOLLOW, &path);
+ kfree(syspath);
+ if (r)
+ return r;
+
+ inode = path.dentry->d_inode;
+
+ r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS);
+ path_put(&path);
+ if (r)
+ return r;
+
+ bar_found = true;
+ }
+
+ /* If no resources, probably something special */
+ if (!bar_found)
+ return -EPERM;
+
+ return 0;
+#else
+ return -EINVAL; /* No way to control the device without sysfs */
+#endif
+}
+
+static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
+ struct kvm_assigned_pci_dev *assigned_dev)
+{
+ int r = 0, idx;
+ struct kvm_assigned_dev_kernel *match;
+ struct pci_dev *dev;
+
+ if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU))
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ idx = srcu_read_lock(&kvm->srcu);
+
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_dev->assigned_dev_id);
+ if (match) {
+ /* device already assigned */
+ r = -EEXIST;
+ goto out;
+ }
+
+ match = kzalloc(sizeof(struct kvm_assigned_dev_kernel), GFP_KERNEL);
+ if (match == NULL) {
+ printk(KERN_INFO "%s: Couldn't allocate memory\n",
+ __func__);
+ r = -ENOMEM;
+ goto out;
+ }
+ dev = pci_get_domain_bus_and_slot(assigned_dev->segnr,
+ assigned_dev->busnr,
+ assigned_dev->devfn);
+ if (!dev) {
+ printk(KERN_INFO "%s: host device not found\n", __func__);
+ r = -EINVAL;
+ goto out_free;
+ }
+
+ /* Don't allow bridges to be assigned */
+ if (dev->hdr_type != PCI_HEADER_TYPE_NORMAL) {
+ r = -EPERM;
+ goto out_put;
+ }
+
+ r = probe_sysfs_permissions(dev);
+ if (r)
+ goto out_put;
+
+ if (pci_enable_device(dev)) {
+ printk(KERN_INFO "%s: Could not enable PCI device\n", __func__);
+ r = -EBUSY;
+ goto out_put;
+ }
+ r = pci_request_regions(dev, "kvm_assigned_device");
+ if (r) {
+ printk(KERN_INFO "%s: Could not get access to device regions\n",
+ __func__);
+ goto out_disable;
+ }
+
+ pci_reset_function(dev);
+ pci_save_state(dev);
+ match->pci_saved_state = pci_store_saved_state(dev);
+ if (!match->pci_saved_state)
+ printk(KERN_DEBUG "%s: Couldn't store %s saved state\n",
+ __func__, dev_name(&dev->dev));
+
+ if (!pci_intx_mask_supported(dev))
+ assigned_dev->flags &= ~KVM_DEV_ASSIGN_PCI_2_3;
+
+ match->assigned_dev_id = assigned_dev->assigned_dev_id;
+ match->host_segnr = assigned_dev->segnr;
+ match->host_busnr = assigned_dev->busnr;
+ match->host_devfn = assigned_dev->devfn;
+ match->flags = assigned_dev->flags;
+ match->dev = dev;
+ spin_lock_init(&match->intx_lock);
+ spin_lock_init(&match->intx_mask_lock);
+ match->irq_source_id = -1;
+ match->kvm = kvm;
+ match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
+
+ list_add(&match->list, &kvm->arch.assigned_dev_head);
+
+ if (!kvm->arch.iommu_domain) {
+ r = kvm_iommu_map_guest(kvm);
+ if (r)
+ goto out_list_del;
+ }
+ r = kvm_assign_device(kvm, match->dev);
+ if (r)
+ goto out_list_del;
+
+out:
+ srcu_read_unlock(&kvm->srcu, idx);
+ mutex_unlock(&kvm->lock);
+ return r;
+out_list_del:
+ if (pci_load_and_free_saved_state(dev, &match->pci_saved_state))
+ printk(KERN_INFO "%s: Couldn't reload %s saved state\n",
+ __func__, dev_name(&dev->dev));
+ list_del(&match->list);
+ pci_release_regions(dev);
+out_disable:
+ pci_disable_device(dev);
+out_put:
+ pci_dev_put(dev);
+out_free:
+ kfree(match);
+ srcu_read_unlock(&kvm->srcu, idx);
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_deassign_device(struct kvm *kvm,
+ struct kvm_assigned_pci_dev *assigned_dev)
+{
+ int r = 0;
+ struct kvm_assigned_dev_kernel *match;
+
+ mutex_lock(&kvm->lock);
+
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_dev->assigned_dev_id);
+ if (!match) {
+ printk(KERN_INFO "%s: device hasn't been assigned before, "
+ "so cannot be deassigned\n", __func__);
+ r = -EINVAL;
+ goto out;
+ }
+
+ kvm_deassign_device(kvm, match->dev);
+
+ kvm_free_assigned_device(kvm, match);
+
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+ struct kvm_assigned_msix_nr *entry_nr)
+{
+ int r = 0;
+ struct kvm_assigned_dev_kernel *adev;
+
+ mutex_lock(&kvm->lock);
+
+ adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ entry_nr->assigned_dev_id);
+ if (!adev) {
+ r = -EINVAL;
+ goto msix_nr_out;
+ }
+
+ if (adev->entries_nr == 0) {
+ adev->entries_nr = entry_nr->entry_nr;
+ if (adev->entries_nr == 0 ||
+ adev->entries_nr > KVM_MAX_MSIX_PER_DEV) {
+ r = -EINVAL;
+ goto msix_nr_out;
+ }
+
+ adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+ entry_nr->entry_nr,
+ GFP_KERNEL);
+ if (!adev->host_msix_entries) {
+ r = -ENOMEM;
+ goto msix_nr_out;
+ }
+ adev->guest_msix_entries =
+ kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr,
+ GFP_KERNEL);
+ if (!adev->guest_msix_entries) {
+ kfree(adev->host_msix_entries);
+ r = -ENOMEM;
+ goto msix_nr_out;
+ }
+ } else /* Not allowed set MSI-X number twice */
+ r = -EINVAL;
+msix_nr_out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+ struct kvm_assigned_msix_entry *entry)
+{
+ int r = 0, i;
+ struct kvm_assigned_dev_kernel *adev;
+
+ mutex_lock(&kvm->lock);
+
+ adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ entry->assigned_dev_id);
+
+ if (!adev) {
+ r = -EINVAL;
+ goto msix_entry_out;
+ }
+
+ for (i = 0; i < adev->entries_nr; i++)
+ if (adev->guest_msix_entries[i].vector == 0 ||
+ adev->guest_msix_entries[i].entry == entry->entry) {
+ adev->guest_msix_entries[i].entry = entry->entry;
+ adev->guest_msix_entries[i].vector = entry->gsi;
+ adev->host_msix_entries[i].entry = entry->entry;
+ break;
+ }
+ if (i == adev->entries_nr) {
+ r = -ENOSPC;
+ goto msix_entry_out;
+ }
+
+msix_entry_out:
+ mutex_unlock(&kvm->lock);
+
+ return r;
+}
+#endif
+
+static int kvm_vm_ioctl_set_pci_irq_mask(struct kvm *kvm,
+ struct kvm_assigned_pci_dev *assigned_dev)
+{
+ int r = 0;
+ struct kvm_assigned_dev_kernel *match;
+
+ mutex_lock(&kvm->lock);
+
+ match = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+ assigned_dev->assigned_dev_id);
+ if (!match) {
+ r = -ENODEV;
+ goto out;
+ }
+
+ spin_lock(&match->intx_mask_lock);
+
+ match->flags &= ~KVM_DEV_ASSIGN_MASK_INTX;
+ match->flags |= assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX;
+
+ if (match->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
+ if (assigned_dev->flags & KVM_DEV_ASSIGN_MASK_INTX) {
+ kvm_set_irq(match->kvm, match->irq_source_id,
+ match->guest_irq, 0, false);
+ /*
+ * Masking at hardware-level is performed on demand,
+ * i.e. when an IRQ actually arrives at the host.
+ */
+ } else if (!(assigned_dev->flags & KVM_DEV_ASSIGN_PCI_2_3)) {
+ /*
+ * Unmask the IRQ line if required. Unmasking at
+ * device level will be performed by user space.
+ */
+ spin_lock_irq(&match->intx_lock);
+ if (match->host_irq_disabled) {
+ enable_irq(match->host_irq);
+ match->host_irq_disabled = false;
+ }
+ spin_unlock_irq(&match->intx_lock);
+ }
+ }
+
+ spin_unlock(&match->intx_mask_lock);
+
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+ unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ int r;
+
+ switch (ioctl) {
+ case KVM_ASSIGN_PCI_DEVICE: {
+ struct kvm_assigned_pci_dev assigned_dev;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+ goto out;
+ r = kvm_vm_ioctl_assign_device(kvm, &assigned_dev);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_ASSIGN_IRQ: {
+ r = -EOPNOTSUPP;
+ break;
+ }
+ case KVM_ASSIGN_DEV_IRQ: {
+ struct kvm_assigned_irq assigned_irq;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+ goto out;
+ r = kvm_vm_ioctl_assign_irq(kvm, &assigned_irq);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_DEASSIGN_DEV_IRQ: {
+ struct kvm_assigned_irq assigned_irq;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_irq, argp, sizeof assigned_irq))
+ goto out;
+ r = kvm_vm_ioctl_deassign_dev_irq(kvm, &assigned_irq);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_DEASSIGN_PCI_DEVICE: {
+ struct kvm_assigned_pci_dev assigned_dev;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+ goto out;
+ r = kvm_vm_ioctl_deassign_device(kvm, &assigned_dev);
+ if (r)
+ goto out;
+ break;
+ }
+#ifdef __KVM_HAVE_MSIX
+ case KVM_ASSIGN_SET_MSIX_NR: {
+ struct kvm_assigned_msix_nr entry_nr;
+ r = -EFAULT;
+ if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+ goto out;
+ r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+ if (r)
+ goto out;
+ break;
+ }
+ case KVM_ASSIGN_SET_MSIX_ENTRY: {
+ struct kvm_assigned_msix_entry entry;
+ r = -EFAULT;
+ if (copy_from_user(&entry, argp, sizeof entry))
+ goto out;
+ r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+ if (r)
+ goto out;
+ break;
+ }
+#endif
+ case KVM_ASSIGN_SET_INTX_MASK: {
+ struct kvm_assigned_pci_dev assigned_dev;
+
+ r = -EFAULT;
+ if (copy_from_user(&assigned_dev, argp, sizeof assigned_dev))
+ goto out;
+ r = kvm_vm_ioctl_set_pci_irq_mask(kvm, &assigned_dev);
+ break;
+ }
+ default:
+ r = -ENOTTY;
+ break;
+ }
+out:
+ return r;
+}
diff --git a/arch/x86/kvm/assigned-dev.h b/arch/x86/kvm/assigned-dev.h
new file mode 100644
index 000000000000..a428c1a211b2
--- /dev/null
+++ b/arch/x86/kvm/assigned-dev.h
@@ -0,0 +1,32 @@
+#ifndef ARCH_X86_KVM_ASSIGNED_DEV_H
+#define ARCH_X86_KVM_ASSIGNED_DEV_H
+
+#include <linux/kvm_host.h>
+
+#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
+int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev);
+int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev);
+
+int kvm_iommu_map_guest(struct kvm *kvm);
+int kvm_iommu_unmap_guest(struct kvm *kvm);
+
+long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+ unsigned long arg);
+
+void kvm_free_all_assigned_devices(struct kvm *kvm);
+#else
+static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
+{
+ return 0;
+}
+
+static inline long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
+ unsigned long arg)
+{
+ return -ENOTTY;
+}
+
+static inline void kvm_free_all_assigned_devices(struct kvm *kvm) {}
+#endif /* CONFIG_KVM_DEVICE_ASSIGNMENT */
+
+#endif /* ARCH_X86_KVM_ASSIGNED_DEV_H */
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 38a0afe83c6b..8a80737ee6e6 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -23,7 +23,7 @@
#include "mmu.h"
#include "trace.h"
-static u32 xstate_required_size(u64 xstate_bv)
+static u32 xstate_required_size(u64 xstate_bv, bool compacted)
{
int feature_bit = 0;
u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
@@ -31,9 +31,10 @@ static u32 xstate_required_size(u64 xstate_bv)
xstate_bv &= XSTATE_EXTEND_MASK;
while (xstate_bv) {
if (xstate_bv & 0x1) {
- u32 eax, ebx, ecx, edx;
+ u32 eax, ebx, ecx, edx, offset;
cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
- ret = max(ret, eax + ebx);
+ offset = compacted ? ret : ebx;
+ ret = max(ret, offset + eax);
}
xstate_bv >>= 1;
@@ -53,24 +54,26 @@ u64 kvm_supported_xcr0(void)
return xcr0;
}
-void kvm_update_cpuid(struct kvm_vcpu *vcpu)
+#define F(x) bit(X86_FEATURE_##x)
+
+int kvm_update_cpuid(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
struct kvm_lapic *apic = vcpu->arch.apic;
best = kvm_find_cpuid_entry(vcpu, 1, 0);
if (!best)
- return;
+ return 0;
/* Update OSXSAVE bit */
if (cpu_has_xsave && best->function == 0x1) {
- best->ecx &= ~(bit(X86_FEATURE_OSXSAVE));
+ best->ecx &= ~F(OSXSAVE);
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
- best->ecx |= bit(X86_FEATURE_OSXSAVE);
+ best->ecx |= F(OSXSAVE);
}
if (apic) {
- if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER))
+ if (best->ecx & F(TSC_DEADLINE_TIMER))
apic->lapic_timer.timer_mode_mask = 3 << 17;
else
apic->lapic_timer.timer_mode_mask = 1 << 17;
@@ -85,10 +88,24 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu)
(best->eax | ((u64)best->edx << 32)) &
kvm_supported_xcr0();
vcpu->arch.guest_xstate_size = best->ebx =
- xstate_required_size(vcpu->arch.xcr0);
+ xstate_required_size(vcpu->arch.xcr0, false);
}
+ best = kvm_find_cpuid_entry(vcpu, 0xD, 1);
+ if (best && (best->eax & (F(XSAVES) | F(XSAVEC))))
+ best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
+
+ /*
+ * The existing code assumes virtual address is 48-bit in the canonical
+ * address checks; exit if it is ever changed.
+ */
+ best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
+ if (best && ((best->eax & 0xff00) >> 8) != 48 &&
+ ((best->eax & 0xff00) >> 8) != 0)
+ return -EINVAL;
+
kvm_pmu_cpuid_update(vcpu);
+ return 0;
}
static int is_efer_nx(void)
@@ -112,8 +129,8 @@ static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
break;
}
}
- if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
- entry->edx &= ~(1 << 20);
+ if (entry && (entry->edx & F(NX)) && !is_efer_nx()) {
+ entry->edx &= ~F(NX);
printk(KERN_INFO "kvm: guest NX capability removed\n");
}
}
@@ -151,10 +168,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
}
vcpu->arch.cpuid_nent = cpuid->nent;
cpuid_fix_nx_cap(vcpu);
- r = 0;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
- kvm_update_cpuid(vcpu);
+ r = kvm_update_cpuid(vcpu);
out_free:
vfree(cpuid_entries);
@@ -178,9 +194,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
vcpu->arch.cpuid_nent = cpuid->nent;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
- kvm_update_cpuid(vcpu);
- return 0;
-
+ r = kvm_update_cpuid(vcpu);
out:
return r;
}
@@ -220,8 +234,6 @@ static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
entry->flags = 0;
}
-#define F(x) bit(X86_FEATURE_##x)
-
static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
u32 func, u32 index, int *nent, int maxnent)
{
@@ -260,6 +272,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
unsigned f_invpcid = kvm_x86_ops->invpcid_supported() ? F(INVPCID) : 0;
unsigned f_mpx = kvm_x86_ops->mpx_supported() ? F(MPX) : 0;
+ unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0;
/* cpuid 1.edx */
const u32 kvm_supported_word0_x86_features =
@@ -310,7 +323,12 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
const u32 kvm_supported_word9_x86_features =
F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
- F(ADX) | F(SMAP);
+ F(ADX) | F(SMAP) | F(AVX512F) | F(AVX512PF) | F(AVX512ER) |
+ F(AVX512CD);
+
+ /* cpuid 0xD.1.eax */
+ const u32 kvm_supported_word10_x86_features =
+ F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | f_xsaves;
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
@@ -446,16 +464,34 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
u64 supported = kvm_supported_xcr0();
entry->eax &= supported;
+ entry->ebx = xstate_required_size(supported, false);
+ entry->ecx = entry->ebx;
entry->edx &= supported >> 32;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ if (!supported)
+ break;
+
for (idx = 1, i = 1; idx < 64; ++idx) {
u64 mask = ((u64)1 << idx);
if (*nent >= maxnent)
goto out;
do_cpuid_1_ent(&entry[i], function, idx);
- if (entry[i].eax == 0 || !(supported & mask))
- continue;
+ if (idx == 1) {
+ entry[i].eax &= kvm_supported_word10_x86_features;
+ entry[i].ebx = 0;
+ if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
+ entry[i].ebx =
+ xstate_required_size(supported,
+ true);
+ } else {
+ if (entry[i].eax == 0 || !(supported & mask))
+ continue;
+ if (WARN_ON_ONCE(entry[i].ecx & 1))
+ continue;
+ }
+ entry[i].ecx = 0;
+ entry[i].edx = 0;
entry[i].flags |=
KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
++*nent;
@@ -767,6 +803,12 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
if (!best)
best = check_cpuid_limit(vcpu, function, index);
+ /*
+ * Perfmon not yet supported for L2 guest.
+ */
+ if (is_guest_mode(vcpu) && function == 0xa)
+ best = NULL;
+
if (best) {
*eax = best->eax;
*ebx = best->ebx;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index a5380590ab0e..4452eedfaedd 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -3,7 +3,7 @@
#include "x86.h"
-void kvm_update_cpuid(struct kvm_vcpu *vcpu);
+int kvm_update_cpuid(struct kvm_vcpu *vcpu);
struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
u32 function, u32 index);
int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
@@ -88,6 +88,14 @@ static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
return best && (best->ecx & bit(X86_FEATURE_X2APIC));
}
+static inline bool guest_cpuid_is_amd(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 0, 0);
+ return best && best->ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx;
+}
+
static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu)
{
struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 03954f7900f5..169b09d76ddd 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -123,6 +123,7 @@
#define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */
#define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */
#define Escape (5<<15) /* Escape to coprocessor instruction */
+#define InstrDual (6<<15) /* Alternate instruction decoding of mod == 3 */
#define Sse (1<<18) /* SSE Vector instruction */
/* Generic ModRM decode. */
#define ModRM (1<<19)
@@ -166,6 +167,8 @@
#define CheckPerm ((u64)1 << 49) /* Has valid check_perm field */
#define NoBigReal ((u64)1 << 50) /* No big real mode */
#define PrivUD ((u64)1 << 51) /* #UD instead of #GP on CPL > 0 */
+#define NearBranch ((u64)1 << 52) /* Near branches */
+#define No16 ((u64)1 << 53) /* No 16 bit operand */
#define DstXacc (DstAccLo | SrcAccHi | SrcWrite)
@@ -209,6 +212,7 @@ struct opcode {
const struct group_dual *gdual;
const struct gprefix *gprefix;
const struct escape *esc;
+ const struct instr_dual *idual;
void (*fastop)(struct fastop *fake);
} u;
int (*check_perm)(struct x86_emulate_ctxt *ctxt);
@@ -231,6 +235,11 @@ struct escape {
struct opcode high[64];
};
+struct instr_dual {
+ struct opcode mod012;
+ struct opcode mod3;
+};
+
/* EFLAGS bit definitions. */
#define EFLG_ID (1<<21)
#define EFLG_VIP (1<<20)
@@ -379,6 +388,15 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
ON64(FOP2E(op##q, rax, cl)) \
FOP_END
+/* 2 operand, src and dest are reversed */
+#define FASTOP2R(op, name) \
+ FOP_START(name) \
+ FOP2E(op##b, dl, al) \
+ FOP2E(op##w, dx, ax) \
+ FOP2E(op##l, edx, eax) \
+ ON64(FOP2E(op##q, rdx, rax)) \
+ FOP_END
+
#define FOP3E(op, dst, src, src2) \
FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
@@ -477,9 +495,9 @@ address_mask(struct x86_emulate_ctxt *ctxt, unsigned long reg)
}
static inline unsigned long
-register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg)
+register_address(struct x86_emulate_ctxt *ctxt, int reg)
{
- return address_mask(ctxt, reg);
+ return address_mask(ctxt, reg_read(ctxt, reg));
}
static void masked_increment(ulong *reg, ulong mask, int inc)
@@ -488,7 +506,7 @@ static void masked_increment(ulong *reg, ulong mask, int inc)
}
static inline void
-register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc)
+register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
{
ulong mask;
@@ -496,7 +514,7 @@ register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, in
mask = ~0UL;
else
mask = ad_mask(ctxt);
- masked_increment(reg, mask, inc);
+ masked_increment(reg_rmw(ctxt, reg), mask, inc);
}
static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
@@ -504,11 +522,6 @@ static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc);
}
-static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
-{
- register_address_increment(ctxt, &ctxt->_eip, rel);
-}
-
static u32 desc_limit_scaled(struct desc_struct *desc)
{
u32 limit = get_desc_limit(desc);
@@ -527,6 +540,7 @@ static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg)
static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec,
u32 error, bool valid)
{
+ WARN_ON(vec > 0x1f);
ctxt->exception.vector = vec;
ctxt->exception.error_code = error;
ctxt->exception.error_code_valid = valid;
@@ -611,23 +625,28 @@ static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size)
return true;
}
-static int __linearize(struct x86_emulate_ctxt *ctxt,
- struct segmented_address addr,
- unsigned size, bool write, bool fetch,
- ulong *linear)
+static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
+ struct segmented_address addr,
+ unsigned *max_size, unsigned size,
+ bool write, bool fetch,
+ enum x86emul_mode mode, ulong *linear)
{
struct desc_struct desc;
bool usable;
ulong la;
u32 lim;
u16 sel;
- unsigned cpl;
la = seg_base(ctxt, addr.seg) + addr.ea;
- switch (ctxt->mode) {
+ *max_size = 0;
+ switch (mode) {
case X86EMUL_MODE_PROT64:
- if (((signed long)la << 16) >> 16 != la)
- return emulate_gp(ctxt, 0);
+ if (is_noncanonical_address(la))
+ goto bad;
+
+ *max_size = min_t(u64, ~0u, (1ull << 48) - la);
+ if (size > *max_size)
+ goto bad;
break;
default:
usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL,
@@ -642,50 +661,29 @@ static int __linearize(struct x86_emulate_ctxt *ctxt,
if (!fetch && (desc.type & 8) && !(desc.type & 2))
goto bad;
lim = desc_limit_scaled(&desc);
- if ((ctxt->mode == X86EMUL_MODE_REAL) && !fetch &&
- (ctxt->d & NoBigReal)) {
- /* la is between zero and 0xffff */
- if (la > 0xffff || (u32)(la + size - 1) > 0xffff)
- goto bad;
- } else if ((desc.type & 8) || !(desc.type & 4)) {
- /* expand-up segment */
- if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
- goto bad;
- } else {
+ if (!(desc.type & 8) && (desc.type & 4)) {
/* expand-down segment */
- if (addr.ea <= lim || (u32)(addr.ea + size - 1) <= lim)
+ if (addr.ea <= lim)
goto bad;
lim = desc.d ? 0xffffffff : 0xffff;
- if (addr.ea > lim || (u32)(addr.ea + size - 1) > lim)
- goto bad;
- }
- cpl = ctxt->ops->cpl(ctxt);
- if (!(desc.type & 8)) {
- /* data segment */
- if (cpl > desc.dpl)
- goto bad;
- } else if ((desc.type & 8) && !(desc.type & 4)) {
- /* nonconforming code segment */
- if (cpl != desc.dpl)
- goto bad;
- } else if ((desc.type & 8) && (desc.type & 4)) {
- /* conforming code segment */
- if (cpl < desc.dpl)
- goto bad;
}
+ if (addr.ea > lim)
+ goto bad;
+ *max_size = min_t(u64, ~0u, (u64)lim + 1 - addr.ea);
+ if (size > *max_size)
+ goto bad;
+ la &= (u32)-1;
break;
}
- if (fetch ? ctxt->mode != X86EMUL_MODE_PROT64 : ctxt->ad_bytes != 8)
- la &= (u32)-1;
if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
return emulate_gp(ctxt, 0);
*linear = la;
return X86EMUL_CONTINUE;
bad:
if (addr.seg == VCPU_SREG_SS)
- return emulate_ss(ctxt, sel);
+ return emulate_ss(ctxt, 0);
else
- return emulate_gp(ctxt, sel);
+ return emulate_gp(ctxt, 0);
}
static int linearize(struct x86_emulate_ctxt *ctxt,
@@ -693,9 +691,56 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
unsigned size, bool write,
ulong *linear)
{
- return __linearize(ctxt, addr, size, write, false, linear);
+ unsigned max_size;
+ return __linearize(ctxt, addr, &max_size, size, write, false,
+ ctxt->mode, linear);
+}
+
+static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
+ enum x86emul_mode mode)
+{
+ ulong linear;
+ int rc;
+ unsigned max_size;
+ struct segmented_address addr = { .seg = VCPU_SREG_CS,
+ .ea = dst };
+
+ if (ctxt->op_bytes != sizeof(unsigned long))
+ addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
+ rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear);
+ if (rc == X86EMUL_CONTINUE)
+ ctxt->_eip = addr.ea;
+ return rc;
+}
+
+static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
+{
+ return assign_eip(ctxt, dst, ctxt->mode);
+}
+
+static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
+ const struct desc_struct *cs_desc)
+{
+ enum x86emul_mode mode = ctxt->mode;
+
+#ifdef CONFIG_X86_64
+ if (ctxt->mode >= X86EMUL_MODE_PROT32 && cs_desc->l) {
+ u64 efer = 0;
+
+ ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+ if (efer & EFER_LMA)
+ mode = X86EMUL_MODE_PROT64;
+ }
+#endif
+ if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32)
+ mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+ return assign_eip(ctxt, dst, mode);
}
+static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
+{
+ return assign_eip_near(ctxt, ctxt->_eip + rel);
+}
static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
@@ -718,17 +763,28 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
{
int rc;
- unsigned size;
+ unsigned size, max_size;
unsigned long linear;
int cur_size = ctxt->fetch.end - ctxt->fetch.data;
struct segmented_address addr = { .seg = VCPU_SREG_CS,
.ea = ctxt->eip + cur_size };
- size = 15UL ^ cur_size;
- rc = __linearize(ctxt, addr, size, false, true, &linear);
+ /*
+ * We do not know exactly how many bytes will be needed, and
+ * __linearize is expensive, so fetch as much as possible. We
+ * just have to avoid going beyond the 15 byte limit, the end
+ * of the segment, or the end of the page.
+ *
+ * __linearize is called with size 0 so that it does not do any
+ * boundary check itself. Instead, we use max_size to check
+ * against op_size.
+ */
+ rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode,
+ &linear);
if (unlikely(rc != X86EMUL_CONTINUE))
return rc;
+ size = min_t(unsigned, 15UL ^ cur_size, max_size);
size = min_t(unsigned, size, PAGE_SIZE - offset_in_page(linear));
/*
@@ -738,7 +794,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
* still, we must have hit the 15-byte boundary.
*/
if (unlikely(size < op_size))
- return X86EMUL_UNHANDLEABLE;
+ return emulate_gp(ctxt, 0);
+
rc = ctxt->ops->fetch(ctxt, linear, ctxt->fetch.end,
size, &ctxt->exception);
if (unlikely(rc != X86EMUL_CONTINUE))
@@ -750,8 +807,10 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size)
static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt,
unsigned size)
{
- if (unlikely(ctxt->fetch.end - ctxt->fetch.ptr < size))
- return __do_insn_fetch_bytes(ctxt, size);
+ unsigned done_size = ctxt->fetch.end - ctxt->fetch.ptr;
+
+ if (unlikely(done_size < size))
+ return __do_insn_fetch_bytes(ctxt, size - done_size);
else
return X86EMUL_CONTINUE;
}
@@ -856,6 +915,8 @@ FASTOP2W(btc);
FASTOP2(xadd);
+FASTOP2R(cmp, cmp_r);
+
static u8 test_cc(unsigned int condition, unsigned long flags)
{
u8 rc;
@@ -1166,6 +1227,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
if (index_reg != 4)
modrm_ea += reg_read(ctxt, index_reg) << scale;
} else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) {
+ modrm_ea += insn_fetch(s32, ctxt);
if (ctxt->mode == X86EMUL_MODE_PROT64)
ctxt->rip_relative = 1;
} else {
@@ -1174,10 +1236,6 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
adjust_modrm_seg(ctxt, base_reg);
}
switch (ctxt->modrm_mod) {
- case 0:
- if (ctxt->modrm_rm == 5)
- modrm_ea += insn_fetch(s32, ctxt);
- break;
case 1:
modrm_ea += insn_fetch(s8, ctxt);
break;
@@ -1229,7 +1287,8 @@ static void fetch_bit_operand(struct x86_emulate_ctxt *ctxt)
else
sv = (s64)ctxt->src.val & (s64)mask;
- ctxt->dst.addr.mem.ea += (sv >> 3);
+ ctxt->dst.addr.mem.ea = address_mask(ctxt,
+ ctxt->dst.addr.mem.ea + (sv >> 3));
}
/* only subword offset */
@@ -1415,7 +1474,9 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt,
/* Does not support long mode */
static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
- u16 selector, int seg, u8 cpl, bool in_task_switch)
+ u16 selector, int seg, u8 cpl,
+ bool in_task_switch,
+ struct desc_struct *desc)
{
struct desc_struct seg_desc, old_desc;
u8 dpl, rpl;
@@ -1468,7 +1529,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
return ret;
err_code = selector & 0xfffc;
- err_vec = GP_VECTOR;
+ err_vec = in_task_switch ? TS_VECTOR : GP_VECTOR;
/* can't load system descriptor into segment selector */
if (seg <= VCPU_SREG_GS && !seg_desc.s)
@@ -1503,6 +1564,15 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
if (rpl > cpl || dpl != cpl)
goto exception;
}
+ /* in long-mode d/b must be clear if l is set */
+ if (seg_desc.d && seg_desc.l) {
+ u64 efer = 0;
+
+ ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+ if (efer & EFER_LMA)
+ goto exception;
+ }
+
/* CS(RPL) <- CPL */
selector = (selector & 0xfffc) | cpl;
break;
@@ -1544,20 +1614,24 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
sizeof(base3), &ctxt->exception);
if (ret != X86EMUL_CONTINUE)
return ret;
+ if (is_noncanonical_address(get_desc_base(&seg_desc) |
+ ((u64)base3 << 32)))
+ return emulate_gp(ctxt, 0);
}
load:
ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
+ if (desc)
+ *desc = seg_desc;
return X86EMUL_CONTINUE;
exception:
- emulate_exception(ctxt, err_vec, err_code, true);
- return X86EMUL_PROPAGATE_FAULT;
+ return emulate_exception(ctxt, err_vec, err_code, true);
}
static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt,
u16 selector, int seg)
{
u8 cpl = ctxt->ops->cpl(ctxt);
- return __load_segment_descriptor(ctxt, selector, seg, cpl, false);
+ return __load_segment_descriptor(ctxt, selector, seg, cpl, false, NULL);
}
static void write_register_operand(struct operand *op)
@@ -1740,6 +1814,10 @@ static int em_push_sreg(struct x86_emulate_ctxt *ctxt)
int seg = ctxt->src2.val;
ctxt->src.val = get_segment_selector(ctxt, seg);
+ if (ctxt->op_bytes == 4) {
+ rsp_increment(ctxt, -2);
+ ctxt->op_bytes = 2;
+ }
return em_push(ctxt);
}
@@ -1783,7 +1861,7 @@ static int em_pusha(struct x86_emulate_ctxt *ctxt)
static int em_pushf(struct x86_emulate_ctxt *ctxt)
{
- ctxt->src.val = (unsigned long)ctxt->eflags;
+ ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM;
return em_push(ctxt);
}
@@ -1951,42 +2029,49 @@ static int em_iret(struct x86_emulate_ctxt *ctxt)
static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
- unsigned short sel;
+ unsigned short sel, old_sel;
+ struct desc_struct old_desc, new_desc;
+ const struct x86_emulate_ops *ops = ctxt->ops;
+ u8 cpl = ctxt->ops->cpl(ctxt);
+
+ /* Assignment of RIP may only fail in 64-bit mode */
+ if (ctxt->mode == X86EMUL_MODE_PROT64)
+ ops->get_segment(ctxt, &old_sel, &old_desc, NULL,
+ VCPU_SREG_CS);
memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
- rc = load_segment_descriptor(ctxt, sel, VCPU_SREG_CS);
+ rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl, false,
+ &new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
- ctxt->_eip = 0;
- memcpy(&ctxt->_eip, ctxt->src.valptr, ctxt->op_bytes);
- return X86EMUL_CONTINUE;
+ rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ if (rc != X86EMUL_CONTINUE) {
+ WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
+ /* assigning eip failed; restore the old cs */
+ ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
+ return rc;
+ }
+ return rc;
}
-static int em_grp45(struct x86_emulate_ctxt *ctxt)
+static int em_jmp_abs(struct x86_emulate_ctxt *ctxt)
{
- int rc = X86EMUL_CONTINUE;
+ return assign_eip_near(ctxt, ctxt->src.val);
+}
- switch (ctxt->modrm_reg) {
- case 2: /* call near abs */ {
- long int old_eip;
- old_eip = ctxt->_eip;
- ctxt->_eip = ctxt->src.val;
- ctxt->src.val = old_eip;
- rc = em_push(ctxt);
- break;
- }
- case 4: /* jmp abs */
- ctxt->_eip = ctxt->src.val;
- break;
- case 5: /* jmp far */
- rc = em_jmp_far(ctxt);
- break;
- case 6: /* push */
- rc = em_push(ctxt);
- break;
- }
+static int em_call_near_abs(struct x86_emulate_ctxt *ctxt)
+{
+ int rc;
+ long int old_eip;
+
+ old_eip = ctxt->_eip;
+ rc = assign_eip_near(ctxt, ctxt->src.val);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ ctxt->src.val = old_eip;
+ rc = em_push(ctxt);
return rc;
}
@@ -2013,30 +2098,47 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt)
static int em_ret(struct x86_emulate_ctxt *ctxt)
{
- ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = &ctxt->_eip;
- ctxt->dst.bytes = ctxt->op_bytes;
- return em_pop(ctxt);
+ int rc;
+ unsigned long eip;
+
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ return assign_eip_near(ctxt, eip);
}
static int em_ret_far(struct x86_emulate_ctxt *ctxt)
{
int rc;
- unsigned long cs;
+ unsigned long eip, cs;
+ u16 old_cs;
int cpl = ctxt->ops->cpl(ctxt);
+ struct desc_struct old_desc, new_desc;
+ const struct x86_emulate_ops *ops = ctxt->ops;
+
+ if (ctxt->mode == X86EMUL_MODE_PROT64)
+ ops->get_segment(ctxt, &old_cs, &old_desc, NULL,
+ VCPU_SREG_CS);
- rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes);
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
- if (ctxt->op_bytes == 4)
- ctxt->_eip = (u32)ctxt->_eip;
rc = emulate_pop(ctxt, &cs, ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
/* Outer-privilege level return is not implemented */
if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
return X86EMUL_UNHANDLEABLE;
- rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS);
+ rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, cpl, false,
+ &new_desc);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rc = assign_eip_far(ctxt, eip, &new_desc);
+ if (rc != X86EMUL_CONTINUE) {
+ WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
+ ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
+ }
return rc;
}
@@ -2216,6 +2318,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data);
ctxt->eflags &= ~msr_data;
+ ctxt->eflags |= EFLG_RESERVED_ONE_MASK;
#endif
} else {
/* legacy mode */
@@ -2249,11 +2352,9 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt)
&& !vendor_intel(ctxt))
return emulate_ud(ctxt);
- /* XXX sysenter/sysexit have not been tested in 64bit mode.
- * Therefore, we inject an #UD.
- */
+ /* sysenter/sysexit have not been tested in 64bit mode. */
if (ctxt->mode == X86EMUL_MODE_PROT64)
- return emulate_ud(ctxt);
+ return X86EMUL_UNHANDLEABLE;
setup_syscalls_segments(ctxt, &cs, &ss);
@@ -2297,7 +2398,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
{
const struct x86_emulate_ops *ops = ctxt->ops;
struct desc_struct cs, ss;
- u64 msr_data;
+ u64 msr_data, rcx, rdx;
int usermode;
u16 cs_sel = 0, ss_sel = 0;
@@ -2313,6 +2414,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
else
usermode = X86EMUL_MODE_PROT32;
+ rcx = reg_read(ctxt, VCPU_REGS_RCX);
+ rdx = reg_read(ctxt, VCPU_REGS_RDX);
+
cs.dpl = 3;
ss.dpl = 3;
ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data);
@@ -2322,6 +2426,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
if ((msr_data & 0xfffc) == 0x0)
return emulate_gp(ctxt, 0);
ss_sel = (u16)(msr_data + 24);
+ rcx = (u32)rcx;
+ rdx = (u32)rdx;
break;
case X86EMUL_MODE_PROT64:
cs_sel = (u16)(msr_data + 32);
@@ -2330,6 +2436,9 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ss_sel = cs_sel + 8;
cs.d = 0;
cs.l = 1;
+ if (is_noncanonical_address(rcx) ||
+ is_noncanonical_address(rdx))
+ return emulate_gp(ctxt, 0);
break;
}
cs_sel |= SELECTOR_RPL_MASK;
@@ -2338,8 +2447,8 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS);
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
- ctxt->_eip = reg_read(ctxt, VCPU_REGS_RDX);
- *reg_write(ctxt, VCPU_REGS_RSP) = reg_read(ctxt, VCPU_REGS_RCX);
+ ctxt->_eip = rdx;
+ *reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;
}
@@ -2457,19 +2566,24 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt,
* Now load segment descriptors. If fault happens at this stage
* it is handled in a context of new task
*/
- ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
@@ -2488,7 +2602,6 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
save_state_to_tss16(ctxt, &tss_seg);
@@ -2496,13 +2609,11 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
ret = ops->read_std(ctxt, new_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
if (old_tss_sel != 0xffff) {
@@ -2513,7 +2624,6 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt,
sizeof tss_seg.prev_task_link,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
}
@@ -2594,25 +2704,32 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
* Now load segment descriptors. If fault happenes at this stage
* it is handled in a context of new task
*/
- ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR,
+ cpl, true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
- ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, true);
+ ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl,
+ true, NULL);
if (ret != X86EMUL_CONTINUE)
return ret;
@@ -2695,7 +2812,8 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
*
* 1. jmp/call/int to task gate: Check against DPL of the task gate
* 2. Exception/IRQ/iret: No check is performed
- * 3. jmp/call to TSS: Check against DPL of the TSS
+ * 3. jmp/call to TSS/task-gate: No check is performed since the
+ * hardware checks it before exiting.
*/
if (reason == TASK_SWITCH_GATE) {
if (idt_index != -1) {
@@ -2712,19 +2830,13 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt,
if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl)
return emulate_gp(ctxt, (idt_index << 3) | 0x2);
}
- } else if (reason != TASK_SWITCH_IRET) {
- int dpl = next_tss_desc.dpl;
- if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl)
- return emulate_gp(ctxt, tss_selector);
}
-
desc_limit = desc_limit_scaled(&next_tss_desc);
if (!next_tss_desc.p ||
((desc_limit < 0x67 && (next_tss_desc.type & 8)) ||
desc_limit < 0x2b)) {
- emulate_ts(ctxt, tss_selector & 0xfffc);
- return X86EMUL_PROPAGATE_FAULT;
+ return emulate_ts(ctxt, tss_selector & 0xfffc);
}
if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
@@ -2796,8 +2908,8 @@ static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg,
{
int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count;
- register_address_increment(ctxt, reg_rmw(ctxt, reg), df * op->bytes);
- op->addr.mem.ea = register_address(ctxt, reg_read(ctxt, reg));
+ register_address_increment(ctxt, reg, df * op->bytes);
+ op->addr.mem.ea = register_address(ctxt, reg);
}
static int em_das(struct x86_emulate_ctxt *ctxt)
@@ -2880,10 +2992,13 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
static int em_call(struct x86_emulate_ctxt *ctxt)
{
+ int rc;
long rel = ctxt->src.val;
ctxt->src.val = (unsigned long)ctxt->_eip;
- jmp_rel(ctxt, rel);
+ rc = jmp_rel(ctxt, rel);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
return em_push(ctxt);
}
@@ -2892,34 +3007,50 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
u16 sel, old_cs;
ulong old_eip;
int rc;
+ struct desc_struct old_desc, new_desc;
+ const struct x86_emulate_ops *ops = ctxt->ops;
+ int cpl = ctxt->ops->cpl(ctxt);
- old_cs = get_segment_selector(ctxt, VCPU_SREG_CS);
old_eip = ctxt->_eip;
+ ops->get_segment(ctxt, &old_cs, &old_desc, NULL, VCPU_SREG_CS);
memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
- if (load_segment_descriptor(ctxt, sel, VCPU_SREG_CS))
+ rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl, false,
+ &new_desc);
+ if (rc != X86EMUL_CONTINUE)
return X86EMUL_CONTINUE;
- ctxt->_eip = 0;
- memcpy(&ctxt->_eip, ctxt->src.valptr, ctxt->op_bytes);
+ rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ if (rc != X86EMUL_CONTINUE)
+ goto fail;
ctxt->src.val = old_cs;
rc = em_push(ctxt);
if (rc != X86EMUL_CONTINUE)
- return rc;
+ goto fail;
ctxt->src.val = old_eip;
- return em_push(ctxt);
+ rc = em_push(ctxt);
+ /* If we failed, we tainted the memory, but the very least we should
+ restore cs */
+ if (rc != X86EMUL_CONTINUE)
+ goto fail;
+ return rc;
+fail:
+ ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
+ return rc;
+
}
static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
{
int rc;
+ unsigned long eip;
- ctxt->dst.type = OP_REG;
- ctxt->dst.addr.reg = &ctxt->_eip;
- ctxt->dst.bytes = ctxt->op_bytes;
- rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes);
+ rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rc = assign_eip_near(ctxt, eip);
if (rc != X86EMUL_CONTINUE)
return rc;
rsp_increment(ctxt, ctxt->src.val);
@@ -3016,7 +3147,7 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
ctxt->dst.val = swab64(ctxt->src.val);
break;
default:
- return X86EMUL_PROPAGATE_FAULT;
+ BUG();
}
return X86EMUL_CONTINUE;
}
@@ -3079,6 +3210,8 @@ static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt)
return emulate_ud(ctxt);
ctxt->dst.val = get_segment_selector(ctxt, ctxt->modrm_reg);
+ if (ctxt->dst.bytes == 4 && ctxt->dst.type == OP_MEM)
+ ctxt->dst.bytes = 2;
return X86EMUL_CONTINUE;
}
@@ -3140,12 +3273,8 @@ static int em_clts(struct x86_emulate_ctxt *ctxt)
static int em_vmcall(struct x86_emulate_ctxt *ctxt)
{
- int rc;
-
- if (ctxt->modrm_mod != 3 || ctxt->modrm_rm != 1)
- return X86EMUL_UNHANDLEABLE;
+ int rc = ctxt->ops->fix_hypercall(ctxt);
- rc = ctxt->ops->fix_hypercall(ctxt);
if (rc != X86EMUL_CONTINUE)
return rc;
@@ -3185,7 +3314,7 @@ static int em_sidt(struct x86_emulate_ctxt *ctxt)
return emulate_store_desc_ptr(ctxt, ctxt->ops->get_idt);
}
-static int em_lgdt(struct x86_emulate_ctxt *ctxt)
+static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt)
{
struct desc_ptr desc_ptr;
int rc;
@@ -3197,12 +3326,23 @@ static int em_lgdt(struct x86_emulate_ctxt *ctxt)
ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
- ctxt->ops->set_gdt(ctxt, &desc_ptr);
+ if (ctxt->mode == X86EMUL_MODE_PROT64 &&
+ is_noncanonical_address(desc_ptr.address))
+ return emulate_gp(ctxt, 0);
+ if (lgdt)
+ ctxt->ops->set_gdt(ctxt, &desc_ptr);
+ else
+ ctxt->ops->set_idt(ctxt, &desc_ptr);
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
return X86EMUL_CONTINUE;
}
+static int em_lgdt(struct x86_emulate_ctxt *ctxt)
+{
+ return em_lgdt_lidt(ctxt, true);
+}
+
static int em_vmmcall(struct x86_emulate_ctxt *ctxt)
{
int rc;
@@ -3216,20 +3356,7 @@ static int em_vmmcall(struct x86_emulate_ctxt *ctxt)
static int em_lidt(struct x86_emulate_ctxt *ctxt)
{
- struct desc_ptr desc_ptr;
- int rc;
-
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- ctxt->op_bytes = 8;
- rc = read_descriptor(ctxt, ctxt->src.addr.mem,
- &desc_ptr.size, &desc_ptr.address,
- ctxt->op_bytes);
- if (rc != X86EMUL_CONTINUE)
- return rc;
- ctxt->ops->set_idt(ctxt, &desc_ptr);
- /* Disable writeback. */
- ctxt->dst.type = OP_NONE;
- return X86EMUL_CONTINUE;
+ return em_lgdt_lidt(ctxt, false);
}
static int em_smsw(struct x86_emulate_ctxt *ctxt)
@@ -3250,20 +3377,24 @@ static int em_lmsw(struct x86_emulate_ctxt *ctxt)
static int em_loop(struct x86_emulate_ctxt *ctxt)
{
- register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
+ int rc = X86EMUL_CONTINUE;
+
+ register_address_increment(ctxt, VCPU_REGS_RCX, -1);
if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
(ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
- return X86EMUL_CONTINUE;
+ return rc;
}
static int em_jcxz(struct x86_emulate_ctxt *ctxt)
{
+ int rc = X86EMUL_CONTINUE;
+
if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0)
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
- return X86EMUL_CONTINUE;
+ return rc;
}
static int em_in(struct x86_emulate_ctxt *ctxt)
@@ -3351,6 +3482,12 @@ static int em_bswap(struct x86_emulate_ctxt *ctxt)
return X86EMUL_CONTINUE;
}
+static int em_clflush(struct x86_emulate_ctxt *ctxt)
+{
+ /* emulating clflush regardless of cpuid */
+ return X86EMUL_CONTINUE;
+}
+
static bool valid_cr(int nr)
{
switch (nr) {
@@ -3412,7 +3549,7 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
if (efer & EFER_LMA)
- rsvd = CR3_L_MODE_RESERVED_BITS;
+ rsvd = CR3_L_MODE_RESERVED_BITS & ~CR3_PCID_INVD;
if (new_val & rsvd)
return emulate_gp(ctxt, 0);
@@ -3454,8 +3591,15 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt)
if ((cr4 & X86_CR4_DE) && (dr == 4 || dr == 5))
return emulate_ud(ctxt);
- if (check_dr7_gd(ctxt))
+ if (check_dr7_gd(ctxt)) {
+ ulong dr6;
+
+ ctxt->ops->get_dr(ctxt, 6, &dr6);
+ dr6 &= ~15;
+ dr6 |= DR6_BD | DR6_RTM;
+ ctxt->ops->set_dr(ctxt, 6, dr6);
return emulate_db(ctxt);
+ }
return X86EMUL_CONTINUE;
}
@@ -3542,6 +3686,7 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
#define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
#define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
+#define ID(_f, _i) { .flags = ((_f) | InstrDual | ModRM), .u.idual = (_i) }
#define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
#define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
@@ -3563,6 +3708,12 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt)
F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \
F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e)
+static const struct opcode group7_rm0[] = {
+ N,
+ I(SrcNone | Priv | EmulateOnUD, em_vmcall),
+ N, N, N, N, N, N,
+};
+
static const struct opcode group7_rm1[] = {
DI(SrcNone | Priv, monitor),
DI(SrcNone | Priv, mwait),
@@ -3632,11 +3783,11 @@ static const struct opcode group4[] = {
static const struct opcode group5[] = {
F(DstMem | SrcNone | Lock, em_inc),
F(DstMem | SrcNone | Lock, em_dec),
- I(SrcMem | Stack, em_grp45),
+ I(SrcMem | NearBranch, em_call_near_abs),
I(SrcMemFAddr | ImplicitOps | Stack, em_call_far),
- I(SrcMem | Stack, em_grp45),
- I(SrcMemFAddr | ImplicitOps, em_grp45),
- I(SrcMem | Stack, em_grp45), D(Undefined),
+ I(SrcMem | NearBranch, em_jmp_abs),
+ I(SrcMemFAddr | ImplicitOps, em_jmp_far),
+ I(SrcMem | Stack, em_push), D(Undefined),
};
static const struct opcode group6[] = {
@@ -3656,7 +3807,7 @@ static const struct group_dual group7 = { {
II(SrcMem16 | Mov | Priv, em_lmsw, lmsw),
II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg),
}, {
- I(SrcNone | Priv | EmulateOnUD, em_vmcall),
+ EXT(0, group7_rm0),
EXT(0, group7_rm1),
N, EXT(0, group7_rm3),
II(SrcNone | DstMem | Mov, em_smsw, smsw), N,
@@ -3683,18 +3834,36 @@ static const struct opcode group11[] = {
X7(D(Undefined)),
};
+static const struct gprefix pfx_0f_ae_7 = {
+ I(SrcMem | ByteOp, em_clflush), N, N, N,
+};
+
+static const struct group_dual group15 = { {
+ N, N, N, N, N, N, N, GP(0, &pfx_0f_ae_7),
+}, {
+ N, N, N, N, N, N, N, N,
+} };
+
static const struct gprefix pfx_0f_6f_0f_7f = {
I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
};
-static const struct gprefix pfx_vmovntpx = {
- I(0, em_mov), N, N, N,
+static const struct instr_dual instr_dual_0f_2b = {
+ I(0, em_mov), N
+};
+
+static const struct gprefix pfx_0f_2b = {
+ ID(0, &instr_dual_0f_2b), ID(0, &instr_dual_0f_2b), N, N,
};
static const struct gprefix pfx_0f_28_0f_29 = {
I(Aligned, em_mov), I(Aligned, em_mov), N, N,
};
+static const struct gprefix pfx_0f_e7 = {
+ N, I(Sse, em_mov), N, N,
+};
+
static const struct escape escape_d9 = { {
N, N, N, N, N, N, N, I(DstMem, em_fnstcw),
}, {
@@ -3758,6 +3927,10 @@ static const struct escape escape_dd = { {
N, N, N, N, N, N, N, N,
} };
+static const struct instr_dual instr_dual_0f_c3 = {
+ I(DstMem | SrcReg | ModRM | No16 | Mov, em_mov), N
+};
+
static const struct opcode opcode_table[256] = {
/* 0x00 - 0x07 */
F6ALU(Lock, em_add),
@@ -3802,7 +3975,7 @@ static const struct opcode opcode_table[256] = {
I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */
I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */
/* 0x70 - 0x7F */
- X16(D(SrcImmByte)),
+ X16(D(SrcImmByte | NearBranch)),
/* 0x80 - 0x87 */
G(ByteOp | DstMem | SrcImm, group1),
G(DstMem | SrcImm, group1),
@@ -3829,20 +4002,20 @@ static const struct opcode opcode_table[256] = {
I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
I2bv(SrcSI | DstDI | Mov | String, em_mov),
- F2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
+ F2bv(SrcSI | DstDI | String | NoWrite, em_cmp_r),
/* 0xA8 - 0xAF */
F2bv(DstAcc | SrcImm | NoWrite, em_test),
I2bv(SrcAcc | DstDI | Mov | String, em_mov),
I2bv(SrcSI | DstAcc | Mov | String, em_mov),
- F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
+ F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
/* 0xB0 - 0xB7 */
X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
/* 0xB8 - 0xBF */
X8(I(DstReg | SrcImm64 | Mov, em_mov)),
/* 0xC0 - 0xC7 */
G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2),
- I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
- I(ImplicitOps | Stack, em_ret),
+ I(ImplicitOps | NearBranch | SrcImmU16, em_ret_near_imm),
+ I(ImplicitOps | NearBranch, em_ret),
I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg),
I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg),
G(ByteOp, group11), G(0, group11),
@@ -3862,13 +4035,14 @@ static const struct opcode opcode_table[256] = {
/* 0xD8 - 0xDF */
N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
/* 0xE0 - 0xE7 */
- X3(I(SrcImmByte, em_loop)),
- I(SrcImmByte, em_jcxz),
+ X3(I(SrcImmByte | NearBranch, em_loop)),
+ I(SrcImmByte | NearBranch, em_jcxz),
I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in),
I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out),
/* 0xE8 - 0xEF */
- I(SrcImm | Stack, em_call), D(SrcImm | ImplicitOps),
- I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps),
+ I(SrcImm | NearBranch, em_call), D(SrcImm | ImplicitOps | NearBranch),
+ I(SrcImmFAddr | No64, em_jmp_far),
+ D(SrcImmByte | ImplicitOps | NearBranch),
I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in),
I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out),
/* 0xF0 - 0xF7 */
@@ -3887,10 +4061,11 @@ static const struct opcode twobyte_table[256] = {
N, I(ImplicitOps | EmulateOnUD, em_syscall),
II(ImplicitOps | Priv, em_clts, clts), N,
DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
- N, D(ImplicitOps | ModRM), N, N,
+ N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N,
/* 0x10 - 0x1F */
N, N, N, N, N, N, N, N,
- D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
+ D(ImplicitOps | ModRM | SrcMem | NoAccess),
+ N, N, N, N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess),
/* 0x20 - 0x2F */
DIP(ModRM | DstMem | Priv | Op3264 | NoMod, cr_read, check_cr_read),
DIP(ModRM | DstMem | Priv | Op3264 | NoMod, dr_read, check_dr_read),
@@ -3901,7 +4076,7 @@ static const struct opcode twobyte_table[256] = {
N, N, N, N,
GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29),
GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29),
- N, GP(ModRM | DstMem | SrcReg | Sse | Mov | Aligned, &pfx_vmovntpx),
+ N, GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_2b),
N, N, N, N,
/* 0x30 - 0x3F */
II(ImplicitOps | Priv, em_wrmsr, wrmsr),
@@ -3927,7 +4102,7 @@ static const struct opcode twobyte_table[256] = {
N, N, N, N,
N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f),
/* 0x80 - 0x8F */
- X16(D(SrcImm)),
+ X16(D(SrcImm | NearBranch)),
/* 0x90 - 0x9F */
X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
/* 0xA0 - 0xA7 */
@@ -3942,7 +4117,7 @@ static const struct opcode twobyte_table[256] = {
F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts),
F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd),
F(DstMem | SrcReg | Src2CL | ModRM, em_shrd),
- D(ModRM), F(DstReg | SrcMem | ModRM, em_imul),
+ GD(0, &group15), F(DstReg | SrcMem | ModRM, em_imul),
/* 0xB0 - 0xB7 */
I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg),
I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg),
@@ -3958,24 +4133,33 @@ static const struct opcode twobyte_table[256] = {
D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
/* 0xC0 - 0xC7 */
F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd),
- N, D(DstMem | SrcReg | ModRM | Mov),
+ N, ID(0, &instr_dual_0f_c3),
N, N, N, GD(0, &group9),
/* 0xC8 - 0xCF */
X8(I(DstReg, em_bswap)),
/* 0xD0 - 0xDF */
N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
/* 0xE0 - 0xEF */
- N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
+ N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_e7),
+ N, N, N, N, N, N, N, N,
/* 0xF0 - 0xFF */
N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N
};
+static const struct instr_dual instr_dual_0f_38_f0 = {
+ I(DstReg | SrcMem | Mov, em_movbe), N
+};
+
+static const struct instr_dual instr_dual_0f_38_f1 = {
+ I(DstMem | SrcReg | Mov, em_movbe), N
+};
+
static const struct gprefix three_byte_0f_38_f0 = {
- I(DstReg | SrcMem | Mov, em_movbe), N, N, N
+ ID(0, &instr_dual_0f_38_f0), N, N, N
};
static const struct gprefix three_byte_0f_38_f1 = {
- I(DstMem | SrcReg | Mov, em_movbe), N, N, N
+ ID(0, &instr_dual_0f_38_f1), N, N, N
};
/*
@@ -3988,8 +4172,8 @@ static const struct opcode opcode_map_0f_38[256] = {
/* 0x80 - 0xef */
X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N),
/* 0xf0 - 0xf1 */
- GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f0),
- GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f1),
+ GP(EmulateOnUD | ModRM, &three_byte_0f_38_f0),
+ GP(EmulateOnUD | ModRM, &three_byte_0f_38_f1),
/* 0xf2 - 0xff */
N, N, X4(N), X8(N)
};
@@ -4111,7 +4295,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt, reg_read(ctxt, VCPU_REGS_RDI));
+ register_address(ctxt, VCPU_REGS_RDI);
op->addr.mem.seg = VCPU_SREG_ES;
op->val = 0;
op->count = 1;
@@ -4123,6 +4307,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
fetch_register_operand(op);
break;
case OpCL:
+ op->type = OP_IMM;
op->bytes = 1;
op->val = reg_read(ctxt, VCPU_REGS_RCX) & 0xff;
break;
@@ -4130,6 +4315,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
rc = decode_imm(ctxt, op, 1, true);
break;
case OpOne:
+ op->type = OP_IMM;
op->bytes = 1;
op->val = 1;
break;
@@ -4163,7 +4349,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt, reg_read(ctxt, VCPU_REGS_RSI));
+ register_address(ctxt, VCPU_REGS_RSI);
op->addr.mem.seg = ctxt->seg_override;
op->val = 0;
op->count = 1;
@@ -4172,7 +4358,7 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt,
+ address_mask(ctxt,
reg_read(ctxt, VCPU_REGS_RBX) +
(reg_read(ctxt, VCPU_REGS_RAX) & 0xff));
op->addr.mem.seg = ctxt->seg_override;
@@ -4188,21 +4374,27 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
ctxt->memop.bytes = ctxt->op_bytes + 2;
goto mem_common;
case OpES:
+ op->type = OP_IMM;
op->val = VCPU_SREG_ES;
break;
case OpCS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_CS;
break;
case OpSS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_SS;
break;
case OpDS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_DS;
break;
case OpFS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_FS;
break;
case OpGS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_GS;
break;
case OpImplicit:
@@ -4338,8 +4530,7 @@ done_prefixes:
/* vex-prefix instructions are not implemented */
if (ctxt->opcode_len == 1 && (ctxt->b == 0xc5 || ctxt->b == 0xc4) &&
- (mode == X86EMUL_MODE_PROT64 ||
- (mode >= X86EMUL_MODE_PROT16 && (ctxt->modrm & 0x80)))) {
+ (mode == X86EMUL_MODE_PROT64 || (ctxt->modrm & 0xc0) == 0xc0)) {
ctxt->d = NotImpl;
}
@@ -4377,6 +4568,12 @@ done_prefixes:
else
opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
break;
+ case InstrDual:
+ if ((ctxt->modrm >> 6) == 3)
+ opcode = opcode.u.idual->mod3;
+ else
+ opcode = opcode.u.idual->mod012;
+ break;
default:
return EMULATION_FAILED;
}
@@ -4395,7 +4592,8 @@ done_prefixes:
return EMULATION_FAILED;
if (unlikely(ctxt->d &
- (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
+ (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm|NearBranch|
+ No16))) {
/*
* These are copied unconditionally here, and checked unconditionally
* in x86_emulate_insn.
@@ -4406,8 +4604,12 @@ done_prefixes:
if (ctxt->d & NotImpl)
return EMULATION_FAILED;
- if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
- ctxt->op_bytes = 8;
+ if (mode == X86EMUL_MODE_PROT64) {
+ if (ctxt->op_bytes == 4 && (ctxt->d & Stack))
+ ctxt->op_bytes = 8;
+ else if (ctxt->d & NearBranch)
+ ctxt->op_bytes = 8;
+ }
if (ctxt->d & Op3264) {
if (mode == X86EMUL_MODE_PROT64)
@@ -4416,6 +4618,9 @@ done_prefixes:
ctxt->op_bytes = 4;
}
+ if ((ctxt->d & No16) && ctxt->op_bytes == 2)
+ ctxt->op_bytes = 4;
+
if (ctxt->d & Sse)
ctxt->op_bytes = 16;
else if (ctxt->d & Mmx)
@@ -4458,10 +4663,11 @@ done_prefixes:
/* Decode and fetch the destination operand: register or memory. */
rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
-done:
if (ctxt->rip_relative)
- ctxt->memopp->addr.mem.ea += ctxt->_eip;
+ ctxt->memopp->addr.mem.ea = address_mask(ctxt,
+ ctxt->memopp->addr.mem.ea + ctxt->_eip);
+done:
return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
}
@@ -4603,6 +4809,12 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
goto done;
}
+ /* Instruction can only be executed in protected mode */
+ if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
+ rc = emulate_ud(ctxt);
+ goto done;
+ }
+
/* Privileged instruction can be executed only in CPL=0 */
if ((ctxt->d & Priv) && ops->cpl(ctxt)) {
if (ctxt->d & PrivUD)
@@ -4612,12 +4824,6 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
goto done;
}
- /* Instruction can only be executed in protected mode */
- if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
- rc = emulate_ud(ctxt);
- goto done;
- }
-
/* Do instruction specific permission checks */
if (ctxt->d & CheckPerm) {
rc = ctxt->check_perm(ctxt);
@@ -4711,7 +4917,7 @@ special_insn:
break;
case 0x70 ... 0x7f: /* jcc (short) */
if (test_cc(ctxt->b, ctxt->eflags))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
break;
case 0x8d: /* lea r16/r32, m */
ctxt->dst.val = ctxt->src.addr.mem.ea;
@@ -4741,7 +4947,7 @@ special_insn:
break;
case 0xe9: /* jmp rel */
case 0xeb: /* jmp rel short */
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
ctxt->dst.type = OP_NONE; /* Disable writeback. */
break;
case 0xf4: /* hlt */
@@ -4802,8 +5008,7 @@ writeback:
count = ctxt->src.count;
else
count = ctxt->dst.count;
- register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX),
- -count);
+ register_address_increment(ctxt, VCPU_REGS_RCX, -count);
if (!string_insn_completed(ctxt)) {
/*
@@ -4829,8 +5034,10 @@ writeback:
ctxt->eip = ctxt->_eip;
done:
- if (rc == X86EMUL_PROPAGATE_FAULT)
+ if (rc == X86EMUL_PROPAGATE_FAULT) {
+ WARN_ON(ctxt->exception.vector > 0x1f);
ctxt->have_exception = true;
+ }
if (rc == X86EMUL_INTERCEPTED)
return EMULATION_INTERCEPTED;
@@ -4864,13 +5071,11 @@ twobyte_insn:
break;
case 0x80 ... 0x8f: /* jnz rel, etc*/
if (test_cc(ctxt->b, ctxt->eflags))
- jmp_rel(ctxt, ctxt->src.val);
+ rc = jmp_rel(ctxt, ctxt->src.val);
break;
case 0x90 ... 0x9f: /* setcc r/m8 */
ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags);
break;
- case 0xae: /* clflush */
- break;
case 0xb6 ... 0xb7: /* movzx */
ctxt->dst.bytes = ctxt->op_bytes;
ctxt->dst.val = (ctxt->src.bytes == 1) ? (u8) ctxt->src.val
@@ -4881,11 +5086,6 @@ twobyte_insn:
ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val :
(s16) ctxt->src.val;
break;
- case 0xc3: /* movnti */
- ctxt->dst.bytes = ctxt->op_bytes;
- ctxt->dst.val = (ctxt->op_bytes == 8) ? (u64) ctxt->src.val :
- (u32) ctxt->src.val;
- break;
default:
goto cannot_emulate;
}
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 518d86471b76..298781d4cfb4 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -262,8 +262,10 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
return;
timer = &pit->pit_state.timer;
+ mutex_lock(&pit->pit_state.lock);
if (hrtimer_cancel(timer))
hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+ mutex_unlock(&pit->pit_state.lock);
}
static void destroy_pit_timer(struct kvm_pit *pit)
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
new file mode 100644
index 000000000000..b1947e0f3e10
--- /dev/null
+++ b/arch/x86/kvm/ioapic.c
@@ -0,0 +1,675 @@
+/*
+ * Copyright (C) 2001 MandrakeSoft S.A.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * MandrakeSoft S.A.
+ * 43, rue d'Aboukir
+ * 75002 Paris - France
+ * http://www.linux-mandrake.com/
+ * http://www.mandrakesoft.com/
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation; either
+ * version 2 of the License, or (at your option) any later version.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * Yunhong Jiang <yunhong.jiang@intel.com>
+ * Yaozu (Eddie) Dong <eddie.dong@intel.com>
+ * Based on Xen 3.1 code.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/kvm.h>
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <linux/smp.h>
+#include <linux/hrtimer.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <asm/processor.h>
+#include <asm/page.h>
+#include <asm/current.h>
+#include <trace/events/kvm.h>
+
+#include "ioapic.h"
+#include "lapic.h"
+#include "irq.h"
+
+#if 0
+#define ioapic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg)
+#else
+#define ioapic_debug(fmt, arg...)
+#endif
+static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
+ bool line_status);
+
+static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
+ unsigned long addr,
+ unsigned long length)
+{
+ unsigned long result = 0;
+
+ switch (ioapic->ioregsel) {
+ case IOAPIC_REG_VERSION:
+ result = ((((IOAPIC_NUM_PINS - 1) & 0xff) << 16)
+ | (IOAPIC_VERSION_ID & 0xff));
+ break;
+
+ case IOAPIC_REG_APIC_ID:
+ case IOAPIC_REG_ARB_ID:
+ result = ((ioapic->id & 0xf) << 24);
+ break;
+
+ default:
+ {
+ u32 redir_index = (ioapic->ioregsel - 0x10) >> 1;
+ u64 redir_content;
+
+ if (redir_index < IOAPIC_NUM_PINS)
+ redir_content =
+ ioapic->redirtbl[redir_index].bits;
+ else
+ redir_content = ~0ULL;
+
+ result = (ioapic->ioregsel & 0x1) ?
+ (redir_content >> 32) & 0xffffffff :
+ redir_content & 0xffffffff;
+ break;
+ }
+ }
+
+ return result;
+}
+
+static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
+{
+ ioapic->rtc_status.pending_eoi = 0;
+ bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
+}
+
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
+
+static void rtc_status_pending_eoi_check_valid(struct kvm_ioapic *ioapic)
+{
+ if (WARN_ON(ioapic->rtc_status.pending_eoi < 0))
+ kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
+static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
+{
+ bool new_val, old_val;
+ struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+ union kvm_ioapic_redirect_entry *e;
+
+ e = &ioapic->redirtbl[RTC_GSI];
+ if (!kvm_apic_match_dest(vcpu, NULL, 0, e->fields.dest_id,
+ e->fields.dest_mode))
+ return;
+
+ new_val = kvm_apic_pending_eoi(vcpu, e->fields.vector);
+ old_val = test_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+
+ if (new_val == old_val)
+ return;
+
+ if (new_val) {
+ __set_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+ ioapic->rtc_status.pending_eoi++;
+ } else {
+ __clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
+ ioapic->rtc_status.pending_eoi--;
+ rtc_status_pending_eoi_check_valid(ioapic);
+ }
+}
+
+void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
+{
+ struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+
+ spin_lock(&ioapic->lock);
+ __rtc_irq_eoi_tracking_restore_one(vcpu);
+ spin_unlock(&ioapic->lock);
+}
+
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
+{
+ struct kvm_vcpu *vcpu;
+ int i;
+
+ if (RTC_GSI >= IOAPIC_NUM_PINS)
+ return;
+
+ rtc_irq_eoi_tracking_reset(ioapic);
+ kvm_for_each_vcpu(i, vcpu, ioapic->kvm)
+ __rtc_irq_eoi_tracking_restore_one(vcpu);
+}
+
+static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
+{
+ if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) {
+ --ioapic->rtc_status.pending_eoi;
+ rtc_status_pending_eoi_check_valid(ioapic);
+ }
+}
+
+static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
+{
+ if (ioapic->rtc_status.pending_eoi > 0)
+ return true; /* coalesced */
+
+ return false;
+}
+
+static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
+ int irq_level, bool line_status)
+{
+ union kvm_ioapic_redirect_entry entry;
+ u32 mask = 1 << irq;
+ u32 old_irr;
+ int edge, ret;
+
+ entry = ioapic->redirtbl[irq];
+ edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
+
+ if (!irq_level) {
+ ioapic->irr &= ~mask;
+ ret = 1;
+ goto out;
+ }
+
+ /*
+ * Return 0 for coalesced interrupts; for edge-triggered interrupts,
+ * this only happens if a previous edge has not been delivered due
+ * do masking. For level interrupts, the remote_irr field tells
+ * us if the interrupt is waiting for an EOI.
+ *
+ * RTC is special: it is edge-triggered, but userspace likes to know
+ * if it has been already ack-ed via EOI because coalesced RTC
+ * interrupts lead to time drift in Windows guests. So we track
+ * EOI manually for the RTC interrupt.
+ */
+ if (irq == RTC_GSI && line_status &&
+ rtc_irq_check_coalesced(ioapic)) {
+ ret = 0;
+ goto out;
+ }
+
+ old_irr = ioapic->irr;
+ ioapic->irr |= mask;
+ if ((edge && old_irr == ioapic->irr) ||
+ (!edge && entry.fields.remote_irr)) {
+ ret = 0;
+ goto out;
+ }
+
+ ret = ioapic_service(ioapic, irq, line_status);
+
+out:
+ trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
+ return ret;
+}
+
+static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr)
+{
+ u32 idx;
+
+ rtc_irq_eoi_tracking_reset(ioapic);
+ for_each_set_bit(idx, &irr, IOAPIC_NUM_PINS)
+ ioapic_set_irq(ioapic, idx, 1, true);
+
+ kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
+
+static void update_handled_vectors(struct kvm_ioapic *ioapic)
+{
+ DECLARE_BITMAP(handled_vectors, 256);
+ int i;
+
+ memset(handled_vectors, 0, sizeof(handled_vectors));
+ for (i = 0; i < IOAPIC_NUM_PINS; ++i)
+ __set_bit(ioapic->redirtbl[i].fields.vector, handled_vectors);
+ memcpy(ioapic->handled_vectors, handled_vectors,
+ sizeof(handled_vectors));
+ smp_wmb();
+}
+
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
+ u32 *tmr)
+{
+ struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+ union kvm_ioapic_redirect_entry *e;
+ int index;
+
+ spin_lock(&ioapic->lock);
+ for (index = 0; index < IOAPIC_NUM_PINS; index++) {
+ e = &ioapic->redirtbl[index];
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG ||
+ kvm_irq_has_notifier(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index) ||
+ index == RTC_GSI) {
+ if (kvm_apic_match_dest(vcpu, NULL, 0,
+ e->fields.dest_id, e->fields.dest_mode)) {
+ __set_bit(e->fields.vector,
+ (unsigned long *)eoi_exit_bitmap);
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG)
+ __set_bit(e->fields.vector,
+ (unsigned long *)tmr);
+ }
+ }
+ }
+ spin_unlock(&ioapic->lock);
+}
+
+void kvm_vcpu_request_scan_ioapic(struct kvm *kvm)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+ if (!ioapic)
+ return;
+ kvm_make_scan_ioapic_request(kvm);
+}
+
+static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
+{
+ unsigned index;
+ bool mask_before, mask_after;
+ union kvm_ioapic_redirect_entry *e;
+
+ switch (ioapic->ioregsel) {
+ case IOAPIC_REG_VERSION:
+ /* Writes are ignored. */
+ break;
+
+ case IOAPIC_REG_APIC_ID:
+ ioapic->id = (val >> 24) & 0xf;
+ break;
+
+ case IOAPIC_REG_ARB_ID:
+ break;
+
+ default:
+ index = (ioapic->ioregsel - 0x10) >> 1;
+
+ ioapic_debug("change redir index %x val %x\n", index, val);
+ if (index >= IOAPIC_NUM_PINS)
+ return;
+ e = &ioapic->redirtbl[index];
+ mask_before = e->fields.mask;
+ if (ioapic->ioregsel & 1) {
+ e->bits &= 0xffffffff;
+ e->bits |= (u64) val << 32;
+ } else {
+ e->bits &= ~0xffffffffULL;
+ e->bits |= (u32) val;
+ e->fields.remote_irr = 0;
+ }
+ update_handled_vectors(ioapic);
+ mask_after = e->fields.mask;
+ if (mask_before != mask_after)
+ kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
+ && ioapic->irr & (1 << index))
+ ioapic_service(ioapic, index, false);
+ kvm_vcpu_request_scan_ioapic(ioapic->kvm);
+ break;
+ }
+}
+
+static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
+{
+ union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq];
+ struct kvm_lapic_irq irqe;
+ int ret;
+
+ if (entry->fields.mask)
+ return -1;
+
+ ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
+ "vector=%x trig_mode=%x\n",
+ entry->fields.dest_id, entry->fields.dest_mode,
+ entry->fields.delivery_mode, entry->fields.vector,
+ entry->fields.trig_mode);
+
+ irqe.dest_id = entry->fields.dest_id;
+ irqe.vector = entry->fields.vector;
+ irqe.dest_mode = entry->fields.dest_mode;
+ irqe.trig_mode = entry->fields.trig_mode;
+ irqe.delivery_mode = entry->fields.delivery_mode << 8;
+ irqe.level = 1;
+ irqe.shorthand = 0;
+
+ if (irqe.trig_mode == IOAPIC_EDGE_TRIG)
+ ioapic->irr &= ~(1 << irq);
+
+ if (irq == RTC_GSI && line_status) {
+ /*
+ * pending_eoi cannot ever become negative (see
+ * rtc_status_pending_eoi_check_valid) and the caller
+ * ensures that it is only called if it is >= zero, namely
+ * if rtc_irq_check_coalesced returns false).
+ */
+ BUG_ON(ioapic->rtc_status.pending_eoi != 0);
+ ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
+ ioapic->rtc_status.dest_map);
+ ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
+ } else
+ ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);
+
+ if (ret && irqe.trig_mode == IOAPIC_LEVEL_TRIG)
+ entry->fields.remote_irr = 1;
+
+ return ret;
+}
+
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+ int level, bool line_status)
+{
+ int ret, irq_level;
+
+ BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
+
+ spin_lock(&ioapic->lock);
+ irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
+ irq_source_id, level);
+ ret = ioapic_set_irq(ioapic, irq, irq_level, line_status);
+
+ spin_unlock(&ioapic->lock);
+
+ return ret;
+}
+
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
+{
+ int i;
+
+ spin_lock(&ioapic->lock);
+ for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
+ __clear_bit(irq_source_id, &ioapic->irq_states[i]);
+ spin_unlock(&ioapic->lock);
+}
+
+static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
+{
+ int i;
+ struct kvm_ioapic *ioapic = container_of(work, struct kvm_ioapic,
+ eoi_inject.work);
+ spin_lock(&ioapic->lock);
+ for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+ union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+ if (ent->fields.trig_mode != IOAPIC_LEVEL_TRIG)
+ continue;
+
+ if (ioapic->irr & (1 << i) && !ent->fields.remote_irr)
+ ioapic_service(ioapic, i, false);
+ }
+ spin_unlock(&ioapic->lock);
+}
+
+#define IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT 10000
+
+static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
+ struct kvm_ioapic *ioapic, int vector, int trigger_mode)
+{
+ int i;
+
+ for (i = 0; i < IOAPIC_NUM_PINS; i++) {
+ union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
+
+ if (ent->fields.vector != vector)
+ continue;
+
+ if (i == RTC_GSI)
+ rtc_irq_eoi(ioapic, vcpu);
+ /*
+ * We are dropping lock while calling ack notifiers because ack
+ * notifier callbacks for assigned devices call into IOAPIC
+ * recursively. Since remote_irr is cleared only after call
+ * to notifiers if the same vector will be delivered while lock
+ * is dropped it will be put into irr and will be delivered
+ * after ack notifier returns.
+ */
+ spin_unlock(&ioapic->lock);
+ kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
+ spin_lock(&ioapic->lock);
+
+ if (trigger_mode != IOAPIC_LEVEL_TRIG)
+ continue;
+
+ ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
+ ent->fields.remote_irr = 0;
+ if (!ent->fields.mask && (ioapic->irr & (1 << i))) {
+ ++ioapic->irq_eoi[i];
+ if (ioapic->irq_eoi[i] == IOAPIC_SUCCESSIVE_IRQ_MAX_COUNT) {
+ /*
+ * Real hardware does not deliver the interrupt
+ * immediately during eoi broadcast, and this
+ * lets a buggy guest make slow progress
+ * even if it does not correctly handle a
+ * level-triggered interrupt. Emulate this
+ * behavior if we detect an interrupt storm.
+ */
+ schedule_delayed_work(&ioapic->eoi_inject, HZ / 100);
+ ioapic->irq_eoi[i] = 0;
+ trace_kvm_ioapic_delayed_eoi_inj(ent->bits);
+ } else {
+ ioapic_service(ioapic, i, false);
+ }
+ } else {
+ ioapic->irq_eoi[i] = 0;
+ }
+ }
+}
+
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ smp_rmb();
+ return test_bit(vector, ioapic->handled_vectors);
+}
+
+void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector, int trigger_mode)
+{
+ struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic;
+
+ spin_lock(&ioapic->lock);
+ __kvm_ioapic_update_eoi(vcpu, ioapic, vector, trigger_mode);
+ spin_unlock(&ioapic->lock);
+}
+
+static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
+{
+ return container_of(dev, struct kvm_ioapic, dev);
+}
+
+static inline int ioapic_in_range(struct kvm_ioapic *ioapic, gpa_t addr)
+{
+ return ((addr >= ioapic->base_address &&
+ (addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));
+}
+
+static int ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
+ void *val)
+{
+ struct kvm_ioapic *ioapic = to_ioapic(this);
+ u32 result;
+ if (!ioapic_in_range(ioapic, addr))
+ return -EOPNOTSUPP;
+
+ ioapic_debug("addr %lx\n", (unsigned long)addr);
+ ASSERT(!(addr & 0xf)); /* check alignment */
+
+ addr &= 0xff;
+ spin_lock(&ioapic->lock);
+ switch (addr) {
+ case IOAPIC_REG_SELECT:
+ result = ioapic->ioregsel;
+ break;
+
+ case IOAPIC_REG_WINDOW:
+ result = ioapic_read_indirect(ioapic, addr, len);
+ break;
+
+ default:
+ result = 0;
+ break;
+ }
+ spin_unlock(&ioapic->lock);
+
+ switch (len) {
+ case 8:
+ *(u64 *) val = result;
+ break;
+ case 1:
+ case 2:
+ case 4:
+ memcpy(val, (char *)&result, len);
+ break;
+ default:
+ printk(KERN_WARNING "ioapic: wrong length %d\n", len);
+ }
+ return 0;
+}
+
+static int ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
+ const void *val)
+{
+ struct kvm_ioapic *ioapic = to_ioapic(this);
+ u32 data;
+ if (!ioapic_in_range(ioapic, addr))
+ return -EOPNOTSUPP;
+
+ ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
+ (void*)addr, len, val);
+ ASSERT(!(addr & 0xf)); /* check alignment */
+
+ switch (len) {
+ case 8:
+ case 4:
+ data = *(u32 *) val;
+ break;
+ case 2:
+ data = *(u16 *) val;
+ break;
+ case 1:
+ data = *(u8 *) val;
+ break;
+ default:
+ printk(KERN_WARNING "ioapic: Unsupported size %d\n", len);
+ return 0;
+ }
+
+ addr &= 0xff;
+ spin_lock(&ioapic->lock);
+ switch (addr) {
+ case IOAPIC_REG_SELECT:
+ ioapic->ioregsel = data & 0xFF; /* 8-bit register */
+ break;
+
+ case IOAPIC_REG_WINDOW:
+ ioapic_write_indirect(ioapic, data);
+ break;
+
+ default:
+ break;
+ }
+ spin_unlock(&ioapic->lock);
+ return 0;
+}
+
+static void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
+{
+ int i;
+
+ cancel_delayed_work_sync(&ioapic->eoi_inject);
+ for (i = 0; i < IOAPIC_NUM_PINS; i++)
+ ioapic->redirtbl[i].fields.mask = 1;
+ ioapic->base_address = IOAPIC_DEFAULT_BASE_ADDRESS;
+ ioapic->ioregsel = 0;
+ ioapic->irr = 0;
+ ioapic->id = 0;
+ memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS);
+ rtc_irq_eoi_tracking_reset(ioapic);
+ update_handled_vectors(ioapic);
+}
+
+static const struct kvm_io_device_ops ioapic_mmio_ops = {
+ .read = ioapic_mmio_read,
+ .write = ioapic_mmio_write,
+};
+
+int kvm_ioapic_init(struct kvm *kvm)
+{
+ struct kvm_ioapic *ioapic;
+ int ret;
+
+ ioapic = kzalloc(sizeof(struct kvm_ioapic), GFP_KERNEL);
+ if (!ioapic)
+ return -ENOMEM;
+ spin_lock_init(&ioapic->lock);
+ INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
+ kvm->arch.vioapic = ioapic;
+ kvm_ioapic_reset(ioapic);
+ kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
+ ioapic->kvm = kvm;
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, ioapic->base_address,
+ IOAPIC_MEM_LENGTH, &ioapic->dev);
+ mutex_unlock(&kvm->slots_lock);
+ if (ret < 0) {
+ kvm->arch.vioapic = NULL;
+ kfree(ioapic);
+ }
+
+ return ret;
+}
+
+void kvm_ioapic_destroy(struct kvm *kvm)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+ cancel_delayed_work_sync(&ioapic->eoi_inject);
+ if (ioapic) {
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
+ kvm->arch.vioapic = NULL;
+ kfree(ioapic);
+ }
+}
+
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+ struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+ if (!ioapic)
+ return -EINVAL;
+
+ spin_lock(&ioapic->lock);
+ memcpy(state, ioapic, sizeof(struct kvm_ioapic_state));
+ spin_unlock(&ioapic->lock);
+ return 0;
+}
+
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state)
+{
+ struct kvm_ioapic *ioapic = ioapic_irqchip(kvm);
+ if (!ioapic)
+ return -EINVAL;
+
+ spin_lock(&ioapic->lock);
+ memcpy(ioapic, state, sizeof(struct kvm_ioapic_state));
+ ioapic->irr = 0;
+ update_handled_vectors(ioapic);
+ kvm_vcpu_request_scan_ioapic(kvm);
+ kvm_ioapic_inject_all(ioapic, state->irr);
+ spin_unlock(&ioapic->lock);
+ return 0;
+}
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
new file mode 100644
index 000000000000..3c9195535ffc
--- /dev/null
+++ b/arch/x86/kvm/ioapic.h
@@ -0,0 +1,119 @@
+#ifndef __KVM_IO_APIC_H
+#define __KVM_IO_APIC_H
+
+#include <linux/kvm_host.h>
+
+#include "iodev.h"
+
+struct kvm;
+struct kvm_vcpu;
+
+#define IOAPIC_NUM_PINS KVM_IOAPIC_NUM_PINS
+#define IOAPIC_VERSION_ID 0x11 /* IOAPIC version */
+#define IOAPIC_EDGE_TRIG 0
+#define IOAPIC_LEVEL_TRIG 1
+
+#define IOAPIC_DEFAULT_BASE_ADDRESS 0xfec00000
+#define IOAPIC_MEM_LENGTH 0x100
+
+/* Direct registers. */
+#define IOAPIC_REG_SELECT 0x00
+#define IOAPIC_REG_WINDOW 0x10
+
+/* Indirect registers. */
+#define IOAPIC_REG_APIC_ID 0x00 /* x86 IOAPIC only */
+#define IOAPIC_REG_VERSION 0x01
+#define IOAPIC_REG_ARB_ID 0x02 /* x86 IOAPIC only */
+
+/*ioapic delivery mode*/
+#define IOAPIC_FIXED 0x0
+#define IOAPIC_LOWEST_PRIORITY 0x1
+#define IOAPIC_PMI 0x2
+#define IOAPIC_NMI 0x4
+#define IOAPIC_INIT 0x5
+#define IOAPIC_EXTINT 0x7
+
+#ifdef CONFIG_X86
+#define RTC_GSI 8
+#else
+#define RTC_GSI -1U
+#endif
+
+struct rtc_status {
+ int pending_eoi;
+ DECLARE_BITMAP(dest_map, KVM_MAX_VCPUS);
+};
+
+union kvm_ioapic_redirect_entry {
+ u64 bits;
+ struct {
+ u8 vector;
+ u8 delivery_mode:3;
+ u8 dest_mode:1;
+ u8 delivery_status:1;
+ u8 polarity:1;
+ u8 remote_irr:1;
+ u8 trig_mode:1;
+ u8 mask:1;
+ u8 reserve:7;
+ u8 reserved[4];
+ u8 dest_id;
+ } fields;
+};
+
+struct kvm_ioapic {
+ u64 base_address;
+ u32 ioregsel;
+ u32 id;
+ u32 irr;
+ u32 pad;
+ union kvm_ioapic_redirect_entry redirtbl[IOAPIC_NUM_PINS];
+ unsigned long irq_states[IOAPIC_NUM_PINS];
+ struct kvm_io_device dev;
+ struct kvm *kvm;
+ void (*ack_notifier)(void *opaque, int irq);
+ spinlock_t lock;
+ DECLARE_BITMAP(handled_vectors, 256);
+ struct rtc_status rtc_status;
+ struct delayed_work eoi_inject;
+ u32 irq_eoi[IOAPIC_NUM_PINS];
+};
+
+#ifdef DEBUG
+#define ASSERT(x) \
+do { \
+ if (!(x)) { \
+ printk(KERN_EMERG "assertion failed %s: %d: %s\n", \
+ __FILE__, __LINE__, #x); \
+ BUG(); \
+ } \
+} while (0)
+#else
+#define ASSERT(x) do { } while (0)
+#endif
+
+static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm)
+{
+ return kvm->arch.vioapic;
+}
+
+void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
+int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
+ int short_hand, unsigned int dest, int dest_mode);
+int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
+void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
+ int trigger_mode);
+bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
+int kvm_ioapic_init(struct kvm *kvm);
+void kvm_ioapic_destroy(struct kvm *kvm);
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+ int level, bool line_status);
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq, unsigned long *dest_map);
+int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
+void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap,
+ u32 *tmr);
+
+#endif
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
new file mode 100644
index 000000000000..17b73eeac8a4
--- /dev/null
+++ b/arch/x86/kvm/iommu.c
@@ -0,0 +1,353 @@
+/*
+ * Copyright (c) 2006, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Copyright (C) 2006-2008 Intel Corporation
+ * Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ *
+ * Author: Allen M. Kay <allen.m.kay@intel.com>
+ * Author: Weidong Han <weidong.han@intel.com>
+ * Author: Ben-Ami Yassour <benami@il.ibm.com>
+ */
+
+#include <linux/list.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/stat.h>
+#include <linux/dmar.h>
+#include <linux/iommu.h>
+#include <linux/intel-iommu.h>
+#include "assigned-dev.h"
+
+static bool allow_unsafe_assigned_interrupts;
+module_param_named(allow_unsafe_assigned_interrupts,
+ allow_unsafe_assigned_interrupts, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(allow_unsafe_assigned_interrupts,
+ "Enable device assignment on platforms without interrupt remapping support.");
+
+static int kvm_iommu_unmap_memslots(struct kvm *kvm);
+static void kvm_iommu_put_pages(struct kvm *kvm,
+ gfn_t base_gfn, unsigned long npages);
+
+static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
+ unsigned long npages)
+{
+ gfn_t end_gfn;
+ pfn_t pfn;
+
+ pfn = gfn_to_pfn_memslot(slot, gfn);
+ end_gfn = gfn + npages;
+ gfn += 1;
+
+ if (is_error_noslot_pfn(pfn))
+ return pfn;
+
+ while (gfn < end_gfn)
+ gfn_to_pfn_memslot(slot, gfn++);
+
+ return pfn;
+}
+
+static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+{
+ unsigned long i;
+
+ for (i = 0; i < npages; ++i)
+ kvm_release_pfn_clean(pfn + i);
+}
+
+int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+ gfn_t gfn, end_gfn;
+ pfn_t pfn;
+ int r = 0;
+ struct iommu_domain *domain = kvm->arch.iommu_domain;
+ int flags;
+
+ /* check if iommu exists and in use */
+ if (!domain)
+ return 0;
+
+ gfn = slot->base_gfn;
+ end_gfn = gfn + slot->npages;
+
+ flags = IOMMU_READ;
+ if (!(slot->flags & KVM_MEM_READONLY))
+ flags |= IOMMU_WRITE;
+ if (!kvm->arch.iommu_noncoherent)
+ flags |= IOMMU_CACHE;
+
+
+ while (gfn < end_gfn) {
+ unsigned long page_size;
+
+ /* Check if already mapped */
+ if (iommu_iova_to_phys(domain, gfn_to_gpa(gfn))) {
+ gfn += 1;
+ continue;
+ }
+
+ /* Get the page size we could use to map */
+ page_size = kvm_host_page_size(kvm, gfn);
+
+ /* Make sure the page_size does not exceed the memslot */
+ while ((gfn + (page_size >> PAGE_SHIFT)) > end_gfn)
+ page_size >>= 1;
+
+ /* Make sure gfn is aligned to the page size we want to map */
+ while ((gfn << PAGE_SHIFT) & (page_size - 1))
+ page_size >>= 1;
+
+ /* Make sure hva is aligned to the page size we want to map */
+ while (__gfn_to_hva_memslot(slot, gfn) & (page_size - 1))
+ page_size >>= 1;
+
+ /*
+ * Pin all pages we are about to map in memory. This is
+ * important because we unmap and unpin in 4kb steps later.
+ */
+ pfn = kvm_pin_pages(slot, gfn, page_size >> PAGE_SHIFT);
+ if (is_error_noslot_pfn(pfn)) {
+ gfn += 1;
+ continue;
+ }
+
+ /* Map into IO address space */
+ r = iommu_map(domain, gfn_to_gpa(gfn), pfn_to_hpa(pfn),
+ page_size, flags);
+ if (r) {
+ printk(KERN_ERR "kvm_iommu_map_address:"
+ "iommu failed to map pfn=%llx\n", pfn);
+ kvm_unpin_pages(kvm, pfn, page_size >> PAGE_SHIFT);
+ goto unmap_pages;
+ }
+
+ gfn += page_size >> PAGE_SHIFT;
+
+
+ }
+
+ return 0;
+
+unmap_pages:
+ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn);
+ return r;
+}
+
+static int kvm_iommu_map_memslots(struct kvm *kvm)
+{
+ int idx, r = 0;
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+
+ if (kvm->arch.iommu_noncoherent)
+ kvm_arch_register_noncoherent_dma(kvm);
+
+ idx = srcu_read_lock(&kvm->srcu);
+ slots = kvm_memslots(kvm);
+
+ kvm_for_each_memslot(memslot, slots) {
+ r = kvm_iommu_map_pages(kvm, memslot);
+ if (r)
+ break;
+ }
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ return r;
+}
+
+int kvm_assign_device(struct kvm *kvm, struct pci_dev *pdev)
+{
+ struct iommu_domain *domain = kvm->arch.iommu_domain;
+ int r;
+ bool noncoherent;
+
+ /* check if iommu exists and in use */
+ if (!domain)
+ return 0;
+
+ if (pdev == NULL)
+ return -ENODEV;
+
+ r = iommu_attach_device(domain, &pdev->dev);
+ if (r) {
+ dev_err(&pdev->dev, "kvm assign device failed ret %d", r);
+ return r;
+ }
+
+ noncoherent = !iommu_capable(&pci_bus_type, IOMMU_CAP_CACHE_COHERENCY);
+
+ /* Check if need to update IOMMU page table for guest memory */
+ if (noncoherent != kvm->arch.iommu_noncoherent) {
+ kvm_iommu_unmap_memslots(kvm);
+ kvm->arch.iommu_noncoherent = noncoherent;
+ r = kvm_iommu_map_memslots(kvm);
+ if (r)
+ goto out_unmap;
+ }
+
+ pci_set_dev_assigned(pdev);
+
+ dev_info(&pdev->dev, "kvm assign device\n");
+
+ return 0;
+out_unmap:
+ kvm_iommu_unmap_memslots(kvm);
+ return r;
+}
+
+int kvm_deassign_device(struct kvm *kvm, struct pci_dev *pdev)
+{
+ struct iommu_domain *domain = kvm->arch.iommu_domain;
+
+ /* check if iommu exists and in use */
+ if (!domain)
+ return 0;
+
+ if (pdev == NULL)
+ return -ENODEV;
+
+ iommu_detach_device(domain, &pdev->dev);
+
+ pci_clear_dev_assigned(pdev);
+
+ dev_info(&pdev->dev, "kvm deassign device\n");
+
+ return 0;
+}
+
+int kvm_iommu_map_guest(struct kvm *kvm)
+{
+ int r;
+
+ if (!iommu_present(&pci_bus_type)) {
+ printk(KERN_ERR "%s: iommu not found\n", __func__);
+ return -ENODEV;
+ }
+
+ mutex_lock(&kvm->slots_lock);
+
+ kvm->arch.iommu_domain = iommu_domain_alloc(&pci_bus_type);
+ if (!kvm->arch.iommu_domain) {
+ r = -ENOMEM;
+ goto out_unlock;
+ }
+
+ if (!allow_unsafe_assigned_interrupts &&
+ !iommu_capable(&pci_bus_type, IOMMU_CAP_INTR_REMAP)) {
+ printk(KERN_WARNING "%s: No interrupt remapping support,"
+ " disallowing device assignment."
+ " Re-enble with \"allow_unsafe_assigned_interrupts=1\""
+ " module option.\n", __func__);
+ iommu_domain_free(kvm->arch.iommu_domain);
+ kvm->arch.iommu_domain = NULL;
+ r = -EPERM;
+ goto out_unlock;
+ }
+
+ r = kvm_iommu_map_memslots(kvm);
+ if (r)
+ kvm_iommu_unmap_memslots(kvm);
+
+out_unlock:
+ mutex_unlock(&kvm->slots_lock);
+ return r;
+}
+
+static void kvm_iommu_put_pages(struct kvm *kvm,
+ gfn_t base_gfn, unsigned long npages)
+{
+ struct iommu_domain *domain;
+ gfn_t end_gfn, gfn;
+ pfn_t pfn;
+ u64 phys;
+
+ domain = kvm->arch.iommu_domain;
+ end_gfn = base_gfn + npages;
+ gfn = base_gfn;
+
+ /* check if iommu exists and in use */
+ if (!domain)
+ return;
+
+ while (gfn < end_gfn) {
+ unsigned long unmap_pages;
+ size_t size;
+
+ /* Get physical address */
+ phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
+
+ if (!phys) {
+ gfn++;
+ continue;
+ }
+
+ pfn = phys >> PAGE_SHIFT;
+
+ /* Unmap address from IO address space */
+ size = iommu_unmap(domain, gfn_to_gpa(gfn), PAGE_SIZE);
+ unmap_pages = 1ULL << get_order(size);
+
+ /* Unpin all pages we just unmapped to not leak any memory */
+ kvm_unpin_pages(kvm, pfn, unmap_pages);
+
+ gfn += unmap_pages;
+ }
+}
+
+void kvm_iommu_unmap_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
+{
+ kvm_iommu_put_pages(kvm, slot->base_gfn, slot->npages);
+}
+
+static int kvm_iommu_unmap_memslots(struct kvm *kvm)
+{
+ int idx;
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ slots = kvm_memslots(kvm);
+
+ kvm_for_each_memslot(memslot, slots)
+ kvm_iommu_unmap_pages(kvm, memslot);
+
+ srcu_read_unlock(&kvm->srcu, idx);
+
+ if (kvm->arch.iommu_noncoherent)
+ kvm_arch_unregister_noncoherent_dma(kvm);
+
+ return 0;
+}
+
+int kvm_iommu_unmap_guest(struct kvm *kvm)
+{
+ struct iommu_domain *domain = kvm->arch.iommu_domain;
+
+ /* check if iommu exists and in use */
+ if (!domain)
+ return 0;
+
+ mutex_lock(&kvm->slots_lock);
+ kvm_iommu_unmap_memslots(kvm);
+ kvm->arch.iommu_domain = NULL;
+ kvm->arch.iommu_noncoherent = false;
+ mutex_unlock(&kvm->slots_lock);
+
+ iommu_domain_free(domain);
+ return 0;
+}
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
new file mode 100644
index 000000000000..72298b3ac025
--- /dev/null
+++ b/arch/x86/kvm/irq_comm.c
@@ -0,0 +1,332 @@
+/*
+ * irq_comm.c: Common API for in kernel interrupt controller
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ * Authors:
+ * Yaozu (Eddie) Dong <Eddie.dong@intel.com>
+ *
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <trace/events/kvm.h>
+
+#include <asm/msidef.h>
+
+#include "irq.h"
+
+#include "ioapic.h"
+
+static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ struct kvm_pic *pic = pic_irqchip(kvm);
+ return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
+}
+
+static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
+ line_status);
+}
+
+inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
+{
+ return irq->delivery_mode == APIC_DM_LOWEST;
+}
+
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq, unsigned long *dest_map)
+{
+ int i, r = -1;
+ struct kvm_vcpu *vcpu, *lowest = NULL;
+
+ if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
+ kvm_is_dm_lowest_prio(irq)) {
+ printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+ irq->delivery_mode = APIC_DM_FIXED;
+ }
+
+ if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
+ return r;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!kvm_apic_present(vcpu))
+ continue;
+
+ if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
+ irq->dest_id, irq->dest_mode))
+ continue;
+
+ if (!kvm_is_dm_lowest_prio(irq)) {
+ if (r < 0)
+ r = 0;
+ r += kvm_apic_set_irq(vcpu, irq, dest_map);
+ } else if (kvm_lapic_enabled(vcpu)) {
+ if (!lowest)
+ lowest = vcpu;
+ else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+ lowest = vcpu;
+ }
+ }
+
+ if (lowest)
+ r = kvm_apic_set_irq(lowest, irq, dest_map);
+
+ return r;
+}
+
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm_lapic_irq *irq)
+{
+ trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+ irq->dest_id = (e->msi.address_lo &
+ MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+ irq->vector = (e->msi.data &
+ MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+ irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+ irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+ irq->delivery_mode = e->msi.data & 0x700;
+ irq->level = 1;
+ irq->shorthand = 0;
+ /* TODO Deal with RH bit of MSI message address */
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level, bool line_status)
+{
+ struct kvm_lapic_irq irq;
+
+ if (!level)
+ return -1;
+
+ kvm_set_msi_irq(e, &irq);
+
+ return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
+}
+
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm)
+{
+ struct kvm_lapic_irq irq;
+ int r;
+
+ kvm_set_msi_irq(e, &irq);
+
+ if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+ return r;
+ else
+ return -EWOULDBLOCK;
+}
+
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ * -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ * Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
+{
+ struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
+ struct kvm_kernel_irq_routing_entry *e;
+ int ret = -EINVAL;
+ int idx;
+
+ trace_kvm_set_irq(irq, level, irq_source_id);
+
+ /*
+ * Injection into either PIC or IOAPIC might need to scan all CPUs,
+ * which would need to be retried from thread context; when same GSI
+ * is connected to both PIC and IOAPIC, we'd have to report a
+ * partial failure here.
+ * Since there's no easy way to do this, we only support injecting MSI
+ * which is limited to 1:1 GSI mapping.
+ */
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ if (kvm_irq_map_gsi(kvm, entries, irq) > 0) {
+ e = &entries[0];
+ if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+ ret = kvm_set_msi_inatomic(e, kvm);
+ else
+ ret = -EWOULDBLOCK;
+ }
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+ return ret;
+}
+
+int kvm_request_irq_source_id(struct kvm *kvm)
+{
+ unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
+ int irq_source_id;
+
+ mutex_lock(&kvm->irq_lock);
+ irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
+
+ if (irq_source_id >= BITS_PER_LONG) {
+ printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n");
+ irq_source_id = -EFAULT;
+ goto unlock;
+ }
+
+ ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+ ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+ set_bit(irq_source_id, bitmap);
+unlock:
+ mutex_unlock(&kvm->irq_lock);
+
+ return irq_source_id;
+}
+
+void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
+{
+ ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+ ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+
+ mutex_lock(&kvm->irq_lock);
+ if (irq_source_id < 0 ||
+ irq_source_id >= BITS_PER_LONG) {
+ printk(KERN_ERR "kvm: IRQ source ID out of range!\n");
+ goto unlock;
+ }
+ clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+ if (!irqchip_in_kernel(kvm))
+ goto unlock;
+
+ kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
+ kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
+unlock:
+ mutex_unlock(&kvm->irq_lock);
+}
+
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn)
+{
+ mutex_lock(&kvm->irq_lock);
+ kimn->irq = irq;
+ hlist_add_head_rcu(&kimn->link, &kvm->arch.mask_notifier_list);
+ mutex_unlock(&kvm->irq_lock);
+}
+
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_del_rcu(&kimn->link);
+ mutex_unlock(&kvm->irq_lock);
+ synchronize_srcu(&kvm->irq_srcu);
+}
+
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+ bool mask)
+{
+ struct kvm_irq_mask_notifier *kimn;
+ int idx, gsi;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_rcu(kimn, &kvm->arch.mask_notifier_list, link)
+ if (kimn->irq == gsi)
+ kimn->func(kimn, mask);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+{
+ int r = -EINVAL;
+ int delta;
+ unsigned max_pin;
+
+ switch (ue->type) {
+ case KVM_IRQ_ROUTING_IRQCHIP:
+ delta = 0;
+ switch (ue->u.irqchip.irqchip) {
+ case KVM_IRQCHIP_PIC_MASTER:
+ e->set = kvm_set_pic_irq;
+ max_pin = PIC_NUM_PINS;
+ break;
+ case KVM_IRQCHIP_PIC_SLAVE:
+ e->set = kvm_set_pic_irq;
+ max_pin = PIC_NUM_PINS;
+ delta = 8;
+ break;
+ case KVM_IRQCHIP_IOAPIC:
+ max_pin = KVM_IOAPIC_NUM_PINS;
+ e->set = kvm_set_ioapic_irq;
+ break;
+ default:
+ goto out;
+ }
+ e->irqchip.irqchip = ue->u.irqchip.irqchip;
+ e->irqchip.pin = ue->u.irqchip.pin + delta;
+ if (e->irqchip.pin >= max_pin)
+ goto out;
+ break;
+ case KVM_IRQ_ROUTING_MSI:
+ e->set = kvm_set_msi;
+ e->msi.address_lo = ue->u.msi.address_lo;
+ e->msi.address_hi = ue->u.msi.address_hi;
+ e->msi.data = ue->u.msi.data;
+ break;
+ default:
+ goto out;
+ }
+
+ r = 0;
+out:
+ return r;
+}
+
+#define IOAPIC_ROUTING_ENTRY(irq) \
+ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
+ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
+#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
+
+#define PIC_ROUTING_ENTRY(irq) \
+ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
+ .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
+#define ROUTING_ENTRY2(irq) \
+ IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
+
+static const struct kvm_irq_routing_entry default_routing[] = {
+ ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
+ ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
+ ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
+ ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
+ ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
+ ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
+ ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
+ ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
+ ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
+ ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
+ ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
+ ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
+};
+
+int kvm_setup_default_irq_routing(struct kvm *kvm)
+{
+ return kvm_set_irq_routing(kvm, default_routing,
+ ARRAY_SIZE(default_routing), 0);
+}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 08e8a899e005..4f0c0b954686 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -68,6 +68,9 @@
#define MAX_APIC_VECTOR 256
#define APIC_VECTORS_PER_REG 32
+#define APIC_BROADCAST 0xFF
+#define X2APIC_BROADCAST 0xFFFFFFFFul
+
#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)
@@ -112,17 +115,6 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
struct static_key_deferred apic_hw_disabled __read_mostly;
struct static_key_deferred apic_sw_disabled __read_mostly;
-static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
-{
- if ((kvm_apic_get_reg(apic, APIC_SPIV) ^ val) & APIC_SPIV_APIC_ENABLED) {
- if (val & APIC_SPIV_APIC_ENABLED)
- static_key_slow_dec_deferred(&apic_sw_disabled);
- else
- static_key_slow_inc(&apic_sw_disabled.key);
- }
- apic_set_reg(apic, APIC_SPIV, val);
-}
-
static inline int apic_enabled(struct kvm_lapic *apic)
{
return kvm_apic_sw_enabled(apic) && kvm_apic_hw_enabled(apic);
@@ -140,8 +132,6 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
}
-#define KVM_X2APIC_CID_BITS 0
-
static void recalculate_apic_map(struct kvm *kvm)
{
struct kvm_apic_map *new, *old = NULL;
@@ -160,42 +150,56 @@ static void recalculate_apic_map(struct kvm *kvm)
new->cid_shift = 8;
new->cid_mask = 0;
new->lid_mask = 0xff;
+ new->broadcast = APIC_BROADCAST;
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvm_lapic *apic = vcpu->arch.apic;
- u16 cid, lid;
- u32 ldr;
if (!kvm_apic_present(vcpu))
continue;
+ if (apic_x2apic_mode(apic)) {
+ new->ldr_bits = 32;
+ new->cid_shift = 16;
+ new->cid_mask = new->lid_mask = 0xffff;
+ new->broadcast = X2APIC_BROADCAST;
+ } else if (kvm_apic_get_reg(apic, APIC_LDR)) {
+ if (kvm_apic_get_reg(apic, APIC_DFR) ==
+ APIC_DFR_CLUSTER) {
+ new->cid_shift = 4;
+ new->cid_mask = 0xf;
+ new->lid_mask = 0xf;
+ } else {
+ new->cid_shift = 8;
+ new->cid_mask = 0;
+ new->lid_mask = 0xff;
+ }
+ }
+
/*
* All APICs have to be configured in the same mode by an OS.
* We take advatage of this while building logical id loockup
- * table. After reset APICs are in xapic/flat mode, so if we
- * find apic with different setting we assume this is the mode
+ * table. After reset APICs are in software disabled mode, so if
+ * we find apic with different setting we assume this is the mode
* OS wants all apics to be in; build lookup table accordingly.
*/
- if (apic_x2apic_mode(apic)) {
- new->ldr_bits = 32;
- new->cid_shift = 16;
- new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
- new->lid_mask = 0xffff;
- } else if (kvm_apic_sw_enabled(apic) &&
- !new->cid_mask /* flat mode */ &&
- kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
- new->cid_shift = 4;
- new->cid_mask = 0xf;
- new->lid_mask = 0xf;
- }
+ if (kvm_apic_sw_enabled(apic))
+ break;
+ }
- new->phys_map[kvm_apic_id(apic)] = apic;
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvm_lapic *apic = vcpu->arch.apic;
+ u16 cid, lid;
+ u32 ldr, aid;
+ aid = kvm_apic_id(apic);
ldr = kvm_apic_get_reg(apic, APIC_LDR);
cid = apic_cluster_id(new, ldr);
lid = apic_logical_id(new, ldr);
- if (lid)
+ if (aid < ARRAY_SIZE(new->phys_map))
+ new->phys_map[aid] = apic;
+ if (lid && cid < ARRAY_SIZE(new->logical_map))
new->logical_map[cid][ffs(lid) - 1] = apic;
}
out:
@@ -210,6 +214,22 @@ out:
kvm_vcpu_request_scan_ioapic(kvm);
}
+static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
+{
+ bool enabled = val & APIC_SPIV_APIC_ENABLED;
+
+ apic_set_reg(apic, APIC_SPIV, val);
+
+ if (enabled != apic->sw_enabled) {
+ apic->sw_enabled = enabled;
+ if (enabled) {
+ static_key_slow_dec_deferred(&apic_sw_disabled);
+ recalculate_apic_map(apic->vcpu->kvm);
+ } else
+ static_key_slow_inc(&apic_sw_disabled.key);
+ }
+}
+
static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
{
apic_set_reg(apic, APIC_ID, id << 24);
@@ -234,21 +254,17 @@ static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type)
static inline int apic_lvtt_oneshot(struct kvm_lapic *apic)
{
- return ((kvm_apic_get_reg(apic, APIC_LVTT) &
- apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT);
+ return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_ONESHOT;
}
static inline int apic_lvtt_period(struct kvm_lapic *apic)
{
- return ((kvm_apic_get_reg(apic, APIC_LVTT) &
- apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC);
+ return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_PERIODIC;
}
static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic)
{
- return ((kvm_apic_get_reg(apic, APIC_LVTT) &
- apic->lapic_timer.timer_mode_mask) ==
- APIC_LVT_TIMER_TSCDEADLINE);
+ return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_TSCDEADLINE;
}
static inline int apic_lvt_nmi_mode(u32 lvt_val)
@@ -323,8 +339,12 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
{
- apic->irr_pending = true;
apic_set_vector(vec, apic->regs + APIC_IRR);
+ /*
+ * irr_pending must be true if any interrupt is pending; set it after
+ * APIC_IRR to avoid race with apic_clear_irr
+ */
+ apic->irr_pending = true;
}
static inline int apic_search_irr(struct kvm_lapic *apic)
@@ -356,13 +376,15 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
vcpu = apic->vcpu;
- apic_clear_vector(vec, apic->regs + APIC_IRR);
- if (unlikely(kvm_apic_vid_enabled(vcpu->kvm)))
+ if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) {
/* try to update RVI */
+ apic_clear_vector(vec, apic->regs + APIC_IRR);
kvm_make_request(KVM_REQ_EVENT, vcpu);
- else {
- vec = apic_search_irr(apic);
- apic->irr_pending = (vec != -1);
+ } else {
+ apic->irr_pending = false;
+ apic_clear_vector(vec, apic->regs + APIC_IRR);
+ if (apic_search_irr(apic) != -1)
+ apic->irr_pending = true;
}
}
@@ -555,16 +577,25 @@ static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
apic_update_ppr(apic);
}
-int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
+static int kvm_apic_broadcast(struct kvm_lapic *apic, u32 dest)
+{
+ return dest == (apic_x2apic_mode(apic) ?
+ X2APIC_BROADCAST : APIC_BROADCAST);
+}
+
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest)
{
- return dest == 0xff || kvm_apic_id(apic) == dest;
+ return kvm_apic_id(apic) == dest || kvm_apic_broadcast(apic, dest);
}
-int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda)
{
int result = 0;
u32 logical_id;
+ if (kvm_apic_broadcast(apic, mda))
+ return 1;
+
if (apic_x2apic_mode(apic)) {
logical_id = kvm_apic_get_reg(apic, APIC_LDR);
return logical_id & mda;
@@ -592,7 +623,7 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
}
int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
- int short_hand, int dest, int dest_mode)
+ int short_hand, unsigned int dest, int dest_mode)
{
int result = 0;
struct kvm_lapic *target = vcpu->arch.apic;
@@ -654,15 +685,24 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
if (!map)
goto out;
+ if (irq->dest_id == map->broadcast)
+ goto out;
+
+ ret = true;
+
if (irq->dest_mode == 0) { /* physical mode */
- if (irq->delivery_mode == APIC_DM_LOWEST ||
- irq->dest_id == 0xff)
+ if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
goto out;
- dst = &map->phys_map[irq->dest_id & 0xff];
+
+ dst = &map->phys_map[irq->dest_id];
} else {
u32 mda = irq->dest_id << (32 - map->ldr_bits);
+ u16 cid = apic_cluster_id(map, mda);
+
+ if (cid >= ARRAY_SIZE(map->logical_map))
+ goto out;
- dst = map->logical_map[apic_cluster_id(map, mda)];
+ dst = map->logical_map[cid];
bitmap = apic_logical_id(map, mda);
@@ -688,8 +728,6 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
*r = 0;
*r += kvm_apic_set_irq(dst[i]->vcpu, irq, dest_map);
}
-
- ret = true;
out:
rcu_read_unlock();
return ret;
@@ -706,6 +744,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
int result = 0;
struct kvm_vcpu *vcpu = apic->vcpu;
+ trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
+ trig_mode, vector);
switch (delivery_mode) {
case APIC_DM_LOWEST:
vcpu->arch.apic_arb_prio++;
@@ -727,8 +767,6 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_vcpu_kick(vcpu);
}
- trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
- trig_mode, vector, false);
break;
case APIC_DM_REMRD:
@@ -1031,6 +1069,26 @@ static void update_divide_count(struct kvm_lapic *apic)
apic->divide_count);
}
+static void apic_timer_expired(struct kvm_lapic *apic)
+{
+ struct kvm_vcpu *vcpu = apic->vcpu;
+ wait_queue_head_t *q = &vcpu->wq;
+
+ /*
+ * Note: KVM_REQ_PENDING_TIMER is implicitly checked in
+ * vcpu_enter_guest.
+ */
+ if (atomic_read(&apic->lapic_timer.pending))
+ return;
+
+ atomic_inc(&apic->lapic_timer.pending);
+ /* FIXME: this code should not know anything about vcpus */
+ kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+
+ if (waitqueue_active(q))
+ wake_up_interruptible(q);
+}
+
static void start_apic_timer(struct kvm_lapic *apic)
{
ktime_t now;
@@ -1093,9 +1151,10 @@ static void start_apic_timer(struct kvm_lapic *apic)
if (likely(tscdeadline > guest_tsc)) {
ns = (tscdeadline - guest_tsc) * 1000000ULL;
do_div(ns, this_tsc_khz);
- }
- hrtimer_start(&apic->lapic_timer.timer,
- ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+ hrtimer_start(&apic->lapic_timer.timer,
+ ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+ } else
+ apic_timer_expired(apic);
local_irq_restore(flags);
}
@@ -1200,17 +1259,20 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
break;
- case APIC_LVTT:
- if ((kvm_apic_get_reg(apic, APIC_LVTT) &
- apic->lapic_timer.timer_mode_mask) !=
- (val & apic->lapic_timer.timer_mode_mask))
+ case APIC_LVTT: {
+ u32 timer_mode = val & apic->lapic_timer.timer_mode_mask;
+
+ if (apic->lapic_timer.timer_mode != timer_mode) {
+ apic->lapic_timer.timer_mode = timer_mode;
hrtimer_cancel(&apic->lapic_timer.timer);
+ }
if (!kvm_apic_sw_enabled(apic))
val |= APIC_LVT_MASKED;
val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
apic_set_reg(apic, APIC_LVTT, val);
break;
+ }
case APIC_TMICT:
if (apic_lvtt_tscdeadline(apic))
@@ -1317,7 +1379,7 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE))
static_key_slow_dec_deferred(&apic_hw_disabled);
- if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED))
+ if (!apic->sw_enabled)
static_key_slow_dec_deferred(&apic_sw_disabled);
if (apic->regs)
@@ -1416,6 +1478,10 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
apic->base_address = apic->vcpu->arch.apic_base &
MSR_IA32_APICBASE_BASE;
+ if ((value & MSR_IA32_APICBASE_ENABLE) &&
+ apic->base_address != APIC_DEFAULT_PHYS_BASE)
+ pr_warn_once("APIC base relocation is unsupported by KVM");
+
/* with FSB delivery interrupt, we can restart APIC functionality */
apic_debug("apic base msr is 0x%016" PRIx64 ", and base address is "
"0x%lx.\n", apic->vcpu->arch.apic_base, apic->base_address);
@@ -1441,6 +1507,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
for (i = 0; i < APIC_LVT_NUM; i++)
apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
+ apic->lapic_timer.timer_mode = 0;
apic_set_reg(apic, APIC_LVT0,
SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
@@ -1532,23 +1599,8 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
{
struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
- struct kvm_vcpu *vcpu = apic->vcpu;
- wait_queue_head_t *q = &vcpu->wq;
-
- /*
- * There is a race window between reading and incrementing, but we do
- * not care about potentially losing timer events in the !reinject
- * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
- * in vcpu_enter_guest.
- */
- if (!atomic_read(&ktimer->pending)) {
- atomic_inc(&ktimer->pending);
- /* FIXME: this code should not know anything about vcpus */
- kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
- }
- if (waitqueue_active(q))
- wake_up_interruptible(q);
+ apic_timer_expired(apic);
if (lapic_is_periodic(apic)) {
hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
@@ -1639,6 +1691,8 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
if (atomic_read(&apic->lapic_timer.pending) > 0) {
kvm_apic_local_deliver(apic, APIC_LVTT);
+ if (apic_lvtt_tscdeadline(apic))
+ apic->lapic_timer.tscdeadline = 0;
atomic_set(&apic->lapic_timer.pending, 0);
}
}
@@ -1685,6 +1739,9 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
1 : count_vectors(apic->regs + APIC_ISR);
apic->highest_isr_cache = -1;
+ if (kvm_x86_ops->hwapic_irr_update)
+ kvm_x86_ops->hwapic_irr_update(vcpu,
+ apic_find_highest_irr(apic));
kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic));
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_rtc_eoi_tracking_restore_one(vcpu);
@@ -1829,8 +1886,11 @@ int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
return 1;
+ if (reg == APIC_ICR2)
+ return 1;
+
/* if this is ICR write vector before command */
- if (msr == 0x830)
+ if (reg == APIC_ICR)
apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
return apic_reg_write(apic, reg, (u32)data);
}
@@ -1843,9 +1903,15 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
return 1;
+ if (reg == APIC_DFR || reg == APIC_ICR2) {
+ apic_debug("KVM_APIC_READ: read x2apic reserved register %x\n",
+ reg);
+ return 1;
+ }
+
if (apic_reg_read(apic, reg, 4, &low))
return 1;
- if (msr == 0x830)
+ if (reg == APIC_ICR)
apic_reg_read(apic, APIC_ICR2, 4, &high);
*data = (((u64)high) << 32) | low;
@@ -1900,7 +1966,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- unsigned int sipi_vector;
+ u8 sipi_vector;
unsigned long pe;
if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 6a11845fd8b9..c674fce53cf9 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -11,6 +11,7 @@
struct kvm_timer {
struct hrtimer timer;
s64 period; /* unit: ns */
+ u32 timer_mode;
u32 timer_mode_mask;
u64 tscdeadline;
atomic_t pending; /* accumulated triggered timers */
@@ -22,6 +23,7 @@ struct kvm_lapic {
struct kvm_timer lapic_timer;
u32 divide_count;
struct kvm_vcpu *vcpu;
+ bool sw_enabled;
bool irr_pending;
/* Number of bits set in ISR. */
s16 isr_count;
@@ -55,8 +57,8 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu);
void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr);
void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
-int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
-int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
+int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u32 dest);
+int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u32 mda);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
unsigned long *dest_map);
int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
@@ -119,11 +121,11 @@ static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
extern struct static_key_deferred apic_sw_disabled;
-static inline int kvm_apic_sw_enabled(struct kvm_lapic *apic)
+static inline bool kvm_apic_sw_enabled(struct kvm_lapic *apic)
{
if (static_key_false(&apic_sw_disabled.key))
- return kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
- return APIC_SPIV_APIC_ENABLED;
+ return apic->sw_enabled;
+ return true;
}
static inline bool kvm_apic_present(struct kvm_vcpu *vcpu)
@@ -152,8 +154,6 @@ static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
ldr >>= 32 - map->ldr_bits;
cid = (ldr >> map->cid_shift) & map->cid_mask;
- BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
-
return cid;
}
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 931467881da7..f83fc6c5e0ba 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -199,24 +199,27 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask)
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
/*
- * spte bits of bit 3 ~ bit 11 are used as low 9 bits of generation number,
- * the bits of bits 52 ~ bit 61 are used as high 10 bits of generation
- * number.
+ * the low bit of the generation number is always presumed to be zero.
+ * This disables mmio caching during memslot updates. The concept is
+ * similar to a seqcount but instead of retrying the access we just punt
+ * and ignore the cache.
+ *
+ * spte bits 3-11 are used as bits 1-9 of the generation number,
+ * the bits 52-61 are used as bits 10-19 of the generation number.
*/
-#define MMIO_SPTE_GEN_LOW_SHIFT 3
+#define MMIO_SPTE_GEN_LOW_SHIFT 2
#define MMIO_SPTE_GEN_HIGH_SHIFT 52
-#define MMIO_GEN_SHIFT 19
-#define MMIO_GEN_LOW_SHIFT 9
-#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 1)
+#define MMIO_GEN_SHIFT 20
+#define MMIO_GEN_LOW_SHIFT 10
+#define MMIO_GEN_LOW_MASK ((1 << MMIO_GEN_LOW_SHIFT) - 2)
#define MMIO_GEN_MASK ((1 << MMIO_GEN_SHIFT) - 1)
-#define MMIO_MAX_GEN ((1 << MMIO_GEN_SHIFT) - 1)
static u64 generation_mmio_spte_mask(unsigned int gen)
{
u64 mask;
- WARN_ON(gen > MMIO_MAX_GEN);
+ WARN_ON(gen & ~MMIO_GEN_MASK);
mask = (gen & MMIO_GEN_LOW_MASK) << MMIO_SPTE_GEN_LOW_SHIFT;
mask |= ((u64)gen >> MMIO_GEN_LOW_SHIFT) << MMIO_SPTE_GEN_HIGH_SHIFT;
@@ -236,12 +239,7 @@ static unsigned int get_mmio_spte_generation(u64 spte)
static unsigned int kvm_current_mmio_generation(struct kvm *kvm)
{
- /*
- * Init kvm generation close to MMIO_MAX_GEN to easily test the
- * code of handling generation number wrap-around.
- */
- return (kvm_memslots(kvm)->generation +
- MMIO_MAX_GEN - 150) & MMIO_GEN_MASK;
+ return kvm_memslots(kvm)->generation & MMIO_GEN_MASK;
}
static void mark_mmio_spte(struct kvm *kvm, u64 *sptep, u64 gfn,
@@ -264,13 +262,13 @@ static bool is_mmio_spte(u64 spte)
static gfn_t get_mmio_spte_gfn(u64 spte)
{
- u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask;
+ u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
return (spte & ~mask) >> PAGE_SHIFT;
}
static unsigned get_mmio_spte_access(u64 spte)
{
- u64 mask = generation_mmio_spte_mask(MMIO_MAX_GEN) | shadow_mmio_mask;
+ u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask;
return (spte & ~mask) & ~PAGE_MASK;
}
@@ -296,11 +294,6 @@ static bool check_mmio_spte(struct kvm *kvm, u64 spte)
return likely(kvm_gen == spte_gen);
}
-static inline u64 rsvd_bits(int s, int e)
-{
- return ((1ULL << (e - s + 1)) - 1) << s;
-}
-
void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
u64 dirty_mask, u64 nx_mask, u64 x_mask)
{
@@ -636,7 +629,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
* kvm mmu, before reclaiming the page, we should
* unmap it from mmu first.
*/
- WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+ WARN_ON(!kvm_is_reserved_pfn(pfn) && !page_count(pfn_to_page(pfn)));
if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
kvm_set_pfn_accessed(pfn);
@@ -1180,7 +1173,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
* Write-protect on the specified @sptep, @pt_protect indicates whether
* spte write-protection is caused by protecting shadow page table.
*
- * Note: write protection is difference between drity logging and spte
+ * Note: write protection is difference between dirty logging and spte
* protection:
* - for dirty logging, the spte can be set to writable at anytime if
* its dirty bitmap is properly set.
@@ -1268,7 +1261,8 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
}
static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
- struct kvm_memory_slot *slot, unsigned long data)
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ unsigned long data)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1276,7 +1270,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
while ((sptep = rmap_get_first(*rmapp, &iter))) {
BUG_ON(!(*sptep & PT_PRESENT_MASK));
- rmap_printk("kvm_rmap_unmap_hva: spte %p %llx\n", sptep, *sptep);
+ rmap_printk("kvm_rmap_unmap_hva: spte %p %llx gfn %llx (%d)\n",
+ sptep, *sptep, gfn, level);
drop_spte(kvm, sptep);
need_tlb_flush = 1;
@@ -1286,7 +1281,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
}
static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
- struct kvm_memory_slot *slot, unsigned long data)
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ unsigned long data)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1300,7 +1296,8 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
BUG_ON(!is_shadow_present_pte(*sptep));
- rmap_printk("kvm_set_pte_rmapp: spte %p %llx\n", sptep, *sptep);
+ rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n",
+ sptep, *sptep, gfn, level);
need_flush = 1;
@@ -1334,6 +1331,8 @@ static int kvm_handle_hva_range(struct kvm *kvm,
int (*handler)(struct kvm *kvm,
unsigned long *rmapp,
struct kvm_memory_slot *slot,
+ gfn_t gfn,
+ int level,
unsigned long data))
{
int j;
@@ -1363,6 +1362,7 @@ static int kvm_handle_hva_range(struct kvm *kvm,
j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
unsigned long idx, idx_end;
unsigned long *rmapp;
+ gfn_t gfn = gfn_start;
/*
* {idx(page_j) | page_j intersects with
@@ -1373,8 +1373,10 @@ static int kvm_handle_hva_range(struct kvm *kvm,
rmapp = __gfn_to_rmap(gfn_start, j, memslot);
- for (; idx <= idx_end; ++idx)
- ret |= handler(kvm, rmapp++, memslot, data);
+ for (; idx <= idx_end;
+ ++idx, gfn += (1UL << KVM_HPAGE_GFN_SHIFT(j)))
+ ret |= handler(kvm, rmapp++, memslot,
+ gfn, j, data);
}
}
@@ -1385,6 +1387,7 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
unsigned long data,
int (*handler)(struct kvm *kvm, unsigned long *rmapp,
struct kvm_memory_slot *slot,
+ gfn_t gfn, int level,
unsigned long data))
{
return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
@@ -1406,24 +1409,14 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
}
static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
- struct kvm_memory_slot *slot, unsigned long data)
+ struct kvm_memory_slot *slot, gfn_t gfn, int level,
+ unsigned long data)
{
u64 *sptep;
struct rmap_iterator uninitialized_var(iter);
int young = 0;
- /*
- * In case of absence of EPT Access and Dirty Bits supports,
- * emulate the accessed bit for EPT, by checking if this page has
- * an EPT mapping, and clearing it if it does. On the next access,
- * a new EPT mapping will be established.
- * This has some overhead, but not as much as the cost of swapping
- * out actively used pages or breaking up actively used hugepages.
- */
- if (!shadow_accessed_mask) {
- young = kvm_unmap_rmapp(kvm, rmapp, slot, data);
- goto out;
- }
+ BUG_ON(!shadow_accessed_mask);
for (sptep = rmap_get_first(*rmapp, &iter); sptep;
sptep = rmap_get_next(&iter)) {
@@ -1435,14 +1428,13 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
(unsigned long *)sptep);
}
}
-out:
- /* @data has hva passed to kvm_age_hva(). */
- trace_kvm_age_page(data, slot, young);
+ trace_kvm_age_page(gfn, level, slot, young);
return young;
}
static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
- struct kvm_memory_slot *slot, unsigned long data)
+ struct kvm_memory_slot *slot, gfn_t gfn,
+ int level, unsigned long data)
{
u64 *sptep;
struct rmap_iterator iter;
@@ -1480,13 +1472,33 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
- kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0);
+ kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0);
kvm_flush_remote_tlbs(vcpu->kvm);
}
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
{
- return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp);
+ /*
+ * In case of absence of EPT Access and Dirty Bits supports,
+ * emulate the accessed bit for EPT, by checking if this page has
+ * an EPT mapping, and clearing it if it does. On the next access,
+ * a new EPT mapping will be established.
+ * This has some overhead, but not as much as the cost of swapping
+ * out actively used pages or breaking up actively used hugepages.
+ */
+ if (!shadow_accessed_mask) {
+ /*
+ * We are holding the kvm->mmu_lock, and we are blowing up
+ * shadow PTEs. MMU notifier consumers need to be kept at bay.
+ * This is correct as long as we don't decouple the mmu_lock
+ * protected regions (like invalidate_range_start|end does).
+ */
+ kvm->mmu_notifier_seq++;
+ return kvm_handle_hva_range(kvm, start, end, 0,
+ kvm_unmap_rmapp);
+ }
+
+ return kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp);
}
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
@@ -1749,7 +1761,7 @@ static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
return 1;
}
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
@@ -1802,7 +1814,7 @@ static void kvm_sync_pages(struct kvm_vcpu *vcpu, gfn_t gfn)
kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list);
if (flush)
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
struct mmu_page_path {
@@ -2448,7 +2460,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
spte |= PT_PAGE_SIZE_MASK;
if (tdp_enabled)
spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
- kvm_is_mmio_pfn(pfn));
+ kvm_is_reserved_pfn(pfn));
if (host_writable)
spte |= SPTE_HOST_WRITEABLE;
@@ -2536,7 +2548,7 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
true, host_writable)) {
if (write_fault)
*emulate = 1;
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
if (unlikely(is_mmio_spte(*sptep) && emulate))
@@ -2724,7 +2736,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
* PT_PAGE_TABLE_LEVEL and there would be no adjustment done
* here.
*/
- if (!is_error_noslot_pfn(pfn) && !kvm_is_mmio_pfn(pfn) &&
+ if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn) &&
level == PT_PAGE_TABLE_LEVEL &&
PageTransCompound(pfn_to_page(pfn)) &&
!has_wrprotected_page(vcpu->kvm, gfn, PT_DIRECTORY_LEVEL)) {
@@ -3163,7 +3175,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu)
if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
return;
- vcpu_clear_mmio_info(vcpu, ~0ul);
+ vcpu_clear_mmio_info(vcpu, MMIO_GVA_ANY);
kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC);
if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) {
hpa_t root = vcpu->arch.mmu.root_hpa;
@@ -3206,7 +3218,7 @@ static gpa_t nonpaging_gva_to_gpa_nested(struct kvm_vcpu *vcpu, gva_t vaddr,
{
if (exception)
exception->error_code = 0;
- return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access);
+ return vcpu->arch.nested_mmu.translate_gpa(vcpu, vaddr, access, exception);
}
static bool quickly_check_mmio_pf(struct kvm_vcpu *vcpu, u64 addr, bool direct)
@@ -3450,13 +3462,6 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu,
context->nx = false;
}
-void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
-{
- ++vcpu->stat.tlb_flush;
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-}
-EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb);
-
void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu)
{
mmu_free_roots(vcpu);
@@ -3518,6 +3523,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
int maxphyaddr = cpuid_maxphyaddr(vcpu);
u64 exb_bit_rsvd = 0;
u64 gbpages_bit_rsvd = 0;
+ u64 nonleaf_bit8_rsvd = 0;
context->bad_mt_xwr = 0;
@@ -3525,6 +3531,14 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
exb_bit_rsvd = rsvd_bits(63, 63);
if (!guest_cpuid_has_gbpages(vcpu))
gbpages_bit_rsvd = rsvd_bits(7, 7);
+
+ /*
+ * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
+ * leaf entries) on AMD CPUs only.
+ */
+ if (guest_cpuid_is_amd(vcpu))
+ nonleaf_bit8_rsvd = rsvd_bits(8, 8);
+
switch (context->root_level) {
case PT32_ROOT_LEVEL:
/* no rsvd bits for 2 level 4K page table entries */
@@ -3559,9 +3573,9 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
break;
case PT64_ROOT_LEVEL:
context->rsvd_bits_mask[0][3] = exb_bit_rsvd |
- rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7);
+ nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][2] = exb_bit_rsvd |
- gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
+ nonleaf_bit8_rsvd | gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][1] = exb_bit_rsvd |
rsvd_bits(maxphyaddr, 51);
context->rsvd_bits_mask[0][0] = exb_bit_rsvd |
@@ -3962,7 +3976,7 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page,
if (remote_flush)
kvm_flush_remote_tlbs(vcpu->kvm);
else if (local_flush)
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa,
@@ -4223,7 +4237,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
{
vcpu->arch.mmu.invlpg(vcpu, gva);
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
++vcpu->stat.invlpg;
}
EXPORT_SYMBOL_GPL(kvm_mmu_invlpg);
@@ -4433,8 +4447,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
* The very rare case: if the generation-number is round,
* zap all shadow pages.
*/
- if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
- printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
+ if (unlikely(kvm_current_mmio_generation(kvm) == 0)) {
+ printk_ratelimited(KERN_DEBUG "kvm: zapping shadow pages for mmio generation wraparound\n");
kvm_mmu_invalidate_zap_all_pages(kvm);
}
}
@@ -4534,7 +4548,7 @@ int kvm_mmu_module_init(void)
if (!mmu_page_header_cache)
goto nomem;
- if (percpu_counter_init(&kvm_total_used_mmu_pages, 0))
+ if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL))
goto nomem;
register_shrinker(&mmu_shrinker);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index b982112d2ca5..bde8ee725754 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -56,6 +56,11 @@
#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
+static inline u64 rsvd_bits(int s, int e)
+{
+ return ((1ULL << (e - s + 1)) - 1) << s;
+}
+
int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 5aaf35641768..ce463a9cc8fb 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -22,7 +22,7 @@
__entry->unsync = sp->unsync;
#define KVM_MMU_PAGE_PRINTK() ({ \
- const u32 saved_len = p->len; \
+ const char *saved_ptr = trace_seq_buffer_ptr(p); \
static const char *access_str[] = { \
"---", "--x", "w--", "w-x", "-u-", "-ux", "wu-", "wux" \
}; \
@@ -41,7 +41,7 @@
role.nxe ? "" : "!", \
__entry->root_count, \
__entry->unsync ? "unsync" : "sync", 0); \
- p->buffer + saved_len; \
+ saved_ptr; \
})
#define kvm_mmu_trace_pferr_flags \
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 410776528265..fd49c867b25a 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -298,8 +298,7 @@ retry_walk:
}
#endif
walker->max_level = walker->level;
- ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
- (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
+ ASSERT(!(is_long_mode(vcpu) && !is_pae(vcpu)));
accessed_dirty = PT_GUEST_ACCESSED_MASK;
pt_access = pte_access = ACC_ALL;
@@ -321,9 +320,22 @@ retry_walk:
walker->pte_gpa[walker->level - 1] = pte_gpa;
real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
- PFERR_USER_MASK|PFERR_WRITE_MASK);
+ PFERR_USER_MASK|PFERR_WRITE_MASK,
+ &walker->fault);
+
+ /*
+ * FIXME: This can happen if emulation (for of an INS/OUTS
+ * instruction) triggers a nested page fault. The exit
+ * qualification / exit info field will incorrectly have
+ * "guest page access" as the nested page fault's cause,
+ * instead of "guest page structure access". To fix this,
+ * the x86_exception struct should be augmented with enough
+ * information to fix the exit_qualification or exit_info_1
+ * fields.
+ */
if (unlikely(real_gfn == UNMAPPED_GVA))
- goto error;
+ return 0;
+
real_gfn = gpa_to_gfn(real_gfn);
host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
@@ -364,7 +376,7 @@ retry_walk:
if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
gfn += pse36_gfn_delta(pte);
- real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
+ real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access, &walker->fault);
if (real_gpa == UNMAPPED_GVA)
return 0;
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 3dd6accb64ec..8e6b7d869d2f 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -15,6 +15,7 @@
#include <linux/types.h>
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
+#include <asm/perf_event.h>
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
@@ -463,7 +464,8 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
{
struct kvm_pmu *pmu = &vcpu->arch.pmu;
struct kvm_cpuid_entry2 *entry;
- unsigned bitmap_len;
+ union cpuid10_eax eax;
+ union cpuid10_edx edx;
pmu->nr_arch_gp_counters = 0;
pmu->nr_arch_fixed_counters = 0;
@@ -475,25 +477,27 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
if (!entry)
return;
+ eax.full = entry->eax;
+ edx.full = entry->edx;
- pmu->version = entry->eax & 0xff;
+ pmu->version = eax.split.version_id;
if (!pmu->version)
return;
- pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff,
- INTEL_PMC_MAX_GENERIC);
- pmu->counter_bitmask[KVM_PMC_GP] =
- ((u64)1 << ((entry->eax >> 16) & 0xff)) - 1;
- bitmap_len = (entry->eax >> 24) & 0xff;
- pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1);
+ pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
+ INTEL_PMC_MAX_GENERIC);
+ pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+ pmu->available_event_types = ~entry->ebx &
+ ((1ull << eax.split.mask_length) - 1);
if (pmu->version == 1) {
pmu->nr_arch_fixed_counters = 0;
} else {
- pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
+ pmu->nr_arch_fixed_counters =
+ min_t(int, edx.split.num_counters_fixed,
INTEL_PMC_MAX_FIXED);
pmu->counter_bitmask[KVM_PMC_FIXED] =
- ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
+ ((u64)1 << edx.split.bit_width_fixed) - 1;
}
pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index ddf742768ecf..41dd0387cccb 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -622,7 +622,7 @@ static int has_svm(void)
return 1;
}
-static void svm_hardware_disable(void *garbage)
+static void svm_hardware_disable(void)
{
/* Make sure we clean up behind us */
if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
@@ -633,7 +633,7 @@ static void svm_hardware_disable(void *garbage)
amd_pmu_disable_virt();
}
-static int svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void)
{
struct svm_cpu_data *sd;
@@ -670,7 +670,7 @@ static int svm_hardware_enable(void *garbage)
if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
- __get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT;
+ __this_cpu_write(current_tsc_ratio, TSC_RATIO_DEFAULT);
}
@@ -1056,9 +1056,11 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool ho
{
struct vcpu_svm *svm = to_svm(vcpu);
- WARN_ON(adjustment < 0);
- if (host)
- adjustment = svm_scale_tsc(vcpu, adjustment);
+ if (host) {
+ if (svm->tsc_ratio != TSC_RATIO_DEFAULT)
+ WARN_ON(adjustment < 0);
+ adjustment = svm_scale_tsc(vcpu, (u64)adjustment);
+ }
svm->vmcb->control.tsc_offset += adjustment;
if (is_guest_mode(vcpu))
@@ -1257,7 +1259,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
svm->asid_generation = 0;
init_vmcb(svm);
- svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+ svm->vcpu.arch.apic_base = APIC_DEFAULT_PHYS_BASE |
+ MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&svm->vcpu))
svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP;
@@ -1312,8 +1315,8 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
if (static_cpu_has(X86_FEATURE_TSCRATEMSR) &&
- svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) {
- __get_cpu_var(current_tsc_ratio) = svm->tsc_ratio;
+ svm->tsc_ratio != __this_cpu_read(current_tsc_ratio)) {
+ __this_cpu_write(current_tsc_ratio, svm->tsc_ratio);
wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio);
}
}
@@ -1974,10 +1977,26 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm->vmcb->control.exit_code = SVM_EXIT_NPF;
- svm->vmcb->control.exit_code_hi = 0;
- svm->vmcb->control.exit_info_1 = fault->error_code;
- svm->vmcb->control.exit_info_2 = fault->address;
+ if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) {
+ /*
+ * TODO: track the cause of the nested page fault, and
+ * correctly fill in the high bits of exit_info_1.
+ */
+ svm->vmcb->control.exit_code = SVM_EXIT_NPF;
+ svm->vmcb->control.exit_code_hi = 0;
+ svm->vmcb->control.exit_info_1 = (1ULL << 32);
+ svm->vmcb->control.exit_info_2 = fault->address;
+ }
+
+ svm->vmcb->control.exit_info_1 &= ~0xffffffffULL;
+ svm->vmcb->control.exit_info_1 |= fault->error_code;
+
+ /*
+ * The present bit is always zero for page structure faults on real
+ * hardware.
+ */
+ if (svm->vmcb->control.exit_info_1 & (2ULL << 32))
+ svm->vmcb->control.exit_info_1 &= ~1;
nested_svm_vmexit(svm);
}
@@ -2982,7 +3001,6 @@ static int dr_interception(struct vcpu_svm *svm)
{
int reg, dr;
unsigned long val;
- int err;
if (svm->vcpu.guest_debug == 0) {
/*
@@ -3002,12 +3020,15 @@ static int dr_interception(struct vcpu_svm *svm)
dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0;
if (dr >= 16) { /* mov to DRn */
+ if (!kvm_require_dr(&svm->vcpu, dr - 16))
+ return 1;
val = kvm_register_read(&svm->vcpu, reg);
kvm_set_dr(&svm->vcpu, dr - 16, val);
} else {
- err = kvm_get_dr(&svm->vcpu, dr, &val);
- if (!err)
- kvm_register_write(&svm->vcpu, reg, val);
+ if (!kvm_require_dr(&svm->vcpu, dr))
+ return 1;
+ kvm_get_dr(&svm->vcpu, dr, &val);
+ kvm_register_write(&svm->vcpu, reg, val);
}
skip_emulated_instruction(&svm->vcpu);
@@ -3031,7 +3052,7 @@ static int cr8_write_interception(struct vcpu_svm *svm)
return 0;
}
-u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu));
return vmcb->control.tsc_offset +
@@ -3234,7 +3255,7 @@ static int wrmsr_interception(struct vcpu_svm *svm)
msr.host_initiated = false;
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
- if (svm_set_msr(&svm->vcpu, &msr)) {
+ if (kvm_set_msr(&svm->vcpu, &msr)) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(&svm->vcpu, 0);
} else {
@@ -3534,9 +3555,9 @@ static int handle_exit(struct kvm_vcpu *vcpu)
if (exit_code >= ARRAY_SIZE(svm_exit_handlers)
|| !svm_exit_handlers[exit_code]) {
- kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
- kvm_run->hw.hardware_exit_reason = exit_code;
- return 0;
+ WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_code);
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
return svm_exit_handlers[exit_code](svm);
@@ -4106,6 +4127,11 @@ static bool svm_mpx_supported(void)
return false;
}
+static bool svm_xsaves_supported(void)
+{
+ return false;
+}
+
static bool svm_has_wbinvd_exit(void)
{
return true;
@@ -4305,6 +4331,10 @@ static void svm_handle_external_intr(struct kvm_vcpu *vcpu)
local_irq_enable();
}
+static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+}
+
static struct kvm_x86_ops svm_x86_ops = {
.cpu_has_kvm_support = has_svm,
.disabled_by_bios = is_disabled,
@@ -4349,7 +4379,6 @@ static struct kvm_x86_ops svm_x86_ops = {
.cache_reg = svm_cache_reg,
.get_rflags = svm_get_rflags,
.set_rflags = svm_set_rflags,
- .fpu_activate = svm_fpu_activate,
.fpu_deactivate = svm_fpu_deactivate,
.tlb_flush = svm_flush_tlb,
@@ -4390,6 +4419,7 @@ static struct kvm_x86_ops svm_x86_ops = {
.rdtscp_supported = svm_rdtscp_supported,
.invpcid_supported = svm_invpcid_supported,
.mpx_supported = svm_mpx_supported,
+ .xsaves_supported = svm_xsaves_supported,
.set_supported_cpuid = svm_set_supported_cpuid,
@@ -4406,6 +4436,8 @@ static struct kvm_x86_ops svm_x86_ops = {
.check_intercept = svm_check_intercept,
.handle_external_intr = svm_handle_external_intr,
+
+ .sched_in = svm_sched_in,
};
static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index e850a7d332be..c2a34bb5ad93 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -5,6 +5,7 @@
#include <asm/vmx.h>
#include <asm/svm.h>
#include <asm/clocksource.h>
+#include <asm/pvclock-abi.h>
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
@@ -415,15 +416,14 @@ TRACE_EVENT(kvm_apic_ipi,
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec, bool coalesced),
- TP_ARGS(apicid, dm, tm, vec, coalesced),
+ TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
__field( __u8, tm )
__field( __u8, vec )
- __field( bool, coalesced )
),
TP_fast_assign(
@@ -431,14 +431,12 @@ TRACE_EVENT(kvm_apic_accept_irq,
__entry->dm = dm;
__entry->tm = tm;
__entry->vec = vec;
- __entry->coalesced = coalesced;
),
- TP_printk("apicid %x vec %u (%s|%s)%s",
+ TP_printk("apicid %x vec %u (%s|%s)",
__entry->apicid, __entry->vec,
__print_symbolic((__entry->dm >> 8 & 0x7), kvm_deliver_mode),
- __entry->tm ? "level" : "edge",
- __entry->coalesced ? " (coalesced)" : "")
+ __entry->tm ? "level" : "edge")
);
TRACE_EVENT(kvm_eoi,
@@ -850,6 +848,72 @@ TRACE_EVENT(kvm_track_tsc,
#endif /* CONFIG_X86_64 */
+TRACE_EVENT(kvm_ple_window,
+ TP_PROTO(bool grow, unsigned int vcpu_id, int new, int old),
+ TP_ARGS(grow, vcpu_id, new, old),
+
+ TP_STRUCT__entry(
+ __field( bool, grow )
+ __field( unsigned int, vcpu_id )
+ __field( int, new )
+ __field( int, old )
+ ),
+
+ TP_fast_assign(
+ __entry->grow = grow;
+ __entry->vcpu_id = vcpu_id;
+ __entry->new = new;
+ __entry->old = old;
+ ),
+
+ TP_printk("vcpu %u: ple_window %d (%s %d)",
+ __entry->vcpu_id,
+ __entry->new,
+ __entry->grow ? "grow" : "shrink",
+ __entry->old)
+);
+
+#define trace_kvm_ple_window_grow(vcpu_id, new, old) \
+ trace_kvm_ple_window(true, vcpu_id, new, old)
+#define trace_kvm_ple_window_shrink(vcpu_id, new, old) \
+ trace_kvm_ple_window(false, vcpu_id, new, old)
+
+TRACE_EVENT(kvm_pvclock_update,
+ TP_PROTO(unsigned int vcpu_id, struct pvclock_vcpu_time_info *pvclock),
+ TP_ARGS(vcpu_id, pvclock),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, vcpu_id )
+ __field( __u32, version )
+ __field( __u64, tsc_timestamp )
+ __field( __u64, system_time )
+ __field( __u32, tsc_to_system_mul )
+ __field( __s8, tsc_shift )
+ __field( __u8, flags )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->version = pvclock->version;
+ __entry->tsc_timestamp = pvclock->tsc_timestamp;
+ __entry->system_time = pvclock->system_time;
+ __entry->tsc_to_system_mul = pvclock->tsc_to_system_mul;
+ __entry->tsc_shift = pvclock->tsc_shift;
+ __entry->flags = pvclock->flags;
+ ),
+
+ TP_printk("vcpu_id %u, pvclock { version %u, tsc_timestamp 0x%llx, "
+ "system_time 0x%llx, tsc_to_system_mul 0x%x, tsc_shift %d, "
+ "flags 0x%x }",
+ __entry->vcpu_id,
+ __entry->version,
+ __entry->tsc_timestamp,
+ __entry->system_time,
+ __entry->tsc_to_system_mul,
+ __entry->tsc_shift,
+ __entry->flags)
+);
+
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bfe11cf124a1..d4c58d884838 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -99,13 +99,15 @@ module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
static bool __read_mostly nested = 0;
module_param(nested, bool, S_IRUGO);
+static u64 __read_mostly host_xss;
+
#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
#define KVM_VM_CR0_ALWAYS_ON \
(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
#define KVM_CR4_GUEST_OWNED_BITS \
(X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \
- | X86_CR4_OSXMMEXCPT)
+ | X86_CR4_OSXMMEXCPT | X86_CR4_TSD)
#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
@@ -125,14 +127,32 @@ module_param(nested, bool, S_IRUGO);
* Time is measured based on a counter that runs at the same rate as the TSC,
* refer SDM volume 3b section 21.6.13 & 22.1.3.
*/
-#define KVM_VMX_DEFAULT_PLE_GAP 128
-#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+#define KVM_VMX_DEFAULT_PLE_GAP 128
+#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
+#define KVM_VMX_DEFAULT_PLE_WINDOW_GROW 2
+#define KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK 0
+#define KVM_VMX_DEFAULT_PLE_WINDOW_MAX \
+ INT_MAX / KVM_VMX_DEFAULT_PLE_WINDOW_GROW
+
static int ple_gap = KVM_VMX_DEFAULT_PLE_GAP;
module_param(ple_gap, int, S_IRUGO);
static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
module_param(ple_window, int, S_IRUGO);
+/* Default doubles per-vcpu window every exit. */
+static int ple_window_grow = KVM_VMX_DEFAULT_PLE_WINDOW_GROW;
+module_param(ple_window_grow, int, S_IRUGO);
+
+/* Default resets per-vcpu window every exit to ple_window. */
+static int ple_window_shrink = KVM_VMX_DEFAULT_PLE_WINDOW_SHRINK;
+module_param(ple_window_shrink, int, S_IRUGO);
+
+/* Default is to compute the maximum so we can never overflow. */
+static int ple_window_actual_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
+static int ple_window_max = KVM_VMX_DEFAULT_PLE_WINDOW_MAX;
+module_param(ple_window_max, int, S_IRUGO);
+
extern const ulong vmx_return;
#define NR_AUTOLOAD_MSRS 8
@@ -196,6 +216,7 @@ struct __packed vmcs12 {
u64 virtual_apic_page_addr;
u64 apic_access_addr;
u64 ept_pointer;
+ u64 xss_exit_bitmap;
u64 guest_physical_address;
u64 vmcs_link_pointer;
u64 guest_ia32_debugctl;
@@ -379,6 +400,7 @@ struct nested_vmx {
* we must keep them pinned while L2 runs.
*/
struct page *apic_access_page;
+ struct page *virtual_apic_page;
u64 msr_ia32_feature_control;
struct hrtimer preemption_timer;
@@ -453,6 +475,7 @@ struct vcpu_vmx {
int gs_ldt_reload_needed;
int fs_reload_needed;
u64 msr_host_bndcfgs;
+ unsigned long vmcs_host_cr4; /* May not match real cr4 */
} host_state;
struct {
int vm86_active;
@@ -484,6 +507,10 @@ struct vcpu_vmx {
/* Support for a guest hypervisor (nested VMX) */
struct nested_vmx nested;
+
+ /* Dynamic PLE window. */
+ int ple_window;
+ bool ple_window_dirty;
};
enum segment_cache_field {
@@ -533,6 +560,7 @@ static int max_shadow_read_only_fields =
ARRAY_SIZE(shadow_read_only_fields);
static unsigned long shadow_read_write_fields[] = {
+ TPR_THRESHOLD,
GUEST_RIP,
GUEST_RSP,
GUEST_CR0,
@@ -591,6 +619,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr),
FIELD64(APIC_ACCESS_ADDR, apic_access_addr),
FIELD64(EPT_POINTER, ept_pointer),
+ FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
@@ -695,12 +724,15 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD(HOST_RSP, host_rsp),
FIELD(HOST_RIP, host_rip),
};
-static const int max_vmcs_field = ARRAY_SIZE(vmcs_field_to_offset_table);
static inline short vmcs_field_to_offset(unsigned long field)
{
- if (field >= max_vmcs_field || vmcs_field_to_offset_table[field] == 0)
- return -1;
+ BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
+
+ if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) ||
+ vmcs_field_to_offset_table[field] == 0)
+ return -ENOENT;
+
return vmcs_field_to_offset_table[field];
}
@@ -733,6 +765,7 @@ static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
static bool vmx_mpx_supported(void);
+static bool vmx_xsaves_supported(void);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg);
@@ -743,6 +776,7 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var);
static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx);
static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx);
+static int alloc_identity_pagetable(struct kvm *kvm);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -1072,6 +1106,12 @@ static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
}
+static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES) &&
+ vmx_xsaves_supported();
+}
+
static inline bool is_exception(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -1601,7 +1641,7 @@ static void reload_tss(void)
/*
* VT restores TR but not its size. Useless.
*/
- struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+ struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
struct desc_struct *descs;
descs = (void *)gdt->address;
@@ -1633,12 +1673,20 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
clear_atomic_switch_msr(vmx, MSR_EFER);
- /* On ept, can't emulate nx, and must switch nx atomically */
- if (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX)) {
+
+ /*
+ * On EPT, we can't emulate NX, so we must switch EFER atomically.
+ * On CPUs that support "load IA32_EFER", always switch EFER
+ * atomically, since it's faster than switching it manually.
+ */
+ if (cpu_has_load_ia32_efer ||
+ (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
guest_efer = vmx->vcpu.arch.efer;
if (!(guest_efer & EFER_LMA))
guest_efer &= ~EFER_LME;
- add_atomic_switch_msr(vmx, MSR_EFER, guest_efer, host_efer);
+ if (guest_efer != host_efer)
+ add_atomic_switch_msr(vmx, MSR_EFER,
+ guest_efer, host_efer);
return false;
}
@@ -1647,7 +1695,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
static unsigned long segment_base(u16 selector)
{
- struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+ struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
struct desc_struct *d;
unsigned long table_base;
unsigned long v;
@@ -1777,7 +1825,7 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
*/
if (!user_has_fpu() && !vmx->vcpu.guest_fpu_loaded)
stts();
- load_gdt(&__get_cpu_var(host_gdt));
+ load_gdt(this_cpu_ptr(&host_gdt));
}
static void vmx_load_host_state(struct vcpu_vmx *vmx)
@@ -1807,7 +1855,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
}
if (vmx->loaded_vmcs->cpu != cpu) {
- struct desc_ptr *gdt = &__get_cpu_var(host_gdt);
+ struct desc_ptr *gdt = this_cpu_ptr(&host_gdt);
unsigned long sysenter_esp;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
@@ -2135,7 +2183,7 @@ static u64 guest_read_tsc(void)
* Like guest_read_tsc, but always returns L1's notion of the timestamp
* counter, even if a nested guest (L2) is currently running.
*/
-u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
{
u64 tsc_offset;
@@ -2330,7 +2378,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
- CPU_BASED_PAUSE_EXITING |
+ CPU_BASED_PAUSE_EXITING | CPU_BASED_TPR_SHADOW |
CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
/*
* We can allow some features even when not supported by the
@@ -2351,12 +2399,13 @@ static __init void nested_vmx_setup_ctls_msrs(void)
nested_vmx_secondary_ctls_low = 0;
nested_vmx_secondary_ctls_high &=
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
- SECONDARY_EXEC_UNRESTRICTED_GUEST |
- SECONDARY_EXEC_WBINVD_EXITING;
+ SECONDARY_EXEC_WBINVD_EXITING |
+ SECONDARY_EXEC_XSAVES;
if (enable_ept) {
/* nested EPT: emulate EPT also to L1 */
- nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
+ nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT |
+ SECONDARY_EXEC_UNRESTRICTED_GUEST;
nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
VMX_EPT_INVEPT_BIT;
@@ -2532,6 +2581,11 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
if (!nested_vmx_allowed(vcpu))
return 1;
return vmx_get_vmx_msr(vcpu, msr_index, pdata);
+ case MSR_IA32_XSS:
+ if (!vmx_xsaves_supported())
+ return 1;
+ data = vcpu->arch.ia32_xss;
+ break;
case MSR_TSC_AUX:
if (!to_vmx(vcpu)->rdtscp_enabled)
return 1;
@@ -2601,6 +2655,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_CR_PAT:
if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
+ if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+ return 1;
vmcs_write64(GUEST_IA32_PAT, data);
vcpu->arch.pat = data;
break;
@@ -2621,6 +2677,22 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
return 1; /* they are read-only */
+ case MSR_IA32_XSS:
+ if (!vmx_xsaves_supported())
+ return 1;
+ /*
+ * The only supported bit as of Skylake is bit 8, but
+ * it is not supported on KVM.
+ */
+ if (data != 0)
+ return 1;
+ vcpu->arch.ia32_xss = data;
+ if (vcpu->arch.ia32_xss != host_xss)
+ add_atomic_switch_msr(vmx, MSR_IA32_XSS,
+ vcpu->arch.ia32_xss, host_xss);
+ else
+ clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
+ break;
case MSR_TSC_AUX:
if (!vmx->rdtscp_enabled)
return 1;
@@ -2631,12 +2703,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
default:
msr = find_msr_entry(vmx, msr_index);
if (msr) {
+ u64 old_msr_data = msr->data;
msr->data = data;
if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
preempt_disable();
- kvm_set_shared_msr(msr->index, msr->data,
- msr->mask);
+ ret = kvm_set_shared_msr(msr->index, msr->data,
+ msr->mask);
preempt_enable();
+ if (ret)
+ msr->data = old_msr_data;
}
break;
}
@@ -2704,7 +2779,7 @@ static void kvm_cpu_vmxon(u64 addr)
: "memory", "cc");
}
-static int hardware_enable(void *garbage)
+static int hardware_enable(void)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
@@ -2744,7 +2819,7 @@ static int hardware_enable(void *garbage)
ept_sync_global();
}
- native_store_gdt(&__get_cpu_var(host_gdt));
+ native_store_gdt(this_cpu_ptr(&host_gdt));
return 0;
}
@@ -2768,7 +2843,7 @@ static void kvm_cpu_vmxoff(void)
asm volatile (__ex(ASM_VMX_VMXOFF) : : : "cc");
}
-static void hardware_disable(void *garbage)
+static void hardware_disable(void)
{
if (vmm_exclusive) {
vmclear_local_loaded_vmcss();
@@ -2853,7 +2928,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
SECONDARY_EXEC_ENABLE_INVPCID |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
- SECONDARY_EXEC_SHADOW_VMCS;
+ SECONDARY_EXEC_SHADOW_VMCS |
+ SECONDARY_EXEC_XSAVES;
if (adjust_vmx_controls(min2, opt2,
MSR_IA32_VMX_PROCBASED_CTLS2,
&_cpu_based_2nd_exec_control) < 0)
@@ -2976,6 +3052,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
}
}
+ if (cpu_has_xsaves)
+ rdmsrl(MSR_IA32_XSS, host_xss);
+
return 0;
}
@@ -3079,68 +3158,6 @@ static __init int alloc_kvm_area(void)
return 0;
}
-static __init int hardware_setup(void)
-{
- if (setup_vmcs_config(&vmcs_config) < 0)
- return -EIO;
-
- if (boot_cpu_has(X86_FEATURE_NX))
- kvm_enable_efer_bits(EFER_NX);
-
- if (!cpu_has_vmx_vpid())
- enable_vpid = 0;
- if (!cpu_has_vmx_shadow_vmcs())
- enable_shadow_vmcs = 0;
- if (enable_shadow_vmcs)
- init_vmcs_shadow_fields();
-
- if (!cpu_has_vmx_ept() ||
- !cpu_has_vmx_ept_4levels()) {
- enable_ept = 0;
- enable_unrestricted_guest = 0;
- enable_ept_ad_bits = 0;
- }
-
- if (!cpu_has_vmx_ept_ad_bits())
- enable_ept_ad_bits = 0;
-
- if (!cpu_has_vmx_unrestricted_guest())
- enable_unrestricted_guest = 0;
-
- if (!cpu_has_vmx_flexpriority())
- flexpriority_enabled = 0;
-
- if (!cpu_has_vmx_tpr_shadow())
- kvm_x86_ops->update_cr8_intercept = NULL;
-
- if (enable_ept && !cpu_has_vmx_ept_2m_page())
- kvm_disable_largepages();
-
- if (!cpu_has_vmx_ple())
- ple_gap = 0;
-
- if (!cpu_has_vmx_apicv())
- enable_apicv = 0;
-
- if (enable_apicv)
- kvm_x86_ops->update_cr8_intercept = NULL;
- else {
- kvm_x86_ops->hwapic_irr_update = NULL;
- kvm_x86_ops->deliver_posted_interrupt = NULL;
- kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
- }
-
- if (nested)
- nested_vmx_setup_ctls_msrs();
-
- return alloc_kvm_area();
-}
-
-static __exit void hardware_unsetup(void)
-{
- free_kvm_area();
-}
-
static bool emulation_required(struct kvm_vcpu *vcpu)
{
return emulate_invalid_guest_state && !guest_state_valid(vcpu);
@@ -3905,7 +3922,7 @@ static int init_rmode_tss(struct kvm *kvm)
{
gfn_t fn;
u16 data = 0;
- int r, idx, ret = 0;
+ int idx, r;
idx = srcu_read_lock(&kvm->srcu);
fn = kvm->arch.tss_addr >> PAGE_SHIFT;
@@ -3927,32 +3944,32 @@ static int init_rmode_tss(struct kvm *kvm)
r = kvm_write_guest_page(kvm, fn, &data,
RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
sizeof(u8));
- if (r < 0)
- goto out;
-
- ret = 1;
out:
srcu_read_unlock(&kvm->srcu, idx);
- return ret;
+ return r;
}
static int init_rmode_identity_map(struct kvm *kvm)
{
- int i, idx, r, ret;
+ int i, idx, r = 0;
pfn_t identity_map_pfn;
u32 tmp;
if (!enable_ept)
- return 1;
- if (unlikely(!kvm->arch.ept_identity_pagetable)) {
- printk(KERN_ERR "EPT: identity-mapping pagetable "
- "haven't been allocated!\n");
return 0;
- }
+
+ /* Protect kvm->arch.ept_identity_pagetable_done. */
+ mutex_lock(&kvm->slots_lock);
+
if (likely(kvm->arch.ept_identity_pagetable_done))
- return 1;
- ret = 0;
+ goto out2;
+
identity_map_pfn = kvm->arch.ept_identity_map_addr >> PAGE_SHIFT;
+
+ r = alloc_identity_pagetable(kvm);
+ if (r < 0)
+ goto out2;
+
idx = srcu_read_lock(&kvm->srcu);
r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
if (r < 0)
@@ -3967,10 +3984,13 @@ static int init_rmode_identity_map(struct kvm *kvm)
goto out;
}
kvm->arch.ept_identity_pagetable_done = true;
- ret = 1;
+
out:
srcu_read_unlock(&kvm->srcu, idx);
- return ret;
+
+out2:
+ mutex_unlock(&kvm->slots_lock);
+ return r;
}
static void seg_setup(int seg)
@@ -3995,23 +4015,28 @@ static int alloc_apic_access_page(struct kvm *kvm)
int r = 0;
mutex_lock(&kvm->slots_lock);
- if (kvm->arch.apic_access_page)
+ if (kvm->arch.apic_access_page_done)
goto out;
kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
- kvm_userspace_mem.guest_phys_addr = 0xfee00000ULL;
+ kvm_userspace_mem.guest_phys_addr = APIC_DEFAULT_PHYS_BASE;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
if (r)
goto out;
- page = gfn_to_page(kvm, 0xfee00);
+ page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
if (is_error_page(page)) {
r = -EFAULT;
goto out;
}
- kvm->arch.apic_access_page = page;
+ /*
+ * Do not pin the page in memory, so that memory hot-unplug
+ * is able to migrate it.
+ */
+ put_page(page);
+ kvm->arch.apic_access_page_done = true;
out:
mutex_unlock(&kvm->slots_lock);
return r;
@@ -4019,31 +4044,20 @@ out:
static int alloc_identity_pagetable(struct kvm *kvm)
{
- struct page *page;
+ /* Called with kvm->slots_lock held. */
+
struct kvm_userspace_memory_region kvm_userspace_mem;
int r = 0;
- mutex_lock(&kvm->slots_lock);
- if (kvm->arch.ept_identity_pagetable)
- goto out;
+ BUG_ON(kvm->arch.ept_identity_pagetable_done);
+
kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
kvm_userspace_mem.flags = 0;
kvm_userspace_mem.guest_phys_addr =
kvm->arch.ept_identity_map_addr;
kvm_userspace_mem.memory_size = PAGE_SIZE;
r = __kvm_set_memory_region(kvm, &kvm_userspace_mem);
- if (r)
- goto out;
-
- page = gfn_to_page(kvm, kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
- if (is_error_page(page)) {
- r = -EFAULT;
- goto out;
- }
- kvm->arch.ept_identity_pagetable = page;
-out:
- mutex_unlock(&kvm->slots_lock);
return r;
}
@@ -4235,11 +4249,16 @@ static void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
u32 low32, high32;
unsigned long tmpl;
struct desc_ptr dt;
+ unsigned long cr4;
vmcs_writel(HOST_CR0, read_cr0() & ~X86_CR0_TS); /* 22.2.3 */
- vmcs_writel(HOST_CR4, read_cr4()); /* 22.2.3, 22.2.5 */
vmcs_writel(HOST_CR3, read_cr3()); /* 22.2.3 FIXME: shadow tables */
+ /* Save the most likely value for this task's CR4 in the VMCS. */
+ cr4 = read_cr4();
+ vmcs_writel(HOST_CR4, cr4); /* 22.2.3, 22.2.5 */
+ vmx->host_state.vmcs_host_cr4 = cr4;
+
vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS); /* 22.2.4 */
#ifdef CONFIG_X86_64
/*
@@ -4355,6 +4374,7 @@ static void ept_set_mmio_spte_mask(void)
kvm_mmu_set_mmio_spte_mask((0x3ull << 62) | 0x6ull);
}
+#define VMX_XSS_EXIT_BITMAP 0
/*
* Sets up the vmcs for emulated real mode.
*/
@@ -4402,7 +4422,8 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
if (ple_gap) {
vmcs_write32(PLE_GAP, ple_gap);
- vmcs_write32(PLE_WINDOW, ple_window);
+ vmx->ple_window = ple_window;
+ vmx->ple_window_dirty = true;
}
vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
@@ -4463,6 +4484,9 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
set_cr4_guest_host_mask(vmx);
+ if (vmx_xsaves_supported())
+ vmcs_write64(XSS_EXIT_BITMAP, VMX_XSS_EXIT_BITMAP);
+
return 0;
}
@@ -4477,7 +4501,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
kvm_set_cr8(&vmx->vcpu, 0);
- apic_base_msr.data = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+ apic_base_msr.data = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_bsp(&vmx->vcpu))
apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
apic_base_msr.host_initiated = true;
@@ -4537,9 +4561,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
vmcs_write32(TPR_THRESHOLD, 0);
}
- if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm))
- vmcs_write64(APIC_ACCESS_ADDR,
- page_to_phys(vmx->vcpu.kvm->arch.apic_access_page));
+ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
if (vmx_vm_has_apicv(vcpu->kvm))
memset(&vmx->pi_desc, 0, sizeof(struct pi_desc));
@@ -4729,10 +4751,7 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
if (ret)
return ret;
kvm->arch.tss_addr = addr;
- if (!init_rmode_tss(kvm))
- return -ENOMEM;
-
- return 0;
+ return init_rmode_tss(kvm);
}
static bool rmode_exception(struct kvm_vcpu *vcpu, int vec)
@@ -5126,13 +5145,20 @@ static int handle_cr(struct kvm_vcpu *vcpu)
static int handle_dr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification;
- int dr, reg;
+ int dr, dr7, reg;
+
+ exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+ dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
+
+ /* First, if DR does not exist, trigger UD */
+ if (!kvm_require_dr(vcpu, dr))
+ return 1;
/* Do not handle if the CPL > 0, will trigger GP on re-entry */
if (!kvm_require_cpl(vcpu, 0))
return 1;
- dr = vmcs_readl(GUEST_DR7);
- if (dr & DR7_GD) {
+ dr7 = vmcs_readl(GUEST_DR7);
+ if (dr7 & DR7_GD) {
/*
* As the vm-exit takes precedence over the debug trap, we
* need to emulate the latter, either for the host or the
@@ -5140,17 +5166,14 @@ static int handle_dr(struct kvm_vcpu *vcpu)
*/
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
vcpu->run->debug.arch.dr6 = vcpu->arch.dr6;
- vcpu->run->debug.arch.dr7 = dr;
- vcpu->run->debug.arch.pc =
- vmcs_readl(GUEST_CS_BASE) +
- vmcs_readl(GUEST_RIP);
+ vcpu->run->debug.arch.dr7 = dr7;
+ vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu);
vcpu->run->debug.arch.exception = DB_VECTOR;
vcpu->run->exit_reason = KVM_EXIT_DEBUG;
return 0;
} else {
- vcpu->arch.dr7 &= ~DR7_GD;
+ vcpu->arch.dr6 &= ~15;
vcpu->arch.dr6 |= DR6_BD | DR6_RTM;
- vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
kvm_queue_exception(vcpu, DB_VECTOR);
return 1;
}
@@ -5172,8 +5195,6 @@ static int handle_dr(struct kvm_vcpu *vcpu)
return 1;
}
- exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
reg = DEBUG_REG_ACCESS_REG(exit_qualification);
if (exit_qualification & TYPE_MOV_FROM_DR) {
unsigned long val;
@@ -5257,7 +5278,7 @@ static int handle_wrmsr(struct kvm_vcpu *vcpu)
msr.data = data;
msr.index = ecx;
msr.host_initiated = false;
- if (vmx_set_msr(vcpu, &msr) != 0) {
+ if (kvm_set_msr(vcpu, &msr) != 0) {
trace_kvm_msr_write_ex(ecx, data);
kvm_inject_gp(vcpu, 0);
return 1;
@@ -5354,6 +5375,20 @@ static int handle_xsetbv(struct kvm_vcpu *vcpu)
return 1;
}
+static int handle_xsaves(struct kvm_vcpu *vcpu)
+{
+ skip_emulated_instruction(vcpu);
+ WARN(1, "this should never happen\n");
+ return 1;
+}
+
+static int handle_xrstors(struct kvm_vcpu *vcpu)
+{
+ skip_emulated_instruction(vcpu);
+ WARN(1, "this should never happen\n");
+ return 1;
+}
+
static int handle_apic_access(struct kvm_vcpu *vcpu)
{
if (likely(fasteoi)) {
@@ -5455,7 +5490,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
}
/* clear all local breakpoint enable flags */
- vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55);
+ vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x155);
/*
* TODO: What about debug traps on tss switch?
@@ -5502,11 +5537,11 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
trace_kvm_page_fault(gpa, exit_qualification);
/* It is a write fault? */
- error_code = exit_qualification & (1U << 1);
+ error_code = exit_qualification & PFERR_WRITE_MASK;
/* It is a fetch fault? */
- error_code |= (exit_qualification & (1U << 2)) << 2;
+ error_code |= (exit_qualification << 2) & PFERR_FETCH_MASK;
/* ept page table is present? */
- error_code |= (exit_qualification >> 3) & 0x1;
+ error_code |= (exit_qualification >> 3) & PFERR_PRESENT_MASK;
vcpu->arch.exit_qualification = exit_qualification;
@@ -5521,17 +5556,18 @@ static u64 ept_rsvd_mask(u64 spte, int level)
for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
mask |= (1ULL << i);
- if (level > 2)
+ if (level == 4)
/* bits 7:3 reserved */
mask |= 0xf8;
- else if (level == 2) {
- if (spte & (1ULL << 7))
- /* 2MB ref, bits 20:12 reserved */
- mask |= 0x1ff000;
- else
- /* bits 6:3 reserved */
- mask |= 0x78;
- }
+ else if (spte & (1ULL << 7))
+ /*
+ * 1GB/2MB page, bits 29:12 or 20:12 reserved respectively,
+ * level == 1 if the hypervisor is using the ignored bit 7.
+ */
+ mask |= (PAGE_SIZE << ((level - 1) * 9)) - PAGE_SIZE;
+ else if (level > 1)
+ /* bits 6:3 reserved */
+ mask |= 0x78;
return mask;
}
@@ -5561,7 +5597,8 @@ static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
WARN_ON(1);
}
- if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) {
+ /* bits 5:3 are _not_ reserved for large page or leaf page */
+ if ((rsvd_bits & 0x38) == 0) {
u64 ept_mem_type = (spte & 0x38) >> 3;
if (ept_mem_type == 2 || ept_mem_type == 3 ||
@@ -5676,12 +5713,283 @@ out:
return ret;
}
+static int __grow_ple_window(int val)
+{
+ if (ple_window_grow < 1)
+ return ple_window;
+
+ val = min(val, ple_window_actual_max);
+
+ if (ple_window_grow < ple_window)
+ val *= ple_window_grow;
+ else
+ val += ple_window_grow;
+
+ return val;
+}
+
+static int __shrink_ple_window(int val, int modifier, int minimum)
+{
+ if (modifier < 1)
+ return ple_window;
+
+ if (modifier < ple_window)
+ val /= modifier;
+ else
+ val -= modifier;
+
+ return max(val, minimum);
+}
+
+static void grow_ple_window(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int old = vmx->ple_window;
+
+ vmx->ple_window = __grow_ple_window(old);
+
+ if (vmx->ple_window != old)
+ vmx->ple_window_dirty = true;
+
+ trace_kvm_ple_window_grow(vcpu->vcpu_id, vmx->ple_window, old);
+}
+
+static void shrink_ple_window(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ int old = vmx->ple_window;
+
+ vmx->ple_window = __shrink_ple_window(old,
+ ple_window_shrink, ple_window);
+
+ if (vmx->ple_window != old)
+ vmx->ple_window_dirty = true;
+
+ trace_kvm_ple_window_shrink(vcpu->vcpu_id, vmx->ple_window, old);
+}
+
+/*
+ * ple_window_actual_max is computed to be one grow_ple_window() below
+ * ple_window_max. (See __grow_ple_window for the reason.)
+ * This prevents overflows, because ple_window_max is int.
+ * ple_window_max effectively rounded down to a multiple of ple_window_grow in
+ * this process.
+ * ple_window_max is also prevented from setting vmx->ple_window < ple_window.
+ */
+static void update_ple_window_actual_max(void)
+{
+ ple_window_actual_max =
+ __shrink_ple_window(max(ple_window_max, ple_window),
+ ple_window_grow, INT_MIN);
+}
+
+static __init int hardware_setup(void)
+{
+ int r = -ENOMEM, i, msr;
+
+ rdmsrl_safe(MSR_EFER, &host_efer);
+
+ for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
+ kvm_define_shared_msr(i, vmx_msr_index[i]);
+
+ vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_io_bitmap_a)
+ return r;
+
+ vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_io_bitmap_b)
+ goto out;
+
+ vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_msr_bitmap_legacy)
+ goto out1;
+
+ vmx_msr_bitmap_legacy_x2apic =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_msr_bitmap_legacy_x2apic)
+ goto out2;
+
+ vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_msr_bitmap_longmode)
+ goto out3;
+
+ vmx_msr_bitmap_longmode_x2apic =
+ (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_msr_bitmap_longmode_x2apic)
+ goto out4;
+ vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_vmread_bitmap)
+ goto out5;
+
+ vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
+ if (!vmx_vmwrite_bitmap)
+ goto out6;
+
+ memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
+ memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
+
+ /*
+ * Allow direct access to the PC debug port (it is often used for I/O
+ * delays, but the vmexits simply slow things down).
+ */
+ memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
+ clear_bit(0x80, vmx_io_bitmap_a);
+
+ memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
+
+ memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
+ memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
+
+ if (setup_vmcs_config(&vmcs_config) < 0) {
+ r = -EIO;
+ goto out7;
+ }
+
+ if (boot_cpu_has(X86_FEATURE_NX))
+ kvm_enable_efer_bits(EFER_NX);
+
+ if (!cpu_has_vmx_vpid())
+ enable_vpid = 0;
+ if (!cpu_has_vmx_shadow_vmcs())
+ enable_shadow_vmcs = 0;
+ if (enable_shadow_vmcs)
+ init_vmcs_shadow_fields();
+
+ if (!cpu_has_vmx_ept() ||
+ !cpu_has_vmx_ept_4levels()) {
+ enable_ept = 0;
+ enable_unrestricted_guest = 0;
+ enable_ept_ad_bits = 0;
+ }
+
+ if (!cpu_has_vmx_ept_ad_bits())
+ enable_ept_ad_bits = 0;
+
+ if (!cpu_has_vmx_unrestricted_guest())
+ enable_unrestricted_guest = 0;
+
+ if (!cpu_has_vmx_flexpriority()) {
+ flexpriority_enabled = 0;
+
+ /*
+ * set_apic_access_page_addr() is used to reload apic access
+ * page upon invalidation. No need to do anything if the
+ * processor does not have the APIC_ACCESS_ADDR VMCS field.
+ */
+ kvm_x86_ops->set_apic_access_page_addr = NULL;
+ }
+
+ if (!cpu_has_vmx_tpr_shadow())
+ kvm_x86_ops->update_cr8_intercept = NULL;
+
+ if (enable_ept && !cpu_has_vmx_ept_2m_page())
+ kvm_disable_largepages();
+
+ if (!cpu_has_vmx_ple())
+ ple_gap = 0;
+
+ if (!cpu_has_vmx_apicv())
+ enable_apicv = 0;
+
+ if (enable_apicv)
+ kvm_x86_ops->update_cr8_intercept = NULL;
+ else {
+ kvm_x86_ops->hwapic_irr_update = NULL;
+ kvm_x86_ops->deliver_posted_interrupt = NULL;
+ kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
+ }
+
+ if (nested)
+ nested_vmx_setup_ctls_msrs();
+
+ vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
+ vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
+ vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
+ vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
+ vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
+ vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
+ vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
+
+ memcpy(vmx_msr_bitmap_legacy_x2apic,
+ vmx_msr_bitmap_legacy, PAGE_SIZE);
+ memcpy(vmx_msr_bitmap_longmode_x2apic,
+ vmx_msr_bitmap_longmode, PAGE_SIZE);
+
+ if (enable_apicv) {
+ for (msr = 0x800; msr <= 0x8ff; msr++)
+ vmx_disable_intercept_msr_read_x2apic(msr);
+
+ /* According SDM, in x2apic mode, the whole id reg is used.
+ * But in KVM, it only use the highest eight bits. Need to
+ * intercept it */
+ vmx_enable_intercept_msr_read_x2apic(0x802);
+ /* TMCCT */
+ vmx_enable_intercept_msr_read_x2apic(0x839);
+ /* TPR */
+ vmx_disable_intercept_msr_write_x2apic(0x808);
+ /* EOI */
+ vmx_disable_intercept_msr_write_x2apic(0x80b);
+ /* SELF-IPI */
+ vmx_disable_intercept_msr_write_x2apic(0x83f);
+ }
+
+ if (enable_ept) {
+ kvm_mmu_set_mask_ptes(0ull,
+ (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
+ (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
+ 0ull, VMX_EPT_EXECUTABLE_MASK);
+ ept_set_mmio_spte_mask();
+ kvm_enable_tdp();
+ } else
+ kvm_disable_tdp();
+
+ update_ple_window_actual_max();
+
+ return alloc_kvm_area();
+
+out7:
+ free_page((unsigned long)vmx_vmwrite_bitmap);
+out6:
+ free_page((unsigned long)vmx_vmread_bitmap);
+out5:
+ free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
+out4:
+ free_page((unsigned long)vmx_msr_bitmap_longmode);
+out3:
+ free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+out2:
+ free_page((unsigned long)vmx_msr_bitmap_legacy);
+out1:
+ free_page((unsigned long)vmx_io_bitmap_b);
+out:
+ free_page((unsigned long)vmx_io_bitmap_a);
+
+ return r;
+}
+
+static __exit void hardware_unsetup(void)
+{
+ free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
+ free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
+ free_page((unsigned long)vmx_msr_bitmap_legacy);
+ free_page((unsigned long)vmx_msr_bitmap_longmode);
+ free_page((unsigned long)vmx_io_bitmap_b);
+ free_page((unsigned long)vmx_io_bitmap_a);
+ free_page((unsigned long)vmx_vmwrite_bitmap);
+ free_page((unsigned long)vmx_vmread_bitmap);
+
+ free_kvm_area();
+}
+
/*
* Indicate a busy-waiting vcpu in spinlock. We do not enable the PAUSE
* exiting, so only get here on cpu with PAUSE-Loop-Exiting.
*/
static int handle_pause(struct kvm_vcpu *vcpu)
{
+ if (ple_gap)
+ grow_ple_window(vcpu);
+
skip_emulated_instruction(vcpu);
kvm_vcpu_on_spin(vcpu);
@@ -6146,7 +6454,11 @@ static void free_nested(struct vcpu_vmx *vmx)
/* Unpin physical memory we referred to in current vmcs02 */
if (vmx->nested.apic_access_page) {
nested_release_page(vmx->nested.apic_access_page);
- vmx->nested.apic_access_page = 0;
+ vmx->nested.apic_access_page = NULL;
+ }
+ if (vmx->nested.virtual_apic_page) {
+ nested_release_page(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page = NULL;
}
nested_free_all_saved_vmcss(vmx);
@@ -6245,58 +6557,60 @@ static inline int vmcs_field_readonly(unsigned long field)
* some of the bits we return here (e.g., on 32-bit guests, only 32 bits of
* 64-bit fields are to be returned).
*/
-static inline bool vmcs12_read_any(struct kvm_vcpu *vcpu,
- unsigned long field, u64 *ret)
+static inline int vmcs12_read_any(struct kvm_vcpu *vcpu,
+ unsigned long field, u64 *ret)
{
short offset = vmcs_field_to_offset(field);
char *p;
if (offset < 0)
- return 0;
+ return offset;
p = ((char *)(get_vmcs12(vcpu))) + offset;
switch (vmcs_field_type(field)) {
case VMCS_FIELD_TYPE_NATURAL_WIDTH:
*ret = *((natural_width *)p);
- return 1;
+ return 0;
case VMCS_FIELD_TYPE_U16:
*ret = *((u16 *)p);
- return 1;
+ return 0;
case VMCS_FIELD_TYPE_U32:
*ret = *((u32 *)p);
- return 1;
+ return 0;
case VMCS_FIELD_TYPE_U64:
*ret = *((u64 *)p);
- return 1;
+ return 0;
default:
- return 0; /* can never happen. */
+ WARN_ON(1);
+ return -ENOENT;
}
}
-static inline bool vmcs12_write_any(struct kvm_vcpu *vcpu,
- unsigned long field, u64 field_value){
+static inline int vmcs12_write_any(struct kvm_vcpu *vcpu,
+ unsigned long field, u64 field_value){
short offset = vmcs_field_to_offset(field);
char *p = ((char *) get_vmcs12(vcpu)) + offset;
if (offset < 0)
- return false;
+ return offset;
switch (vmcs_field_type(field)) {
case VMCS_FIELD_TYPE_U16:
*(u16 *)p = field_value;
- return true;
+ return 0;
case VMCS_FIELD_TYPE_U32:
*(u32 *)p = field_value;
- return true;
+ return 0;
case VMCS_FIELD_TYPE_U64:
*(u64 *)p = field_value;
- return true;
+ return 0;
case VMCS_FIELD_TYPE_NATURAL_WIDTH:
*(natural_width *)p = field_value;
- return true;
+ return 0;
default:
- return false; /* can never happen. */
+ WARN_ON(1);
+ return -ENOENT;
}
}
@@ -6310,6 +6624,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
const unsigned long *fields = shadow_read_write_fields;
const int num_fields = max_shadow_read_write_fields;
+ preempt_disable();
+
vmcs_load(shadow_vmcs);
for (i = 0; i < num_fields; i++) {
@@ -6327,12 +6643,17 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
case VMCS_FIELD_TYPE_NATURAL_WIDTH:
field_value = vmcs_readl(field);
break;
+ default:
+ WARN_ON(1);
+ continue;
}
vmcs12_write_any(&vmx->vcpu, field, field_value);
}
vmcs_clear(shadow_vmcs);
vmcs_load(vmx->loaded_vmcs->vmcs);
+
+ preempt_enable();
}
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
@@ -6370,6 +6691,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
case VMCS_FIELD_TYPE_NATURAL_WIDTH:
vmcs_writel(field, (long)field_value);
break;
+ default:
+ WARN_ON(1);
+ break;
}
}
}
@@ -6408,7 +6732,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
/* Decode instruction info and find the field to read */
field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
/* Read the field, zero-extended to a u64 field_value */
- if (!vmcs12_read_any(vcpu, field, &field_value)) {
+ if (vmcs12_read_any(vcpu, field, &field_value) < 0) {
nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
skip_emulated_instruction(vcpu);
return 1;
@@ -6478,7 +6802,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
return 1;
}
- if (!vmcs12_write_any(vcpu, field, field_value)) {
+ if (vmcs12_write_any(vcpu, field, field_value) < 0) {
nested_vmx_failValid(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
skip_emulated_instruction(vcpu);
return 1;
@@ -6617,7 +6941,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
switch (type) {
case VMX_EPT_EXTENT_GLOBAL:
kvm_mmu_sync_roots(vcpu);
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
nested_vmx_succeed(vcpu);
break;
default:
@@ -6630,6 +6954,12 @@ static int handle_invept(struct kvm_vcpu *vcpu)
return 1;
}
+static int handle_invvpid(struct kvm_vcpu *vcpu)
+{
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -6675,6 +7005,9 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait,
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor,
[EXIT_REASON_INVEPT] = handle_invept,
+ [EXIT_REASON_INVVPID] = handle_invvpid,
+ [EXIT_REASON_XSAVES] = handle_xsaves,
+ [EXIT_REASON_XRSTORS] = handle_xrstors,
};
static const int kvm_vmx_max_exit_handlers =
@@ -6892,6 +7225,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_TASK_SWITCH:
return 1;
case EXIT_REASON_CPUID:
+ if (kvm_register_read(vcpu, VCPU_REGS_RAX) == 0xa)
+ return 0;
return 1;
case EXIT_REASON_HLT:
return nested_cpu_has(vmcs12, CPU_BASED_HLT_EXITING);
@@ -6908,7 +7243,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
- case EXIT_REASON_INVEPT:
+ case EXIT_REASON_INVEPT: case EXIT_REASON_INVVPID:
/*
* VMX instructions trap unconditionally. This allows L1 to
* emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6936,7 +7271,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_MCE_DURING_VMENTRY:
return 0;
case EXIT_REASON_TPR_BELOW_THRESHOLD:
- return 1;
+ return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
case EXIT_REASON_APIC_ACCESS:
return nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
@@ -6960,6 +7295,14 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_WBINVD_EXITING);
case EXIT_REASON_XSETBV:
return 1;
+ case EXIT_REASON_XSAVES: case EXIT_REASON_XRSTORS:
+ /*
+ * This should never happen, since it is not possible to
+ * set XSS to a non-zero value---neither in L1 nor in L2.
+ * If if it were, XSS would have to be checked against
+ * the XSS exit bitmap in vmcs12.
+ */
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
default:
return 1;
}
@@ -7049,14 +7392,20 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
&& kvm_vmx_exit_handlers[exit_reason])
return kvm_vmx_exit_handlers[exit_reason](vcpu);
else {
- vcpu->run->exit_reason = KVM_EXIT_UNKNOWN;
- vcpu->run->hw.hardware_exit_reason = exit_reason;
+ WARN_ONCE(1, "vmx: unexpected exit reason 0x%x\n", exit_reason);
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
}
- return 0;
}
static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ if (is_guest_mode(vcpu) &&
+ nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+ return;
+
if (irr == -1 || tpr < irr) {
vmcs_write32(TPR_THRESHOLD, 0);
return;
@@ -7094,6 +7443,29 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
vmx_set_msr_bitmap(vcpu);
}
+static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * Currently we do not handle the nested case where L2 has an
+ * APIC access page of its own; that page is still pinned.
+ * Hence, we skip the case where the VCPU is in guest mode _and_
+ * L1 prepared an APIC access page for L2.
+ *
+ * For the case where L1 and L2 share the same APIC access page
+ * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear
+ * in the vmcs12), this function will only update either the vmcs01
+ * or the vmcs02. If the former, the vmcs02 will be updated by
+ * prepare_vmcs02. If the latter, the vmcs01 will be updated in
+ * the next L2->L1 exit.
+ */
+ if (!is_guest_mode(vcpu) ||
+ !nested_cpu_has2(vmx->nested.current_vmcs12,
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+ vmcs_write64(APIC_ACCESS_ADDR, hpa);
+}
+
static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
{
u16 status;
@@ -7119,6 +7491,9 @@ static void vmx_set_rvi(int vector)
u16 status;
u8 old;
+ if (vector == -1)
+ vector = 0;
+
status = vmcs_read16(GUEST_INTR_STATUS);
old = (u8)status & 0xff;
if ((u8)vector != old) {
@@ -7130,22 +7505,23 @@ static void vmx_set_rvi(int vector)
static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
{
+ if (!is_guest_mode(vcpu)) {
+ vmx_set_rvi(max_irr);
+ return;
+ }
+
if (max_irr == -1)
return;
/*
- * If a vmexit is needed, vmx_check_nested_events handles it.
+ * In guest mode. If a vmexit is needed, vmx_check_nested_events
+ * handles it.
*/
- if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+ if (nested_exit_on_intr(vcpu))
return;
- if (!is_guest_mode(vcpu)) {
- vmx_set_rvi(max_irr);
- return;
- }
-
/*
- * Fall back to pre-APICv interrupt injection since L2
+ * Else, fall back to pre-APICv interrupt injection since L2
* is run without virtual interrupt delivery.
*/
if (!kvm_event_needs_reinjection(vcpu) &&
@@ -7242,6 +7618,12 @@ static bool vmx_mpx_supported(void)
(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_BNDCFGS);
}
+static bool vmx_xsaves_supported(void)
+{
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_XSAVES;
+}
+
static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
{
u32 exit_intr_info;
@@ -7376,7 +7758,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long debugctlmsr;
+ unsigned long debugctlmsr, cr4;
/* Record the guest's net vcpu time for enforced NMI injections. */
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
@@ -7387,6 +7769,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (vmx->emulation_required)
return;
+ if (vmx->ple_window_dirty) {
+ vmx->ple_window_dirty = false;
+ vmcs_write32(PLE_WINDOW, vmx->ple_window);
+ }
+
if (vmx->nested.sync_shadow_vmcs) {
copy_vmcs12_to_shadow(vmx);
vmx->nested.sync_shadow_vmcs = false;
@@ -7397,6 +7784,12 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
+ cr4 = read_cr4();
+ if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+ vmcs_writel(HOST_CR4, cr4);
+ vmx->host_state.vmcs_host_cr4 = cr4;
+ }
+
/* When single-stepping over STI and MOV SS, we must clear the
* corresponding interruptibility bits in the guest state. Otherwise
* vmentry fails as it then expects bit 14 (BS) in pending debug
@@ -7642,10 +8035,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
if (!kvm->arch.ept_identity_map_addr)
kvm->arch.ept_identity_map_addr =
VMX_EPT_IDENTITY_PAGETABLE_ADDR;
- err = -ENOMEM;
- if (alloc_identity_pagetable(kvm) != 0)
- goto free_vmcs;
- if (!init_rmode_identity_map(kvm))
+ err = init_rmode_identity_map(kvm);
+ if (err)
goto free_vmcs;
}
@@ -7824,6 +8215,55 @@ static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
kvm_inject_page_fault(vcpu, fault);
}
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /* TODO: Also verify bits beyond physical address width are 0 */
+ if (!PAGE_ALIGNED(vmcs12->apic_access_addr))
+ return false;
+
+ /*
+ * Translate L1 physical address to host physical
+ * address for vmcs02. Keep the page pinned, so this
+ * physical address remains valid. We keep a reference
+ * to it so we can release it later.
+ */
+ if (vmx->nested.apic_access_page) /* shouldn't happen */
+ nested_release_page(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page =
+ nested_get_page(vcpu, vmcs12->apic_access_addr);
+ }
+
+ if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) {
+ /* TODO: Also verify bits beyond physical address width are 0 */
+ if (!PAGE_ALIGNED(vmcs12->virtual_apic_page_addr))
+ return false;
+
+ if (vmx->nested.virtual_apic_page) /* shouldn't happen */
+ nested_release_page(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page =
+ nested_get_page(vcpu, vmcs12->virtual_apic_page_addr);
+
+ /*
+ * Failing the vm entry is _not_ what the processor does
+ * but it's basically the only possibility we have.
+ * We could still enter the guest if CR8 load exits are
+ * enabled, CR8 store exits are enabled, and virtualize APIC
+ * access is disabled; in this case the processor would never
+ * use the TPR shadow and we could simply clear the bit from
+ * the execution control. But such a configuration is useless,
+ * so let's keep the code simple.
+ */
+ if (!vmx->nested.virtual_apic_page)
+ return false;
+ }
+
+ return true;
+}
+
static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
{
u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
@@ -7849,7 +8289,7 @@ static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
/*
* prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
* L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
- * with L0's requirements for its guest (a.k.a. vmsc01), so we can run the L2
+ * with L0's requirements for its guest (a.k.a. vmcs01), so we can run the L2
* guest in a way that will both be appropriate to L1's requests, and our
* needs. In addition to modifying the active vmcs (which is vmcs02), this
* function also has additional necessary side-effects, like setting various
@@ -7919,6 +8359,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+ if (nested_cpu_has_xsaves(vmcs12))
+ vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
vmcs_write64(VMCS_LINK_POINTER, -1ull);
exec_control = vmcs12->pin_based_vm_exec_control;
@@ -7970,16 +8412,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (exec_control & SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) {
/*
- * Translate L1 physical address to host physical
- * address for vmcs02. Keep the page pinned, so this
- * physical address remains valid. We keep a reference
- * to it so we can release it later.
- */
- if (vmx->nested.apic_access_page) /* shouldn't happen */
- nested_release_page(vmx->nested.apic_access_page);
- vmx->nested.apic_access_page =
- nested_get_page(vcpu, vmcs12->apic_access_addr);
- /*
* If translation failed, no matter: This feature asks
* to exit when accessing the given address, and if it
* can never be accessed, this feature won't do
@@ -7994,8 +8426,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
} else if (vm_need_virtualize_apic_accesses(vmx->vcpu.kvm)) {
exec_control |=
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
- vmcs_write64(APIC_ACCESS_ADDR,
- page_to_phys(vcpu->kvm->arch.apic_access_page));
+ kvm_vcpu_reload_apic_access_page(vcpu);
}
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
@@ -8024,6 +8455,13 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
exec_control &= ~CPU_BASED_TPR_SHADOW;
exec_control |= vmcs12->cpu_based_vm_exec_control;
+
+ if (exec_control & CPU_BASED_TPR_SHADOW) {
+ vmcs_write64(VIRTUAL_APIC_PAGE_ADDR,
+ page_to_phys(vmx->nested.virtual_apic_page));
+ vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
+ }
+
/*
* Merging of IO and MSR bitmaps not currently supported.
* Rather, exit every time.
@@ -8185,8 +8623,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
return 1;
}
- if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
- !PAGE_ALIGNED(vmcs12->apic_access_addr)) {
+ if (!nested_get_vmcs12_pages(vcpu, vmcs12)) {
/*TODO: Also verify bits beyond physical address width are 0*/
nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
return 1;
@@ -8564,6 +9001,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
if (vmx_mpx_supported())
vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+ if (nested_cpu_has_xsaves(vmcs12))
+ vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
/* update exit information fields: */
@@ -8790,8 +9229,18 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
/* Unpin physical memory we referred to in vmcs02 */
if (vmx->nested.apic_access_page) {
nested_release_page(vmx->nested.apic_access_page);
- vmx->nested.apic_access_page = 0;
+ vmx->nested.apic_access_page = NULL;
}
+ if (vmx->nested.virtual_apic_page) {
+ nested_release_page(vmx->nested.virtual_apic_page);
+ vmx->nested.virtual_apic_page = NULL;
+ }
+
+ /*
+ * We are now running in L2, mmu_notifier will force to reload the
+ * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
+ */
+ kvm_vcpu_reload_apic_access_page(vcpu);
/*
* Exiting from L2 to L1, we're now back to L1 which thinks it just
@@ -8846,6 +9295,12 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu,
return X86EMUL_CONTINUE;
}
+static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+ if (ple_gap)
+ shrink_ple_window(vcpu);
+}
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
@@ -8890,7 +9345,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
.cache_reg = vmx_cache_reg,
.get_rflags = vmx_get_rflags,
.set_rflags = vmx_set_rflags,
- .fpu_activate = vmx_fpu_activate,
.fpu_deactivate = vmx_fpu_deactivate,
.tlb_flush = vmx_flush_tlb,
@@ -8913,6 +9367,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
.set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode,
+ .set_apic_access_page_addr = vmx_set_apic_access_page_addr,
.vm_has_apicv = vmx_vm_has_apicv,
.load_eoi_exitmap = vmx_load_eoi_exitmap,
.hwapic_irr_update = vmx_hwapic_irr_update,
@@ -8949,156 +9404,32 @@ static struct kvm_x86_ops vmx_x86_ops = {
.check_intercept = vmx_check_intercept,
.handle_external_intr = vmx_handle_external_intr,
.mpx_supported = vmx_mpx_supported,
+ .xsaves_supported = vmx_xsaves_supported,
.check_nested_events = vmx_check_nested_events,
+
+ .sched_in = vmx_sched_in,
};
static int __init vmx_init(void)
{
- int r, i, msr;
-
- rdmsrl_safe(MSR_EFER, &host_efer);
-
- for (i = 0; i < ARRAY_SIZE(vmx_msr_index); ++i)
- kvm_define_shared_msr(i, vmx_msr_index[i]);
-
- vmx_io_bitmap_a = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_io_bitmap_a)
- return -ENOMEM;
-
- r = -ENOMEM;
-
- vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_io_bitmap_b)
- goto out;
-
- vmx_msr_bitmap_legacy = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_legacy)
- goto out1;
-
- vmx_msr_bitmap_legacy_x2apic =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_legacy_x2apic)
- goto out2;
-
- vmx_msr_bitmap_longmode = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_longmode)
- goto out3;
-
- vmx_msr_bitmap_longmode_x2apic =
- (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_msr_bitmap_longmode_x2apic)
- goto out4;
- vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_vmread_bitmap)
- goto out5;
-
- vmx_vmwrite_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL);
- if (!vmx_vmwrite_bitmap)
- goto out6;
-
- memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
- memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
-
- /*
- * Allow direct access to the PC debug port (it is often used for I/O
- * delays, but the vmexits simply slow things down).
- */
- memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
- clear_bit(0x80, vmx_io_bitmap_a);
-
- memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
-
- memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE);
- memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE);
-
- set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
-
- r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
- __alignof__(struct vcpu_vmx), THIS_MODULE);
+ int r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+ __alignof__(struct vcpu_vmx), THIS_MODULE);
if (r)
- goto out7;
+ return r;
#ifdef CONFIG_KEXEC
rcu_assign_pointer(crash_vmclear_loaded_vmcss,
crash_vmclear_local_loaded_vmcss);
#endif
- vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
- vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
- vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
- vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
- vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
-
- memcpy(vmx_msr_bitmap_legacy_x2apic,
- vmx_msr_bitmap_legacy, PAGE_SIZE);
- memcpy(vmx_msr_bitmap_longmode_x2apic,
- vmx_msr_bitmap_longmode, PAGE_SIZE);
-
- if (enable_apicv) {
- for (msr = 0x800; msr <= 0x8ff; msr++)
- vmx_disable_intercept_msr_read_x2apic(msr);
-
- /* According SDM, in x2apic mode, the whole id reg is used.
- * But in KVM, it only use the highest eight bits. Need to
- * intercept it */
- vmx_enable_intercept_msr_read_x2apic(0x802);
- /* TMCCT */
- vmx_enable_intercept_msr_read_x2apic(0x839);
- /* TPR */
- vmx_disable_intercept_msr_write_x2apic(0x808);
- /* EOI */
- vmx_disable_intercept_msr_write_x2apic(0x80b);
- /* SELF-IPI */
- vmx_disable_intercept_msr_write_x2apic(0x83f);
- }
-
- if (enable_ept) {
- kvm_mmu_set_mask_ptes(0ull,
- (enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
- (enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
- 0ull, VMX_EPT_EXECUTABLE_MASK);
- ept_set_mmio_spte_mask();
- kvm_enable_tdp();
- } else
- kvm_disable_tdp();
-
return 0;
-
-out7:
- free_page((unsigned long)vmx_vmwrite_bitmap);
-out6:
- free_page((unsigned long)vmx_vmread_bitmap);
-out5:
- free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
-out4:
- free_page((unsigned long)vmx_msr_bitmap_longmode);
-out3:
- free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
-out2:
- free_page((unsigned long)vmx_msr_bitmap_legacy);
-out1:
- free_page((unsigned long)vmx_io_bitmap_b);
-out:
- free_page((unsigned long)vmx_io_bitmap_a);
- return r;
}
static void __exit vmx_exit(void)
{
- free_page((unsigned long)vmx_msr_bitmap_legacy_x2apic);
- free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic);
- free_page((unsigned long)vmx_msr_bitmap_legacy);
- free_page((unsigned long)vmx_msr_bitmap_longmode);
- free_page((unsigned long)vmx_io_bitmap_b);
- free_page((unsigned long)vmx_io_bitmap_a);
- free_page((unsigned long)vmx_vmwrite_bitmap);
- free_page((unsigned long)vmx_vmread_bitmap);
-
#ifdef CONFIG_KEXEC
- rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL);
+ RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
synchronize_rcu();
#endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f1e22d3b286..c259814200bd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -27,6 +27,7 @@
#include "kvm_cache_regs.h"
#include "x86.h"
#include "cpuid.h"
+#include "assigned-dev.h"
#include <linux/clocksource.h>
#include <linux/interrupt.h>
@@ -229,24 +230,29 @@ static void kvm_shared_msr_cpu_online(void)
shared_msr_update(i, shared_msrs_global.msrs[i]);
}
-void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+int kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
+ int err;
if (((value ^ smsr->values[slot].curr) & mask) == 0)
- return;
+ return 0;
smsr->values[slot].curr = value;
- wrmsrl(shared_msrs_global.msrs[slot], value);
+ err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
+ if (err)
+ return 1;
+
if (!smsr->registered) {
smsr->urn.on_user_return = kvm_on_user_return;
user_return_notifier_register(&smsr->urn);
smsr->registered = true;
}
+ return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
-static void drop_user_return_notifiers(void *ignore)
+static void drop_user_return_notifiers(void)
{
unsigned int cpu = smp_processor_id();
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
@@ -348,6 +354,8 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
if (!vcpu->arch.exception.pending) {
queue:
+ if (has_error && !is_protmode(vcpu))
+ has_error = false;
vcpu->arch.exception.pending = true;
vcpu->arch.exception.has_error_code = has_error;
vcpu->arch.exception.nr = nr;
@@ -408,12 +416,14 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
}
EXPORT_SYMBOL_GPL(kvm_inject_page_fault);
-void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+static bool kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
else
vcpu->arch.mmu.inject_page_fault(vcpu, fault);
+
+ return fault->nested_page_fault;
}
void kvm_inject_nmi(struct kvm_vcpu *vcpu)
@@ -448,6 +458,16 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl)
}
EXPORT_SYMBOL_GPL(kvm_require_cpl);
+bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr)
+{
+ if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+ return true;
+
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return false;
+}
+EXPORT_SYMBOL_GPL(kvm_require_dr);
+
/*
* This function will be used to read from the physical memory of the currently
* running guest. The difference to kvm_read_guest_page is that this function
@@ -457,11 +477,12 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
gfn_t ngfn, void *data, int offset, int len,
u32 access)
{
+ struct x86_exception exception;
gfn_t real_gfn;
gpa_t ngpa;
ngpa = gfn_to_gpa(ngfn);
- real_gfn = mmu->translate_gpa(vcpu, ngpa, access);
+ real_gfn = mmu->translate_gpa(vcpu, ngpa, access, &exception);
if (real_gfn == UNMAPPED_GVA)
return -EFAULT;
@@ -648,6 +669,12 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR)))
return 1;
+ if (xcr0 & XSTATE_AVX512) {
+ if (!(xcr0 & XSTATE_YMM))
+ return 1;
+ if ((xcr0 & XSTATE_AVX512) != XSTATE_AVX512)
+ return 1;
+ }
kvm_put_guest_xcr0(vcpu);
vcpu->arch.xcr0 = xcr0;
@@ -724,9 +751,13 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4);
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
+#ifdef CONFIG_X86_64
+ cr3 &= ~CR3_PCID_INVD;
+#endif
+
if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
kvm_mmu_sync_roots(vcpu);
- kvm_mmu_flush_tlb(vcpu);
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
@@ -803,8 +834,6 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
vcpu->arch.eff_db[dr] = val;
break;
case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return 1; /* #UD */
/* fall through */
case 6:
if (val & 0xffffffff00000000ULL)
@@ -813,8 +842,6 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
kvm_update_dr6(vcpu);
break;
case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return 1; /* #UD */
/* fall through */
default: /* 7 */
if (val & 0xffffffff00000000ULL)
@@ -829,27 +856,21 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
- int res;
-
- res = __kvm_set_dr(vcpu, dr, val);
- if (res > 0)
- kvm_queue_exception(vcpu, UD_VECTOR);
- else if (res < 0)
+ if (__kvm_set_dr(vcpu, dr, val)) {
kvm_inject_gp(vcpu, 0);
-
- return res;
+ return 1;
+ }
+ return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_dr);
-static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
+int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
switch (dr) {
case 0 ... 3:
*val = vcpu->arch.db[dr];
break;
case 4:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return 1;
/* fall through */
case 6:
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
@@ -858,23 +879,11 @@ static int _kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
*val = kvm_x86_ops->get_dr6(vcpu);
break;
case 5:
- if (kvm_read_cr4_bits(vcpu, X86_CR4_DE))
- return 1;
/* fall through */
default: /* 7 */
*val = vcpu->arch.dr7;
break;
}
-
- return 0;
-}
-
-int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
-{
- if (_kvm_get_dr(vcpu, dr, val)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
- return 1;
- }
return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dr);
@@ -984,7 +993,6 @@ void kvm_enable_efer_bits(u64 mask)
}
EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
-
/*
* Writes msr value into into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
@@ -992,8 +1000,34 @@ EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
*/
int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
+ switch (msr->index) {
+ case MSR_FS_BASE:
+ case MSR_GS_BASE:
+ case MSR_KERNEL_GS_BASE:
+ case MSR_CSTAR:
+ case MSR_LSTAR:
+ if (is_noncanonical_address(msr->data))
+ return 1;
+ break;
+ case MSR_IA32_SYSENTER_EIP:
+ case MSR_IA32_SYSENTER_ESP:
+ /*
+ * IA32_SYSENTER_ESP and IA32_SYSENTER_EIP cause #GP if
+ * non-canonical address is written on Intel but not on
+ * AMD (which ignores the top 32-bits, because it does
+ * not implement 64-bit SYSENTER).
+ *
+ * 64-bit code should hence be able to write a non-canonical
+ * value on AMD. Making the address canonical ensures that
+ * vmentry does not fail on Intel after writing a non-canonical
+ * value, and that something deterministic happens if the guest
+ * invokes 64-bit SYSENTER.
+ */
+ msr->data = get_canonical(msr->data);
+ }
return kvm_x86_ops->set_msr(vcpu, msr);
}
+EXPORT_SYMBOL_GPL(kvm_set_msr);
/*
* Adapt set_msr() to msr_io()'s calling convention
@@ -1204,21 +1238,22 @@ void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
bool vcpus_matched;
- bool do_request = false;
struct kvm_arch *ka = &vcpu->kvm->arch;
struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 ==
atomic_read(&vcpu->kvm->online_vcpus));
- if (vcpus_matched && gtod->clock.vclock_mode == VCLOCK_TSC)
- if (!ka->use_master_clock)
- do_request = 1;
-
- if (!vcpus_matched && ka->use_master_clock)
- do_request = 1;
-
- if (do_request)
+ /*
+ * Once the masterclock is enabled, always perform request in
+ * order to update it.
+ *
+ * In order to enable masterclock, the host clocksource must be TSC
+ * and the vcpus need to have matched TSCs. When that happens,
+ * perform request to enable masterclock.
+ */
+ if (ka->use_master_clock ||
+ (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -1518,7 +1553,7 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
pvclock_update_vm_gtod_copy(kvm);
kvm_for_each_vcpu(i, vcpu, kvm)
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
/* guest entries allowed */
kvm_for_each_vcpu(i, vcpu, kvm)
@@ -1556,7 +1591,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
+ this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
if (unlikely(this_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
@@ -1604,16 +1639,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
vcpu->last_guest_tsc = tsc_timestamp;
+ if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+ &guest_hv_clock, sizeof(guest_hv_clock))))
+ return 0;
+
/*
* The interface expects us to write an even number signaling that the
* update is finished. Since the guest won't see the intermediate
* state, we just increase by 2 at the end.
*/
- vcpu->hv_clock.version += 2;
-
- if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
- &guest_hv_clock, sizeof(guest_hv_clock))))
- return 0;
+ vcpu->hv_clock.version = guest_hv_clock.version + 2;
/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
@@ -1629,6 +1664,8 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->hv_clock.flags = pvclock_flags;
+ trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+
kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
&vcpu->hv_clock,
sizeof(vcpu->hv_clock));
@@ -1661,7 +1698,7 @@ static void kvmclock_update_fn(struct work_struct *work)
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
kvm_vcpu_kick(vcpu);
}
}
@@ -1670,7 +1707,7 @@ static void kvm_gen_kvmclock_update(struct kvm_vcpu *v)
{
struct kvm *kvm = v->kvm;
- set_bit(KVM_REQ_CLOCK_UPDATE, &v->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
schedule_delayed_work(&kvm->arch.kvmclock_update_work,
KVMCLOCK_UPDATE_DELAY);
}
@@ -1723,9 +1760,10 @@ static bool valid_mtrr_type(unsigned t)
return t < 8 && (1 << t) & 0x73; /* 0, 1, 4, 5, 6 */
}
-static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
int i;
+ u64 mask;
if (!msr_mtrr_valid(msr))
return false;
@@ -1747,14 +1785,31 @@ static bool mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data)
}
/* variable MTRRs */
- return valid_mtrr_type(data & 0xff);
+ WARN_ON(!(msr >= 0x200 && msr < 0x200 + 2 * KVM_NR_VAR_MTRR));
+
+ mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+ if ((msr & 1) == 0) {
+ /* MTRR base */
+ if (!valid_mtrr_type(data & 0xff))
+ return false;
+ mask |= 0xf00;
+ } else
+ /* MTRR mask */
+ mask |= 0x7ff;
+ if (data & mask) {
+ kvm_inject_gp(vcpu, 0);
+ return false;
+ }
+
+ return true;
}
+EXPORT_SYMBOL_GPL(kvm_mtrr_valid);
static int set_msr_mtrr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
u64 *p = (u64 *)&vcpu->arch.mtrr_state.fixed_ranges;
- if (!mtrr_valid(vcpu, msr, data))
+ if (!kvm_mtrr_valid(vcpu, msr, data))
return 1;
if (msr == MSR_MTRRdefType) {
@@ -1805,7 +1860,7 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
break;
default:
if (msr >= MSR_IA32_MC0_CTL &&
- msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
+ msr < MSR_IA32_MCx_CTL(bank_num)) {
u32 offset = msr - MSR_IA32_MC0_CTL;
/* only 0 or all 1s can be written to IA32_MCi_CTL
* some Linux kernels though clear bit 10 in bank 4 to
@@ -2089,7 +2144,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_TSC_ADJUST:
if (guest_cpuid_has_tsc_adjust(vcpu)) {
if (!msr_info->host_initiated) {
- u64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
+ s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true);
}
vcpu->arch.ia32_tsc_adjust_msr = data;
@@ -2164,7 +2219,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_MCG_CTL:
case MSR_IA32_MCG_STATUS:
- case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
+ case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
return set_msr_mce(vcpu, msr, data);
/* Performance counters are not protected by a CPUID bit,
@@ -2330,7 +2385,7 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
break;
default:
if (msr >= MSR_IA32_MC0_CTL &&
- msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
+ msr < MSR_IA32_MCx_CTL(bank_num)) {
u32 offset = msr - MSR_IA32_MC0_CTL;
data = vcpu->arch.mce_banks[offset];
break;
@@ -2419,7 +2474,13 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_K7_HWCR:
case MSR_VM_HSAVE_PA:
case MSR_K7_EVNTSEL0:
+ case MSR_K7_EVNTSEL1:
+ case MSR_K7_EVNTSEL2:
+ case MSR_K7_EVNTSEL3:
case MSR_K7_PERFCTR0:
+ case MSR_K7_PERFCTR1:
+ case MSR_K7_PERFCTR2:
+ case MSR_K7_PERFCTR3:
case MSR_K8_INT_PENDING_MSG:
case MSR_AMD64_NB_CFG:
case MSR_FAM10H_MMIO_CONF_BASE:
@@ -2505,7 +2566,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case MSR_IA32_MCG_CAP:
case MSR_IA32_MCG_CTL:
case MSR_IA32_MCG_STATUS:
- case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
+ case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
return get_msr_mce(vcpu, msr, pdata);
case MSR_K7_CLK_CTL:
/*
@@ -2823,7 +2884,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
vcpu->arch.tsc_offset_adjustment = 0;
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
}
if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
@@ -3049,7 +3110,7 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu,
unsigned long val;
memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db));
- _kvm_get_dr(vcpu, 6, &val);
+ kvm_get_dr(vcpu, 6, &val);
dbgregs->dr6 = val;
dbgregs->dr7 = vcpu->arch.dr7;
dbgregs->flags = 0;
@@ -3071,15 +3132,89 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
return 0;
}
+#define XSTATE_COMPACTION_ENABLED (1ULL << 63)
+
+static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu)
+{
+ struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+ u64 xstate_bv = xsave->xsave_hdr.xstate_bv;
+ u64 valid;
+
+ /*
+ * Copy legacy XSAVE area, to avoid complications with CPUID
+ * leaves 0 and 1 in the loop below.
+ */
+ memcpy(dest, xsave, XSAVE_HDR_OFFSET);
+
+ /* Set XSTATE_BV */
+ *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
+
+ /*
+ * Copy each region from the possibly compacted offset to the
+ * non-compacted offset.
+ */
+ valid = xstate_bv & ~XSTATE_FPSSE;
+ while (valid) {
+ u64 feature = valid & -valid;
+ int index = fls64(feature) - 1;
+ void *src = get_xsave_addr(xsave, feature);
+
+ if (src) {
+ u32 size, offset, ecx, edx;
+ cpuid_count(XSTATE_CPUID, index,
+ &size, &offset, &ecx, &edx);
+ memcpy(dest + offset, src, size);
+ }
+
+ valid -= feature;
+ }
+}
+
+static void load_xsave(struct kvm_vcpu *vcpu, u8 *src)
+{
+ struct xsave_struct *xsave = &vcpu->arch.guest_fpu.state->xsave;
+ u64 xstate_bv = *(u64 *)(src + XSAVE_HDR_OFFSET);
+ u64 valid;
+
+ /*
+ * Copy legacy XSAVE area, to avoid complications with CPUID
+ * leaves 0 and 1 in the loop below.
+ */
+ memcpy(xsave, src, XSAVE_HDR_OFFSET);
+
+ /* Set XSTATE_BV and possibly XCOMP_BV. */
+ xsave->xsave_hdr.xstate_bv = xstate_bv;
+ if (cpu_has_xsaves)
+ xsave->xsave_hdr.xcomp_bv = host_xcr0 | XSTATE_COMPACTION_ENABLED;
+
+ /*
+ * Copy each region from the non-compacted offset to the
+ * possibly compacted offset.
+ */
+ valid = xstate_bv & ~XSTATE_FPSSE;
+ while (valid) {
+ u64 feature = valid & -valid;
+ int index = fls64(feature) - 1;
+ void *dest = get_xsave_addr(xsave, feature);
+
+ if (dest) {
+ u32 size, offset, ecx, edx;
+ cpuid_count(XSTATE_CPUID, index,
+ &size, &offset, &ecx, &edx);
+ memcpy(dest, src + offset, size);
+ } else
+ WARN_ON_ONCE(1);
+
+ valid -= feature;
+ }
+}
+
static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
struct kvm_xsave *guest_xsave)
{
if (cpu_has_xsave) {
- memcpy(guest_xsave->region,
- &vcpu->arch.guest_fpu.state->xsave,
- vcpu->arch.guest_xstate_size);
- *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &=
- vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE;
+ memset(guest_xsave, 0, sizeof(struct kvm_xsave));
+ fill_xsave((u8 *) guest_xsave->region, vcpu);
} else {
memcpy(guest_xsave->region,
&vcpu->arch.guest_fpu.state->fxsave,
@@ -3103,8 +3238,7 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
*/
if (xstate_bv & ~kvm_supported_xcr0())
return -EINVAL;
- memcpy(&vcpu->arch.guest_fpu.state->xsave,
- guest_xsave->region, vcpu->arch.guest_xstate_size);
+ load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
if (xstate_bv & ~XSTATE_FPSSE)
return -EINVAL;
@@ -3947,7 +4081,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
}
default:
- ;
+ r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
}
out:
return r;
@@ -4040,16 +4174,16 @@ void kvm_get_segment(struct kvm_vcpu *vcpu,
kvm_x86_ops->get_segment(vcpu, var, seg);
}
-gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
+ struct x86_exception *exception)
{
gpa_t t_gpa;
- struct x86_exception exception;
BUG_ON(!mmu_is_nested(vcpu));
/* NPT walks are always user-walks */
access |= PFERR_USER_MASK;
- t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception);
+ t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, exception);
return t_gpa;
}
@@ -4610,7 +4744,7 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt)
int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest)
{
- return _kvm_get_dr(emul_to_vcpu(ctxt), dr, dest);
+ return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest);
}
int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value)
@@ -4906,16 +5040,18 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
}
}
-static void inject_emulated_exception(struct kvm_vcpu *vcpu)
+static bool inject_emulated_exception(struct kvm_vcpu *vcpu)
{
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
if (ctxt->exception.vector == PF_VECTOR)
- kvm_propagate_fault(vcpu, &ctxt->exception);
- else if (ctxt->exception.error_code_valid)
+ return kvm_propagate_fault(vcpu, &ctxt->exception);
+
+ if (ctxt->exception.error_code_valid)
kvm_queue_exception_e(vcpu, ctxt->exception.vector,
ctxt->exception.error_code);
else
kvm_queue_exception(vcpu, ctxt->exception.vector);
+ return false;
}
static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
@@ -4972,7 +5108,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
++vcpu->stat.insn_emulation_fail;
trace_kvm_emulate_insn_failed(vcpu);
- if (!is_guest_mode(vcpu)) {
+ if (!is_guest_mode(vcpu) && kvm_x86_ops->get_cpl(vcpu) == 0) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
@@ -5152,21 +5288,17 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflag
static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
{
- struct kvm_run *kvm_run = vcpu->run;
- unsigned long eip = vcpu->arch.emulate_ctxt.eip;
- u32 dr6 = 0;
-
if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
(vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
- dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+ struct kvm_run *kvm_run = vcpu->run;
+ unsigned long eip = kvm_get_linear_rip(vcpu);
+ u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0,
vcpu->arch.guest_debug_dr7,
vcpu->arch.eff_db);
if (dr6 != 0) {
kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
- kvm_run->debug.arch.pc = kvm_rip_read(vcpu) +
- get_segment_base(vcpu, VCPU_SREG_CS);
-
+ kvm_run->debug.arch.pc = eip;
kvm_run->debug.arch.exception = DB_VECTOR;
kvm_run->exit_reason = KVM_EXIT_DEBUG;
*r = EMULATE_USER_EXIT;
@@ -5176,7 +5308,8 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) &&
!(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) {
- dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+ unsigned long eip = kvm_get_linear_rip(vcpu);
+ u32 dr6 = kvm_vcpu_check_hw_bp(eip, 0,
vcpu->arch.dr7,
vcpu->arch.db);
@@ -5224,6 +5357,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
ctxt->interruptibility = 0;
ctxt->have_exception = false;
+ ctxt->exception.vector = -1;
ctxt->perm_ok = false;
ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
@@ -5276,8 +5410,9 @@ restart:
}
if (ctxt->have_exception) {
- inject_emulated_exception(vcpu);
r = EMULATE_DONE;
+ if (inject_emulated_exception(vcpu))
+ return r;
} else if (vcpu->arch.pio.count) {
if (!vcpu->arch.pio.in) {
/* FIXME: return into emulator if single-stepping. */
@@ -5304,7 +5439,9 @@ restart:
kvm_rip_write(vcpu, ctxt->eip);
if (r == EMULATE_DONE)
kvm_vcpu_check_singlestep(vcpu, rflags, &r);
- __kvm_set_rflags(vcpu, ctxt->eflags);
+ if (!ctxt->have_exception ||
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+ __kvm_set_rflags(vcpu, ctxt->eflags);
/*
* For STI, interrupts are shadowed; so KVM_REQ_EVENT will
@@ -5545,7 +5682,7 @@ static void kvm_set_mmio_spte_mask(void)
* entry to generate page fault with PFER.RSV = 1.
*/
/* Mask the reserved physical address bits. */
- mask = ((1ull << (51 - maxphyaddr + 1)) - 1) << maxphyaddr;
+ mask = rsvd_bits(maxphyaddr, 51);
/* Bit 62 is always reserved for 32bit host. */
mask |= 0x3ull << 62;
@@ -5576,7 +5713,7 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
spin_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
- set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
atomic_set(&kvm_guest_has_master_clock, 0);
spin_unlock(&kvm_lock);
}
@@ -5904,6 +6041,12 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
X86_EFLAGS_RF);
+ if (vcpu->arch.exception.nr == DB_VECTOR &&
+ (vcpu->arch.dr7 & DR7_GD)) {
+ vcpu->arch.dr7 &= ~DR7_GD;
+ kvm_update_dr7(vcpu);
+ }
+
kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
vcpu->arch.exception.has_error_code,
vcpu->arch.exception.error_code,
@@ -5989,6 +6132,44 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
kvm_apic_update_tmr(vcpu, tmr);
}
+static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ ++vcpu->stat.tlb_flush;
+ kvm_x86_ops->tlb_flush(vcpu);
+}
+
+void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
+{
+ struct page *page = NULL;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return;
+
+ if (!kvm_x86_ops->set_apic_access_page_addr)
+ return;
+
+ page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+ kvm_x86_ops->set_apic_access_page_addr(vcpu, page_to_phys(page));
+
+ /*
+ * Do not pin apic access page in memory, the MMU notifier
+ * will call us again if it is migrated or swapped out.
+ */
+ put_page(page);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+ /*
+ * The physical address of apic access page is stored in the VMCS.
+ * Update it when it becomes invalid.
+ */
+ if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
+ kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
/*
* Returns 1 to let __vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
@@ -6018,7 +6199,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
kvm_mmu_sync_roots(vcpu);
if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
- kvm_x86_ops->tlb_flush(vcpu);
+ kvm_vcpu_flush_tlb(vcpu);
if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
r = 0;
@@ -6049,6 +6230,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_deliver_pmi(vcpu);
if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu))
vcpu_scan_ioapic(vcpu);
+ if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu))
+ kvm_vcpu_reload_apic_access_page(vcpu);
}
if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
@@ -6772,6 +6955,9 @@ int fx_init(struct kvm_vcpu *vcpu)
return err;
fpu_finit(&vcpu->arch.guest_fpu);
+ if (cpu_has_xsaves)
+ vcpu->arch.guest_fpu.state->xsave.xsave_hdr.xcomp_bv =
+ host_xcr0 | XSTATE_COMPACTION_ENABLED;
/*
* Ensure guest xcr0 is valid for loading
@@ -6923,7 +7109,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
kvm_x86_ops->vcpu_reset(vcpu);
}
-void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
+void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
{
struct kvm_segment cs;
@@ -6934,7 +7120,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, unsigned int vector)
kvm_rip_write(vcpu, 0);
}
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
@@ -6945,7 +7131,7 @@ int kvm_arch_hardware_enable(void *garbage)
bool stable, backwards_tsc = false;
kvm_shared_msr_cpu_online();
- ret = kvm_x86_ops->hardware_enable(garbage);
+ ret = kvm_x86_ops->hardware_enable();
if (ret != 0)
return ret;
@@ -6954,7 +7140,7 @@ int kvm_arch_hardware_enable(void *garbage)
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!stable && vcpu->cpu == smp_processor_id())
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
if (stable && vcpu->arch.last_host_tsc > local_tsc) {
backwards_tsc = true;
if (vcpu->arch.last_host_tsc > max_tsc)
@@ -7008,8 +7194,7 @@ int kvm_arch_hardware_enable(void *garbage)
kvm_for_each_vcpu(i, vcpu, kvm) {
vcpu->arch.tsc_offset_adjustment += delta_cyc;
vcpu->arch.last_host_tsc = local_tsc;
- set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
- &vcpu->requests);
+ kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
}
/*
@@ -7026,10 +7211,10 @@ int kvm_arch_hardware_enable(void *garbage)
return 0;
}
-void kvm_arch_hardware_disable(void *garbage)
+void kvm_arch_hardware_disable(void)
{
- kvm_x86_ops->hardware_disable(garbage);
- drop_user_return_notifiers(garbage);
+ kvm_x86_ops->hardware_disable();
+ drop_user_return_notifiers();
}
int kvm_arch_hardware_setup(void)
@@ -7146,11 +7331,17 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
static_key_slow_dec(&kvm_no_apic_vcpu);
}
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
+{
+ kvm_x86_ops->sched_in(vcpu, cpu);
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
if (type)
return -EINVAL;
+ INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
@@ -7237,10 +7428,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
- if (kvm->arch.apic_access_page)
- put_page(kvm->arch.apic_access_page);
- if (kvm->arch.ept_identity_pagetable)
- put_page(kvm->arch.ept_identity_pagetable);
kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
}
@@ -7435,12 +7622,18 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
return kvm_x86_ops->interrupt_allowed(vcpu);
}
-bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
+unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu)
{
- unsigned long current_rip = kvm_rip_read(vcpu) +
- get_segment_base(vcpu, VCPU_SREG_CS);
+ if (is_64_bit_mode(vcpu))
+ return kvm_rip_read(vcpu);
+ return (u32)(get_segment_base(vcpu, VCPU_SREG_CS) +
+ kvm_rip_read(vcpu));
+}
+EXPORT_SYMBOL_GPL(kvm_get_linear_rip);
- return current_rip == linear_rip;
+bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip)
+{
+ return kvm_get_linear_rip(vcpu) == linear_rip;
}
EXPORT_SYMBOL_GPL(kvm_is_linear_rip);
@@ -7643,3 +7836,4 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 306a1b77581f..cc1d61af6140 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -88,15 +88,23 @@ static inline void vcpu_cache_mmio_info(struct kvm_vcpu *vcpu,
vcpu->arch.mmio_gva = gva & PAGE_MASK;
vcpu->arch.access = access;
vcpu->arch.mmio_gfn = gfn;
+ vcpu->arch.mmio_gen = kvm_memslots(vcpu->kvm)->generation;
+}
+
+static inline bool vcpu_match_mmio_gen(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.mmio_gen == kvm_memslots(vcpu->kvm)->generation;
}
/*
- * Clear the mmio cache info for the given gva,
- * specially, if gva is ~0ul, we clear all mmio cache info.
+ * Clear the mmio cache info for the given gva. If gva is MMIO_GVA_ANY, we
+ * clear all mmio cache info.
*/
+#define MMIO_GVA_ANY (~(gva_t)0)
+
static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
{
- if (gva != (~0ul) && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
+ if (gva != MMIO_GVA_ANY && vcpu->arch.mmio_gva != (gva & PAGE_MASK))
return;
vcpu->arch.mmio_gva = 0;
@@ -104,7 +112,8 @@ static inline void vcpu_clear_mmio_info(struct kvm_vcpu *vcpu, gva_t gva)
static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
{
- if (vcpu->arch.mmio_gva && vcpu->arch.mmio_gva == (gva & PAGE_MASK))
+ if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gva &&
+ vcpu->arch.mmio_gva == (gva & PAGE_MASK))
return true;
return false;
@@ -112,7 +121,8 @@ static inline bool vcpu_match_mmio_gva(struct kvm_vcpu *vcpu, unsigned long gva)
static inline bool vcpu_match_mmio_gpa(struct kvm_vcpu *vcpu, gpa_t gpa)
{
- if (vcpu->arch.mmio_gfn && vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
+ if (vcpu_match_mmio_gen(vcpu) && vcpu->arch.mmio_gfn &&
+ vcpu->arch.mmio_gfn == gpa >> PAGE_SHIFT)
return true;
return false;
@@ -149,8 +159,11 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception);
+bool kvm_mtrr_valid(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+
#define KVM_SUPPORTED_XCR0 (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \
- | XSTATE_BNDREGS | XSTATE_BNDCSR)
+ | XSTATE_BNDREGS | XSTATE_BNDCSR \
+ | XSTATE_AVX512)
extern u64 host_xcr0;
extern u64 kvm_supported_xcr0(void);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index aae94132bc24..c1c1544b8485 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -841,7 +841,7 @@ static void __init lguest_init_IRQ(void)
{
unsigned int i;
- for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+ for (i = FIRST_EXTERNAL_VECTOR; i < FIRST_SYSTEM_VECTOR; i++) {
/* Some systems map "vectors" to interrupts weirdly. Not us! */
__this_cpu_write(vector_irq[i], i - FIRST_EXTERNAL_VECTOR);
if (i != SYSCALL_VECTOR)
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 4d4f96a27638..1530afb07c85 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -20,11 +20,10 @@ lib-y := delay.o misc.o cmdline.o
lib-y += thunk_$(BITS).o
lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_SMP) += rwlock.o
lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
-obj-y += msr.o msr-reg.o msr-reg-export.o hash.o
+obj-y += msr.o msr-reg.o msr-reg-export.o
ifeq ($(CONFIG_X86_32),y)
obj-y += atomic64_32.o
@@ -39,7 +38,7 @@ endif
else
obj-y += iomap_copy_64.o
lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
- lib-y += thunk_64.o clear_page_64.o copy_page_64.o
+ lib-y += clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
lib-y += copy_user_64.o copy_user_nocache_64.o
lib-y += cmpxchg16b_emu.o
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 1e572c507d06..40a172541ee2 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -6,15 +6,8 @@
*
*/
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
#include <asm/dwarf2.h>
-
-#ifdef CONFIG_SMP
-#define SEG_PREFIX %gs:
-#else
-#define SEG_PREFIX
-#endif
+#include <asm/percpu.h>
.text
@@ -39,24 +32,25 @@ CFI_STARTPROC
# *atomic* on a single cpu (as provided by the this_cpu_xx class of
# macros).
#
-this_cpu_cmpxchg16b_emu:
- pushf
+ pushfq_cfi
cli
- cmpq SEG_PREFIX(%rsi), %rax
- jne not_same
- cmpq SEG_PREFIX 8(%rsi), %rdx
- jne not_same
+ cmpq PER_CPU_VAR((%rsi)), %rax
+ jne .Lnot_same
+ cmpq PER_CPU_VAR(8(%rsi)), %rdx
+ jne .Lnot_same
- movq %rbx, SEG_PREFIX(%rsi)
- movq %rcx, SEG_PREFIX 8(%rsi)
+ movq %rbx, PER_CPU_VAR((%rsi))
+ movq %rcx, PER_CPU_VAR(8(%rsi))
- popf
+ CFI_REMEMBER_STATE
+ popfq_cfi
mov $1, %al
ret
- not_same:
- popf
+ CFI_RESTORE_STATE
+.Lnot_same:
+ popfq_cfi
xor %al,%al
ret
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 828cb710dec2..b4807fce5177 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,11 +7,8 @@
*/
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
#include <asm/dwarf2.h>
-
.text
/*
@@ -30,27 +27,28 @@ CFI_STARTPROC
# set the whole ZF thing (caller will just compare
# eax:edx with the expected value)
#
-cmpxchg8b_emu:
- pushfl
+ pushfl_cfi
cli
cmpl (%esi), %eax
- jne not_same
+ jne .Lnot_same
cmpl 4(%esi), %edx
- jne half_same
+ jne .Lhalf_same
movl %ebx, (%esi)
movl %ecx, 4(%esi)
- popfl
+ CFI_REMEMBER_STATE
+ popfl_cfi
ret
- not_same:
+ CFI_RESTORE_STATE
+.Lnot_same:
movl (%esi), %eax
- half_same:
+.Lhalf_same:
movl 4(%esi), %edx
- popfl
+ popfl_cfi
ret
CFI_ENDPROC
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 7609e0e421ec..1318f75d56e4 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -41,9 +41,8 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
while (((unsigned long)src & 6) && len >= 2) {
__u16 val16;
- *errp = __get_user(val16, (const __u16 __user *)src);
- if (*errp)
- return isum;
+ if (__get_user(val16, (const __u16 __user *)src))
+ goto out_err;
*(__u16 *)dst = val16;
isum = (__force __wsum)add32_with_carry(
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
deleted file mode 100644
index ff4fa51a5b1f..000000000000
--- a/arch/x86/lib/hash.c
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * Some portions derived from code covered by the following notice:
- *
- * Copyright (c) 2010-2013 Intel Corporation. All rights reserved.
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/hash.h>
-#include <linux/init.h>
-
-#include <asm/processor.h>
-#include <asm/cpufeature.h>
-#include <asm/hash.h>
-
-static inline u32 crc32_u32(u32 crc, u32 val)
-{
-#ifdef CONFIG_AS_CRC32
- asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val));
-#else
- asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val));
-#endif
- return crc;
-}
-
-static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
-{
- const u32 *p32 = (const u32 *) data;
- u32 i, tmp = 0;
-
- for (i = 0; i < len / 4; i++)
- seed = crc32_u32(seed, *p32++);
-
- switch (len & 3) {
- case 3:
- tmp |= *((const u8 *) p32 + 2) << 16;
- /* fallthrough */
- case 2:
- tmp |= *((const u8 *) p32 + 1) << 8;
- /* fallthrough */
- case 1:
- tmp |= *((const u8 *) p32);
- seed = crc32_u32(seed, tmp);
- break;
- }
-
- return seed;
-}
-
-static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
-{
- const u32 *p32 = (const u32 *) data;
- u32 i;
-
- for (i = 0; i < len; i++)
- seed = crc32_u32(seed, *p32++);
-
- return seed;
-}
-
-void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
-{
- if (cpu_has_xmm4_2) {
- ops->hash = intel_crc4_2_hash;
- ops->hash2 = intel_crc4_2_hash2;
- }
-}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 54fcffed28ed..1313ae6b478b 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -28,7 +28,7 @@
/* Verify next sizeof(t) bytes can be on the same instruction */
#define validate_next(t, insn, n) \
- ((insn)->next_byte + sizeof(t) + n - (insn)->kaddr <= MAX_INSN_SIZE)
+ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
#define __get_next(t, insn) \
({ t r = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
@@ -50,10 +50,11 @@
* @kaddr: address (in kernel memory) of instruction (or copy thereof)
* @x86_64: !0 for 64-bit kernel or 64-bit app
*/
-void insn_init(struct insn *insn, const void *kaddr, int x86_64)
+void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
{
memset(insn, 0, sizeof(*insn));
insn->kaddr = kaddr;
+ insn->end_kaddr = kaddr + buf_len;
insn->next_byte = kaddr;
insn->x86_64 = x86_64 ? 1 : 0;
insn->opnd_bytes = 4;
diff --git a/arch/x86/lib/rwlock.S b/arch/x86/lib/rwlock.S
deleted file mode 100644
index 1cad22139c88..000000000000
--- a/arch/x86/lib/rwlock.S
+++ /dev/null
@@ -1,44 +0,0 @@
-/* Slow paths of read/write spinlocks. */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-#include <asm/rwlock.h>
-
-#ifdef CONFIG_X86_32
-# define __lock_ptr eax
-#else
-# define __lock_ptr rdi
-#endif
-
-ENTRY(__write_lock_failed)
- CFI_STARTPROC
- FRAME
-0: LOCK_PREFIX
- WRITE_LOCK_ADD($RW_LOCK_BIAS) (%__lock_ptr)
-1: rep; nop
- cmpl $WRITE_LOCK_CMP, (%__lock_ptr)
- jne 1b
- LOCK_PREFIX
- WRITE_LOCK_SUB($RW_LOCK_BIAS) (%__lock_ptr)
- jnz 0b
- ENDFRAME
- ret
- CFI_ENDPROC
-END(__write_lock_failed)
-
-ENTRY(__read_lock_failed)
- CFI_STARTPROC
- FRAME
-0: LOCK_PREFIX
- READ_LOCK_SIZE(inc) (%__lock_ptr)
-1: rep; nop
- READ_LOCK_SIZE(cmp) $1, (%__lock_ptr)
- js 1b
- LOCK_PREFIX
- READ_LOCK_SIZE(dec) (%__lock_ptr)
- js 0b
- ENDFRAME
- ret
- CFI_ENDPROC
-END(__read_lock_failed)
diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S
index 28f85c916712..e28cdaf5ac2c 100644
--- a/arch/x86/lib/thunk_32.S
+++ b/arch/x86/lib/thunk_32.S
@@ -6,25 +6,46 @@
*/
#include <linux/linkage.h>
#include <asm/asm.h>
+ #include <asm/dwarf2.h>
-#ifdef CONFIG_TRACE_IRQFLAGS
/* put return address in eax (arg1) */
- .macro thunk_ra name,func
+ .macro THUNK name, func, put_ret_addr_in_eax=0
.globl \name
\name:
- pushl %eax
- pushl %ecx
- pushl %edx
+ CFI_STARTPROC
+ pushl_cfi %eax
+ CFI_REL_OFFSET eax, 0
+ pushl_cfi %ecx
+ CFI_REL_OFFSET ecx, 0
+ pushl_cfi %edx
+ CFI_REL_OFFSET edx, 0
+
+ .if \put_ret_addr_in_eax
/* Place EIP in the arg1 */
movl 3*4(%esp), %eax
+ .endif
+
call \func
- popl %edx
- popl %ecx
- popl %eax
+ popl_cfi %edx
+ CFI_RESTORE edx
+ popl_cfi %ecx
+ CFI_RESTORE ecx
+ popl_cfi %eax
+ CFI_RESTORE eax
ret
+ CFI_ENDPROC
_ASM_NOKPROBE(\name)
.endm
- thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller
- thunk_ra trace_hardirqs_off_thunk,trace_hardirqs_off_caller
+#ifdef CONFIG_TRACE_IRQFLAGS
+ THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+ THUNK ___preempt_schedule_context, preempt_schedule_context
#endif
+#endif
+
diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S
index 92d9feaff42b..b30b5ebd614a 100644
--- a/arch/x86/lib/thunk_64.S
+++ b/arch/x86/lib/thunk_64.S
@@ -38,6 +38,13 @@
THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
#endif
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+#ifdef CONFIG_CONTEXT_TRACKING
+ THUNK ___preempt_schedule_context, preempt_schedule_context
+#endif
+#endif
+
/* SAVE_ARGS below is used only for the .cfi directives it contains. */
CFI_STARTPROC
SAVE_ARGS
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 6a19ad9f370d..ecfdc46a024a 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -30,3 +30,5 @@ obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
obj-$(CONFIG_MEMTEST) += memtest.o
+
+obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 95a427e57887..f0cedf3395af 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -76,6 +76,9 @@ static struct addr_marker address_markers[] = {
# ifdef CONFIG_X86_ESPFIX64
{ ESPFIX_BASE_ADDR, "ESPfix Area", 16 },
# endif
+# ifdef CONFIG_EFI
+ { EFI_VA_END, "EFI Runtime Services" },
+# endif
{ __START_KERNEL_map, "High Kernel Mapping" },
{ MODULES_VADDR, "Modules" },
{ MODULES_END, "End Modules" },
@@ -126,7 +129,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
if (!pgprot_val(prot)) {
/* Not present */
- pt_dump_cont_printf(m, dmsg, " ");
+ pt_dump_cont_printf(m, dmsg, " ");
} else {
if (pr & _PAGE_USER)
pt_dump_cont_printf(m, dmsg, "USR ");
@@ -145,18 +148,16 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
else
pt_dump_cont_printf(m, dmsg, " ");
- /* Bit 9 has a different meaning on level 3 vs 4 */
- if (level <= 3) {
- if (pr & _PAGE_PSE)
- pt_dump_cont_printf(m, dmsg, "PSE ");
- else
- pt_dump_cont_printf(m, dmsg, " ");
- } else {
- if (pr & _PAGE_PAT)
- pt_dump_cont_printf(m, dmsg, "pat ");
- else
- pt_dump_cont_printf(m, dmsg, " ");
- }
+ /* Bit 7 has a different meaning on level 3 vs 4 */
+ if (level <= 3 && pr & _PAGE_PSE)
+ pt_dump_cont_printf(m, dmsg, "PSE ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
+ if ((level == 4 && pr & _PAGE_PAT) ||
+ ((level == 3 || level == 2) && pr & _PAGE_PAT_LARGE))
+ pt_dump_cont_printf(m, dmsg, "pat ");
+ else
+ pt_dump_cont_printf(m, dmsg, " ");
if (pr & _PAGE_GLOBAL)
pt_dump_cont_printf(m, dmsg, "GLB ");
else
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a24194681513..38dcec403b46 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -3,7 +3,6 @@
* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
* Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
*/
-#include <linux/magic.h> /* STACK_END_MAGIC */
#include <linux/sched.h> /* test_thread_flag(), ... */
#include <linux/kdebug.h> /* oops_begin/end, ... */
#include <linux/module.h> /* search_exception_table */
@@ -350,7 +349,7 @@ out:
void vmalloc_sync_all(void)
{
- sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
+ sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0);
}
/*
@@ -649,7 +648,6 @@ no_context(struct pt_regs *regs, unsigned long error_code,
unsigned long address, int signal, int si_code)
{
struct task_struct *tsk = current;
- unsigned long *stackend;
unsigned long flags;
int sig;
@@ -709,8 +707,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
show_fault_oops(regs, error_code, address);
- stackend = end_of_stack(tsk);
- if (tsk != &init_task && *stackend != STACK_END_MAGIC)
+ if (task_stack_end_corrupted(tsk))
printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");
tsk->thread.cr2 = address;
@@ -847,11 +844,8 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
unsigned int fault)
{
struct task_struct *tsk = current;
- struct mm_struct *mm = tsk->mm;
int code = BUS_ADRERR;
- up_read(&mm->mmap_sem);
-
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER)) {
no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
@@ -882,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
unsigned long address, unsigned int fault)
{
if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
- up_read(&current->mm->mmap_sem);
no_context(regs, error_code, address, 0, 0);
return;
}
@@ -890,14 +883,11 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
if (fault & VM_FAULT_OOM) {
/* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER)) {
- up_read(&current->mm->mmap_sem);
no_context(regs, error_code, address,
SIGSEGV, SEGV_MAPERR);
return;
}
- up_read(&current->mm->mmap_sem);
-
/*
* We ran out of memory, call the OOM killer, and return the
* userspace (which will retry the fault, or kill us if we got
@@ -933,8 +923,17 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
* cross-processor TLB flush, even if no stale TLB entries exist
* on other processors.
*
+ * Spurious faults may only occur if the TLB contains an entry with
+ * fewer permission than the page table entry. Non-present (P = 0)
+ * and reserved bit (R = 1) faults are never spurious.
+ *
* There are no security implications to leaving a stale TLB when
* increasing the permissions on a page.
+ *
+ * Returns non-zero if a spurious fault was handled, zero otherwise.
+ *
+ * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3
+ * (Optional Invalidation).
*/
static noinline int
spurious_fault(unsigned long error_code, unsigned long address)
@@ -945,8 +944,17 @@ spurious_fault(unsigned long error_code, unsigned long address)
pte_t *pte;
int ret;
- /* Reserved-bit violation or user access to kernel space? */
- if (error_code & (PF_USER | PF_RSVD))
+ /*
+ * Only writes to RO or instruction fetches from NX may cause
+ * spurious faults.
+ *
+ * These could be from user or supervisor accesses but the TLB
+ * is only lazily flushed after a kernel mapping protection
+ * change, so user accesses are not expected to cause spurious
+ * faults.
+ */
+ if (error_code != (PF_WRITE | PF_PROT)
+ && error_code != (PF_INSTR | PF_PROT))
return 0;
pgd = init_mm.pgd + pgd_index(address);
@@ -1047,7 +1055,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code,
struct vm_area_struct *vma;
struct task_struct *tsk;
struct mm_struct *mm;
- int fault;
+ int fault, major = 0;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
@@ -1222,47 +1230,50 @@ good_area:
* we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
*/
fault = handle_mm_fault(mm, vma, address, flags);
+ major |= fault & VM_FAULT_MAJOR;
/*
- * If we need to retry but a fatal signal is pending, handle the
- * signal first. We do not need to release the mmap_sem because it
- * would already be released in __lock_page_or_retry in mm/filemap.c.
+ * If we need to retry the mmap_sem has already been released,
+ * and if there is a fatal signal pending there is no guarantee
+ * that we made any progress. Handle this case first.
*/
- if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+ if (unlikely(fault & VM_FAULT_RETRY)) {
+ /* Retry at most once */
+ if (flags & FAULT_FLAG_ALLOW_RETRY) {
+ flags &= ~FAULT_FLAG_ALLOW_RETRY;
+ flags |= FAULT_FLAG_TRIED;
+ if (!fatal_signal_pending(tsk))
+ goto retry;
+ }
+
+ /* User mode? Just return to handle the fatal exception */
+ if (flags & FAULT_FLAG_USER)
+ return;
+
+ /* Not returning to user mode? Handle exceptions or die: */
+ no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
return;
+ }
+ up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, fault);
return;
}
/*
- * Major/minor page fault accounting is only done on the
- * initial attempt. If we go through a retry, it is extremely
- * likely that the page will be found in page cache at that point.
+ * Major/minor page fault accounting. If any of the events
+ * returned VM_FAULT_MAJOR, we account it as a major fault.
*/
- if (flags & FAULT_FLAG_ALLOW_RETRY) {
- if (fault & VM_FAULT_MAJOR) {
- tsk->maj_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
- regs, address);
- } else {
- tsk->min_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
- regs, address);
- }
- if (fault & VM_FAULT_RETRY) {
- /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
- * of starvation. */
- flags &= ~FAULT_FLAG_ALLOW_RETRY;
- flags |= FAULT_FLAG_TRIED;
- goto retry;
- }
+ if (major) {
+ tsk->maj_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+ } else {
+ tsk->min_flt++;
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
}
check_v8086_mode(regs, address, tsk);
-
- up_read(&mm->mmap_sem);
}
NOKPROBE_SYMBOL(__do_page_fault);
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 207d9aef662d..d7547824e763 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -15,7 +15,7 @@
static inline pte_t gup_get_pte(pte_t *ptep)
{
#ifndef CONFIG_X86_PAE
- return ACCESS_ONCE(*ptep);
+ return READ_ONCE(*ptep);
#else
/*
* With get_user_pages_fast, we walk down the pagetables without taking
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 66dba36f2343..08a7d313538a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -27,6 +27,35 @@
#include "mm_internal.h"
+/*
+ * Tables translating between page_cache_type_t and pte encoding.
+ * Minimal supported modes are defined statically, modified if more supported
+ * cache modes are available.
+ * Index into __cachemode2pte_tbl is the cachemode.
+ * Index into __pte2cachemode_tbl are the caching attribute bits of the pte
+ * (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2.
+ */
+uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
+ [_PAGE_CACHE_MODE_WB] = 0,
+ [_PAGE_CACHE_MODE_WC] = _PAGE_PWT,
+ [_PAGE_CACHE_MODE_UC_MINUS] = _PAGE_PCD,
+ [_PAGE_CACHE_MODE_UC] = _PAGE_PCD | _PAGE_PWT,
+ [_PAGE_CACHE_MODE_WT] = _PAGE_PCD,
+ [_PAGE_CACHE_MODE_WP] = _PAGE_PCD,
+};
+EXPORT_SYMBOL_GPL(__cachemode2pte_tbl);
+uint8_t __pte2cachemode_tbl[8] = {
+ [__pte2cm_idx(0)] = _PAGE_CACHE_MODE_WB,
+ [__pte2cm_idx(_PAGE_PWT)] = _PAGE_CACHE_MODE_WC,
+ [__pte2cm_idx(_PAGE_PCD)] = _PAGE_CACHE_MODE_UC_MINUS,
+ [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD)] = _PAGE_CACHE_MODE_UC,
+ [__pte2cm_idx(_PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
+ [__pte2cm_idx(_PAGE_PWT | _PAGE_PAT)] = _PAGE_CACHE_MODE_WC,
+ [__pte2cm_idx(_PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
+ [__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
+};
+EXPORT_SYMBOL_GPL(__pte2cachemode_tbl);
+
static unsigned long __initdata pgt_buf_start;
static unsigned long __initdata pgt_buf_end;
static unsigned long __initdata pgt_buf_top;
@@ -409,20 +438,20 @@ static unsigned long __init init_range_memory_mapping(
static unsigned long __init get_new_step_size(unsigned long step_size)
{
/*
- * Explain why we shift by 5 and why we don't have to worry about
- * 'step_size << 5' overflowing:
- *
- * initial mapped size is PMD_SIZE (2M).
+ * Initial mapped size is PMD_SIZE (2M).
* We can not set step_size to be PUD_SIZE (1G) yet.
* In worse case, when we cross the 1G boundary, and
* PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
- * to map 1G range with PTE. Use 5 as shift for now.
+ * to map 1G range with PTE. Hence we use one less than the
+ * difference of page table level shifts.
*
- * Don't need to worry about overflow, on 32bit, when step_size
- * is 0, round_down() returns 0 for start, and that turns it
- * into 0x100000000ULL.
+ * Don't need to worry about overflow in the top-down case, on 32bit,
+ * when step_size is 0, round_down() returns 0 for start, and that
+ * turns it into 0x100000000ULL.
+ * In the bottom-up case, round_up(x, 0) returns 0 though too, which
+ * needs to be taken into consideration by the code below.
*/
- return step_size << 5;
+ return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
}
/**
@@ -442,7 +471,6 @@ static void __init memory_map_top_down(unsigned long map_start,
unsigned long step_size;
unsigned long addr;
unsigned long mapped_ram_size = 0;
- unsigned long new_mapped_ram_size;
/* xen has big range in reserved near end of ram, skip it at first.*/
addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
@@ -467,14 +495,12 @@ static void __init memory_map_top_down(unsigned long map_start,
start = map_start;
} else
start = map_start;
- new_mapped_ram_size = init_range_memory_mapping(start,
+ mapped_ram_size += init_range_memory_mapping(start,
last_start);
last_start = start;
min_pfn_mapped = last_start >> PAGE_SHIFT;
- /* only increase step_size after big range get mapped */
- if (new_mapped_ram_size > mapped_ram_size)
+ if (mapped_ram_size >= step_size)
step_size = get_new_step_size(step_size);
- mapped_ram_size += new_mapped_ram_size;
}
if (real_end < map_end)
@@ -495,7 +521,7 @@ static void __init memory_map_top_down(unsigned long map_start,
static void __init memory_map_bottom_up(unsigned long map_start,
unsigned long map_end)
{
- unsigned long next, new_mapped_ram_size, start;
+ unsigned long next, start;
unsigned long mapped_ram_size = 0;
/* step_size need to be small so pgt_buf from BRK could cover it */
unsigned long step_size = PMD_SIZE;
@@ -510,19 +536,19 @@ static void __init memory_map_bottom_up(unsigned long map_start,
* for page table.
*/
while (start < map_end) {
- if (map_end - start > step_size) {
+ if (step_size && map_end - start > step_size) {
next = round_up(start + 1, step_size);
if (next > map_end)
next = map_end;
- } else
+ } else {
next = map_end;
+ }
- new_mapped_ram_size = init_range_memory_mapping(start, next);
+ mapped_ram_size += init_range_memory_mapping(start, next);
start = next;
- if (new_mapped_ram_size > mapped_ram_size)
+ if (mapped_ram_size >= step_size)
step_size = get_new_step_size(step_size);
- mapped_ram_size += new_mapped_ram_size;
}
}
@@ -674,10 +700,10 @@ void __init zone_sizes_init(void)
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+ max_zone_pfns[ZONE_DMA] = min(MAX_DMA_PFN, max_low_pfn);
#endif
#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+ max_zone_pfns[ZONE_DMA32] = min(MAX_DMA32_PFN, max_low_pfn);
#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
@@ -687,3 +713,11 @@ void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}
+void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
+{
+ /* entry 0 MUST be WB (hardwired to speed up translations) */
+ BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB);
+
+ __cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
+ __pte2cachemode_tbl[entry] = cache;
+}
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 7d05565ba781..c8140e12816a 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -537,7 +537,7 @@ static void __init pagetable_init(void)
permanent_kmaps_init(pgd_base);
}
-pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
+pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL);
EXPORT_SYMBOL_GPL(__supported_pte_mask);
/* user-defined highmem size */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5621c47d7a1a..30eb05ae7061 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -52,7 +52,6 @@
#include <asm/numa.h>
#include <asm/cacheflush.h>
#include <asm/init.h>
-#include <asm/uv/uv.h>
#include <asm/setup.h>
#include "mm_internal.h"
@@ -151,7 +150,7 @@ early_param("gbpages", parse_direct_gbpages_on);
* around without checking the pgd every time.
*/
-pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
+pteval_t __supported_pte_mask __read_mostly = ~0;
EXPORT_SYMBOL_GPL(__supported_pte_mask);
int force_personality32;
@@ -178,7 +177,7 @@ __setup("noexec32=", nonx32_setup);
* When memory was added/removed make sure all the processes MM have
* suitable PGD entries in the local PGD level page.
*/
-void sync_global_pgds(unsigned long start, unsigned long end)
+void sync_global_pgds(unsigned long start, unsigned long end, int removed)
{
unsigned long address;
@@ -186,7 +185,12 @@ void sync_global_pgds(unsigned long start, unsigned long end)
const pgd_t *pgd_ref = pgd_offset_k(address);
struct page *page;
- if (pgd_none(*pgd_ref))
+ /*
+ * When it is called after memory hot remove, pgd_none()
+ * returns true. In this case (removed == 1), we must clear
+ * the PGD entries in the local PGD level page.
+ */
+ if (pgd_none(*pgd_ref) && !removed)
continue;
spin_lock(&pgd_lock);
@@ -199,12 +203,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
+ if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
BUG_ON(pgd_page_vaddr(*pgd)
!= pgd_page_vaddr(*pgd_ref));
+ if (removed) {
+ if (pgd_none(*pgd_ref) && !pgd_none(*pgd))
+ pgd_clear(pgd);
+ } else {
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ }
+
spin_unlock(pgt_lock);
}
spin_unlock(&pgd_lock);
@@ -327,12 +337,15 @@ pte_t * __init populate_extra_pte(unsigned long vaddr)
* Create large page table mappings for a range of physical addresses.
*/
static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
- pgprot_t prot)
+ enum page_cache_mode cache)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
+ pgprot_t prot;
+ pgprot_val(prot) = pgprot_val(PAGE_KERNEL_LARGE) |
+ pgprot_val(pgprot_4k_2_large(cachemode2pgprot(cache)));
BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
pgd = pgd_offset_k((unsigned long)__va(phys));
@@ -355,12 +368,12 @@ static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
{
- __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
+ __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_WB);
}
void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
{
- __init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
+ __init_extra_mapping(phys, size, _PAGE_CACHE_MODE_UC);
}
/*
@@ -633,7 +646,7 @@ kernel_physical_mapping_init(unsigned long start,
}
if (pgd_changed)
- sync_global_pgds(addr, end - 1);
+ sync_global_pgds(addr, end - 1, 0);
__flush_tlb_all();
@@ -976,25 +989,26 @@ static void __meminit
remove_pagetable(unsigned long start, unsigned long end, bool direct)
{
unsigned long next;
+ unsigned long addr;
pgd_t *pgd;
pud_t *pud;
bool pgd_changed = false;
- for (; start < end; start = next) {
- next = pgd_addr_end(start, end);
+ for (addr = start; addr < end; addr = next) {
+ next = pgd_addr_end(addr, end);
- pgd = pgd_offset_k(start);
+ pgd = pgd_offset_k(addr);
if (!pgd_present(*pgd))
continue;
pud = (pud_t *)pgd_page_vaddr(*pgd);
- remove_pud_table(pud, start, next, direct);
+ remove_pud_table(pud, addr, next, direct);
if (free_pud_table(pud, pgd))
pgd_changed = true;
}
if (pgd_changed)
- sync_global_pgds(start, end - 1);
+ sync_global_pgds(start, end - 1, 1);
flush_tlb_all();
}
@@ -1111,7 +1125,7 @@ void mark_rodata_ro(void)
unsigned long end = (unsigned long) &__end_rodata_hpage_align;
unsigned long text_end = PFN_ALIGN(&__stop___ex_table);
unsigned long rodata_end = PFN_ALIGN(&__end_rodata);
- unsigned long all_end = PFN_ALIGN(&_end);
+ unsigned long all_end;
printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
(end - start) >> 10);
@@ -1122,7 +1136,16 @@ void mark_rodata_ro(void)
/*
* The rodata/data/bss/brk section (but not the kernel text!)
* should also be not-executable.
+ *
+ * We align all_end to PMD_SIZE because the existing mapping
+ * is a full PMD. If we would align _brk_end to PAGE_SIZE we
+ * split the PMD and the reminder between _brk_end and the end
+ * of the PMD will remain mapped executable.
+ *
+ * Any PMD which was setup after the one which covers _brk_end
+ * has been zapped already via cleanup_highmem().
*/
+ all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
rodata_test();
@@ -1181,66 +1204,15 @@ int kern_addr_valid(unsigned long addr)
return pfn_valid(pte_pfn(*pte));
}
-/*
- * A pseudo VMA to allow ptrace access for the vsyscall page. This only
- * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
- * not need special handling anymore:
- */
-static const char *gate_vma_name(struct vm_area_struct *vma)
-{
- return "[vsyscall]";
-}
-static struct vm_operations_struct gate_vma_ops = {
- .name = gate_vma_name,
-};
-static struct vm_area_struct gate_vma = {
- .vm_start = VSYSCALL_ADDR,
- .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
- .vm_page_prot = PAGE_READONLY_EXEC,
- .vm_flags = VM_READ | VM_EXEC,
- .vm_ops = &gate_vma_ops,
-};
-
-struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
-{
-#ifdef CONFIG_IA32_EMULATION
- if (!mm || mm->context.ia32_compat)
- return NULL;
-#endif
- return &gate_vma;
-}
-
-int in_gate_area(struct mm_struct *mm, unsigned long addr)
-{
- struct vm_area_struct *vma = get_gate_vma(mm);
-
- if (!vma)
- return 0;
-
- return (addr >= vma->vm_start) && (addr < vma->vm_end);
-}
-
-/*
- * Use this when you have no reliable mm, typically from interrupt
- * context. It is less reliable than using a task's mm and may give
- * false positives.
- */
-int in_gate_area_no_mm(unsigned long addr)
-{
- return (addr & PAGE_MASK) == VSYSCALL_ADDR;
-}
-
static unsigned long probe_memory_block_size(void)
{
/* start from 2g */
unsigned long bz = 1UL<<31;
-#ifdef CONFIG_X86_UV
- if (is_uv_system()) {
- printk(KERN_INFO "UV: memory block size 2GB\n");
+ if (totalram_pages >= (64ULL << (30 - PAGE_SHIFT))) {
+ pr_info("Using 2GB memory block size for large-memory system\n");
return 2UL * 1024 * 1024 * 1024;
}
-#endif
/* less than 64g installed */
if ((max_pfn << PAGE_SHIFT) < (16UL << 32))
@@ -1341,7 +1313,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
else
err = vmemmap_populate_basepages(start, end, node);
if (!err)
- sync_global_pgds(start, end - 1);
+ sync_global_pgds(start, end - 1, 0);
return err;
}
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 7b179b499fa3..9ca35fc60cfe 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -33,17 +33,17 @@ static int is_io_mapping_possible(resource_size_t base, unsigned long size)
int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot)
{
- unsigned long flag = _PAGE_CACHE_WC;
+ enum page_cache_mode pcm = _PAGE_CACHE_MODE_WC;
int ret;
if (!is_io_mapping_possible(base, size))
return -EINVAL;
- ret = io_reserve_memtype(base, base + size, &flag);
+ ret = io_reserve_memtype(base, base + size, &pcm);
if (ret)
return ret;
- *prot = __pgprot(__PAGE_KERNEL | flag);
+ *prot = __pgprot(__PAGE_KERNEL | cachemode2protval(pcm));
return 0;
}
EXPORT_SYMBOL_GPL(iomap_create_wc);
@@ -82,8 +82,10 @@ iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
* MTRR is UC or WC. UC_MINUS gets the real intention, of the
* user, which is "WC if the MTRR is WC, UC if you can't do that."
*/
- if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
- prot = PAGE_KERNEL_UC_MINUS;
+ if (!pat_enabled && pgprot_val(prot) ==
+ (__PAGE_KERNEL | cachemode2protval(_PAGE_CACHE_MODE_WC)))
+ prot = __pgprot(__PAGE_KERNEL |
+ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, prot);
}
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index baff1da354e0..fdf617c00e2f 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -29,20 +29,20 @@
* conflicts.
*/
int ioremap_change_attr(unsigned long vaddr, unsigned long size,
- unsigned long prot_val)
+ enum page_cache_mode pcm)
{
unsigned long nrpages = size >> PAGE_SHIFT;
int err;
- switch (prot_val) {
- case _PAGE_CACHE_UC:
+ switch (pcm) {
+ case _PAGE_CACHE_MODE_UC:
default:
err = _set_memory_uc(vaddr, nrpages);
break;
- case _PAGE_CACHE_WC:
+ case _PAGE_CACHE_MODE_WC:
err = _set_memory_wc(vaddr, nrpages);
break;
- case _PAGE_CACHE_WB:
+ case _PAGE_CACHE_MODE_WB:
err = _set_memory_wb(vaddr, nrpages);
break;
}
@@ -75,17 +75,18 @@ static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
* caller shouldn't need to know that small detail.
*/
static void __iomem *__ioremap_caller(resource_size_t phys_addr,
- unsigned long size, unsigned long prot_val, void *caller)
+ unsigned long size, enum page_cache_mode pcm, void *caller)
{
unsigned long offset, vaddr;
resource_size_t pfn, last_pfn, last_addr;
const resource_size_t unaligned_phys_addr = phys_addr;
const unsigned long unaligned_size = size;
struct vm_struct *area;
- unsigned long new_prot_val;
+ enum page_cache_mode new_pcm;
pgprot_t prot;
int retval;
void __iomem *ret_addr;
+ int ram_region;
/* Don't allow wraparound or zero size */
last_addr = phys_addr + size - 1;
@@ -108,12 +109,23 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
/*
* Don't allow anybody to remap normal RAM that we're using..
*/
- pfn = phys_addr >> PAGE_SHIFT;
- last_pfn = last_addr >> PAGE_SHIFT;
- if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
- __ioremap_check_ram) == 1)
+ /* First check if whole region can be identified as RAM or not */
+ ram_region = region_is_ram(phys_addr, size);
+ if (ram_region > 0) {
+ WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
+ (unsigned long int)phys_addr,
+ (unsigned long int)last_addr);
return NULL;
+ }
+ /* If could not be identified(-1), check page by page */
+ if (ram_region < 0) {
+ pfn = phys_addr >> PAGE_SHIFT;
+ last_pfn = last_addr >> PAGE_SHIFT;
+ if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+ __ioremap_check_ram) == 1)
+ return NULL;
+ }
/*
* Mappings have to be page-aligned
*/
@@ -122,38 +134,40 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
size = PAGE_ALIGN(last_addr+1) - phys_addr;
retval = reserve_memtype(phys_addr, (u64)phys_addr + size,
- prot_val, &new_prot_val);
+ pcm, &new_pcm);
if (retval) {
printk(KERN_ERR "ioremap reserve_memtype failed %d\n", retval);
return NULL;
}
- if (prot_val != new_prot_val) {
- if (!is_new_memtype_allowed(phys_addr, size,
- prot_val, new_prot_val)) {
+ if (pcm != new_pcm) {
+ if (!is_new_memtype_allowed(phys_addr, size, pcm, new_pcm)) {
printk(KERN_ERR
- "ioremap error for 0x%llx-0x%llx, requested 0x%lx, got 0x%lx\n",
+ "ioremap error for 0x%llx-0x%llx, requested 0x%x, got 0x%x\n",
(unsigned long long)phys_addr,
(unsigned long long)(phys_addr + size),
- prot_val, new_prot_val);
+ pcm, new_pcm);
goto err_free_memtype;
}
- prot_val = new_prot_val;
+ pcm = new_pcm;
}
- switch (prot_val) {
- case _PAGE_CACHE_UC:
+ prot = PAGE_KERNEL_IO;
+ switch (pcm) {
+ case _PAGE_CACHE_MODE_UC:
default:
- prot = PAGE_KERNEL_IO_NOCACHE;
+ prot = __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_UC));
break;
- case _PAGE_CACHE_UC_MINUS:
- prot = PAGE_KERNEL_IO_UC_MINUS;
+ case _PAGE_CACHE_MODE_UC_MINUS:
+ prot = __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS));
break;
- case _PAGE_CACHE_WC:
- prot = PAGE_KERNEL_IO_WC;
+ case _PAGE_CACHE_MODE_WC:
+ prot = __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_WC));
break;
- case _PAGE_CACHE_WB:
- prot = PAGE_KERNEL_IO;
+ case _PAGE_CACHE_MODE_WB:
break;
}
@@ -166,7 +180,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
area->phys_addr = phys_addr;
vaddr = (unsigned long) area->addr;
- if (kernel_map_sync_memtype(phys_addr, size, prot_val))
+ if (kernel_map_sync_memtype(phys_addr, size, pcm))
goto err_free_area;
if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot))
@@ -215,14 +229,14 @@ void __iomem *ioremap_nocache(resource_size_t phys_addr, unsigned long size)
{
/*
* Ideally, this should be:
- * pat_enabled ? _PAGE_CACHE_UC : _PAGE_CACHE_UC_MINUS;
+ * pat_enabled ? _PAGE_CACHE_MODE_UC : _PAGE_CACHE_MODE_UC_MINUS;
*
* Till we fix all X drivers to use ioremap_wc(), we will use
* UC MINUS.
*/
- unsigned long val = _PAGE_CACHE_UC_MINUS;
+ enum page_cache_mode pcm = _PAGE_CACHE_MODE_UC_MINUS;
- return __ioremap_caller(phys_addr, size, val,
+ return __ioremap_caller(phys_addr, size, pcm,
__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_nocache);
@@ -240,7 +254,7 @@ EXPORT_SYMBOL(ioremap_nocache);
void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
{
if (pat_enabled)
- return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WC,
__builtin_return_address(0));
else
return ioremap_nocache(phys_addr, size);
@@ -249,7 +263,7 @@ EXPORT_SYMBOL(ioremap_wc);
void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
{
- return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WB,
+ return __ioremap_caller(phys_addr, size, _PAGE_CACHE_MODE_WB,
__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_cache);
@@ -257,7 +271,8 @@ EXPORT_SYMBOL(ioremap_cache);
void __iomem *ioremap_prot(resource_size_t phys_addr, unsigned long size,
unsigned long prot_val)
{
- return __ioremap_caller(phys_addr, size, (prot_val & _PAGE_CACHE_MASK),
+ return __ioremap_caller(phys_addr, size,
+ pgprot2cachemode(__pgprot(prot_val)),
__builtin_return_address(0));
}
EXPORT_SYMBOL(ioremap_prot);
@@ -315,7 +330,7 @@ EXPORT_SYMBOL(iounmap);
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
* access
*/
-void *xlate_dev_mem_ptr(unsigned long phys)
+void *xlate_dev_mem_ptr(phys_addr_t phys)
{
void *addr;
unsigned long start = phys & PAGE_MASK;
@@ -331,7 +346,7 @@ void *xlate_dev_mem_ptr(unsigned long phys)
return addr;
}
-void unxlate_dev_mem_ptr(unsigned long phys, void *addr)
+void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr)
{
if (page_is_ram(phys >> PAGE_SHIFT))
return;
diff --git a/arch/x86/mm/kmemcheck/kmemcheck.c b/arch/x86/mm/kmemcheck/kmemcheck.c
index dd89a13f1051..b4f2e7e9e907 100644
--- a/arch/x86/mm/kmemcheck/kmemcheck.c
+++ b/arch/x86/mm/kmemcheck/kmemcheck.c
@@ -140,7 +140,7 @@ static DEFINE_PER_CPU(struct kmemcheck_context, kmemcheck_context);
bool kmemcheck_active(struct pt_regs *regs)
{
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
return data->balance > 0;
}
@@ -148,7 +148,7 @@ bool kmemcheck_active(struct pt_regs *regs)
/* Save an address that needs to be shown/hidden */
static void kmemcheck_save_addr(unsigned long addr)
{
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
BUG_ON(data->n_addrs >= ARRAY_SIZE(data->addr));
data->addr[data->n_addrs++] = addr;
@@ -156,7 +156,7 @@ static void kmemcheck_save_addr(unsigned long addr)
static unsigned int kmemcheck_show_all(void)
{
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
unsigned int i;
unsigned int n;
@@ -169,7 +169,7 @@ static unsigned int kmemcheck_show_all(void)
static unsigned int kmemcheck_hide_all(void)
{
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
unsigned int i;
unsigned int n;
@@ -185,7 +185,7 @@ static unsigned int kmemcheck_hide_all(void)
*/
void kmemcheck_show(struct pt_regs *regs)
{
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
BUG_ON(!irqs_disabled());
@@ -226,7 +226,7 @@ void kmemcheck_show(struct pt_regs *regs)
*/
void kmemcheck_hide(struct pt_regs *regs)
{
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
int n;
BUG_ON(!irqs_disabled());
@@ -528,7 +528,7 @@ static void kmemcheck_access(struct pt_regs *regs,
const uint8_t *insn_primary;
unsigned int size;
- struct kmemcheck_context *data = &__get_cpu_var(kmemcheck_context);
+ struct kmemcheck_context *data = this_cpu_ptr(&kmemcheck_context);
/* Recursive fault -- ouch. */
if (data->busy) {
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
index 6b563a118891..62474ba66c8e 100644
--- a/arch/x86/mm/mm_internal.h
+++ b/arch/x86/mm/mm_internal.h
@@ -16,4 +16,6 @@ void zone_sizes_init(void);
extern int after_bootmem;
+void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
+
#endif /* __X86_MM_INTERNAL_H */
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
new file mode 100644
index 000000000000..67ebf5751222
--- /dev/null
+++ b/arch/x86/mm/mpx.c
@@ -0,0 +1,928 @@
+/*
+ * mpx.c - Memory Protection eXtensions
+ *
+ * Copyright (c) 2014, Intel Corporation.
+ * Qiaowei Ren <qiaowei.ren@intel.com>
+ * Dave Hansen <dave.hansen@intel.com>
+ */
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/sched/sysctl.h>
+
+#include <asm/i387.h>
+#include <asm/insn.h>
+#include <asm/mman.h>
+#include <asm/mmu_context.h>
+#include <asm/mpx.h>
+#include <asm/processor.h>
+#include <asm/fpu-internal.h>
+
+static const char *mpx_mapping_name(struct vm_area_struct *vma)
+{
+ return "[mpx]";
+}
+
+static struct vm_operations_struct mpx_vma_ops = {
+ .name = mpx_mapping_name,
+};
+
+static int is_mpx_vma(struct vm_area_struct *vma)
+{
+ return (vma->vm_ops == &mpx_vma_ops);
+}
+
+/*
+ * This is really a simplified "vm_mmap". it only handles MPX
+ * bounds tables (the bounds directory is user-allocated).
+ *
+ * Later on, we use the vma->vm_ops to uniquely identify these
+ * VMAs.
+ */
+static unsigned long mpx_mmap(unsigned long len)
+{
+ unsigned long ret;
+ unsigned long addr, pgoff;
+ struct mm_struct *mm = current->mm;
+ vm_flags_t vm_flags;
+ struct vm_area_struct *vma;
+
+ /* Only bounds table and bounds directory can be allocated here */
+ if (len != MPX_BD_SIZE_BYTES && len != MPX_BT_SIZE_BYTES)
+ return -EINVAL;
+
+ down_write(&mm->mmap_sem);
+
+ /* Too many mappings? */
+ if (mm->map_count > sysctl_max_map_count) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* Obtain the address to map to. we verify (or select) it and ensure
+ * that it represents a valid section of the address space.
+ */
+ addr = get_unmapped_area(NULL, 0, len, 0, MAP_ANONYMOUS | MAP_PRIVATE);
+ if (addr & ~PAGE_MASK) {
+ ret = addr;
+ goto out;
+ }
+
+ vm_flags = VM_READ | VM_WRITE | VM_MPX |
+ mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
+
+ /* Set pgoff according to addr for anon_vma */
+ pgoff = addr >> PAGE_SHIFT;
+
+ ret = mmap_region(NULL, addr, len, vm_flags, pgoff);
+ if (IS_ERR_VALUE(ret))
+ goto out;
+
+ vma = find_vma(mm, ret);
+ if (!vma) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ vma->vm_ops = &mpx_vma_ops;
+
+ if (vm_flags & VM_LOCKED) {
+ up_write(&mm->mmap_sem);
+ mm_populate(ret, len);
+ return ret;
+ }
+
+out:
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+enum reg_type {
+ REG_TYPE_RM = 0,
+ REG_TYPE_INDEX,
+ REG_TYPE_BASE,
+};
+
+static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
+ enum reg_type type)
+{
+ int regno = 0;
+
+ static const int regoff[] = {
+ offsetof(struct pt_regs, ax),
+ offsetof(struct pt_regs, cx),
+ offsetof(struct pt_regs, dx),
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, sp),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+ offsetof(struct pt_regs, r8),
+ offsetof(struct pt_regs, r9),
+ offsetof(struct pt_regs, r10),
+ offsetof(struct pt_regs, r11),
+ offsetof(struct pt_regs, r12),
+ offsetof(struct pt_regs, r13),
+ offsetof(struct pt_regs, r14),
+ offsetof(struct pt_regs, r15),
+#endif
+ };
+ int nr_registers = ARRAY_SIZE(regoff);
+ /*
+ * Don't possibly decode a 32-bit instructions as
+ * reading a 64-bit-only register.
+ */
+ if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
+ nr_registers -= 8;
+
+ switch (type) {
+ case REG_TYPE_RM:
+ regno = X86_MODRM_RM(insn->modrm.value);
+ if (X86_REX_B(insn->rex_prefix.value) == 1)
+ regno += 8;
+ break;
+
+ case REG_TYPE_INDEX:
+ regno = X86_SIB_INDEX(insn->sib.value);
+ if (X86_REX_X(insn->rex_prefix.value) == 1)
+ regno += 8;
+ break;
+
+ case REG_TYPE_BASE:
+ regno = X86_SIB_BASE(insn->sib.value);
+ if (X86_REX_B(insn->rex_prefix.value) == 1)
+ regno += 8;
+ break;
+
+ default:
+ pr_err("invalid register type");
+ BUG();
+ break;
+ }
+
+ if (regno > nr_registers) {
+ WARN_ONCE(1, "decoded an instruction with an invalid register");
+ return -EINVAL;
+ }
+ return regoff[regno];
+}
+
+/*
+ * return the address being referenced be instruction
+ * for rm=3 returning the content of the rm reg
+ * for rm!=3 calculates the address using SIB and Disp
+ */
+static void __user *mpx_get_addr_ref(struct insn *insn, struct pt_regs *regs)
+{
+ unsigned long addr, base, indx;
+ int addr_offset, base_offset, indx_offset;
+ insn_byte_t sib;
+
+ insn_get_modrm(insn);
+ insn_get_sib(insn);
+ sib = insn->sib.value;
+
+ if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+ addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+ if (addr_offset < 0)
+ goto out_err;
+ addr = regs_get_register(regs, addr_offset);
+ } else {
+ if (insn->sib.nbytes) {
+ base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
+ if (base_offset < 0)
+ goto out_err;
+
+ indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
+ if (indx_offset < 0)
+ goto out_err;
+
+ base = regs_get_register(regs, base_offset);
+ indx = regs_get_register(regs, indx_offset);
+ addr = base + indx * (1 << X86_SIB_SCALE(sib));
+ } else {
+ addr_offset = get_reg_offset(insn, regs, REG_TYPE_RM);
+ if (addr_offset < 0)
+ goto out_err;
+ addr = regs_get_register(regs, addr_offset);
+ }
+ addr += insn->displacement.value;
+ }
+ return (void __user *)addr;
+out_err:
+ return (void __user *)-1;
+}
+
+static int mpx_insn_decode(struct insn *insn,
+ struct pt_regs *regs)
+{
+ unsigned char buf[MAX_INSN_SIZE];
+ int x86_64 = !test_thread_flag(TIF_IA32);
+ int not_copied;
+ int nr_copied;
+
+ not_copied = copy_from_user(buf, (void __user *)regs->ip, sizeof(buf));
+ nr_copied = sizeof(buf) - not_copied;
+ /*
+ * The decoder _should_ fail nicely if we pass it a short buffer.
+ * But, let's not depend on that implementation detail. If we
+ * did not get anything, just error out now.
+ */
+ if (!nr_copied)
+ return -EFAULT;
+ insn_init(insn, buf, nr_copied, x86_64);
+ insn_get_length(insn);
+ /*
+ * copy_from_user() tries to get as many bytes as we could see in
+ * the largest possible instruction. If the instruction we are
+ * after is shorter than that _and_ we attempt to copy from
+ * something unreadable, we might get a short read. This is OK
+ * as long as the read did not stop in the middle of the
+ * instruction. Check to see if we got a partial instruction.
+ */
+ if (nr_copied < insn->length)
+ return -EFAULT;
+
+ insn_get_opcode(insn);
+ /*
+ * We only _really_ need to decode bndcl/bndcn/bndcu
+ * Error out on anything else.
+ */
+ if (insn->opcode.bytes[0] != 0x0f)
+ goto bad_opcode;
+ if ((insn->opcode.bytes[1] != 0x1a) &&
+ (insn->opcode.bytes[1] != 0x1b))
+ goto bad_opcode;
+
+ return 0;
+bad_opcode:
+ return -EINVAL;
+}
+
+/*
+ * If a bounds overflow occurs then a #BR is generated. This
+ * function decodes MPX instructions to get violation address
+ * and set this address into extended struct siginfo.
+ *
+ * Note that this is not a super precise way of doing this.
+ * Userspace could have, by the time we get here, written
+ * anything it wants in to the instructions. We can not
+ * trust anything about it. They might not be valid
+ * instructions or might encode invalid registers, etc...
+ *
+ * The caller is expected to kfree() the returned siginfo_t.
+ */
+siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
+ struct xsave_struct *xsave_buf)
+{
+ struct bndreg *bndregs, *bndreg;
+ siginfo_t *info = NULL;
+ struct insn insn;
+ uint8_t bndregno;
+ int err;
+
+ err = mpx_insn_decode(&insn, regs);
+ if (err)
+ goto err_out;
+
+ /*
+ * We know at this point that we are only dealing with
+ * MPX instructions.
+ */
+ insn_get_modrm(&insn);
+ bndregno = X86_MODRM_REG(insn.modrm.value);
+ if (bndregno > 3) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ /* get the bndregs _area_ of the xsave structure */
+ bndregs = get_xsave_addr(xsave_buf, XSTATE_BNDREGS);
+ if (!bndregs) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ /* now go select the individual register in the set of 4 */
+ bndreg = &bndregs[bndregno];
+
+ info = kzalloc(sizeof(*info), GFP_KERNEL);
+ if (!info) {
+ err = -ENOMEM;
+ goto err_out;
+ }
+ /*
+ * The registers are always 64-bit, but the upper 32
+ * bits are ignored in 32-bit mode. Also, note that the
+ * upper bounds are architecturally represented in 1's
+ * complement form.
+ *
+ * The 'unsigned long' cast is because the compiler
+ * complains when casting from integers to different-size
+ * pointers.
+ */
+ info->si_lower = (void __user *)(unsigned long)bndreg->lower_bound;
+ info->si_upper = (void __user *)(unsigned long)~bndreg->upper_bound;
+ info->si_addr_lsb = 0;
+ info->si_signo = SIGSEGV;
+ info->si_errno = 0;
+ info->si_code = SEGV_BNDERR;
+ info->si_addr = mpx_get_addr_ref(&insn, regs);
+ /*
+ * We were not able to extract an address from the instruction,
+ * probably because there was something invalid in it.
+ */
+ if (info->si_addr == (void *)-1) {
+ err = -EINVAL;
+ goto err_out;
+ }
+ return info;
+err_out:
+ /* info might be NULL, but kfree() handles that */
+ kfree(info);
+ return ERR_PTR(err);
+}
+
+static __user void *task_get_bounds_dir(struct task_struct *tsk)
+{
+ struct bndcsr *bndcsr;
+
+ if (!cpu_feature_enabled(X86_FEATURE_MPX))
+ return MPX_INVALID_BOUNDS_DIR;
+
+ /*
+ * The bounds directory pointer is stored in a register
+ * only accessible if we first do an xsave.
+ */
+ fpu_save_init(&tsk->thread.fpu);
+ bndcsr = get_xsave_addr(&tsk->thread.fpu.state->xsave, XSTATE_BNDCSR);
+ if (!bndcsr)
+ return MPX_INVALID_BOUNDS_DIR;
+
+ /*
+ * Make sure the register looks valid by checking the
+ * enable bit.
+ */
+ if (!(bndcsr->bndcfgu & MPX_BNDCFG_ENABLE_FLAG))
+ return MPX_INVALID_BOUNDS_DIR;
+
+ /*
+ * Lastly, mask off the low bits used for configuration
+ * flags, and return the address of the bounds table.
+ */
+ return (void __user *)(unsigned long)
+ (bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK);
+}
+
+int mpx_enable_management(struct task_struct *tsk)
+{
+ void __user *bd_base = MPX_INVALID_BOUNDS_DIR;
+ struct mm_struct *mm = tsk->mm;
+ int ret = 0;
+
+ /*
+ * runtime in the userspace will be responsible for allocation of
+ * the bounds directory. Then, it will save the base of the bounds
+ * directory into XSAVE/XRSTOR Save Area and enable MPX through
+ * XRSTOR instruction.
+ *
+ * fpu_xsave() is expected to be very expensive. Storing the bounds
+ * directory here means that we do not have to do xsave in the unmap
+ * path; we can just use mm->bd_addr instead.
+ */
+ bd_base = task_get_bounds_dir(tsk);
+ down_write(&mm->mmap_sem);
+ mm->bd_addr = bd_base;
+ if (mm->bd_addr == MPX_INVALID_BOUNDS_DIR)
+ ret = -ENXIO;
+
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+int mpx_disable_management(struct task_struct *tsk)
+{
+ struct mm_struct *mm = current->mm;
+
+ if (!cpu_feature_enabled(X86_FEATURE_MPX))
+ return -ENXIO;
+
+ down_write(&mm->mmap_sem);
+ mm->bd_addr = MPX_INVALID_BOUNDS_DIR;
+ up_write(&mm->mmap_sem);
+ return 0;
+}
+
+/*
+ * With 32-bit mode, MPX_BT_SIZE_BYTES is 4MB, and the size of each
+ * bounds table is 16KB. With 64-bit mode, MPX_BT_SIZE_BYTES is 2GB,
+ * and the size of each bounds table is 4MB.
+ */
+static int allocate_bt(long __user *bd_entry)
+{
+ unsigned long expected_old_val = 0;
+ unsigned long actual_old_val = 0;
+ unsigned long bt_addr;
+ int ret = 0;
+
+ /*
+ * Carve the virtual space out of userspace for the new
+ * bounds table:
+ */
+ bt_addr = mpx_mmap(MPX_BT_SIZE_BYTES);
+ if (IS_ERR((void *)bt_addr))
+ return PTR_ERR((void *)bt_addr);
+ /*
+ * Set the valid flag (kinda like _PAGE_PRESENT in a pte)
+ */
+ bt_addr = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+
+ /*
+ * Go poke the address of the new bounds table in to the
+ * bounds directory entry out in userspace memory. Note:
+ * we may race with another CPU instantiating the same table.
+ * In that case the cmpxchg will see an unexpected
+ * 'actual_old_val'.
+ *
+ * This can fault, but that's OK because we do not hold
+ * mmap_sem at this point, unlike some of the other part
+ * of the MPX code that have to pagefault_disable().
+ */
+ ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
+ expected_old_val, bt_addr);
+ if (ret)
+ goto out_unmap;
+
+ /*
+ * The user_atomic_cmpxchg_inatomic() will only return nonzero
+ * for faults, *not* if the cmpxchg itself fails. Now we must
+ * verify that the cmpxchg itself completed successfully.
+ */
+ /*
+ * We expected an empty 'expected_old_val', but instead found
+ * an apparently valid entry. Assume we raced with another
+ * thread to instantiate this table and desclare succecss.
+ */
+ if (actual_old_val & MPX_BD_ENTRY_VALID_FLAG) {
+ ret = 0;
+ goto out_unmap;
+ }
+ /*
+ * We found a non-empty bd_entry but it did not have the
+ * VALID_FLAG set. Return an error which will result in
+ * a SEGV since this probably means that somebody scribbled
+ * some invalid data in to a bounds table.
+ */
+ if (expected_old_val != actual_old_val) {
+ ret = -EINVAL;
+ goto out_unmap;
+ }
+ return 0;
+out_unmap:
+ vm_munmap(bt_addr & MPX_BT_ADDR_MASK, MPX_BT_SIZE_BYTES);
+ return ret;
+}
+
+/*
+ * When a BNDSTX instruction attempts to save bounds to a bounds
+ * table, it will first attempt to look up the table in the
+ * first-level bounds directory. If it does not find a table in
+ * the directory, a #BR is generated and we get here in order to
+ * allocate a new table.
+ *
+ * With 32-bit mode, the size of BD is 4MB, and the size of each
+ * bound table is 16KB. With 64-bit mode, the size of BD is 2GB,
+ * and the size of each bound table is 4MB.
+ */
+static int do_mpx_bt_fault(struct xsave_struct *xsave_buf)
+{
+ unsigned long bd_entry, bd_base;
+ struct bndcsr *bndcsr;
+
+ bndcsr = get_xsave_addr(xsave_buf, XSTATE_BNDCSR);
+ if (!bndcsr)
+ return -EINVAL;
+ /*
+ * Mask off the preserve and enable bits
+ */
+ bd_base = bndcsr->bndcfgu & MPX_BNDCFG_ADDR_MASK;
+ /*
+ * The hardware provides the address of the missing or invalid
+ * entry via BNDSTATUS, so we don't have to go look it up.
+ */
+ bd_entry = bndcsr->bndstatus & MPX_BNDSTA_ADDR_MASK;
+ /*
+ * Make sure the directory entry is within where we think
+ * the directory is.
+ */
+ if ((bd_entry < bd_base) ||
+ (bd_entry >= bd_base + MPX_BD_SIZE_BYTES))
+ return -EINVAL;
+
+ return allocate_bt((long __user *)bd_entry);
+}
+
+int mpx_handle_bd_fault(struct xsave_struct *xsave_buf)
+{
+ /*
+ * Userspace never asked us to manage the bounds tables,
+ * so refuse to help.
+ */
+ if (!kernel_managing_mpx_tables(current->mm))
+ return -EINVAL;
+
+ if (do_mpx_bt_fault(xsave_buf)) {
+ force_sig(SIGSEGV, current);
+ /*
+ * The force_sig() is essentially "handling" this
+ * exception, so we do not pass up the error
+ * from do_mpx_bt_fault().
+ */
+ }
+ return 0;
+}
+
+/*
+ * A thin wrapper around get_user_pages(). Returns 0 if the
+ * fault was resolved or -errno if not.
+ */
+static int mpx_resolve_fault(long __user *addr, int write)
+{
+ long gup_ret;
+ int nr_pages = 1;
+ int force = 0;
+
+ gup_ret = get_user_pages(current, current->mm, (unsigned long)addr,
+ nr_pages, write, force, NULL, NULL);
+ /*
+ * get_user_pages() returns number of pages gotten.
+ * 0 means we failed to fault in and get anything,
+ * probably because 'addr' is bad.
+ */
+ if (!gup_ret)
+ return -EFAULT;
+ /* Other error, return it */
+ if (gup_ret < 0)
+ return gup_ret;
+ /* must have gup'd a page and gup_ret>0, success */
+ return 0;
+}
+
+/*
+ * Get the base of bounds tables pointed by specific bounds
+ * directory entry.
+ */
+static int get_bt_addr(struct mm_struct *mm,
+ long __user *bd_entry, unsigned long *bt_addr)
+{
+ int ret;
+ int valid_bit;
+
+ if (!access_ok(VERIFY_READ, (bd_entry), sizeof(*bd_entry)))
+ return -EFAULT;
+
+ while (1) {
+ int need_write = 0;
+
+ pagefault_disable();
+ ret = get_user(*bt_addr, bd_entry);
+ pagefault_enable();
+ if (!ret)
+ break;
+ if (ret == -EFAULT)
+ ret = mpx_resolve_fault(bd_entry, need_write);
+ /*
+ * If we could not resolve the fault, consider it
+ * userspace's fault and error out.
+ */
+ if (ret)
+ return ret;
+ }
+
+ valid_bit = *bt_addr & MPX_BD_ENTRY_VALID_FLAG;
+ *bt_addr &= MPX_BT_ADDR_MASK;
+
+ /*
+ * When the kernel is managing bounds tables, a bounds directory
+ * entry will either have a valid address (plus the valid bit)
+ * *OR* be completely empty. If we see a !valid entry *and* some
+ * data in the address field, we know something is wrong. This
+ * -EINVAL return will cause a SIGSEGV.
+ */
+ if (!valid_bit && *bt_addr)
+ return -EINVAL;
+ /*
+ * Do we have an completely zeroed bt entry? That is OK. It
+ * just means there was no bounds table for this memory. Make
+ * sure to distinguish this from -EINVAL, which will cause
+ * a SEGV.
+ */
+ if (!valid_bit)
+ return -ENOENT;
+
+ return 0;
+}
+
+/*
+ * Free the backing physical pages of bounds table 'bt_addr'.
+ * Assume start...end is within that bounds table.
+ */
+static int zap_bt_entries(struct mm_struct *mm,
+ unsigned long bt_addr,
+ unsigned long start, unsigned long end)
+{
+ struct vm_area_struct *vma;
+ unsigned long addr, len;
+
+ /*
+ * Find the first overlapping vma. If vma->vm_start > start, there
+ * will be a hole in the bounds table. This -EINVAL return will
+ * cause a SIGSEGV.
+ */
+ vma = find_vma(mm, start);
+ if (!vma || vma->vm_start > start)
+ return -EINVAL;
+
+ /*
+ * A NUMA policy on a VM_MPX VMA could cause this bouds table to
+ * be split. So we need to look across the entire 'start -> end'
+ * range of this bounds table, find all of the VM_MPX VMAs, and
+ * zap only those.
+ */
+ addr = start;
+ while (vma && vma->vm_start < end) {
+ /*
+ * We followed a bounds directory entry down
+ * here. If we find a non-MPX VMA, that's bad,
+ * so stop immediately and return an error. This
+ * probably results in a SIGSEGV.
+ */
+ if (!is_mpx_vma(vma))
+ return -EINVAL;
+
+ len = min(vma->vm_end, end) - addr;
+ zap_page_range(vma, addr, len, NULL);
+
+ vma = vma->vm_next;
+ addr = vma->vm_start;
+ }
+
+ return 0;
+}
+
+static int unmap_single_bt(struct mm_struct *mm,
+ long __user *bd_entry, unsigned long bt_addr)
+{
+ unsigned long expected_old_val = bt_addr | MPX_BD_ENTRY_VALID_FLAG;
+ unsigned long actual_old_val = 0;
+ int ret;
+
+ while (1) {
+ int need_write = 1;
+
+ pagefault_disable();
+ ret = user_atomic_cmpxchg_inatomic(&actual_old_val, bd_entry,
+ expected_old_val, 0);
+ pagefault_enable();
+ if (!ret)
+ break;
+ if (ret == -EFAULT)
+ ret = mpx_resolve_fault(bd_entry, need_write);
+ /*
+ * If we could not resolve the fault, consider it
+ * userspace's fault and error out.
+ */
+ if (ret)
+ return ret;
+ }
+ /*
+ * The cmpxchg was performed, check the results.
+ */
+ if (actual_old_val != expected_old_val) {
+ /*
+ * Someone else raced with us to unmap the table.
+ * There was no bounds table pointed to by the
+ * directory, so declare success. Somebody freed
+ * it.
+ */
+ if (!actual_old_val)
+ return 0;
+ /*
+ * Something messed with the bounds directory
+ * entry. We hold mmap_sem for read or write
+ * here, so it could not be a _new_ bounds table
+ * that someone just allocated. Something is
+ * wrong, so pass up the error and SIGSEGV.
+ */
+ return -EINVAL;
+ }
+
+ /*
+ * Note, we are likely being called under do_munmap() already. To
+ * avoid recursion, do_munmap() will check whether it comes
+ * from one bounds table through VM_MPX flag.
+ */
+ return do_munmap(mm, bt_addr, MPX_BT_SIZE_BYTES);
+}
+
+/*
+ * If the bounds table pointed by bounds directory 'bd_entry' is
+ * not shared, unmap this whole bounds table. Otherwise, only free
+ * those backing physical pages of bounds table entries covered
+ * in this virtual address region start...end.
+ */
+static int unmap_shared_bt(struct mm_struct *mm,
+ long __user *bd_entry, unsigned long start,
+ unsigned long end, bool prev_shared, bool next_shared)
+{
+ unsigned long bt_addr;
+ int ret;
+
+ ret = get_bt_addr(mm, bd_entry, &bt_addr);
+ /*
+ * We could see an "error" ret for not-present bounds
+ * tables (not really an error), or actual errors, but
+ * stop unmapping either way.
+ */
+ if (ret)
+ return ret;
+
+ if (prev_shared && next_shared)
+ ret = zap_bt_entries(mm, bt_addr,
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
+ else if (prev_shared)
+ ret = zap_bt_entries(mm, bt_addr,
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(start),
+ bt_addr+MPX_BT_SIZE_BYTES);
+ else if (next_shared)
+ ret = zap_bt_entries(mm, bt_addr, bt_addr,
+ bt_addr+MPX_GET_BT_ENTRY_OFFSET(end));
+ else
+ ret = unmap_single_bt(mm, bd_entry, bt_addr);
+
+ return ret;
+}
+
+/*
+ * A virtual address region being munmap()ed might share bounds table
+ * with adjacent VMAs. We only need to free the backing physical
+ * memory of these shared bounds tables entries covered in this virtual
+ * address region.
+ */
+static int unmap_edge_bts(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ int ret;
+ long __user *bde_start, *bde_end;
+ struct vm_area_struct *prev, *next;
+ bool prev_shared = false, next_shared = false;
+
+ bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
+ bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
+
+ /*
+ * Check whether bde_start and bde_end are shared with adjacent
+ * VMAs.
+ *
+ * We already unliked the VMAs from the mm's rbtree so 'start'
+ * is guaranteed to be in a hole. This gets us the first VMA
+ * before the hole in to 'prev' and the next VMA after the hole
+ * in to 'next'.
+ */
+ next = find_vma_prev(mm, start, &prev);
+ if (prev && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(prev->vm_end-1))
+ == bde_start)
+ prev_shared = true;
+ if (next && (mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(next->vm_start))
+ == bde_end)
+ next_shared = true;
+
+ /*
+ * This virtual address region being munmap()ed is only
+ * covered by one bounds table.
+ *
+ * In this case, if this table is also shared with adjacent
+ * VMAs, only part of the backing physical memory of the bounds
+ * table need be freeed. Otherwise the whole bounds table need
+ * be unmapped.
+ */
+ if (bde_start == bde_end) {
+ return unmap_shared_bt(mm, bde_start, start, end,
+ prev_shared, next_shared);
+ }
+
+ /*
+ * If more than one bounds tables are covered in this virtual
+ * address region being munmap()ed, we need to separately check
+ * whether bde_start and bde_end are shared with adjacent VMAs.
+ */
+ ret = unmap_shared_bt(mm, bde_start, start, end, prev_shared, false);
+ if (ret)
+ return ret;
+ ret = unmap_shared_bt(mm, bde_end, start, end, false, next_shared);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static int mpx_unmap_tables(struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ int ret;
+ long __user *bd_entry, *bde_start, *bde_end;
+ unsigned long bt_addr;
+
+ /*
+ * "Edge" bounds tables are those which are being used by the region
+ * (start -> end), but that may be shared with adjacent areas. If they
+ * turn out to be completely unshared, they will be freed. If they are
+ * shared, we will free the backing store (like an MADV_DONTNEED) for
+ * areas used by this region.
+ */
+ ret = unmap_edge_bts(mm, start, end);
+ switch (ret) {
+ /* non-present tables are OK */
+ case 0:
+ case -ENOENT:
+ /* Success, or no tables to unmap */
+ break;
+ case -EINVAL:
+ case -EFAULT:
+ default:
+ return ret;
+ }
+
+ /*
+ * Only unmap the bounds table that are
+ * 1. fully covered
+ * 2. not at the edges of the mapping, even if full aligned
+ */
+ bde_start = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(start);
+ bde_end = mm->bd_addr + MPX_GET_BD_ENTRY_OFFSET(end-1);
+ for (bd_entry = bde_start + 1; bd_entry < bde_end; bd_entry++) {
+ ret = get_bt_addr(mm, bd_entry, &bt_addr);
+ switch (ret) {
+ case 0:
+ break;
+ case -ENOENT:
+ /* No table here, try the next one */
+ continue;
+ case -EINVAL:
+ case -EFAULT:
+ default:
+ /*
+ * Note: we are being strict here.
+ * Any time we run in to an issue
+ * unmapping tables, we stop and
+ * SIGSEGV.
+ */
+ return ret;
+ }
+
+ ret = unmap_single_bt(mm, bd_entry, bt_addr);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+/*
+ * Free unused bounds tables covered in a virtual address region being
+ * munmap()ed. Assume end > start.
+ *
+ * This function will be called by do_munmap(), and the VMAs covering
+ * the virtual address region start...end have already been split if
+ * necessary, and the 'vma' is the first vma in this range (start -> end).
+ */
+void mpx_notify_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ int ret;
+
+ /*
+ * Refuse to do anything unless userspace has asked
+ * the kernel to help manage the bounds tables,
+ */
+ if (!kernel_managing_mpx_tables(current->mm))
+ return;
+ /*
+ * This will look across the entire 'start -> end' range,
+ * and find all of the non-VM_MPX VMAs.
+ *
+ * To avoid recursion, if a VM_MPX vma is found in the range
+ * (start->end), we will not continue follow-up work. This
+ * recursion represents having bounds tables for bounds tables,
+ * which should not occur normally. Being strict about it here
+ * helps ensure that we do not have an exploitable stack overflow.
+ */
+ do {
+ if (vma->vm_flags & VM_MPX)
+ return;
+ vma = vma->vm_next;
+ } while (vma && vma->vm_start < end);
+
+ ret = mpx_unmap_tables(mm, start, end);
+ if (ret)
+ force_sig(SIGSEGV, current);
+}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index a32b706c401a..1a883705a12a 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -185,8 +185,8 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
return numa_add_memblk_to(nid, start, end, &numa_meminfo);
}
-/* Initialize NODE_DATA for a node on the local memory */
-static void __init setup_node_data(int nid, u64 start, u64 end)
+/* Allocate NODE_DATA for a node on the local memory */
+static void __init alloc_node_data(int nid)
{
const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
u64 nd_pa;
@@ -194,18 +194,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
int tnid;
/*
- * Don't confuse VM with a node that doesn't have the
- * minimum amount of memory:
- */
- if (end && (end - start) < NODE_MIN_SIZE)
- return;
-
- start = roundup(start, ZONE_ALIGN);
-
- printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
- nid, start, end - 1);
-
- /*
* Allocate node data. Try node-local memory and then any node.
* Never allocate in DMA zone.
*/
@@ -222,7 +210,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
nd = __va(nd_pa);
/* report and initialize */
- printk(KERN_INFO " NODE_DATA [mem %#010Lx-%#010Lx]\n",
+ printk(KERN_INFO "NODE_DATA(%d) allocated [mem %#010Lx-%#010Lx]\n", nid,
nd_pa, nd_pa + nd_size - 1);
tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
if (tnid != nid)
@@ -230,9 +218,6 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
node_data[nid] = nd;
memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
- NODE_DATA(nid)->node_id = nid;
- NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
- NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;
node_set_online(nid);
}
@@ -478,6 +463,42 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
return true;
}
+static void __init numa_clear_kernel_node_hotplug(void)
+{
+ int i, nid;
+ nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
+ unsigned long start, end;
+ struct memblock_region *r;
+
+ /*
+ * At this time, all memory regions reserved by memblock are
+ * used by the kernel. Set the nid in memblock.reserved will
+ * mark out all the nodes the kernel resides in.
+ */
+ for (i = 0; i < numa_meminfo.nr_blks; i++) {
+ struct numa_memblk *mb = &numa_meminfo.blk[i];
+
+ memblock_set_node(mb->start, mb->end - mb->start,
+ &memblock.reserved, mb->nid);
+ }
+
+ /* Mark all kernel nodes. */
+ for_each_memblock(reserved, r)
+ node_set(r->nid, numa_kernel_nodes);
+
+ /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
+ for (i = 0; i < numa_meminfo.nr_blks; i++) {
+ nid = numa_meminfo.blk[i].nid;
+ if (!node_isset(nid, numa_kernel_nodes))
+ continue;
+
+ start = numa_meminfo.blk[i].start;
+ end = numa_meminfo.blk[i].end;
+
+ memblock_clear_hotplug(start, end - start);
+ }
+}
+
static int __init numa_register_memblks(struct numa_meminfo *mi)
{
unsigned long uninitialized_var(pfn_align);
@@ -496,6 +517,15 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
}
/*
+ * At very early time, the kernel have to use some memory such as
+ * loading the kernel image. We cannot prevent this anyway. So any
+ * node the kernel resides in should be un-hotpluggable.
+ *
+ * And when we come here, alloc node data won't fail.
+ */
+ numa_clear_kernel_node_hotplug();
+
+ /*
* If sections array is gonna be used for pfn -> nid mapping, check
* whether its granularity is fine enough.
*/
@@ -523,8 +553,17 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
end = max(mi->blk[i].end, end);
}
- if (start < end)
- setup_node_data(nid, start, end);
+ if (start >= end)
+ continue;
+
+ /*
+ * Don't confuse VM with a node that doesn't have the
+ * minimum amount of memory:
+ */
+ if (end && (end - start) < NODE_MIN_SIZE)
+ continue;
+
+ alloc_node_data(nid);
}
/* Dump memblock with node info and return. */
@@ -554,41 +593,6 @@ static void __init numa_init_array(void)
}
}
-static void __init numa_clear_kernel_node_hotplug(void)
-{
- int i, nid;
- nodemask_t numa_kernel_nodes = NODE_MASK_NONE;
- unsigned long start, end;
- struct memblock_region *r;
-
- /*
- * At this time, all memory regions reserved by memblock are
- * used by the kernel. Set the nid in memblock.reserved will
- * mark out all the nodes the kernel resides in.
- */
- for (i = 0; i < numa_meminfo.nr_blks; i++) {
- struct numa_memblk *mb = &numa_meminfo.blk[i];
- memblock_set_node(mb->start, mb->end - mb->start,
- &memblock.reserved, mb->nid);
- }
-
- /* Mark all kernel nodes. */
- for_each_memblock(reserved, r)
- node_set(r->nid, numa_kernel_nodes);
-
- /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */
- for (i = 0; i < numa_meminfo.nr_blks; i++) {
- nid = numa_meminfo.blk[i].nid;
- if (!node_isset(nid, numa_kernel_nodes))
- continue;
-
- start = numa_meminfo.blk[i].start;
- end = numa_meminfo.blk[i].end;
-
- memblock_clear_hotplug(start, end - start);
- }
-}
-
static int __init numa_init(int (*init_func)(void))
{
int i;
@@ -643,15 +647,6 @@ static int __init numa_init(int (*init_func)(void))
}
numa_init_array();
- /*
- * At very early time, the kernel have to use some memory such as
- * loading the kernel image. We cannot prevent this anyway. So any
- * node the kernel resides in should be un-hotpluggable.
- *
- * And when we come here, numa_init() won't fail.
- */
- numa_clear_kernel_node_hotplug();
-
return 0;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index ae242a7c11c7..536ea2fb6e33 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -384,6 +384,26 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
}
/*
+ * Lookup the PMD entry for a virtual address. Return a pointer to the entry
+ * or NULL if not present.
+ */
+pmd_t *lookup_pmd_address(unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+
+ pgd = pgd_offset_k(address);
+ if (pgd_none(*pgd))
+ return NULL;
+
+ pud = pud_offset(pgd, address);
+ if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud))
+ return NULL;
+
+ return pmd_offset(pud, address);
+}
+
+/*
* This is necessary because __pa() does not work on some
* kinds of memory, like vmalloc() or the alloc_remap()
* areas on 32-bit NUMA systems. The percpu areas can
@@ -409,7 +429,7 @@ phys_addr_t slow_virt_to_phys(void *__virt_addr)
psize = page_level_size(level);
pmask = page_level_mask(level);
offset = virt_addr & ~pmask;
- phys_addr = pte_pfn(*pte) << PAGE_SHIFT;
+ phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
return (phys_addr | offset);
}
EXPORT_SYMBOL_GPL(slow_virt_to_phys);
@@ -485,14 +505,23 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
/*
* We are safe now. Check whether the new pgprot is the same:
+ * Convert protection attributes to 4k-format, as cpa->mask* are set
+ * up accordingly.
*/
old_pte = *kpte;
- old_prot = req_prot = pte_pgprot(old_pte);
+ old_prot = req_prot = pgprot_large_2_4k(pte_pgprot(old_pte));
pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
/*
+ * req_prot is in format of 4k pages. It must be converted to large
+ * page format: the caching mode includes the PAT bit located at
+ * different bit positions in the two formats.
+ */
+ req_prot = pgprot_4k_2_large(req_prot);
+
+ /*
* Set the PSE and GLOBAL flags only if the PRESENT flag is
* set otherwise pmd_present/pmd_huge will return true even on
* a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
@@ -585,13 +614,10 @@ __split_large_page(struct cpa_data *cpa, pte_t *kpte, unsigned long address,
paravirt_alloc_pte(&init_mm, page_to_pfn(base));
ref_prot = pte_pgprot(pte_clrhuge(*kpte));
- /*
- * If we ever want to utilize the PAT bit, we need to
- * update this function to make sure it's converted from
- * bit 12 to bit 7 when we cross from the 2MB level to
- * the 4K level:
- */
- WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);
+
+ /* promote PAT bit to correct position */
+ if (level == PG_LEVEL_2M)
+ ref_prot = pgprot_large_2_4k(ref_prot);
#ifdef CONFIG_X86_64
if (level == PG_LEVEL_1G) {
@@ -879,6 +905,7 @@ static int populate_pmd(struct cpa_data *cpa,
{
unsigned int cur_pages = 0;
pmd_t *pmd;
+ pgprot_t pmd_pgprot;
/*
* Not on a 2M boundary?
@@ -910,6 +937,8 @@ static int populate_pmd(struct cpa_data *cpa,
if (num_pages == cur_pages)
return cur_pages;
+ pmd_pgprot = pgprot_4k_2_large(pgprot);
+
while (end - start >= PMD_SIZE) {
/*
@@ -921,7 +950,8 @@ static int populate_pmd(struct cpa_data *cpa,
pmd = pmd_offset(pud, start);
- set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+ set_pmd(pmd, __pmd(cpa->pfn | _PAGE_PSE |
+ massage_pgprot(pmd_pgprot)));
start += PMD_SIZE;
cpa->pfn += PMD_SIZE;
@@ -949,6 +979,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
pud_t *pud;
unsigned long end;
int cur_pages = 0;
+ pgprot_t pud_pgprot;
end = start + (cpa->numpages << PAGE_SHIFT);
@@ -986,12 +1017,14 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
return cur_pages;
pud = pud_offset(pgd, start);
+ pud_pgprot = pgprot_4k_2_large(pgprot);
/*
* Map everything starting from the Gb boundary, possibly with 1G pages
*/
while (end - start >= PUD_SIZE) {
- set_pud(pud, __pud(cpa->pfn | _PAGE_PSE | massage_pgprot(pgprot)));
+ set_pud(pud, __pud(cpa->pfn | _PAGE_PSE |
+ massage_pgprot(pud_pgprot)));
start += PUD_SIZE;
cpa->pfn += PUD_SIZE;
@@ -1304,12 +1337,6 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
return 0;
}
-static inline int cache_attr(pgprot_t attr)
-{
- return pgprot_val(attr) &
- (_PAGE_PAT | _PAGE_PAT_LARGE | _PAGE_PWT | _PAGE_PCD);
-}
-
static int change_page_attr_set_clr(unsigned long *addr, int numpages,
pgprot_t mask_set, pgprot_t mask_clr,
int force_split, int in_flag,
@@ -1390,7 +1417,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
* No need to flush, when we did not set any of the caching
* attributes:
*/
- cache = cache_attr(mask_set);
+ cache = !!pgprot2cachemode(mask_set);
/*
* On success we use CLFLUSH, when the CPU supports it to
@@ -1445,7 +1472,8 @@ int _set_memory_uc(unsigned long addr, int numpages)
* for now UC MINUS. see comments in ioremap_nocache()
*/
return change_page_attr_set(&addr, numpages,
- __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+ cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+ 0);
}
int set_memory_uc(unsigned long addr, int numpages)
@@ -1456,7 +1484,7 @@ int set_memory_uc(unsigned long addr, int numpages)
* for now UC MINUS. see comments in ioremap_nocache()
*/
ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
- _PAGE_CACHE_UC_MINUS, NULL);
+ _PAGE_CACHE_MODE_UC_MINUS, NULL);
if (ret)
goto out_err;
@@ -1474,7 +1502,7 @@ out_err:
EXPORT_SYMBOL(set_memory_uc);
static int _set_memory_array(unsigned long *addr, int addrinarray,
- unsigned long new_type)
+ enum page_cache_mode new_type)
{
int i, j;
int ret;
@@ -1490,11 +1518,13 @@ static int _set_memory_array(unsigned long *addr, int addrinarray,
}
ret = change_page_attr_set(addr, addrinarray,
- __pgprot(_PAGE_CACHE_UC_MINUS), 1);
+ cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+ 1);
- if (!ret && new_type == _PAGE_CACHE_WC)
+ if (!ret && new_type == _PAGE_CACHE_MODE_WC)
ret = change_page_attr_set_clr(addr, addrinarray,
- __pgprot(_PAGE_CACHE_WC),
+ cachemode2pgprot(
+ _PAGE_CACHE_MODE_WC),
__pgprot(_PAGE_CACHE_MASK),
0, CPA_ARRAY, NULL);
if (ret)
@@ -1511,13 +1541,13 @@ out_free:
int set_memory_array_uc(unsigned long *addr, int addrinarray)
{
- return _set_memory_array(addr, addrinarray, _PAGE_CACHE_UC_MINUS);
+ return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_UC_MINUS);
}
EXPORT_SYMBOL(set_memory_array_uc);
int set_memory_array_wc(unsigned long *addr, int addrinarray)
{
- return _set_memory_array(addr, addrinarray, _PAGE_CACHE_WC);
+ return _set_memory_array(addr, addrinarray, _PAGE_CACHE_MODE_WC);
}
EXPORT_SYMBOL(set_memory_array_wc);
@@ -1527,10 +1557,12 @@ int _set_memory_wc(unsigned long addr, int numpages)
unsigned long addr_copy = addr;
ret = change_page_attr_set(&addr, numpages,
- __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+ cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS),
+ 0);
if (!ret) {
ret = change_page_attr_set_clr(&addr_copy, numpages,
- __pgprot(_PAGE_CACHE_WC),
+ cachemode2pgprot(
+ _PAGE_CACHE_MODE_WC),
__pgprot(_PAGE_CACHE_MASK),
0, 0, NULL);
}
@@ -1545,7 +1577,7 @@ int set_memory_wc(unsigned long addr, int numpages)
return set_memory_uc(addr, numpages);
ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
- _PAGE_CACHE_WC, NULL);
+ _PAGE_CACHE_MODE_WC, NULL);
if (ret)
goto out_err;
@@ -1564,6 +1596,7 @@ EXPORT_SYMBOL(set_memory_wc);
int _set_memory_wb(unsigned long addr, int numpages)
{
+ /* WB cache mode is hard wired to all cache attribute bits being 0 */
return change_page_attr_clear(&addr, numpages,
__pgprot(_PAGE_CACHE_MASK), 0);
}
@@ -1586,6 +1619,7 @@ int set_memory_array_wb(unsigned long *addr, int addrinarray)
int i;
int ret;
+ /* WB cache mode is hard wired to all cache attribute bits being 0 */
ret = change_page_attr_clear(addr, addrinarray,
__pgprot(_PAGE_CACHE_MASK), 1);
if (ret)
@@ -1648,7 +1682,7 @@ int set_pages_uc(struct page *page, int numpages)
EXPORT_SYMBOL(set_pages_uc);
static int _set_pages_array(struct page **pages, int addrinarray,
- unsigned long new_type)
+ enum page_cache_mode new_type)
{
unsigned long start;
unsigned long end;
@@ -1666,10 +1700,11 @@ static int _set_pages_array(struct page **pages, int addrinarray,
}
ret = cpa_set_pages_array(pages, addrinarray,
- __pgprot(_PAGE_CACHE_UC_MINUS));
- if (!ret && new_type == _PAGE_CACHE_WC)
+ cachemode2pgprot(_PAGE_CACHE_MODE_UC_MINUS));
+ if (!ret && new_type == _PAGE_CACHE_MODE_WC)
ret = change_page_attr_set_clr(NULL, addrinarray,
- __pgprot(_PAGE_CACHE_WC),
+ cachemode2pgprot(
+ _PAGE_CACHE_MODE_WC),
__pgprot(_PAGE_CACHE_MASK),
0, CPA_PAGES_ARRAY, pages);
if (ret)
@@ -1689,13 +1724,13 @@ err_out:
int set_pages_array_uc(struct page **pages, int addrinarray)
{
- return _set_pages_array(pages, addrinarray, _PAGE_CACHE_UC_MINUS);
+ return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_UC_MINUS);
}
EXPORT_SYMBOL(set_pages_array_uc);
int set_pages_array_wc(struct page **pages, int addrinarray)
{
- return _set_pages_array(pages, addrinarray, _PAGE_CACHE_WC);
+ return _set_pages_array(pages, addrinarray, _PAGE_CACHE_MODE_WC);
}
EXPORT_SYMBOL(set_pages_array_wc);
@@ -1714,6 +1749,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
unsigned long end;
int i;
+ /* WB cache mode is hard wired to all cache attribute bits being 0 */
retval = cpa_clear_pages_array(pages, addrinarray,
__pgprot(_PAGE_CACHE_MASK));
if (retval)
@@ -1801,7 +1837,7 @@ static int __set_pages_np(struct page *page, int numpages)
return __change_page_attr_set_clr(&cpa, 0);
}
-void kernel_map_pages(struct page *page, int numpages, int enable)
+void __kernel_map_pages(struct page *page, int numpages, int enable)
{
if (PageHighMem(page))
return;
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 657438858e83..edf299c8ff6c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -31,6 +31,7 @@
#include <asm/io.h>
#include "pat_internal.h"
+#include "mm_internal.h"
#ifdef CONFIG_X86_PAT
int __read_mostly pat_enabled = 1;
@@ -66,6 +67,75 @@ __setup("debugpat", pat_debug_setup);
static u64 __read_mostly boot_pat_state;
+#ifdef CONFIG_X86_PAT
+/*
+ * X86 PAT uses page flags WC and Uncached together to keep track of
+ * memory type of pages that have backing page struct. X86 PAT supports 3
+ * different memory types, _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC and
+ * _PAGE_CACHE_MODE_UC_MINUS and fourth state where page's memory type has not
+ * been changed from its default (value of -1 used to denote this).
+ * Note we do not support _PAGE_CACHE_MODE_UC here.
+ */
+
+#define _PGMT_DEFAULT 0
+#define _PGMT_WC (1UL << PG_arch_1)
+#define _PGMT_UC_MINUS (1UL << PG_uncached)
+#define _PGMT_WB (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_MASK (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_CLEAR_MASK (~_PGMT_MASK)
+
+static inline enum page_cache_mode get_page_memtype(struct page *pg)
+{
+ unsigned long pg_flags = pg->flags & _PGMT_MASK;
+
+ if (pg_flags == _PGMT_DEFAULT)
+ return -1;
+ else if (pg_flags == _PGMT_WC)
+ return _PAGE_CACHE_MODE_WC;
+ else if (pg_flags == _PGMT_UC_MINUS)
+ return _PAGE_CACHE_MODE_UC_MINUS;
+ else
+ return _PAGE_CACHE_MODE_WB;
+}
+
+static inline void set_page_memtype(struct page *pg,
+ enum page_cache_mode memtype)
+{
+ unsigned long memtype_flags;
+ unsigned long old_flags;
+ unsigned long new_flags;
+
+ switch (memtype) {
+ case _PAGE_CACHE_MODE_WC:
+ memtype_flags = _PGMT_WC;
+ break;
+ case _PAGE_CACHE_MODE_UC_MINUS:
+ memtype_flags = _PGMT_UC_MINUS;
+ break;
+ case _PAGE_CACHE_MODE_WB:
+ memtype_flags = _PGMT_WB;
+ break;
+ default:
+ memtype_flags = _PGMT_DEFAULT;
+ break;
+ }
+
+ do {
+ old_flags = pg->flags;
+ new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
+ } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
+}
+#else
+static inline enum page_cache_mode get_page_memtype(struct page *pg)
+{
+ return -1;
+}
+static inline void set_page_memtype(struct page *pg,
+ enum page_cache_mode memtype)
+{
+}
+#endif
+
enum {
PAT_UC = 0, /* uncached */
PAT_WC = 1, /* Write combining */
@@ -75,6 +145,52 @@ enum {
PAT_UC_MINUS = 7, /* UC, but can be overriden by MTRR */
};
+#define CM(c) (_PAGE_CACHE_MODE_ ## c)
+
+static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
+{
+ enum page_cache_mode cache;
+ char *cache_mode;
+
+ switch (pat_val) {
+ case PAT_UC: cache = CM(UC); cache_mode = "UC "; break;
+ case PAT_WC: cache = CM(WC); cache_mode = "WC "; break;
+ case PAT_WT: cache = CM(WT); cache_mode = "WT "; break;
+ case PAT_WP: cache = CM(WP); cache_mode = "WP "; break;
+ case PAT_WB: cache = CM(WB); cache_mode = "WB "; break;
+ case PAT_UC_MINUS: cache = CM(UC_MINUS); cache_mode = "UC- "; break;
+ default: cache = CM(WB); cache_mode = "WB "; break;
+ }
+
+ memcpy(msg, cache_mode, 4);
+
+ return cache;
+}
+
+#undef CM
+
+/*
+ * Update the cache mode to pgprot translation tables according to PAT
+ * configuration.
+ * Using lower indices is preferred, so we start with highest index.
+ */
+void pat_init_cache_modes(void)
+{
+ int i;
+ enum page_cache_mode cache;
+ char pat_msg[33];
+ u64 pat;
+
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ pat_msg[32] = 0;
+ for (i = 7; i >= 0; i--) {
+ cache = pat_get_cache_mode((pat >> (i * 8)) & 7,
+ pat_msg + 4 * i);
+ update_cache_mode_entry(i, cache);
+ }
+ pr_info("PAT configuration [0-7]: %s\n", pat_msg);
+}
+
#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8))
void pat_init(void)
@@ -124,8 +240,7 @@ void pat_init(void)
wrmsrl(MSR_IA32_CR_PAT, pat);
if (boot_cpu)
- printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
- smp_processor_id(), boot_pat_state, pat);
+ pat_init_cache_modes();
}
#undef PAT
@@ -139,20 +254,21 @@ static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */
* The intersection is based on "Effective Memory Type" tables in IA-32
* SDM vol 3a
*/
-static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
+static unsigned long pat_x_mtrr_type(u64 start, u64 end,
+ enum page_cache_mode req_type)
{
/*
* Look for MTRR hint to get the effective type in case where PAT
* request is for WB.
*/
- if (req_type == _PAGE_CACHE_WB) {
+ if (req_type == _PAGE_CACHE_MODE_WB) {
u8 mtrr_type;
mtrr_type = mtrr_type_lookup(start, end);
if (mtrr_type != MTRR_TYPE_WRBACK)
- return _PAGE_CACHE_UC_MINUS;
+ return _PAGE_CACHE_MODE_UC_MINUS;
- return _PAGE_CACHE_WB;
+ return _PAGE_CACHE_MODE_WB;
}
return req_type;
@@ -207,25 +323,26 @@ static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
* - Find the memtype of all the pages in the range, look for any conflicts
* - In case of no conflicts, set the new memtype for pages in the range
*/
-static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
- unsigned long *new_type)
+static int reserve_ram_pages_type(u64 start, u64 end,
+ enum page_cache_mode req_type,
+ enum page_cache_mode *new_type)
{
struct page *page;
u64 pfn;
- if (req_type == _PAGE_CACHE_UC) {
+ if (req_type == _PAGE_CACHE_MODE_UC) {
/* We do not support strong UC */
WARN_ON_ONCE(1);
- req_type = _PAGE_CACHE_UC_MINUS;
+ req_type = _PAGE_CACHE_MODE_UC_MINUS;
}
for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
- unsigned long type;
+ enum page_cache_mode type;
page = pfn_to_page(pfn);
type = get_page_memtype(page);
if (type != -1) {
- printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n",
+ pr_info("reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%x, req 0x%x\n",
start, end - 1, type, req_type);
if (new_type)
*new_type = type;
@@ -258,21 +375,21 @@ static int free_ram_pages_type(u64 start, u64 end)
/*
* req_type typically has one of the:
- * - _PAGE_CACHE_WB
- * - _PAGE_CACHE_WC
- * - _PAGE_CACHE_UC_MINUS
- * - _PAGE_CACHE_UC
+ * - _PAGE_CACHE_MODE_WB
+ * - _PAGE_CACHE_MODE_WC
+ * - _PAGE_CACHE_MODE_UC_MINUS
+ * - _PAGE_CACHE_MODE_UC
*
* If new_type is NULL, function will return an error if it cannot reserve the
* region with req_type. If new_type is non-NULL, function will return
* available type in new_type in case of no error. In case of any error
* it will return a negative return value.
*/
-int reserve_memtype(u64 start, u64 end, unsigned long req_type,
- unsigned long *new_type)
+int reserve_memtype(u64 start, u64 end, enum page_cache_mode req_type,
+ enum page_cache_mode *new_type)
{
struct memtype *new;
- unsigned long actual_type;
+ enum page_cache_mode actual_type;
int is_range_ram;
int err = 0;
@@ -281,10 +398,10 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
if (!pat_enabled) {
/* This is identical to page table setting without PAT */
if (new_type) {
- if (req_type == _PAGE_CACHE_WC)
- *new_type = _PAGE_CACHE_UC_MINUS;
+ if (req_type == _PAGE_CACHE_MODE_WC)
+ *new_type = _PAGE_CACHE_MODE_UC_MINUS;
else
- *new_type = req_type & _PAGE_CACHE_MASK;
+ *new_type = req_type;
}
return 0;
}
@@ -292,7 +409,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
/* Low ISA region is always mapped WB in page table. No need to track */
if (x86_platform.is_untracked_pat_range(start, end)) {
if (new_type)
- *new_type = _PAGE_CACHE_WB;
+ *new_type = _PAGE_CACHE_MODE_WB;
return 0;
}
@@ -302,7 +419,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
* tools and ACPI tools). Use WB request for WB memory and use
* UC_MINUS otherwise.
*/
- actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);
+ actual_type = pat_x_mtrr_type(start, end, req_type);
if (new_type)
*new_type = actual_type;
@@ -394,12 +511,12 @@ int free_memtype(u64 start, u64 end)
*
* Only to be called when PAT is enabled
*
- * Returns _PAGE_CACHE_WB, _PAGE_CACHE_WC, _PAGE_CACHE_UC_MINUS or
- * _PAGE_CACHE_UC
+ * Returns _PAGE_CACHE_MODE_WB, _PAGE_CACHE_MODE_WC, _PAGE_CACHE_MODE_UC_MINUS
+ * or _PAGE_CACHE_MODE_UC
*/
-static unsigned long lookup_memtype(u64 paddr)
+static enum page_cache_mode lookup_memtype(u64 paddr)
{
- int rettype = _PAGE_CACHE_WB;
+ enum page_cache_mode rettype = _PAGE_CACHE_MODE_WB;
struct memtype *entry;
if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE))
@@ -414,7 +531,7 @@ static unsigned long lookup_memtype(u64 paddr)
* default state and not reserved, and hence of type WB
*/
if (rettype == -1)
- rettype = _PAGE_CACHE_WB;
+ rettype = _PAGE_CACHE_MODE_WB;
return rettype;
}
@@ -425,7 +542,7 @@ static unsigned long lookup_memtype(u64 paddr)
if (entry != NULL)
rettype = entry->type;
else
- rettype = _PAGE_CACHE_UC_MINUS;
+ rettype = _PAGE_CACHE_MODE_UC_MINUS;
spin_unlock(&memtype_lock);
return rettype;
@@ -442,11 +559,11 @@ static unsigned long lookup_memtype(u64 paddr)
* On failure, returns non-zero
*/
int io_reserve_memtype(resource_size_t start, resource_size_t end,
- unsigned long *type)
+ enum page_cache_mode *type)
{
resource_size_t size = end - start;
- unsigned long req_type = *type;
- unsigned long new_type;
+ enum page_cache_mode req_type = *type;
+ enum page_cache_mode new_type;
int ret;
WARN_ON_ONCE(iomem_map_sanity_check(start, size));
@@ -520,13 +637,13 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot)
{
- unsigned long flags = _PAGE_CACHE_WB;
+ enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;
if (!range_is_allowed(pfn, size))
return 0;
if (file->f_flags & O_DSYNC)
- flags = _PAGE_CACHE_UC_MINUS;
+ pcm = _PAGE_CACHE_MODE_UC_MINUS;
#ifdef CONFIG_X86_32
/*
@@ -543,12 +660,12 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
(pfn << PAGE_SHIFT) >= __pa(high_memory)) {
- flags = _PAGE_CACHE_UC;
+ pcm = _PAGE_CACHE_MODE_UC;
}
#endif
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
- flags);
+ cachemode2protval(pcm));
return 1;
}
@@ -556,7 +673,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
* Change the memory type for the physial address range in kernel identity
* mapping space if that range is a part of identity map.
*/
-int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
+int kernel_map_sync_memtype(u64 base, unsigned long size,
+ enum page_cache_mode pcm)
{
unsigned long id_sz;
@@ -574,11 +692,11 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
__pa(high_memory) - base :
size;
- if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
+ if (ioremap_change_attr((unsigned long)__va(base), id_sz, pcm) < 0) {
printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
"for [mem %#010Lx-%#010Lx]\n",
current->comm, current->pid,
- cattr_name(flags),
+ cattr_name(pcm),
base, (unsigned long long)(base + size-1));
return -EINVAL;
}
@@ -595,8 +713,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
{
int is_ram = 0;
int ret;
- unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
- unsigned long flags = want_flags;
+ enum page_cache_mode want_pcm = pgprot2cachemode(*vma_prot);
+ enum page_cache_mode pcm = want_pcm;
is_ram = pat_pagerange_is_ram(paddr, paddr + size);
@@ -609,36 +727,36 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
if (!pat_enabled)
return 0;
- flags = lookup_memtype(paddr);
- if (want_flags != flags) {
+ pcm = lookup_memtype(paddr);
+ if (want_pcm != pcm) {
printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
- cattr_name(want_flags),
+ cattr_name(want_pcm),
(unsigned long long)paddr,
(unsigned long long)(paddr + size - 1),
- cattr_name(flags));
+ cattr_name(pcm));
*vma_prot = __pgprot((pgprot_val(*vma_prot) &
- (~_PAGE_CACHE_MASK)) |
- flags);
+ (~_PAGE_CACHE_MASK)) |
+ cachemode2protval(pcm));
}
return 0;
}
- ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
+ ret = reserve_memtype(paddr, paddr + size, want_pcm, &pcm);
if (ret)
return ret;
- if (flags != want_flags) {
+ if (pcm != want_pcm) {
if (strict_prot ||
- !is_new_memtype_allowed(paddr, size, want_flags, flags)) {
+ !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
free_memtype(paddr, paddr + size);
printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
" for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
- cattr_name(want_flags),
+ cattr_name(want_pcm),
(unsigned long long)paddr,
(unsigned long long)(paddr + size - 1),
- cattr_name(flags));
+ cattr_name(pcm));
return -EINVAL;
}
/*
@@ -647,10 +765,10 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
*/
*vma_prot = __pgprot((pgprot_val(*vma_prot) &
(~_PAGE_CACHE_MASK)) |
- flags);
+ cachemode2protval(pcm));
}
- if (kernel_map_sync_memtype(paddr, size, flags) < 0) {
+ if (kernel_map_sync_memtype(paddr, size, pcm) < 0) {
free_memtype(paddr, paddr + size);
return -EINVAL;
}
@@ -709,7 +827,7 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn, unsigned long addr, unsigned long size)
{
resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
- unsigned long flags;
+ enum page_cache_mode pcm;
/* reserve the whole chunk starting from paddr */
if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
@@ -728,18 +846,18 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
* For anything smaller than the vma size we set prot based on the
* lookup.
*/
- flags = lookup_memtype(paddr);
+ pcm = lookup_memtype(paddr);
/* Check memtype for the remaining pages */
while (size > PAGE_SIZE) {
size -= PAGE_SIZE;
paddr += PAGE_SIZE;
- if (flags != lookup_memtype(paddr))
+ if (pcm != lookup_memtype(paddr))
return -EINVAL;
}
*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
- flags);
+ cachemode2protval(pcm));
return 0;
}
@@ -747,15 +865,15 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
unsigned long pfn)
{
- unsigned long flags;
+ enum page_cache_mode pcm;
if (!pat_enabled)
return 0;
/* Set prot based on lookup */
- flags = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT);
+ pcm = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT);
*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
- flags);
+ cachemode2protval(pcm));
return 0;
}
@@ -791,7 +909,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
pgprot_t pgprot_writecombine(pgprot_t prot)
{
if (pat_enabled)
- return __pgprot(pgprot_val(prot) | _PAGE_CACHE_WC);
+ return __pgprot(pgprot_val(prot) |
+ cachemode2protval(_PAGE_CACHE_MODE_WC));
else
return pgprot_noncached(prot);
}
@@ -824,7 +943,7 @@ static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
{
if (*pos == 0) {
++*pos;
- seq_printf(seq, "PAT memtype list:\n");
+ seq_puts(seq, "PAT memtype list:\n");
}
return memtype_get_idx(*pos);
diff --git a/arch/x86/mm/pat_internal.h b/arch/x86/mm/pat_internal.h
index 77e5ba153fac..f6411620305d 100644
--- a/arch/x86/mm/pat_internal.h
+++ b/arch/x86/mm/pat_internal.h
@@ -10,30 +10,32 @@ struct memtype {
u64 start;
u64 end;
u64 subtree_max_end;
- unsigned long type;
+ enum page_cache_mode type;
struct rb_node rb;
};
-static inline char *cattr_name(unsigned long flags)
+static inline char *cattr_name(enum page_cache_mode pcm)
{
- switch (flags & _PAGE_CACHE_MASK) {
- case _PAGE_CACHE_UC: return "uncached";
- case _PAGE_CACHE_UC_MINUS: return "uncached-minus";
- case _PAGE_CACHE_WB: return "write-back";
- case _PAGE_CACHE_WC: return "write-combining";
- default: return "broken";
+ switch (pcm) {
+ case _PAGE_CACHE_MODE_UC: return "uncached";
+ case _PAGE_CACHE_MODE_UC_MINUS: return "uncached-minus";
+ case _PAGE_CACHE_MODE_WB: return "write-back";
+ case _PAGE_CACHE_MODE_WC: return "write-combining";
+ case _PAGE_CACHE_MODE_WT: return "write-through";
+ case _PAGE_CACHE_MODE_WP: return "write-protected";
+ default: return "broken";
}
}
#ifdef CONFIG_X86_PAT
extern int rbt_memtype_check_insert(struct memtype *new,
- unsigned long *new_type);
+ enum page_cache_mode *new_type);
extern struct memtype *rbt_memtype_erase(u64 start, u64 end);
extern struct memtype *rbt_memtype_lookup(u64 addr);
extern int rbt_memtype_copy_nth_element(struct memtype *out, loff_t pos);
#else
static inline int rbt_memtype_check_insert(struct memtype *new,
- unsigned long *new_type)
+ enum page_cache_mode *new_type)
{ return 0; }
static inline struct memtype *rbt_memtype_erase(u64 start, u64 end)
{ return NULL; }
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 415f6c4ced36..6582adcc8bd9 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/arch/x86/mm/pat_rbtree.c
@@ -122,11 +122,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root,
static int memtype_rb_check_conflict(struct rb_root *root,
u64 start, u64 end,
- unsigned long reqtype, unsigned long *newtype)
+ enum page_cache_mode reqtype,
+ enum page_cache_mode *newtype)
{
struct rb_node *node;
struct memtype *match;
- int found_type = reqtype;
+ enum page_cache_mode found_type = reqtype;
match = memtype_rb_lowest_match(&memtype_rbroot, start, end);
if (match == NULL)
@@ -187,7 +188,8 @@ static void memtype_rb_insert(struct rb_root *root, struct memtype *newdata)
rb_insert_augmented(&newdata->rb, root, &memtype_rb_augment_cb);
}
-int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type)
+int rbt_memtype_check_insert(struct memtype *new,
+ enum page_cache_mode *ret_type)
{
int err = 0;
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 4dd8cf652579..75cc0978d45d 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -59,41 +59,6 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
__flush_tlb_one(vaddr);
}
-/*
- * Associate a large virtual page frame with a given physical page frame
- * and protection flags for that frame. pfn is for the base of the page,
- * vaddr is what the page gets mapped to - both must be properly aligned.
- * The pmd must already be instantiated. Assumes PAE mode.
- */
-void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
-{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
-
- if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */
- printk(KERN_WARNING "set_pmd_pfn: vaddr misaligned\n");
- return; /* BUG(); */
- }
- if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */
- printk(KERN_WARNING "set_pmd_pfn: pfn misaligned\n");
- return; /* BUG(); */
- }
- pgd = swapper_pg_dir + pgd_index(vaddr);
- if (pgd_none(*pgd)) {
- printk(KERN_WARNING "set_pmd_pfn: pgd_none\n");
- return; /* BUG(); */
- }
- pud = pud_offset(pgd, vaddr);
- pmd = pmd_offset(pud, vaddr);
- set_pmd(pmd, pfn_pmd(pfn, flags));
- /*
- * It's enough to flush this one mapping.
- * (PGE mappings get flushed as well)
- */
- __flush_tlb_one(vaddr);
-}
-
unsigned long __FIXADDR_TOP = 0xfffff000;
EXPORT_SYMBOL(__FIXADDR_TOP);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5c8cb8043c5a..987514396c1e 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -8,12 +8,10 @@
* as published by the Free Software Foundation; version 2
* of the License.
*/
-#include <linux/moduleloader.h>
-#include <asm/cacheflush.h>
#include <linux/netdevice.h>
#include <linux/filter.h>
#include <linux/if_vlan.h>
-#include <linux/random.h>
+#include <asm/cacheflush.h>
int bpf_jit_enable __read_mostly;
@@ -26,7 +24,7 @@ extern u8 sk_load_byte_positive_offset[];
extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
extern u8 sk_load_byte_negative_offset[];
-static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
+static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
if (len == 1)
*ptr = bytes;
@@ -54,12 +52,12 @@ static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
#define EMIT4_off32(b1, b2, b3, b4, off) \
do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0)
-static inline bool is_imm8(int value)
+static bool is_imm8(int value)
{
return value <= 127 && value >= -128;
}
-static inline bool is_simm32(s64 value)
+static bool is_simm32(s64 value)
{
return value == (s64) (s32) value;
}
@@ -96,7 +94,7 @@ static int bpf_size_to_x86_bytes(int bpf_size)
#define X86_JGE 0x7D
#define X86_JG 0x7F
-static inline void bpf_flush_icache(void *start, void *end)
+static void bpf_flush_icache(void *start, void *end)
{
mm_segment_t old_fs = get_fs();
@@ -109,39 +107,6 @@ static inline void bpf_flush_icache(void *start, void *end)
#define CHOOSE_LOAD_FUNC(K, func) \
((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
-struct bpf_binary_header {
- unsigned int pages;
- /* Note : for security reasons, bpf code will follow a randomly
- * sized amount of int3 instructions
- */
- u8 image[];
-};
-
-static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
- u8 **image_ptr)
-{
- unsigned int sz, hole;
- struct bpf_binary_header *header;
-
- /* Most of BPF filters are really small,
- * but if some of them fill a page, allow at least
- * 128 extra bytes to insert a random section of int3
- */
- sz = round_up(proglen + sizeof(*header) + 128, PAGE_SIZE);
- header = module_alloc(sz);
- if (!header)
- return NULL;
-
- memset(header, 0xcc, sz); /* fill whole space with int3 instructions */
-
- header->pages = sz / PAGE_SIZE;
- hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header));
-
- /* insert a random number of int3 instructions before BPF code */
- *image_ptr = &header->image[prandom_u32() % hole];
- return header;
-}
-
/* pick a register outside of BPF range for JIT internal work */
#define AUX_REG (MAX_BPF_REG + 1)
@@ -168,24 +133,24 @@ static const int reg2hex[] = {
* which need extra byte of encoding.
* rax,rcx,...,rbp have simpler encoding
*/
-static inline bool is_ereg(u32 reg)
+static bool is_ereg(u32 reg)
{
- if (reg == BPF_REG_5 || reg == AUX_REG ||
- (reg >= BPF_REG_7 && reg <= BPF_REG_9))
- return true;
- else
- return false;
+ return (1 << reg) & (BIT(BPF_REG_5) |
+ BIT(AUX_REG) |
+ BIT(BPF_REG_7) |
+ BIT(BPF_REG_8) |
+ BIT(BPF_REG_9));
}
/* add modifiers if 'reg' maps to x64 registers r8..r15 */
-static inline u8 add_1mod(u8 byte, u32 reg)
+static u8 add_1mod(u8 byte, u32 reg)
{
if (is_ereg(reg))
byte |= 1;
return byte;
}
-static inline u8 add_2mod(u8 byte, u32 r1, u32 r2)
+static u8 add_2mod(u8 byte, u32 r1, u32 r2)
{
if (is_ereg(r1))
byte |= 1;
@@ -195,28 +160,40 @@ static inline u8 add_2mod(u8 byte, u32 r1, u32 r2)
}
/* encode 'dst_reg' register into x64 opcode 'byte' */
-static inline u8 add_1reg(u8 byte, u32 dst_reg)
+static u8 add_1reg(u8 byte, u32 dst_reg)
{
return byte + reg2hex[dst_reg];
}
/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */
-static inline u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
+static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg)
{
return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3);
}
+static void jit_fill_hole(void *area, unsigned int size)
+{
+ /* fill whole space with int3 instructions */
+ memset(area, 0xcc, size);
+}
+
struct jit_context {
- unsigned int cleanup_addr; /* epilogue code offset */
+ int cleanup_addr; /* epilogue code offset */
bool seen_ld_abs;
};
+/* maximum number of bytes emitted while JITing one eBPF insn */
+#define BPF_MAX_INSN_SIZE 128
+#define BPF_INSN_SAFETY 64
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
int oldproglen, struct jit_context *ctx)
{
struct bpf_insn *insn = bpf_prog->insnsi;
int insn_cnt = bpf_prog->len;
- u8 temp[64];
+ bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0);
+ bool seen_exit = false;
+ u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY];
int i;
int proglen = 0;
u8 *prog = temp;
@@ -254,7 +231,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT2(0x31, 0xc0); /* xor eax, eax */
EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */
- if (ctx->seen_ld_abs) {
+ if (seen_ld_abs) {
/* r9d : skb->len - skb->data_len (headlen)
* r10 : skb->data
*/
@@ -393,6 +370,23 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT1_off32(add_1reg(0xB8, dst_reg), imm32);
break;
+ case BPF_LD | BPF_IMM | BPF_DW:
+ if (insn[1].code != 0 || insn[1].src_reg != 0 ||
+ insn[1].dst_reg != 0 || insn[1].off != 0) {
+ /* verifier must catch invalid insns */
+ pr_err("invalid BPF_LD_IMM64 insn\n");
+ return -EINVAL;
+ }
+
+ /* movabsq %rax, imm64 */
+ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg));
+ EMIT(insn[0].imm, 4);
+ EMIT(insn[1].imm, 4);
+
+ insn++;
+ i++;
+ break;
+
/* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */
case BPF_ALU | BPF_MOD | BPF_X:
case BPF_ALU | BPF_DIV | BPF_X:
@@ -515,6 +509,48 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
EMIT3(0xC1, add_1reg(b3, dst_reg), imm32);
break;
+ case BPF_ALU | BPF_LSH | BPF_X:
+ case BPF_ALU | BPF_RSH | BPF_X:
+ case BPF_ALU | BPF_ARSH | BPF_X:
+ case BPF_ALU64 | BPF_LSH | BPF_X:
+ case BPF_ALU64 | BPF_RSH | BPF_X:
+ case BPF_ALU64 | BPF_ARSH | BPF_X:
+
+ /* check for bad case when dst_reg == rcx */
+ if (dst_reg == BPF_REG_4) {
+ /* mov r11, dst_reg */
+ EMIT_mov(AUX_REG, dst_reg);
+ dst_reg = AUX_REG;
+ }
+
+ if (src_reg != BPF_REG_4) { /* common case */
+ EMIT1(0x51); /* push rcx */
+
+ /* mov rcx, src_reg */
+ EMIT_mov(BPF_REG_4, src_reg);
+ }
+
+ /* shl %rax, %cl | shr %rax, %cl | sar %rax, %cl */
+ if (BPF_CLASS(insn->code) == BPF_ALU64)
+ EMIT1(add_1mod(0x48, dst_reg));
+ else if (is_ereg(dst_reg))
+ EMIT1(add_1mod(0x40, dst_reg));
+
+ switch (BPF_OP(insn->code)) {
+ case BPF_LSH: b3 = 0xE0; break;
+ case BPF_RSH: b3 = 0xE8; break;
+ case BPF_ARSH: b3 = 0xF8; break;
+ }
+ EMIT2(0xD3, add_1reg(b3, dst_reg));
+
+ if (src_reg != BPF_REG_4)
+ EMIT1(0x59); /* pop rcx */
+
+ if (insn->dst_reg == BPF_REG_4)
+ /* mov dst_reg, r11 */
+ EMIT_mov(insn->dst_reg, AUX_REG);
+ break;
+
case BPF_ALU | BPF_END | BPF_FROM_BE:
switch (imm32) {
case 16:
@@ -655,7 +691,7 @@ xadd: if (is_imm8(insn->off))
case BPF_JMP | BPF_CALL:
func = (u8 *) __bpf_call_base + imm32;
jmp_offset = func - (image + addrs[i]);
- if (ctx->seen_ld_abs) {
+ if (seen_ld_abs) {
EMIT2(0x41, 0x52); /* push %r10 */
EMIT2(0x41, 0x51); /* push %r9 */
/* need to adjust jmp offset, since
@@ -669,7 +705,7 @@ xadd: if (is_imm8(insn->off))
return -EINVAL;
}
EMIT1_off32(0xE8, jmp_offset);
- if (ctx->seen_ld_abs) {
+ if (seen_ld_abs) {
EMIT2(0x41, 0x59); /* pop %r9 */
EMIT2(0x41, 0x5A); /* pop %r10 */
}
@@ -774,7 +810,8 @@ emit_jmp:
goto common_load;
case BPF_LD | BPF_ABS | BPF_W:
func = CHOOSE_LOAD_FUNC(imm32, sk_load_word);
-common_load: ctx->seen_ld_abs = true;
+common_load:
+ ctx->seen_ld_abs = seen_ld_abs = true;
jmp_offset = func - (image + addrs[i]);
if (!func || !is_simm32(jmp_offset)) {
pr_err("unsupported bpf func %d addr %p image %p\n",
@@ -818,10 +855,11 @@ common_load: ctx->seen_ld_abs = true;
goto common_load;
case BPF_JMP | BPF_EXIT:
- if (i != insn_cnt - 1) {
+ if (seen_exit) {
jmp_offset = ctx->cleanup_addr - addrs[i];
goto emit_jmp;
}
+ seen_exit = true;
/* update cleanup_addr */
ctx->cleanup_addr = proglen;
/* mov rbx, qword ptr [rbp-X] */
@@ -848,6 +886,11 @@ common_load: ctx->seen_ld_abs = true;
}
ilen = prog - temp;
+ if (ilen > BPF_MAX_INSN_SIZE) {
+ pr_err("bpf_jit_compile fatal insn size error\n");
+ return -EFAULT;
+ }
+
if (image) {
if (unlikely(proglen + ilen > oldproglen)) {
pr_err("bpf_jit_compile fatal error\n");
@@ -900,17 +943,20 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
if (proglen <= 0) {
image = NULL;
if (header)
- module_free(NULL, header);
+ bpf_jit_binary_free(header);
goto out;
}
if (image) {
- if (proglen != oldproglen)
+ if (proglen != oldproglen) {
pr_err("bpf_jit: proglen=%d != oldproglen=%d\n",
proglen, oldproglen);
+ goto out;
+ }
break;
}
if (proglen == oldproglen) {
- header = bpf_alloc_binary(proglen, &image);
+ header = bpf_jit_binary_alloc(proglen, &image,
+ 1, jit_fill_hole);
if (!header)
goto out;
}
@@ -924,29 +970,23 @@ void bpf_int_jit_compile(struct bpf_prog *prog)
bpf_flush_icache(header, image + proglen);
set_memory_ro((unsigned long)header, header->pages);
prog->bpf_func = (void *)image;
- prog->jited = 1;
+ prog->jited = true;
}
out:
kfree(addrs);
}
-static void bpf_jit_free_deferred(struct work_struct *work)
+void bpf_jit_free(struct bpf_prog *fp)
{
- struct bpf_prog *fp = container_of(work, struct bpf_prog, work);
unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
struct bpf_binary_header *header = (void *)addr;
+ if (!fp->jited)
+ goto free_filter;
+
set_memory_rw(addr, header->pages);
- module_free(NULL, header);
- kfree(fp);
-}
+ bpf_jit_binary_free(header);
-void bpf_jit_free(struct bpf_prog *fp)
-{
- if (fp->jited) {
- INIT_WORK(&fp->work, bpf_jit_free_deferred);
- schedule_work(&fp->work);
- } else {
- kfree(fp);
- }
+free_filter:
+ bpf_prog_unlock_free(fp);
}
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 379e8bd0deea..1d2e6392f5fa 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -64,11 +64,11 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
{
if (ctr_running)
- model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+ model->check_ctrs(regs, this_cpu_ptr(&cpu_msrs));
else if (!nmi_enabled)
return NMI_DONE;
else
- model->stop(&__get_cpu_var(cpu_msrs));
+ model->stop(this_cpu_ptr(&cpu_msrs));
return NMI_HANDLED;
}
@@ -91,7 +91,7 @@ static void nmi_cpu_save_registers(struct op_msrs *msrs)
static void nmi_cpu_start(void *dummy)
{
- struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+ struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
if (!msrs->controls)
WARN_ON_ONCE(1);
else
@@ -111,7 +111,7 @@ static int nmi_start(void)
static void nmi_cpu_stop(void *dummy)
{
- struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
+ struct op_msrs const *msrs = this_cpu_ptr(&cpu_msrs);
if (!msrs->controls)
WARN_ON_ONCE(1);
else
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 98ab13058f89..ad1d91f475ab 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -372,7 +372,7 @@ static unsigned int get_stagger(void)
{
#ifdef CONFIG_SMP
int cpu = smp_processor_id();
- return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+ return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map));
#endif
return 0;
}
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 059a76c29739..7b20bccf3648 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -81,14 +81,14 @@ struct pci_ops pci_root_ops = {
*/
DEFINE_RAW_SPINLOCK(pci_config_lock);
-static int can_skip_ioresource_align(const struct dmi_system_id *d)
+static int __init can_skip_ioresource_align(const struct dmi_system_id *d)
{
pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
printk(KERN_INFO "PCI: %s detected, can skip ISA alignment\n", d->ident);
return 0;
}
-static const struct dmi_system_id can_skip_pciprobe_dmi_table[] = {
+static const struct dmi_system_id can_skip_pciprobe_dmi_table[] __initconst = {
/*
* Systems where PCI IO resource ISA alignment can be skipped
* when the ISA enable bit in the bridge control is not set
@@ -186,7 +186,7 @@ void pcibios_remove_bus(struct pci_bus *bus)
* on the kernel command line (which was parsed earlier).
*/
-static int set_bf_sort(const struct dmi_system_id *d)
+static int __init set_bf_sort(const struct dmi_system_id *d)
{
if (pci_bf_sort == pci_bf_sort_default) {
pci_bf_sort = pci_dmi_bf;
@@ -195,8 +195,8 @@ static int set_bf_sort(const struct dmi_system_id *d)
return 0;
}
-static void read_dmi_type_b1(const struct dmi_header *dm,
- void *private_data)
+static void __init read_dmi_type_b1(const struct dmi_header *dm,
+ void *private_data)
{
u8 *d = (u8 *)dm + 4;
@@ -217,7 +217,7 @@ static void read_dmi_type_b1(const struct dmi_header *dm,
}
}
-static int find_sort_method(const struct dmi_system_id *d)
+static int __init find_sort_method(const struct dmi_system_id *d)
{
dmi_walk(read_dmi_type_b1, NULL);
@@ -232,7 +232,7 @@ static int find_sort_method(const struct dmi_system_id *d)
* Enable renumbering of PCI bus# ranges to reach all PCI busses (Cardbus)
*/
#ifdef __i386__
-static int assign_all_busses(const struct dmi_system_id *d)
+static int __init assign_all_busses(const struct dmi_system_id *d)
{
pci_probe |= PCI_ASSIGN_ALL_BUSSES;
printk(KERN_INFO "%s detected: enabling PCI bus# renumbering"
@@ -241,7 +241,7 @@ static int assign_all_busses(const struct dmi_system_id *d)
}
#endif
-static int set_scan_all(const struct dmi_system_id *d)
+static int __init set_scan_all(const struct dmi_system_id *d)
{
printk(KERN_INFO "PCI: %s detected, enabling pci=pcie_scan_all\n",
d->ident);
@@ -249,7 +249,7 @@ static int set_scan_all(const struct dmi_system_id *d)
return 0;
}
-static const struct dmi_system_id pciprobe_dmi_table[] = {
+static const struct dmi_system_id pciprobe_dmi_table[] __initconst = {
#ifdef __i386__
/*
* Laptops which need pci=assign-busses to see Cardbus cards
@@ -512,7 +512,7 @@ int __init pcibios_init(void)
return 0;
}
-char * __init pcibios_setup(char *str)
+char *__init pcibios_setup(char *str)
{
if (!strcmp(str, "off")) {
pci_probe = 0;
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 2ae525e0d8ba..9b18ef315a55 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -433,16 +433,14 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
return -EINVAL;
if (pat_enabled && write_combine)
- prot |= _PAGE_CACHE_WC;
+ prot |= cachemode2protval(_PAGE_CACHE_MODE_WC);
else if (pat_enabled || boot_cpu_data.x86 > 3)
/*
* ioremap() and ioremap_nocache() defaults to UC MINUS for now.
* To avoid attribute conflicts, request UC MINUS here
* as well.
*/
- prot |= _PAGE_CACHE_UC_MINUS;
-
- prot |= _PAGE_IOMAP; /* creating a mapping for IO */
+ prot |= cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS);
vma->vm_page_prot = __pgprot(prot);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index b9958c364075..44b9271580b5 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -210,6 +210,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
{
int polarity;
+ if (dev->irq_managed && dev->irq > 0)
+ return 0;
+
if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
polarity = 0; /* active high */
else
@@ -224,13 +227,18 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
if (mp_map_gsi_to_irq(dev->irq, IOAPIC_MAP_ALLOC) < 0)
return -EBUSY;
+ dev->irq_managed = 1;
+
return 0;
}
static void intel_mid_pci_irq_disable(struct pci_dev *dev)
{
- if (!mp_should_keep_irq(&dev->dev) && dev->irq > 0)
+ if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+ dev->irq > 0) {
mp_unmap_irq(dev->irq);
+ dev->irq_managed = 0;
+ }
}
struct pci_ops intel_mid_pci_ops = {
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index eb500c2592ad..5dc6ca5e1741 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1200,11 +1200,12 @@ static int pirq_enable_irq(struct pci_dev *dev)
#ifdef CONFIG_X86_IO_APIC
struct pci_dev *temp_dev;
int irq;
- struct io_apic_irq_attr irq_attr;
+
+ if (dev->irq_managed && dev->irq > 0)
+ return 0;
irq = IO_APIC_get_PCI_irq_vector(dev->bus->number,
- PCI_SLOT(dev->devfn),
- pin - 1, &irq_attr);
+ PCI_SLOT(dev->devfn), pin - 1);
/*
* Busses behind bridges are typically not listed in the MP-table.
* In this case we have to look up the IRQ based on the parent bus,
@@ -1218,7 +1219,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
pin = pci_swizzle_interrupt_pin(dev, pin);
irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
PCI_SLOT(bridge->devfn),
- pin - 1, &irq_attr);
+ pin - 1);
if (irq >= 0)
dev_warn(&dev->dev, "using bridge %s "
"INT %c to get IRQ %d\n",
@@ -1228,6 +1229,7 @@ static int pirq_enable_irq(struct pci_dev *dev)
}
dev = temp_dev;
if (irq >= 0) {
+ dev->irq_managed = 1;
dev->irq = irq;
dev_info(&dev->dev, "PCI->APIC IRQ transform: "
"INT %c -> IRQ %d\n", 'A' + pin - 1, irq);
@@ -1254,11 +1256,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
return 0;
}
+bool mp_should_keep_irq(struct device *dev)
+{
+ if (dev->power.is_prepared)
+ return true;
+#ifdef CONFIG_PM
+ if (dev->power.runtime_status == RPM_SUSPENDING)
+ return true;
+#endif
+
+ return false;
+}
+
static void pirq_disable_irq(struct pci_dev *dev)
{
if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
- dev->irq) {
+ dev->irq_managed && dev->irq) {
mp_unmap_irq(dev->irq);
dev->irq = 0;
+ dev->irq_managed = 0;
}
}
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 248642f4bab7..326198a4434e 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -31,7 +31,7 @@ static DEFINE_MUTEX(pci_mmcfg_lock);
LIST_HEAD(pci_mmcfg_list);
-static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
+static void __init pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
{
if (cfg->res.parent)
release_resource(&cfg->res);
@@ -39,7 +39,7 @@ static __init void pci_mmconfig_remove(struct pci_mmcfg_region *cfg)
kfree(cfg);
}
-static __init void free_all_mmcfg(void)
+static void __init free_all_mmcfg(void)
{
struct pci_mmcfg_region *cfg, *tmp;
@@ -93,7 +93,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start,
return new;
}
-static __init struct pci_mmcfg_region *pci_mmconfig_add(int segment, int start,
+static struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start,
int end, u64 addr)
{
struct pci_mmcfg_region *new;
@@ -125,7 +125,7 @@ struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus)
return NULL;
}
-static const char __init *pci_mmcfg_e7520(void)
+static const char *__init pci_mmcfg_e7520(void)
{
u32 win;
raw_pci_ops->read(0, 0, PCI_DEVFN(0, 0), 0xce, 2, &win);
@@ -140,7 +140,7 @@ static const char __init *pci_mmcfg_e7520(void)
return "Intel Corporation E7520 Memory Controller Hub";
}
-static const char __init *pci_mmcfg_intel_945(void)
+static const char *__init pci_mmcfg_intel_945(void)
{
u32 pciexbar, mask = 0, len = 0;
@@ -184,7 +184,7 @@ static const char __init *pci_mmcfg_intel_945(void)
return "Intel Corporation 945G/GZ/P/PL Express Memory Controller Hub";
}
-static const char __init *pci_mmcfg_amd_fam10h(void)
+static const char *__init pci_mmcfg_amd_fam10h(void)
{
u32 low, high, address;
u64 base, msr;
@@ -235,21 +235,25 @@ static const char __init *pci_mmcfg_amd_fam10h(void)
}
static bool __initdata mcp55_checked;
-static const char __init *pci_mmcfg_nvidia_mcp55(void)
+static const char *__init pci_mmcfg_nvidia_mcp55(void)
{
int bus;
int mcp55_mmconf_found = 0;
- static const u32 extcfg_regnum = 0x90;
- static const u32 extcfg_regsize = 4;
- static const u32 extcfg_enable_mask = 1<<31;
- static const u32 extcfg_start_mask = 0xff<<16;
- static const int extcfg_start_shift = 16;
- static const u32 extcfg_size_mask = 0x3<<28;
- static const int extcfg_size_shift = 28;
- static const int extcfg_sizebus[] = {0x100, 0x80, 0x40, 0x20};
- static const u32 extcfg_base_mask[] = {0x7ff8, 0x7ffc, 0x7ffe, 0x7fff};
- static const int extcfg_base_lshift = 25;
+ static const u32 extcfg_regnum __initconst = 0x90;
+ static const u32 extcfg_regsize __initconst = 4;
+ static const u32 extcfg_enable_mask __initconst = 1 << 31;
+ static const u32 extcfg_start_mask __initconst = 0xff << 16;
+ static const int extcfg_start_shift __initconst = 16;
+ static const u32 extcfg_size_mask __initconst = 0x3 << 28;
+ static const int extcfg_size_shift __initconst = 28;
+ static const int extcfg_sizebus[] __initconst = {
+ 0x100, 0x80, 0x40, 0x20
+ };
+ static const u32 extcfg_base_mask[] __initconst = {
+ 0x7ff8, 0x7ffc, 0x7ffe, 0x7fff
+ };
+ static const int extcfg_base_lshift __initconst = 25;
/*
* do check if amd fam10h already took over
@@ -302,7 +306,7 @@ struct pci_mmcfg_hostbridge_probe {
const char *(*probe)(void);
};
-static struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initdata = {
+static const struct pci_mmcfg_hostbridge_probe pci_mmcfg_probes[] __initconst = {
{ 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL,
PCI_DEVICE_ID_INTEL_E7520_MCH, pci_mmcfg_e7520 },
{ 0, PCI_DEVFN(0, 0), PCI_VENDOR_ID_INTEL,
diff --git a/arch/x86/pci/numachip.c b/arch/x86/pci/numachip.c
index 7307d9d12d15..2e565e65c893 100644
--- a/arch/x86/pci/numachip.c
+++ b/arch/x86/pci/numachip.c
@@ -103,7 +103,7 @@ static int pci_mmcfg_write_numachip(unsigned int seg, unsigned int bus,
return 0;
}
-const struct pci_raw_ops pci_mmcfg_numachip = {
+static const struct pci_raw_ops pci_mmcfg_numachip = {
.read = pci_mmcfg_read_numachip,
.write = pci_mmcfg_write_numachip,
};
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index c77b24a8b2da..9b83b9051ae7 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -79,13 +79,13 @@ union bios32 {
static struct {
unsigned long address;
unsigned short segment;
-} bios32_indirect = { 0, __KERNEL_CS };
+} bios32_indirect __initdata = { 0, __KERNEL_CS };
/*
* Returns the entry point for the given service, NULL on error
*/
-static unsigned long bios32_service(unsigned long service)
+static unsigned long __init bios32_service(unsigned long service)
{
unsigned char return_code; /* %al */
unsigned long address; /* %ebx */
@@ -124,7 +124,7 @@ static struct {
static int pci_bios_present;
-static int check_pcibios(void)
+static int __init check_pcibios(void)
{
u32 signature, eax, ebx, ecx;
u8 status, major_ver, minor_ver, hw_mech;
@@ -312,7 +312,7 @@ static const struct pci_raw_ops pci_bios_access = {
* Try to find PCI BIOS.
*/
-static const struct pci_raw_ops *pci_find_bios(void)
+static const struct pci_raw_ops *__init pci_find_bios(void)
{
union bios32 *check;
unsigned char sum;
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 093f5f4272d3..c489ef2c1a39 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -23,6 +23,8 @@
#include <xen/features.h>
#include <xen/events.h>
#include <asm/xen/pci.h>
+#include <asm/xen/cpuid.h>
+#include <asm/apic.h>
#include <asm/i8259.h>
static int xen_pcifront_enable_irq(struct pci_dev *dev)
@@ -229,7 +231,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
return 1;
list_for_each_entry(msidesc, &dev->msi_list, list) {
- __read_msi_msg(msidesc, &msg);
+ __pci_read_msi_msg(msidesc, &msg);
pirq = MSI_ADDR_EXT_DEST_ID(msg.address_hi) |
((msg.address_lo >> MSI_ADDR_DEST_ID_SHIFT) & 0xff);
if (msg.data != XEN_PIRQ_MSI_DATA ||
@@ -240,7 +242,7 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
goto error;
}
xen_msi_compose_msg(dev, pirq, &msg);
- __write_msi_msg(msidesc, &msg);
+ __pci_write_msi_msg(msidesc, &msg);
dev_dbg(&dev->dev, "xen: msi bound to pirq=%d\n", pirq);
} else {
dev_dbg(&dev->dev,
@@ -394,14 +396,7 @@ static void xen_teardown_msi_irq(unsigned int irq)
{
xen_destroy_irq(irq);
}
-static u32 xen_nop_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
-{
- return 0;
-}
-static u32 xen_nop_msix_mask_irq(struct msi_desc *desc, u32 flag)
-{
- return 0;
-}
+
#endif
int __init pci_xen_init(void)
@@ -425,12 +420,33 @@ int __init pci_xen_init(void)
x86_msi.setup_msi_irqs = xen_setup_msi_irqs;
x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
x86_msi.teardown_msi_irqs = xen_teardown_msi_irqs;
- x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
- x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
+ pci_msi_ignore_mask = 1;
#endif
return 0;
}
+#ifdef CONFIG_PCI_MSI
+void __init xen_msi_init(void)
+{
+ if (!disable_apic) {
+ /*
+ * If hardware supports (x2)APIC virtualization (as indicated
+ * by hypervisor's leaf 4) then we don't need to use pirqs/
+ * event channels for MSI handling and instead use regular
+ * APIC processing
+ */
+ uint32_t eax = cpuid_eax(xen_cpuid_base() + 4);
+
+ if (((eax & XEN_HVM_CPUID_X2APIC_VIRT) && x2apic_mode) ||
+ ((eax & XEN_HVM_CPUID_APIC_ACCESS_VIRT) && cpu_has_apic))
+ return;
+ }
+
+ x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
+ x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+}
+#endif
+
int __init pci_xen_hvm_init(void)
{
if (!xen_have_vector_callback || !xen_feature(XENFEAT_hvm_pirqs))
@@ -445,8 +461,11 @@ int __init pci_xen_hvm_init(void)
#endif
#ifdef CONFIG_PCI_MSI
- x86_msi.setup_msi_irqs = xen_hvm_setup_msi_irqs;
- x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
+ /*
+ * We need to wait until after x2apic is initialized
+ * before we can set MSI IRQ ops.
+ */
+ x86_platform.apic_post_init = xen_msi_init;
#endif
return 0;
}
@@ -506,8 +525,7 @@ int __init pci_xen_initial_domain(void)
x86_msi.setup_msi_irqs = xen_initdom_setup_msi_irqs;
x86_msi.teardown_msi_irq = xen_teardown_msi_irq;
x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
- x86_msi.msi_mask_irq = xen_nop_msi_mask_irq;
- x86_msi.msix_mask_irq = xen_nop_msix_mask_irq;
+ pci_msi_ignore_mask = 1;
#endif
xen_setup_acpi_sci();
__acpi_register_gsi = acpi_register_gsi_xen;
diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c
index f15103dff4b4..d143d216d52b 100644
--- a/arch/x86/platform/efi/efi-bgrt.c
+++ b/arch/x86/platform/efi/efi-bgrt.c
@@ -40,20 +40,40 @@ void __init efi_bgrt_init(void)
if (ACPI_FAILURE(status))
return;
- if (bgrt_tab->header.length < sizeof(*bgrt_tab))
+ if (bgrt_tab->header.length < sizeof(*bgrt_tab)) {
+ pr_err("Ignoring BGRT: invalid length %u (expected %zu)\n",
+ bgrt_tab->header.length, sizeof(*bgrt_tab));
return;
- if (bgrt_tab->version != 1 || bgrt_tab->status != 1)
+ }
+ if (bgrt_tab->version != 1) {
+ pr_err("Ignoring BGRT: invalid version %u (expected 1)\n",
+ bgrt_tab->version);
+ return;
+ }
+ if (bgrt_tab->status != 1) {
+ pr_err("Ignoring BGRT: invalid status %u (expected 1)\n",
+ bgrt_tab->status);
+ return;
+ }
+ if (bgrt_tab->image_type != 0) {
+ pr_err("Ignoring BGRT: invalid image type %u (expected 0)\n",
+ bgrt_tab->image_type);
return;
- if (bgrt_tab->image_type != 0 || !bgrt_tab->image_address)
+ }
+ if (!bgrt_tab->image_address) {
+ pr_err("Ignoring BGRT: null image address\n");
return;
+ }
image = efi_lookup_mapped_addr(bgrt_tab->image_address);
if (!image) {
image = early_memremap(bgrt_tab->image_address,
sizeof(bmp_header));
ioremapped = true;
- if (!image)
+ if (!image) {
+ pr_err("Ignoring BGRT: failed to map image header memory\n");
return;
+ }
}
memcpy_fromio(&bmp_header, image, sizeof(bmp_header));
@@ -61,14 +81,18 @@ void __init efi_bgrt_init(void)
early_iounmap(image, sizeof(bmp_header));
bgrt_image_size = bmp_header.size;
- bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL);
- if (!bgrt_image)
+ bgrt_image = kmalloc(bgrt_image_size, GFP_KERNEL | __GFP_NOWARN);
+ if (!bgrt_image) {
+ pr_err("Ignoring BGRT: failed to allocate memory for image (wanted %zu bytes)\n",
+ bgrt_image_size);
return;
+ }
if (ioremapped) {
image = early_memremap(bgrt_tab->image_address,
bmp_header.size);
if (!image) {
+ pr_err("Ignoring BGRT: failed to map image memory\n");
kfree(bgrt_image);
bgrt_image = NULL;
return;
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 850da94fef30..dbc8627a5cdf 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -70,17 +70,7 @@ static efi_config_table_type_t arch_tables[] __initdata = {
u64 efi_setup; /* efi setup_data physical address */
-static bool disable_runtime __initdata = false;
-static int __init setup_noefi(char *arg)
-{
- disable_runtime = true;
- return 0;
-}
-early_param("noefi", setup_noefi);
-
-int add_efi_memmap;
-EXPORT_SYMBOL(add_efi_memmap);
-
+static int add_efi_memmap __initdata;
static int __init setup_add_efi_memmap(char *arg)
{
add_efi_memmap = 1;
@@ -96,7 +86,7 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
{
efi_status_t status;
- efi_call_phys_prelog();
+ efi_call_phys_prolog();
status = efi_call_phys(efi_phys.set_virtual_address_map,
memory_map_size, descriptor_size,
descriptor_version, virtual_map);
@@ -210,9 +200,12 @@ static void __init print_efi_memmap(void)
for (p = memmap.map, i = 0;
p < memmap.map_end;
p += memmap.desc_size, i++) {
+ char buf[64];
+
md = p;
- pr_info("mem%02u: type=%u, attr=0x%llx, range=[0x%016llx-0x%016llx) (%lluMB)\n",
- i, md->type, md->attribute, md->phys_addr,
+ pr_info("mem%02u: %s range=[0x%016llx-0x%016llx) (%lluMB)\n",
+ i, efi_md_typeattr_format(buf, sizeof(buf), md),
+ md->phys_addr,
md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
(md->num_pages >> (20 - EFI_PAGE_SHIFT)));
}
@@ -344,9 +337,9 @@ static int __init efi_runtime_init32(void)
}
/*
- * We will only need *early* access to the following two
- * EFI runtime services before set_virtual_address_map
- * is invoked.
+ * We will only need *early* access to the SetVirtualAddressMap
+ * EFI runtime service. All other runtime services will be called
+ * via the virtual mapping.
*/
efi_phys.set_virtual_address_map =
(efi_set_virtual_address_map_t *)
@@ -368,9 +361,9 @@ static int __init efi_runtime_init64(void)
}
/*
- * We will only need *early* access to the following two
- * EFI runtime services before set_virtual_address_map
- * is invoked.
+ * We will only need *early* access to the SetVirtualAddressMap
+ * EFI runtime service. All other runtime services will be called
+ * via the virtual mapping.
*/
efi_phys.set_virtual_address_map =
(efi_set_virtual_address_map_t *)
@@ -492,7 +485,7 @@ void __init efi_init(void)
if (!efi_runtime_supported())
pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
else {
- if (disable_runtime || efi_runtime_init())
+ if (efi_runtime_disabled() || efi_runtime_init())
return;
}
if (efi_memmap_init())
@@ -537,7 +530,7 @@ void __init runtime_code_page_mkexec(void)
}
}
-void efi_memory_uc(u64 addr, unsigned long size)
+void __init efi_memory_uc(u64 addr, unsigned long size)
{
unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
u64 npages;
@@ -732,6 +725,7 @@ static void __init kexec_enter_virtual_mode(void)
*/
if (!efi_is_native()) {
efi_unmap_memmap();
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
}
@@ -805,6 +799,7 @@ static void __init __efi_enter_virtual_mode(void)
new_memmap = efi_map_regions(&count, &pg_shift);
if (!new_memmap) {
pr_err("Error reallocating memory, EFI runtime non-functional!\n");
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
}
@@ -812,8 +807,10 @@ static void __init __efi_enter_virtual_mode(void)
BUG_ON(!efi.systab);
- if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
+ if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) {
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
return;
+ }
efi_sync_low_kernel_mappings();
efi_dump_pagetable();
@@ -938,14 +935,11 @@ u64 efi_mem_attributes(unsigned long phys_addr)
return 0;
}
-static int __init parse_efi_cmdline(char *str)
+static int __init arch_parse_efi_cmdline(char *str)
{
- if (*str == '=')
- str++;
-
- if (!strncmp(str, "old_map", 7))
+ if (parse_option_str(str, "old_map"))
set_bit(EFI_OLD_MEMMAP, &efi.flags);
return 0;
}
-early_param("efi", parse_efi_cmdline);
+early_param("efi", arch_parse_efi_cmdline);
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 9ee3491e31fb..40e7cda52936 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -33,7 +33,7 @@
/*
* To make EFI call EFI runtime service in physical addressing mode we need
- * prelog/epilog before/after the invocation to disable interrupt, to
+ * prolog/epilog before/after the invocation to disable interrupt, to
* claim EFI runtime service handler exclusively and to duplicate a memory in
* low memory space say 0 - 3G.
*/
@@ -41,11 +41,13 @@ static unsigned long efi_rt_eflags;
void efi_sync_low_kernel_mappings(void) {}
void __init efi_dump_pagetable(void) {}
-int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
return 0;
}
-void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {}
+void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+}
void __init efi_map_region(efi_memory_desc_t *md)
{
@@ -55,7 +57,7 @@ void __init efi_map_region(efi_memory_desc_t *md)
void __init efi_map_region_fixed(efi_memory_desc_t *md) {}
void __init parse_efi_setup(u64 phys_addr, u32 data_len) {}
-void efi_call_phys_prelog(void)
+void __init efi_call_phys_prolog(void)
{
struct desc_ptr gdt_descr;
@@ -69,7 +71,7 @@ void efi_call_phys_prelog(void)
load_gdt(&gdt_descr);
}
-void efi_call_phys_epilog(void)
+void __init efi_call_phys_epilog(void)
{
struct desc_ptr gdt_descr;
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 290d397e1dd9..17e80d829df0 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -48,8 +48,7 @@ static unsigned long efi_flags __initdata;
* We allocate runtime services regions bottom-up, starting from -4G, i.e.
* 0xffff_ffff_0000_0000 and limit EFI VA mapping space to 64G.
*/
-static u64 efi_va = -4 * (1UL << 30);
-#define EFI_VA_END (-68 * (1UL << 30))
+static u64 efi_va = EFI_VA_START;
/*
* Scratch space used for switching the pagetable in the EFI stub
@@ -79,7 +78,7 @@ static void __init early_code_mapping_set_exec(int executable)
}
}
-void __init efi_call_phys_prelog(void)
+void __init efi_call_phys_prolog(void)
{
unsigned long vaddress;
int pgd;
@@ -139,7 +138,7 @@ void efi_sync_low_kernel_mappings(void)
sizeof(pgd_t) * num_pgds);
}
-int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
unsigned long text;
struct page *page;
@@ -192,7 +191,7 @@ int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
return 0;
}
-void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
{
pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
diff --git a/arch/x86/platform/efi/efi_stub_32.S b/arch/x86/platform/efi/efi_stub_32.S
index fbe66e626c09..040192b50d02 100644
--- a/arch/x86/platform/efi/efi_stub_32.S
+++ b/arch/x86/platform/efi/efi_stub_32.S
@@ -27,13 +27,13 @@ ENTRY(efi_call_phys)
* set to 0x0010, DS and SS have been set to 0x0018. In EFI, I found
* the values of these registers are the same. And, the corresponding
* GDT entries are identical. So I will do nothing about segment reg
- * and GDT, but change GDT base register in prelog and epilog.
+ * and GDT, but change GDT base register in prolog and epilog.
*/
/*
* 1. Now I am running with EIP = <physical address> + PAGE_OFFSET.
* But to make it smoothly switch from virtual mode to flat mode.
- * The mapping of lower virtual memory has been created in prelog and
+ * The mapping of lower virtual memory has been created in prolog and
* epilog.
*/
movl $1f, %edx
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
index 46aa25c8ce06..3c1c3866d82b 100644
--- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
+++ b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
@@ -10,10 +10,9 @@
*/
-/* __attribute__((weak)) makes these declarations overridable */
/* For every CPU addition a new get_<cpuname>_ops interface needs
* to be added.
*/
-extern void *get_penwell_ops(void) __attribute__((weak));
-extern void *get_cloverview_ops(void) __attribute__((weak));
-extern void *get_tangier_ops(void) __attribute__((weak));
+extern void *get_penwell_ops(void);
+extern void *get_cloverview_ops(void);
+extern void *get_tangier_ops(void);
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
index 3c53a90fdb18..c14ad34776c4 100644
--- a/arch/x86/platform/intel-mid/sfi.c
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -106,6 +106,7 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
mp_save_irq(&mp_irq);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
}
return 0;
@@ -176,6 +177,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
mp_irq.dstapic = MP_APIC_ALL;
mp_irq.dstirq = pentry->irq;
mp_save_irq(&mp_irq);
+ mp_map_gsi_to_irq(pentry->irq, IOAPIC_MAP_ALLOC);
}
return 0;
}
diff --git a/arch/x86/platform/iris/iris.c b/arch/x86/platform/iris/iris.c
index 4d171e8640ef..735ba21efe91 100644
--- a/arch/x86/platform/iris/iris.c
+++ b/arch/x86/platform/iris/iris.c
@@ -86,7 +86,6 @@ static int iris_remove(struct platform_device *pdev)
static struct platform_driver iris_driver = {
.driver = {
.name = "iris",
- .owner = THIS_MODULE,
},
.probe = iris_probe,
.remove = iris_remove,
diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c
index a9acde72d4ed..c5350fd27d70 100644
--- a/arch/x86/platform/olpc/olpc-xo1-pm.c
+++ b/arch/x86/platform/olpc/olpc-xo1-pm.c
@@ -170,7 +170,6 @@ static int xo1_pm_remove(struct platform_device *pdev)
static struct platform_driver cs5535_pms_driver = {
.driver = {
.name = "cs5535-pms",
- .owner = THIS_MODULE,
},
.probe = xo1_pm_probe,
.remove = xo1_pm_remove,
@@ -179,7 +178,6 @@ static struct platform_driver cs5535_pms_driver = {
static struct platform_driver cs5535_acpi_driver = {
.driver = {
.name = "olpc-xo1-pm-acpi",
- .owner = THIS_MODULE,
},
.probe = xo1_pm_probe,
.remove = xo1_pm_remove,
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3968d67d366b..994798548b1a 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1367,23 +1367,25 @@ static int ptc_seq_show(struct seq_file *file, void *data)
cpu = *(loff_t *)data;
if (!cpu) {
- seq_printf(file,
- "# cpu bauoff sent stime self locals remotes ncpus localhub ");
- seq_printf(file,
- "remotehub numuvhubs numuvhubs16 numuvhubs8 ");
- seq_printf(file,
- "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries ");
- seq_printf(file,
- "rok resetp resett giveup sto bz throt disable ");
- seq_printf(file,
- "enable wars warshw warwaits enters ipidis plugged ");
- seq_printf(file,
- "ipiover glim cong swack recv rtime all one mult ");
- seq_printf(file,
- "none retry canc nocan reset rcan\n");
+ seq_puts(file,
+ "# cpu bauoff sent stime self locals remotes ncpus localhub ");
+ seq_puts(file, "remotehub numuvhubs numuvhubs16 numuvhubs8 ");
+ seq_puts(file,
+ "numuvhubs4 numuvhubs2 numuvhubs1 dto snacks retries ");
+ seq_puts(file,
+ "rok resetp resett giveup sto bz throt disable ");
+ seq_puts(file,
+ "enable wars warshw warwaits enters ipidis plugged ");
+ seq_puts(file,
+ "ipiover glim cong swack recv rtime all one mult ");
+ seq_puts(file, "none retry canc nocan reset rcan\n");
}
if (cpu < num_possible_cpus() && cpu_online(cpu)) {
bcp = &per_cpu(bau_control, cpu);
+ if (bcp->nobau) {
+ seq_printf(file, "cpu %d bau disabled\n", cpu);
+ return 0;
+ }
stat = bcp->statp;
/* source side statistics */
seq_printf(file,
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index b233681af4de..0ce673645432 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -131,7 +131,7 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
unsigned long mmr_offset, int limit)
{
const struct cpumask *eligible_cpu = cpumask_of(cpu);
- struct irq_cfg *cfg = irq_get_chip_data(irq);
+ struct irq_cfg *cfg = irq_cfg(irq);
unsigned long mmr_value;
struct uv_IO_APIC_route_entry *entry;
int mmr_pnode, err;
@@ -198,13 +198,13 @@ static int
uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
bool force)
{
- struct irq_cfg *cfg = data->chip_data;
+ struct irq_cfg *cfg = irqd_cfg(data);
unsigned int dest;
unsigned long mmr_value, mmr_offset;
struct uv_IO_APIC_route_entry *entry;
int mmr_pnode;
- if (__ioapic_set_affinity(data, mask, &dest))
+ if (apic_set_affinity(data, mask, &dest))
return -1;
mmr_value = 0;
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c89c93320c12..c6b146e67116 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -63,8 +63,8 @@
static struct uv_hub_nmi_s **uv_hub_nmi_list;
-DEFINE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
-EXPORT_PER_CPU_SYMBOL_GPL(__uv_cpu_nmi);
+DEFINE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
+EXPORT_PER_CPU_SYMBOL_GPL(uv_cpu_nmi);
static unsigned long nmi_mmr;
static unsigned long nmi_mmr_clear;
@@ -215,7 +215,7 @@ static int uv_check_nmi(struct uv_hub_nmi_s *hub_nmi)
int nmi = 0;
local64_inc(&uv_nmi_count);
- uv_cpu_nmi.queries++;
+ this_cpu_inc(uv_cpu_nmi.queries);
do {
nmi = atomic_read(&hub_nmi->in_nmi);
@@ -293,7 +293,7 @@ static void uv_nmi_nr_cpus_ping(void)
int cpu;
for_each_cpu(cpu, uv_nmi_cpu_mask)
- atomic_set(&uv_cpu_nmi_per(cpu).pinging, 1);
+ uv_cpu_nmi_per(cpu).pinging = 1;
apic->send_IPI_mask(uv_nmi_cpu_mask, APIC_DM_NMI);
}
@@ -304,8 +304,8 @@ static void uv_nmi_cleanup_mask(void)
int cpu;
for_each_cpu(cpu, uv_nmi_cpu_mask) {
- atomic_set(&uv_cpu_nmi_per(cpu).pinging, 0);
- atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_OUT);
+ uv_cpu_nmi_per(cpu).pinging = 0;
+ uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_OUT;
cpumask_clear_cpu(cpu, uv_nmi_cpu_mask);
}
}
@@ -328,7 +328,7 @@ static int uv_nmi_wait_cpus(int first)
int loop_delay = uv_nmi_loop_delay;
for_each_cpu(j, uv_nmi_cpu_mask) {
- if (atomic_read(&uv_cpu_nmi_per(j).state)) {
+ if (uv_cpu_nmi_per(j).state) {
cpumask_clear_cpu(j, uv_nmi_cpu_mask);
if (++k >= n)
break;
@@ -359,7 +359,7 @@ static int uv_nmi_wait_cpus(int first)
static void uv_nmi_wait(int master)
{
/* indicate this cpu is in */
- atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_IN);
+ this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_IN);
/* if not the first cpu in (the master), then we are a slave cpu */
if (!master)
@@ -419,7 +419,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
"UV:%sNMI process trace for CPU %d\n", dots, cpu);
show_regs(regs);
}
- atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
+ this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE);
}
/* Trigger a slave cpu to dump it's state */
@@ -427,20 +427,20 @@ static void uv_nmi_trigger_dump(int cpu)
{
int retry = uv_nmi_trigger_delay;
- if (atomic_read(&uv_cpu_nmi_per(cpu).state) != UV_NMI_STATE_IN)
+ if (uv_cpu_nmi_per(cpu).state != UV_NMI_STATE_IN)
return;
- atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP);
+ uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP;
do {
cpu_relax();
udelay(10);
- if (atomic_read(&uv_cpu_nmi_per(cpu).state)
+ if (uv_cpu_nmi_per(cpu).state
!= UV_NMI_STATE_DUMP)
return;
} while (--retry > 0);
pr_crit("UV: CPU %d stuck in process dump function\n", cpu);
- atomic_set(&uv_cpu_nmi_per(cpu).state, UV_NMI_STATE_DUMP_DONE);
+ uv_cpu_nmi_per(cpu).state = UV_NMI_STATE_DUMP_DONE;
}
/* Wait until all cpus ready to exit */
@@ -488,7 +488,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
} else {
while (!atomic_read(&uv_nmi_slave_continue))
cpu_relax();
- while (atomic_read(&uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
+ while (this_cpu_read(uv_cpu_nmi.state) != UV_NMI_STATE_DUMP)
cpu_relax();
uv_nmi_dump_state_cpu(cpu, regs);
}
@@ -615,7 +615,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
local_irq_save(flags);
/* If not a UV System NMI, ignore */
- if (!atomic_read(&uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
+ if (!this_cpu_read(uv_cpu_nmi.pinging) && !uv_check_nmi(hub_nmi)) {
local_irq_restore(flags);
return NMI_DONE;
}
@@ -639,7 +639,7 @@ int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
uv_call_kgdb_kdb(cpu, regs, master);
/* Clear per_cpu "in nmi" flag */
- atomic_set(&uv_cpu_nmi.state, UV_NMI_STATE_OUT);
+ this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_OUT);
/* Clear MMR NMI flag on each hub */
uv_clear_nmi(cpu);
@@ -666,16 +666,16 @@ static int uv_handle_nmi_ping(unsigned int reason, struct pt_regs *regs)
{
int ret;
- uv_cpu_nmi.queries++;
- if (!atomic_read(&uv_cpu_nmi.pinging)) {
+ this_cpu_inc(uv_cpu_nmi.queries);
+ if (!this_cpu_read(uv_cpu_nmi.pinging)) {
local64_inc(&uv_nmi_ping_misses);
return NMI_DONE;
}
- uv_cpu_nmi.pings++;
+ this_cpu_inc(uv_cpu_nmi.pings);
local64_inc(&uv_nmi_ping_count);
ret = uv_handle_nmi(reason, regs);
- atomic_set(&uv_cpu_nmi.pinging, 0);
+ this_cpu_write(uv_cpu_nmi.pinging, 0);
return ret;
}
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 5c86786bbfd2..a244237f3cfa 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -365,7 +365,7 @@ __setup("uvrtcevt", uv_enable_evt_rtc);
static __init void uv_rtc_register_clockevents(struct work_struct *dummy)
{
- struct clock_event_device *ced = &__get_cpu_var(cpu_ced);
+ struct clock_event_device *ced = this_cpu_ptr(&cpu_ced);
*ced = clock_event_device_uv;
ced->cpumask = cpumask_of(smp_processor_id());
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 7d28c885d238..291226b952a9 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -13,13 +13,11 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mmzone.h>
+#include <asm/sections.h>
/* Defined in hibernate_asm_32.S */
extern int restore_image(void);
-/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
-
/* Pointer to the temporary resume page tables */
pgd_t *resume_pg_dir;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 35e2bb6c0f37..009947d419a6 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -17,11 +17,9 @@
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/mtrr.h>
+#include <asm/sections.h>
#include <asm/suspend.h>
-/* References to section boundaries */
-extern __visible const void __nosave_begin, __nosave_end;
-
/* Defined in hibernate_asm_64.S */
extern asmlinkage __visible int restore_image(void);
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 899dd2454256..2c835e356349 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -18,11 +18,13 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
targets += kexec-purgatory.c
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
quiet_cmd_bin2c = BIN2C $@
- cmd_bin2c = cat $(obj)/purgatory.ro | $(objtree)/scripts/basic/bin2c kexec_purgatory > $(obj)/kexec-purgatory.c
+ cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
$(call if_changed,bin2c)
+ @:
obj-$(CONFIG_KEXEC_FILE) += kexec-purgatory.o
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 028b78168d85..b3560ece1c9f 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -363,3 +363,5 @@
354 i386 seccomp sys_seccomp
355 i386 getrandom sys_getrandom
356 i386 memfd_create sys_memfd_create
+357 i386 bpf sys_bpf
+358 i386 execveat sys_execveat stub32_execveat
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 35dd922727b9..8d656fbb57aa 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -327,6 +327,8 @@
318 common getrandom sys_getrandom
319 common memfd_create sys_memfd_create
320 common kexec_file_load sys_kexec_file_load
+321 common bpf sys_bpf
+322 64 execveat stub_execveat
#
# x32-specific system call numbers start at 512 to avoid cache impact
@@ -365,3 +367,4 @@
542 x32 getsockopt compat_sys_getsockopt
543 x32 io_setup compat_sys_io_setup
544 x32 io_submit compat_sys_io_submit
+545 x32 execveat stub_x32_execveat
diff --git a/arch/x86/tools/calc_run_size.pl b/arch/x86/tools/calc_run_size.pl
new file mode 100644
index 000000000000..23210baade2d
--- /dev/null
+++ b/arch/x86/tools/calc_run_size.pl
@@ -0,0 +1,39 @@
+#!/usr/bin/perl
+#
+# Calculate the amount of space needed to run the kernel, including room for
+# the .bss and .brk sections.
+#
+# Usage:
+# objdump -h a.out | perl calc_run_size.pl
+use strict;
+
+my $mem_size = 0;
+my $file_offset = 0;
+
+my $sections=" *[0-9]+ \.(?:bss|brk) +";
+while (<>) {
+ if (/^$sections([0-9a-f]+) +(?:[0-9a-f]+ +){2}([0-9a-f]+)/) {
+ my $size = hex($1);
+ my $offset = hex($2);
+ $mem_size += $size;
+ if ($file_offset == 0) {
+ $file_offset = $offset;
+ } elsif ($file_offset != $offset) {
+ # BFD linker shows the same file offset in ELF.
+ # Gold linker shows them as consecutive.
+ next if ($file_offset + $mem_size == $offset + $size);
+
+ printf STDERR "file_offset: 0x%lx\n", $file_offset;
+ printf STDERR "mem_size: 0x%lx\n", $mem_size;
+ printf STDERR "offset: 0x%lx\n", $offset;
+ printf STDERR "size: 0x%lx\n", $size;
+
+ die ".bss and .brk are non-contiguous\n";
+ }
+ }
+}
+
+if ($file_offset == 0) {
+ die "Never found .bss or .brk file offset\n";
+}
+printf("%d\n", $mem_size + $file_offset);
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index 872eb60e7806..ba70ff232917 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -254,7 +254,7 @@ int main(int argc, char **argv)
continue;
/* Decode an instruction */
- insn_init(&insn, insn_buf, x86_64);
+ insn_init(&insn, insn_buf, sizeof(insn_buf), x86_64);
insn_get_length(&insn);
if (insn.next_byte <= insn.kaddr ||
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index bbb1d2259ecf..0c2fae8d929d 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -20,7 +20,10 @@ struct relocs {
static struct relocs relocs16;
static struct relocs relocs32;
+#if ELF_BITS == 64
+static struct relocs relocs32neg;
static struct relocs relocs64;
+#endif
struct section {
Elf_Shdr shdr;
@@ -695,7 +698,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
*
*/
static int per_cpu_shndx = -1;
-Elf_Addr per_cpu_load_addr;
+static Elf_Addr per_cpu_load_addr;
static void percpu_init(void)
{
@@ -762,11 +765,16 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
switch (r_type) {
case R_X86_64_NONE:
+ /* NONE can be ignored. */
+ break;
+
case R_X86_64_PC32:
/*
- * NONE can be ignored and PC relative relocations don't
- * need to be adjusted.
+ * PC relative relocations don't need to be adjusted unless
+ * referencing a percpu symbol.
*/
+ if (is_percpu_sym(sym, symname))
+ add_reloc(&relocs32neg, offset);
break;
case R_X86_64_32:
@@ -986,7 +994,10 @@ static void emit_relocs(int as_text, int use_real_mode)
/* Order the relocations for more efficient processing */
sort_relocs(&relocs16);
sort_relocs(&relocs32);
+#if ELF_BITS == 64
+ sort_relocs(&relocs32neg);
sort_relocs(&relocs64);
+#endif
/* Print the relocations */
if (as_text) {
@@ -1007,14 +1018,21 @@ static void emit_relocs(int as_text, int use_real_mode)
for (i = 0; i < relocs32.count; i++)
write_reloc(relocs32.offset[i], stdout);
} else {
- if (ELF_BITS == 64) {
- /* Print a stop */
- write_reloc(0, stdout);
+#if ELF_BITS == 64
+ /* Print a stop */
+ write_reloc(0, stdout);
- /* Now print each relocation */
- for (i = 0; i < relocs64.count; i++)
- write_reloc(relocs64.offset[i], stdout);
- }
+ /* Now print each relocation */
+ for (i = 0; i < relocs64.count; i++)
+ write_reloc(relocs64.offset[i], stdout);
+
+ /* Print a stop */
+ write_reloc(0, stdout);
+
+ /* Now print each inverse 32-bit relocation */
+ for (i = 0; i < relocs32neg.count; i++)
+ write_reloc(relocs32neg.offset[i], stdout);
+#endif
/* Print a stop */
write_reloc(0, stdout);
diff --git a/arch/x86/tools/test_get_len.c b/arch/x86/tools/test_get_len.c
index 13403fc95a96..56f04db0c9c0 100644
--- a/arch/x86/tools/test_get_len.c
+++ b/arch/x86/tools/test_get_len.c
@@ -149,7 +149,7 @@ int main(int argc, char **argv)
break;
}
/* Decode an instruction */
- insn_init(&insn, insn_buf, x86_64);
+ insn_init(&insn, insn_buf, sizeof(insn_buf), x86_64);
insn_get_length(&insn);
if (insn.length != nb) {
warnings++;
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index cc04e67bfd05..2d7d9a1f5b53 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -29,20 +29,18 @@
#endif /* CONFIG_X86_32 */
-#define read_barrier_depends() do { } while (0)
-
-#ifdef CONFIG_SMP
-
-#define smp_mb() mb()
#ifdef CONFIG_X86_PPRO_FENCE
-#define smp_rmb() rmb()
+#define dma_rmb() rmb()
#else /* CONFIG_X86_PPRO_FENCE */
-#define smp_rmb() barrier()
+#define dma_rmb() barrier()
#endif /* CONFIG_X86_PPRO_FENCE */
+#define dma_wmb() barrier()
-#define smp_wmb() barrier()
+#ifdef CONFIG_SMP
-#define smp_read_barrier_depends() read_barrier_depends()
+#define smp_mb() mb()
+#define smp_rmb() dma_rmb()
+#define smp_wmb() barrier()
#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
#else /* CONFIG_SMP */
@@ -50,11 +48,13 @@
#define smp_mb() barrier()
#define smp_rmb() barrier()
#define smp_wmb() barrier()
-#define smp_read_barrier_depends() do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif /* CONFIG_SMP */
+#define read_barrier_depends() do { } while (0)
+#define smp_read_barrier_depends() do { } while (0)
+
/*
* Stop RDTSC speculation. This is needed when you need to use RDTSC
* (or get_cycles or vread that possibly accesses the TSC) in a defined
diff --git a/arch/x86/um/asm/ptrace.h b/arch/x86/um/asm/ptrace.h
index 54f8102ccde5..e59eef20647b 100644
--- a/arch/x86/um/asm/ptrace.h
+++ b/arch/x86/um/asm/ptrace.h
@@ -47,8 +47,6 @@ struct user_desc;
#ifdef CONFIG_X86_32
-#define HOST_AUDIT_ARCH AUDIT_ARCH_I386
-
extern int ptrace_get_thread_area(struct task_struct *child, int idx,
struct user_desc __user *user_desc);
@@ -57,8 +55,6 @@ extern int ptrace_set_thread_area(struct task_struct *child, int idx,
#else
-#define HOST_AUDIT_ARCH AUDIT_ARCH_X86_64
-
#define PT_REGS_R8(r) UPT_R8(&(r)->regs)
#define PT_REGS_R9(r) UPT_R9(&(r)->regs)
#define PT_REGS_R10(r) UPT_R10(&(r)->regs)
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
new file mode 100644
index 000000000000..9fe77b7b5a0e
--- /dev/null
+++ b/arch/x86/um/asm/syscall.h
@@ -0,0 +1,15 @@
+#ifndef __UM_ASM_SYSCALL_H
+#define __UM_ASM_SYSCALL_H
+
+#include <uapi/linux/audit.h>
+
+static inline int syscall_get_arch(void)
+{
+#ifdef CONFIG_X86_32
+ return AUDIT_ARCH_I386;
+#else
+ return AUDIT_ARCH_X86_64;
+#endif
+}
+
+#endif /* __UM_ASM_SYSCALL_H */
diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S
index 8d0c420465cc..fa4b8b9841ff 100644
--- a/arch/x86/um/checksum_32.S
+++ b/arch/x86/um/checksum_32.S
@@ -214,242 +214,3 @@ csum_partial:
ret
#endif
-
-/*
-unsigned int csum_partial_copy_generic (const char *src, char *dst,
- int len, int sum, int *src_err_ptr, int *dst_err_ptr)
- */
-
-/*
- * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- * DST definitions? It's damn hard to trigger all cases. I hope I got
- * them all but there's no guarantee.
- */
-
-#define SRC(y...) \
- 9999: y; \
- _ASM_EXTABLE(9999b, 6001f)
-
-#define DST(y...) \
- 9999: y; \
- _ASM_EXTABLE(9999b, 6002f)
-
-.align 4
-
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
-#define ARGBASE 16
-#define FP 12
-
-csum_partial_copy_generic_i386:
- subl $4,%esp
- pushl %edi
- pushl %esi
- pushl %ebx
- movl ARGBASE+16(%esp),%eax # sum
- movl ARGBASE+12(%esp),%ecx # len
- movl ARGBASE+4(%esp),%esi # src
- movl ARGBASE+8(%esp),%edi # dst
-
- testl $2, %edi # Check alignment.
- jz 2f # Jump if alignment is ok.
- subl $2, %ecx # Alignment uses up two bytes.
- jae 1f # Jump if we had at least two bytes.
- addl $2, %ecx # ecx was < 2. Deal with it.
- jmp 4f
-SRC(1: movw (%esi), %bx )
- addl $2, %esi
-DST( movw %bx, (%edi) )
- addl $2, %edi
- addw %bx, %ax
- adcl $0, %eax
-2:
- movl %ecx, FP(%esp)
- shrl $5, %ecx
- jz 2f
- testl %esi, %esi
-SRC(1: movl (%esi), %ebx )
-SRC( movl 4(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, (%edi) )
- adcl %edx, %eax
-DST( movl %edx, 4(%edi) )
-
-SRC( movl 8(%esi), %ebx )
-SRC( movl 12(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, 8(%edi) )
- adcl %edx, %eax
-DST( movl %edx, 12(%edi) )
-
-SRC( movl 16(%esi), %ebx )
-SRC( movl 20(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, 16(%edi) )
- adcl %edx, %eax
-DST( movl %edx, 20(%edi) )
-
-SRC( movl 24(%esi), %ebx )
-SRC( movl 28(%esi), %edx )
- adcl %ebx, %eax
-DST( movl %ebx, 24(%edi) )
- adcl %edx, %eax
-DST( movl %edx, 28(%edi) )
-
- lea 32(%esi), %esi
- lea 32(%edi), %edi
- dec %ecx
- jne 1b
- adcl $0, %eax
-2: movl FP(%esp), %edx
- movl %edx, %ecx
- andl $0x1c, %edx
- je 4f
- shrl $2, %edx # This clears CF
-SRC(3: movl (%esi), %ebx )
- adcl %ebx, %eax
-DST( movl %ebx, (%edi) )
- lea 4(%esi), %esi
- lea 4(%edi), %edi
- dec %edx
- jne 3b
- adcl $0, %eax
-4: andl $3, %ecx
- jz 7f
- cmpl $2, %ecx
- jb 5f
-SRC( movw (%esi), %cx )
- leal 2(%esi), %esi
-DST( movw %cx, (%edi) )
- leal 2(%edi), %edi
- je 6f
- shll $16,%ecx
-SRC(5: movb (%esi), %cl )
-DST( movb %cl, (%edi) )
-6: addl %ecx, %eax
- adcl $0, %eax
-7:
-5000:
-
-# Exception handler:
-.section .fixup, "ax"
-
-6001:
- movl ARGBASE+20(%esp), %ebx # src_err_ptr
- movl $-EFAULT, (%ebx)
-
- # zero the complete destination - computing the rest
- # is too much work
- movl ARGBASE+8(%esp), %edi # dst
- movl ARGBASE+12(%esp), %ecx # len
- xorl %eax,%eax
- rep ; stosb
-
- jmp 5000b
-
-6002:
- movl ARGBASE+24(%esp), %ebx # dst_err_ptr
- movl $-EFAULT,(%ebx)
- jmp 5000b
-
-.previous
-
- popl %ebx
- popl %esi
- popl %edi
- popl %ecx # equivalent to addl $4,%esp
- ret
-
-#else
-
-/* Version for PentiumII/PPro */
-
-#define ROUND1(x) \
- SRC(movl x(%esi), %ebx ) ; \
- addl %ebx, %eax ; \
- DST(movl %ebx, x(%edi) ) ;
-
-#define ROUND(x) \
- SRC(movl x(%esi), %ebx ) ; \
- adcl %ebx, %eax ; \
- DST(movl %ebx, x(%edi) ) ;
-
-#define ARGBASE 12
-
-csum_partial_copy_generic_i386:
- pushl %ebx
- pushl %edi
- pushl %esi
- movl ARGBASE+4(%esp),%esi #src
- movl ARGBASE+8(%esp),%edi #dst
- movl ARGBASE+12(%esp),%ecx #len
- movl ARGBASE+16(%esp),%eax #sum
-# movl %ecx, %edx
- movl %ecx, %ebx
- movl %esi, %edx
- shrl $6, %ecx
- andl $0x3c, %ebx
- negl %ebx
- subl %ebx, %esi
- subl %ebx, %edi
- lea -1(%esi),%edx
- andl $-32,%edx
- lea 3f(%ebx,%ebx), %ebx
- testl %esi, %esi
- jmp *%ebx
-1: addl $64,%esi
- addl $64,%edi
- SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl)
- ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)
- ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)
- ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)
- ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4)
-3: adcl $0,%eax
- addl $64, %edx
- dec %ecx
- jge 1b
-4: movl ARGBASE+12(%esp),%edx #len
- andl $3, %edx
- jz 7f
- cmpl $2, %edx
- jb 5f
-SRC( movw (%esi), %dx )
- leal 2(%esi), %esi
-DST( movw %dx, (%edi) )
- leal 2(%edi), %edi
- je 6f
- shll $16,%edx
-5:
-SRC( movb (%esi), %dl )
-DST( movb %dl, (%edi) )
-6: addl %edx, %eax
- adcl $0, %eax
-7:
-.section .fixup, "ax"
-6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr
- movl $-EFAULT, (%ebx)
- # zero the complete destination (computing the rest is too much work)
- movl ARGBASE+8(%esp),%edi # dst
- movl ARGBASE+12(%esp),%ecx # len
- xorl %eax,%eax
- rep; stosb
- jmp 7b
-6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr
- movl $-EFAULT, (%ebx)
- jmp 7b
-.previous
-
- popl %esi
- popl %edi
- popl %ebx
- ret
-
-#undef ROUND
-#undef ROUND1
-
-#endif
diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
index 531d4269e2e3..bd16d6c370ec 100644
--- a/arch/x86/um/sys_call_table_32.c
+++ b/arch/x86/um/sys_call_table_32.c
@@ -34,7 +34,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
extern asmlinkage void sys_ni_syscall(void);
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index f2f0723070ca..5cdfa9db2217 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -31,6 +31,7 @@
#define stub_fork sys_fork
#define stub_vfork sys_vfork
#define stub_execve sys_execve
+#define stub_execveat sys_execveat
#define stub_rt_sigreturn sys_rt_sigreturn
#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
@@ -46,7 +47,7 @@ typedef void (*sys_call_ptr_t)(void);
extern void sys_ni_syscall(void);
-const sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
+const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h
index fd57829b30d8..0224987556ce 100644
--- a/arch/x86/vdso/vdso2c.h
+++ b/arch/x86/vdso/vdso2c.h
@@ -109,16 +109,18 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
/* Validate mapping addresses. */
for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
- if (!syms[i])
+ INT_BITS symval = syms[special_pages[i]];
+
+ if (!symval)
continue; /* The mapping isn't used; ignore it. */
- if (syms[i] % 4096)
+ if (symval % 4096)
fail("%s must be a multiple of 4096\n",
required_syms[i].name);
- if (syms[sym_vvar_start] > syms[i] + 4096)
- fail("%s underruns begin_vvar\n",
+ if (symval + 4096 < syms[sym_vvar_start])
+ fail("%s underruns vvar_start\n",
required_syms[i].name);
- if (syms[i] + 4096 > 0)
+ if (symval + 4096 > 0)
fail("%s is on the wrong side of the vdso text\n",
required_syms[i].name);
}
diff --git a/arch/x86/vdso/vgetcpu.c b/arch/x86/vdso/vgetcpu.c
index 2f94b039e55b..8ec3d1f4ce9a 100644
--- a/arch/x86/vdso/vgetcpu.c
+++ b/arch/x86/vdso/vgetcpu.c
@@ -7,9 +7,7 @@
#include <linux/kernel.h>
#include <linux/getcpu.h>
-#include <linux/jiffies.h>
#include <linux/time.h>
-#include <asm/vsyscall.h>
#include <asm/vgtod.h>
notrace long
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 970463b566cf..1c9f750c3859 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -1,7 +1,8 @@
/*
- * Set up the VMAs to tell the VM about the vDSO.
* Copyright 2007 Andi Kleen, SUSE Labs.
* Subject to the GPL, v.2
+ *
+ * This contains most of the x86 vDSO kernel-side code.
*/
#include <linux/mm.h>
#include <linux/err.h>
@@ -10,17 +11,17 @@
#include <linux/init.h>
#include <linux/random.h>
#include <linux/elf.h>
-#include <asm/vsyscall.h>
+#include <linux/cpu.h>
#include <asm/vgtod.h>
#include <asm/proto.h>
#include <asm/vdso.h>
+#include <asm/vvar.h>
#include <asm/page.h>
#include <asm/hpet.h>
+#include <asm/desc.h>
#if defined(CONFIG_X86_64)
unsigned int __read_mostly vdso64_enabled = 1;
-
-extern unsigned short vdso_sync_cpuid;
#endif
void __init init_vdso_image(const struct vdso_image *image)
@@ -38,28 +39,19 @@ void __init init_vdso_image(const struct vdso_image *image)
image->alt_len));
}
-#if defined(CONFIG_X86_64)
-static int __init init_vdso(void)
-{
- init_vdso_image(&vdso_image_64);
-
-#ifdef CONFIG_X86_X32_ABI
- init_vdso_image(&vdso_image_x32);
-#endif
-
- return 0;
-}
-subsys_initcall(init_vdso);
-#endif
-
struct linux_binprm;
-/* Put the vdso above the (randomized) stack with another randomized offset.
- This way there is no hole in the middle of address space.
- To save memory make sure it is still in the same PTE as the stack top.
- This doesn't give that many random bits.
-
- Only used for the 64-bit and x32 vdsos. */
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset. This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top. This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
static unsigned long vdso_addr(unsigned long start, unsigned len)
{
#ifdef CONFIG_X86_32
@@ -67,22 +59,30 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
#else
unsigned long addr, end;
unsigned offset;
- end = (start + PMD_SIZE - 1) & PMD_MASK;
+
+ /*
+ * Round up the start address. It can start out unaligned as a result
+ * of stack start randomization.
+ */
+ start = PAGE_ALIGN(start);
+
+ /* Round the lowest possible end address up to a PMD boundary. */
+ end = (start + len + PMD_SIZE - 1) & PMD_MASK;
if (end >= TASK_SIZE_MAX)
end = TASK_SIZE_MAX;
end -= len;
- /* This loses some more bits than a modulo, but is cheaper */
- offset = get_random_int() & (PTRS_PER_PTE - 1);
- addr = start + (offset << PAGE_SHIFT);
- if (addr >= end)
- addr = end;
+
+ if (end > start) {
+ offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+ addr = start + (offset << PAGE_SHIFT);
+ } else {
+ addr = start;
+ }
/*
- * page-align it here so that get_unmapped_area doesn't
- * align it wrongfully again to the next page. addr can come in 4K
- * unaligned here as a result of stack start randomization.
+ * Forcibly align the final address in case we have a hardware
+ * issue that requires alignment for performance reasons.
*/
- addr = PAGE_ALIGN(addr);
addr = align_vdso_addr(addr);
return addr;
@@ -238,3 +238,63 @@ static __init int vdso_setup(char *s)
}
__setup("vdso=", vdso_setup);
#endif
+
+#ifdef CONFIG_X86_64
+static void vgetcpu_cpu_init(void *arg)
+{
+ int cpu = smp_processor_id();
+ struct desc_struct d = { };
+ unsigned long node = 0;
+#ifdef CONFIG_NUMA
+ node = cpu_to_node(cpu);
+#endif
+ if (cpu_has(&cpu_data(cpu), X86_FEATURE_RDTSCP))
+ write_rdtscp_aux((node << 12) | cpu);
+
+ /*
+ * Store cpu number in limit so that it can be loaded
+ * quickly in user space in vgetcpu. (12 bits for the CPU
+ * and 8 bits for the node)
+ */
+ d.limit0 = cpu | ((node & 0xf) << 12);
+ d.limit = node >> 4;
+ d.type = 5; /* RO data, expand down, accessed */
+ d.dpl = 3; /* Visible to user code */
+ d.s = 1; /* Not a system segment */
+ d.p = 1; /* Present */
+ d.d = 1; /* 32-bit */
+
+ write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+}
+
+static int
+vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg)
+{
+ long cpu = (long)arg;
+
+ if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
+ smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
+
+ return NOTIFY_DONE;
+}
+
+static int __init init_vdso(void)
+{
+ init_vdso_image(&vdso_image_64);
+
+#ifdef CONFIG_X86_X32_ABI
+ init_vdso_image(&vdso_image_x32);
+#endif
+
+ cpu_notifier_register_begin();
+
+ on_each_cpu(vgetcpu_cpu_init, NULL, 1);
+ /* notifier priority > KVM */
+ __hotcpu_notifier(vgetcpu_cpu_notifier, 30);
+
+ cpu_notifier_register_done();
+
+ return 0;
+}
+subsys_initcall(init_vdso);
+#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index a02e09e18f57..be14cc3e48d5 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -15,12 +15,14 @@
* with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/bitops.h>
#include <linux/efi.h>
#include <linux/init.h>
#include <linux/string.h>
#include <xen/xen-ops.h>
+#include <asm/page.h>
#include <asm/setup.h>
void __init xen_efi_init(void)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c0cb11fb5008..6bf3a13e3e0f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -821,7 +821,7 @@ static void xen_convert_trap_info(const struct desc_ptr *desc,
void xen_copy_trap_info(struct trap_info *traps)
{
- const struct desc_ptr *desc = &__get_cpu_var(idt_desc);
+ const struct desc_ptr *desc = this_cpu_ptr(&idt_desc);
xen_convert_trap_info(desc, traps);
}
@@ -838,7 +838,7 @@ static void xen_load_idt(const struct desc_ptr *desc)
spin_lock(&lock);
- __get_cpu_var(idt_desc) = *desc;
+ memcpy(this_cpu_ptr(&idt_desc), desc, sizeof(idt_desc));
xen_convert_trap_info(desc, traps);
@@ -1100,12 +1100,6 @@ static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
/* Fast syscall setup is all done in hypercalls, so
these are all ignored. Stub them out here to stop
Xen console noise. */
- break;
-
- case MSR_IA32_CR_PAT:
- if (smp_processor_id() == 0)
- xen_set_pat(((u64)high << 32) | low);
- break;
default:
ret = native_write_msr_safe(msr, low, high);
@@ -1463,6 +1457,7 @@ static void __ref xen_setup_gdt(int cpu)
pv_cpu_ops.load_gdt = xen_load_gdt;
}
+#ifdef CONFIG_XEN_PVH
/*
* A PV guest starts with default flags that are not set for PVH, set them
* here asap.
@@ -1508,17 +1503,21 @@ static void __init xen_pvh_early_guest_init(void)
return;
xen_have_vector_callback = 1;
+
+ xen_pvh_early_cpu_init(0, false);
xen_pvh_set_cr_flags(0);
#ifdef CONFIG_X86_32
BUG(); /* PVH: Implement proper support. */
#endif
}
+#endif /* CONFIG_XEN_PVH */
/* First C function to be called on Xen boot */
asmlinkage __visible void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
+ unsigned long initrd_start = 0;
int rc;
if (!xen_start_info)
@@ -1527,7 +1526,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_domain_type = XEN_PV_DOMAIN;
xen_setup_features();
+#ifdef CONFIG_XEN_PVH
xen_pvh_early_guest_init();
+#endif
xen_setup_machphys_mapping();
/* Install Xen paravirt ops */
@@ -1554,12 +1555,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
/* Prevent unwanted bits from being set in PTEs. */
__supported_pte_mask &= ~_PAGE_GLOBAL;
-#if 0
- if (!xen_initial_domain())
-#endif
- __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
-
- __supported_pte_mask |= _PAGE_IOMAP;
/*
* Prevent page tables from being allocated in highmem, even
@@ -1613,14 +1608,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
*/
acpi_numa = -1;
#endif
-#ifdef CONFIG_X86_PAT
- /*
- * For right now disable the PAT. We should remove this once
- * git commit 8eaffa67b43e99ae581622c5133e20b0f48bcef1
- * (xen/pat: Disable PAT support for now) is reverted.
- */
- pat_enabled = 0;
-#endif
/* Don't do the full vcpu_info placement stuff until we have a
possible map and a non-dummy shared_info. */
per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
@@ -1631,8 +1618,12 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_raw_console_write("mapping kernel into physical memory\n");
xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, xen_start_info->nr_pages);
- /* Allocate and initialize top and mid mfn levels for p2m structure */
- xen_build_mfn_list_list();
+ /*
+ * Modify the cache mode translation tables to match Xen's PAT
+ * configuration.
+ */
+
+ pat_init_cache_modes();
/* keep using Xen gdt for now; no urgent need to change it */
@@ -1667,10 +1658,16 @@ asmlinkage __visible void __init xen_start_kernel(void)
new_cpu_data.x86_capability[0] = cpuid_edx(1);
#endif
+ if (xen_start_info->mod_start) {
+ if (xen_start_info->flags & SIF_MOD_START_PFN)
+ initrd_start = PFN_PHYS(xen_start_info->mod_start);
+ else
+ initrd_start = __pa(xen_start_info->mod_start);
+ }
+
/* Poke various useful things into boot_params */
boot_params.hdr.type_of_loader = (9 << 4) | 0;
- boot_params.hdr.ramdisk_image = xen_start_info->mod_start
- ? __pa(xen_start_info->mod_start) : 0;
+ boot_params.hdr.ramdisk_image = initrd_start;
boot_params.hdr.ramdisk_size = xen_start_info->mod_len;
boot_params.hdr.cmd_line_ptr = __pa(xen_start_info->cmd_line);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 16fb0099b7f2..5c1f9ace7ae7 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -387,7 +387,7 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
unsigned long mfn;
if (!xen_feature(XENFEAT_auto_translated_physmap))
- mfn = get_phys_to_machine(pfn);
+ mfn = __pfn_to_mfn(pfn);
else
mfn = pfn;
/*
@@ -399,50 +399,17 @@ static pteval_t pte_pfn_to_mfn(pteval_t val)
if (unlikely(mfn == INVALID_P2M_ENTRY)) {
mfn = 0;
flags = 0;
- } else {
- /*
- * Paramount to do this test _after_ the
- * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
- * IDENTITY_FRAME_BIT resolves to true.
- */
- mfn &= ~FOREIGN_FRAME_BIT;
- if (mfn & IDENTITY_FRAME_BIT) {
- mfn &= ~IDENTITY_FRAME_BIT;
- flags |= _PAGE_IOMAP;
- }
- }
+ } else
+ mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
}
return val;
}
-static pteval_t iomap_pte(pteval_t val)
-{
- if (val & _PAGE_PRESENT) {
- unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
- pteval_t flags = val & PTE_FLAGS_MASK;
-
- /* We assume the pte frame number is a MFN, so
- just use it as-is. */
- val = ((pteval_t)pfn << PAGE_SHIFT) | flags;
- }
-
- return val;
-}
-
__visible pteval_t xen_pte_val(pte_t pte)
{
pteval_t pteval = pte.pte;
-#if 0
- /* If this is a WC pte, convert back from Xen WC to Linux WC */
- if ((pteval & (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT)) == _PAGE_PAT) {
- WARN_ON(!pat_enabled);
- pteval = (pteval & ~_PAGE_PAT) | _PAGE_PWT;
- }
-#endif
- if (xen_initial_domain() && (pteval & _PAGE_IOMAP))
- return pteval;
return pte_mfn_to_pfn(pteval);
}
@@ -454,61 +421,9 @@ __visible pgdval_t xen_pgd_val(pgd_t pgd)
}
PV_CALLEE_SAVE_REGS_THUNK(xen_pgd_val);
-/*
- * Xen's PAT setup is part of its ABI, though I assume entries 6 & 7
- * are reserved for now, to correspond to the Intel-reserved PAT
- * types.
- *
- * We expect Linux's PAT set as follows:
- *
- * Idx PTE flags Linux Xen Default
- * 0 WB WB WB
- * 1 PWT WC WT WT
- * 2 PCD UC- UC- UC-
- * 3 PCD PWT UC UC UC
- * 4 PAT WB WC WB
- * 5 PAT PWT WC WP WT
- * 6 PAT PCD UC- rsv UC-
- * 7 PAT PCD PWT UC rsv UC
- */
-
-void xen_set_pat(u64 pat)
-{
- /* We expect Linux to use a PAT setting of
- * UC UC- WC WB (ignoring the PAT flag) */
- WARN_ON(pat != 0x0007010600070106ull);
-}
-
__visible pte_t xen_make_pte(pteval_t pte)
{
- phys_addr_t addr = (pte & PTE_PFN_MASK);
-#if 0
- /* If Linux is trying to set a WC pte, then map to the Xen WC.
- * If _PAGE_PAT is set, then it probably means it is really
- * _PAGE_PSE, so avoid fiddling with the PAT mapping and hope
- * things work out OK...
- *
- * (We should never see kernel mappings with _PAGE_PSE set,
- * but we could see hugetlbfs mappings, I think.).
- */
- if (pat_enabled && !WARN_ON(pte & _PAGE_PAT)) {
- if ((pte & (_PAGE_PCD | _PAGE_PWT)) == _PAGE_PWT)
- pte = (pte & ~(_PAGE_PCD | _PAGE_PWT)) | _PAGE_PAT;
- }
-#endif
- /*
- * Unprivileged domains are allowed to do IOMAPpings for
- * PCI passthrough, but not map ISA space. The ISA
- * mappings are just dummy local mappings to keep other
- * parts of the kernel happy.
- */
- if (unlikely(pte & _PAGE_IOMAP) &&
- (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
- pte = iomap_pte(pte);
- } else {
- pte &= ~_PAGE_IOMAP;
- pte = pte_pfn_to_mfn(pte);
- }
+ pte = pte_pfn_to_mfn(pte);
return native_make_pte(pte);
}
@@ -1198,20 +1113,16 @@ static void __init xen_cleanhighmap(unsigned long vaddr,
* instead of somewhere later and be confusing. */
xen_mc_flush();
}
-static void __init xen_pagetable_p2m_copy(void)
+
+static void __init xen_pagetable_p2m_free(void)
{
unsigned long size;
unsigned long addr;
- unsigned long new_mfn_list;
-
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return;
size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
- new_mfn_list = xen_revector_p2m_tree();
/* No memory or already called. */
- if (!new_mfn_list || new_mfn_list == xen_start_info->mfn_list)
+ if ((unsigned long)xen_p2m_addr == xen_start_info->mfn_list)
return;
/* using __ka address and sticking INVALID_P2M_ENTRY! */
@@ -1229,8 +1140,6 @@ static void __init xen_pagetable_p2m_copy(void)
size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
memblock_free(__pa(xen_start_info->mfn_list), size);
- /* And revector! Bye bye old array */
- xen_start_info->mfn_list = new_mfn_list;
/* At this stage, cleanup_highmap has already cleaned __ka space
* from _brk_limit way up to the max_pfn_mapped (which is the end of
@@ -1254,14 +1163,35 @@ static void __init xen_pagetable_p2m_copy(void)
}
#endif
-static void __init xen_pagetable_init(void)
+static void __init xen_pagetable_p2m_setup(void)
{
- paging_init();
- xen_setup_shared_info();
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return;
+
+ xen_vmalloc_p2m_tree();
+
#ifdef CONFIG_X86_64
- xen_pagetable_p2m_copy();
+ xen_pagetable_p2m_free();
#endif
+ /* And revector! Bye bye old array */
+ xen_start_info->mfn_list = (unsigned long)xen_p2m_addr;
+}
+
+static void __init xen_pagetable_init(void)
+{
+ paging_init();
xen_post_allocator_init();
+
+ xen_pagetable_p2m_setup();
+
+ /* Allocate and initialize top and mid mfn levels for p2m structure */
+ xen_build_mfn_list_list();
+
+ /* Remap memory freed due to conflicts with E820 map */
+ if (!xen_feature(XENFEAT_auto_translated_physmap))
+ xen_remap_memory();
+
+ xen_setup_shared_info();
}
static void xen_write_cr2(unsigned long cr2)
{
@@ -1494,8 +1424,10 @@ static int xen_pgd_alloc(struct mm_struct *mm)
page->private = (unsigned long)user_pgd;
if (user_pgd != NULL) {
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
user_pgd[pgd_index(VSYSCALL_ADDR)] =
__pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE);
+#endif
ret = 0;
}
@@ -2058,7 +1990,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
# ifdef CONFIG_HIGHMEM
case FIX_KMAP_BEGIN ... FIX_KMAP_END:
# endif
-#else
+#elif defined(CONFIG_X86_VSYSCALL_EMULATION)
case VSYSCALL_PAGE:
#endif
case FIX_TEXT_POKE0:
@@ -2091,13 +2023,13 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
default:
/* By default, set_fixmap is used for hardware mappings */
- pte = mfn_pte(phys, __pgprot(pgprot_val(prot) | _PAGE_IOMAP));
+ pte = mfn_pte(phys, prot);
break;
}
__native_set_fixmap(idx, pte);
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
/* Replicate changes to map the vsyscall page into the user
pagetable vsyscall mapping. */
if (idx == VSYSCALL_PAGE) {
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index 0d82003e76ad..ea54a08d8301 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -54,7 +54,7 @@ DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags);
void xen_mc_flush(void)
{
- struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+ struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
struct multicall_entry *mc;
int ret = 0;
unsigned long flags;
@@ -131,7 +131,7 @@ void xen_mc_flush(void)
struct multicall_space __xen_mc_entry(size_t args)
{
- struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+ struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
struct multicall_space ret;
unsigned argidx = roundup(b->argidx, sizeof(u64));
@@ -162,7 +162,7 @@ struct multicall_space __xen_mc_entry(size_t args)
struct multicall_space xen_mc_extend_args(unsigned long op, size_t size)
{
- struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+ struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
struct multicall_space ret = { NULL, NULL };
BUG_ON(preemptible());
@@ -192,7 +192,7 @@ out:
void xen_mc_callback(void (*fn)(void *), void *data)
{
- struct mc_buffer *b = &__get_cpu_var(mc_buffer);
+ struct mc_buffer *b = this_cpu_ptr(&mc_buffer);
struct callback *cb;
if (b->cbidx == MC_BATCH) {
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 3172692381ae..edbc7a63fd73 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -3,21 +3,22 @@
* guests themselves, but it must also access and update the p2m array
* during suspend/resume when all the pages are reallocated.
*
- * The p2m table is logically a flat array, but we implement it as a
- * three-level tree to allow the address space to be sparse.
+ * The logical flat p2m table is mapped to a linear kernel memory area.
+ * For accesses by Xen a three-level tree linked via mfns only is set up to
+ * allow the address space to be sparse.
*
- * Xen
- * |
- * p2m_top p2m_top_mfn
- * / \ / \
- * p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn
- * / \ / \ / /
- * p2m p2m p2m p2m p2m p2m p2m ...
+ * Xen
+ * |
+ * p2m_top_mfn
+ * / \
+ * p2m_mid_mfn p2m_mid_mfn
+ * / /
+ * p2m p2m p2m ...
*
* The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
*
- * The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
- * maximum representable pseudo-physical address space is:
+ * The p2m_top_mfn level is limited to 1 page, so the maximum representable
+ * pseudo-physical address space is:
* P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
*
* P2M_PER_PAGE depends on the architecture, as a mfn is always
@@ -30,6 +31,9 @@
* leaf entries, or for the top root, or middle one, for which there is a void
* entry, we assume it is "missing". So (for example)
* pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY.
+ * We have a dedicated page p2m_missing with all entries being
+ * INVALID_P2M_ENTRY. This page may be referenced multiple times in the p2m
+ * list/tree in case there are multiple areas with P2M_PER_PAGE invalid pfns.
*
* We also have the possibility of setting 1-1 mappings on certain regions, so
* that:
@@ -39,122 +43,20 @@
* PCI BARs, or ACPI spaces), we can create mappings easily because we
* get the PFN value to match the MFN.
*
- * For this to work efficiently we have one new page p2m_identity and
- * allocate (via reserved_brk) any other pages we need to cover the sides
- * (1GB or 4MB boundary violations). All entries in p2m_identity are set to
- * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs,
- * no other fancy value).
+ * For this to work efficiently we have one new page p2m_identity. All entries
+ * in p2m_identity are set to INVALID_P2M_ENTRY type (Xen toolstack only
+ * recognizes that and MFNs, no other fancy value).
*
* On lookup we spot that the entry points to p2m_identity and return the
* identity value instead of dereferencing and returning INVALID_P2M_ENTRY.
* If the entry points to an allocated page, we just proceed as before and
- * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in
+ * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in
* appropriate functions (pfn_to_mfn).
*
* The reason for having the IDENTITY_FRAME_BIT instead of just returning the
* PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a
* non-identity pfn. To protect ourselves against we elect to set (and get) the
* IDENTITY_FRAME_BIT on all identity mapped PFNs.
- *
- * This simplistic diagram is used to explain the more subtle piece of code.
- * There is also a digram of the P2M at the end that can help.
- * Imagine your E820 looking as so:
- *
- * 1GB 2GB 4GB
- * /-------------------+---------\/----\ /----------\ /---+-----\
- * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM |
- * \-------------------+---------/\----/ \----------/ \---+-----/
- * ^- 1029MB ^- 2001MB
- *
- * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100),
- * 2048MB = 524288 (0x80000)]
- *
- * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB
- * is actually not present (would have to kick the balloon driver to put it in).
- *
- * When we are told to set the PFNs for identity mapping (see patch: "xen/setup:
- * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start
- * of the PFN and the end PFN (263424 and 512256 respectively). The first step
- * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page
- * covers 512^2 of page estate (1GB) and in case the start or end PFN is not
- * aligned on 512^2*PAGE_SIZE (1GB) we reserve_brk new middle and leaf pages as
- * required to split any existing p2m_mid_missing middle pages.
- *
- * With the E820 example above, 263424 is not 1GB aligned so we allocate a
- * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000.
- * Each entry in the allocate page is "missing" (points to p2m_missing).
- *
- * Next stage is to determine if we need to do a more granular boundary check
- * on the 4MB (or 2MB depending on architecture) off the start and end pfn's.
- * We check if the start pfn and end pfn violate that boundary check, and if
- * so reserve_brk a (p2m[x][y]) leaf page. This way we have a much finer
- * granularity of setting which PFNs are missing and which ones are identity.
- * In our example 263424 and 512256 both fail the check so we reserve_brk two
- * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing"
- * values) and assign them to p2m[1][2] and p2m[1][488] respectively.
- *
- * At this point we would at minimum reserve_brk one page, but could be up to
- * three. Each call to set_phys_range_identity has at maximum a three page
- * cost. If we were to query the P2M at this stage, all those entries from
- * start PFN through end PFN (so 1029MB -> 2001MB) would return
- * INVALID_P2M_ENTRY ("missing").
- *
- * The next step is to walk from the start pfn to the end pfn setting
- * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity.
- * If we find that the middle entry is pointing to p2m_missing we can swap it
- * over to p2m_identity - this way covering 4MB (or 2MB) PFN space (and
- * similarly swapping p2m_mid_missing for p2m_mid_identity for larger regions).
- * At this point we do not need to worry about boundary aligment (so no need to
- * reserve_brk a middle page, figure out which PFNs are "missing" and which
- * ones are identity), as that has been done earlier. If we find that the
- * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference
- * that page (which covers 512 PFNs) and set the appropriate PFN with
- * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we
- * set from p2m[1][2][256->511] and p2m[1][488][0->256] with
- * IDENTITY_FRAME_BIT set.
- *
- * All other regions that are void (or not filled) either point to p2m_missing
- * (considered missing) or have the default value of INVALID_P2M_ENTRY (also
- * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511]
- * contain the INVALID_P2M_ENTRY value and are considered "missing."
- *
- * Finally, the region beyond the end of of the E820 (4 GB in this example)
- * is set to be identity (in case there are MMIO regions placed here).
- *
- * This is what the p2m ends up looking (for the E820 above) with this
- * fabulous drawing:
- *
- * p2m /--------------\
- * /-----\ | &mfn_list[0],| /-----------------\
- * | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. |
- * |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] |
- * | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] |
- * |-----| \ | [p2m_identity]+\\ | .... |
- * | 2 |--\ \-------------------->| ... | \\ \----------------/
- * |-----| \ \---------------/ \\
- * | 3 |-\ \ \\ p2m_identity [1]
- * |-----| \ \-------------------->/---------------\ /-----------------\
- * | .. |\ | | [p2m_identity]+-->| ~0, ~0, ~0, ... |
- * \-----/ | | | [p2m_identity]+-->| ..., ~0 |
- * | | | .... | \-----------------/
- * | | +-[x], ~0, ~0.. +\
- * | | \---------------/ \
- * | | \-> /---------------\
- * | V p2m_mid_missing p2m_missing | IDENTITY[@0] |
- * | /-----------------\ /------------\ | IDENTITY[@256]|
- * | | [p2m_missing] +---->| ~0, ~0, ...| | ~0, ~0, .... |
- * | | [p2m_missing] +---->| ..., ~0 | \---------------/
- * | | ... | \------------/
- * | \-----------------/
- * |
- * | p2m_mid_identity
- * | /-----------------\
- * \-->| [p2m_identity] +---->[1]
- * | [p2m_identity] +---->[1]
- * | ... |
- * \-----------------/
- *
- * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
*/
#include <linux/init.h>
@@ -163,9 +65,12 @@
#include <linux/hash.h>
#include <linux/sched.h>
#include <linux/seq_file.h>
+#include <linux/bootmem.h>
+#include <linux/slab.h>
#include <asm/cache.h>
#include <asm/setup.h>
+#include <asm/uaccess.h>
#include <asm/xen/page.h>
#include <asm/xen/hypercall.h>
@@ -173,45 +78,30 @@
#include <xen/balloon.h>
#include <xen/grant_table.h>
+#include "p2m.h"
#include "multicalls.h"
#include "xen-ops.h"
+#define PMDS_PER_MID_PAGE (P2M_MID_PER_PAGE / PTRS_PER_PTE)
+
static void __init m2p_override_init(void);
+unsigned long *xen_p2m_addr __read_mostly;
+EXPORT_SYMBOL_GPL(xen_p2m_addr);
+unsigned long xen_p2m_size __read_mostly;
+EXPORT_SYMBOL_GPL(xen_p2m_size);
unsigned long xen_max_p2m_pfn __read_mostly;
+EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
-#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
-#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *))
-#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **))
-
-#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
-
-/* Placeholders for holes in the address space */
-static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);
-
-static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
-
-static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_identity, P2M_MID_PER_PAGE);
-static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE);
+static DEFINE_SPINLOCK(p2m_update_lock);
-RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
-RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
-
-/* We might hit two boundary violations at the start and end, at max each
- * boundary violation will require three middle nodes. */
-RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3);
-
-/* When we populate back during bootup, the amount of pages can vary. The
- * max we have is seen is 395979, but that does not mean it can't be more.
- * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle
- * it can re-use Xen provided mfn_list array, so we only need to allocate at
- * most three P2M top nodes. */
-RESERVE_BRK(p2m_populated, PAGE_SIZE * 3);
+static unsigned long *p2m_mid_missing_mfn;
+static unsigned long *p2m_top_mfn;
+static unsigned long **p2m_top_mfn_p;
+static unsigned long *p2m_missing;
+static unsigned long *p2m_identity;
+static pte_t *p2m_missing_pte;
+static pte_t *p2m_identity_pte;
static inline unsigned p2m_top_index(unsigned long pfn)
{
@@ -229,14 +119,6 @@ static inline unsigned p2m_index(unsigned long pfn)
return pfn % P2M_PER_PAGE;
}
-static void p2m_top_init(unsigned long ***top)
-{
- unsigned i;
-
- for (i = 0; i < P2M_TOP_PER_PAGE; i++)
- top[i] = p2m_mid_missing;
-}
-
static void p2m_top_mfn_init(unsigned long *top)
{
unsigned i;
@@ -253,79 +135,97 @@ static void p2m_top_mfn_p_init(unsigned long **top)
top[i] = p2m_mid_missing_mfn;
}
-static void p2m_mid_init(unsigned long **mid, unsigned long *leaf)
+static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
- mid[i] = leaf;
+ mid[i] = virt_to_mfn(leaf);
}
-static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf)
+static void p2m_init(unsigned long *p2m)
{
unsigned i;
- for (i = 0; i < P2M_MID_PER_PAGE; i++)
- mid[i] = virt_to_mfn(leaf);
+ for (i = 0; i < P2M_PER_PAGE; i++)
+ p2m[i] = INVALID_P2M_ENTRY;
}
-static void p2m_init(unsigned long *p2m)
+static void p2m_init_identity(unsigned long *p2m, unsigned long pfn)
{
unsigned i;
- for (i = 0; i < P2M_MID_PER_PAGE; i++)
- p2m[i] = INVALID_P2M_ENTRY;
+ for (i = 0; i < P2M_PER_PAGE; i++)
+ p2m[i] = IDENTITY_FRAME(pfn + i);
+}
+
+static void * __ref alloc_p2m_page(void)
+{
+ if (unlikely(!slab_is_available()))
+ return alloc_bootmem_align(PAGE_SIZE, PAGE_SIZE);
+
+ return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
+}
+
+/* Only to be called in case of a race for a page just allocated! */
+static void free_p2m_page(void *p)
+{
+ BUG_ON(!slab_is_available());
+ free_page((unsigned long)p);
}
/*
* Build the parallel p2m_top_mfn and p2m_mid_mfn structures
*
* This is called both at boot time, and after resuming from suspend:
- * - At boot time we're called very early, and must use extend_brk()
+ * - At boot time we're called rather early, and must use alloc_bootmem*()
* to allocate memory.
*
* - After resume we're called from within stop_machine, but the mfn
- * tree should alreay be completely allocated.
+ * tree should already be completely allocated.
*/
void __ref xen_build_mfn_list_list(void)
{
- unsigned long pfn;
+ unsigned long pfn, mfn;
+ pte_t *ptep;
+ unsigned int level, topidx, mididx;
+ unsigned long *mid_mfn_p;
if (xen_feature(XENFEAT_auto_translated_physmap))
return;
/* Pre-initialize p2m_top_mfn to be completely missing */
if (p2m_top_mfn == NULL) {
- p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_mid_missing_mfn = alloc_p2m_page();
p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing);
- p2m_mid_identity_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity);
- p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_top_mfn_p = alloc_p2m_page();
p2m_top_mfn_p_init(p2m_top_mfn_p);
- p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_top_mfn = alloc_p2m_page();
p2m_top_mfn_init(p2m_top_mfn);
} else {
/* Reinitialise, mfn's all change after migration */
p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing);
- p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity);
}
- for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
- unsigned topidx = p2m_top_index(pfn);
- unsigned mididx = p2m_mid_index(pfn);
- unsigned long **mid;
- unsigned long *mid_mfn_p;
+ for (pfn = 0; pfn < xen_max_p2m_pfn && pfn < MAX_P2M_PFN;
+ pfn += P2M_PER_PAGE) {
+ topidx = p2m_top_index(pfn);
+ mididx = p2m_mid_index(pfn);
- mid = p2m_top[topidx];
mid_mfn_p = p2m_top_mfn_p[topidx];
+ ptep = lookup_address((unsigned long)(xen_p2m_addr + pfn),
+ &level);
+ BUG_ON(!ptep || level != PG_LEVEL_4K);
+ mfn = pte_mfn(*ptep);
+ ptep = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
/* Don't bother allocating any mfn mid levels if
* they're just missing, just update the stored mfn,
* since all could have changed over a migrate.
*/
- if (mid == p2m_mid_missing) {
+ if (ptep == p2m_missing_pte || ptep == p2m_identity_pte) {
BUG_ON(mididx);
BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
@@ -334,20 +234,14 @@ void __ref xen_build_mfn_list_list(void)
}
if (mid_mfn_p == p2m_mid_missing_mfn) {
- /*
- * XXX boot-time only! We should never find
- * missing parts of the mfn tree after
- * runtime. extend_brk() will BUG if we call
- * it too late.
- */
- mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ mid_mfn_p = alloc_p2m_page();
p2m_mid_mfn_init(mid_mfn_p, p2m_missing);
p2m_top_mfn_p[topidx] = mid_mfn_p;
}
p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
- mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
+ mid_mfn_p[mididx] = mfn;
}
}
@@ -366,173 +260,235 @@ void xen_setup_mfn_list_list(void)
/* Set up p2m_top to point to the domain-builder provided p2m pages */
void __init xen_build_dynamic_phys_to_machine(void)
{
- unsigned long *mfn_list;
- unsigned long max_pfn;
unsigned long pfn;
if (xen_feature(XENFEAT_auto_translated_physmap))
return;
- mfn_list = (unsigned long *)xen_start_info->mfn_list;
- max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
- xen_max_p2m_pfn = max_pfn;
+ xen_p2m_addr = (unsigned long *)xen_start_info->mfn_list;
+ xen_p2m_size = ALIGN(xen_start_info->nr_pages, P2M_PER_PAGE);
- p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_init(p2m_missing);
- p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_init(p2m_identity);
+ for (pfn = xen_start_info->nr_pages; pfn < xen_p2m_size; pfn++)
+ xen_p2m_addr[pfn] = INVALID_P2M_ENTRY;
- p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_mid_init(p2m_mid_missing, p2m_missing);
- p2m_mid_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_mid_init(p2m_mid_identity, p2m_identity);
+ xen_max_p2m_pfn = xen_p2m_size;
+}
- p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_top_init(p2m_top);
+#define P2M_TYPE_IDENTITY 0
+#define P2M_TYPE_MISSING 1
+#define P2M_TYPE_PFN 2
+#define P2M_TYPE_UNKNOWN 3
- /*
- * The domain builder gives us a pre-constructed p2m array in
- * mfn_list for all the pages initially given to us, so we just
- * need to graft that into our tree structure.
- */
- for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) {
- unsigned topidx = p2m_top_index(pfn);
- unsigned mididx = p2m_mid_index(pfn);
+static int xen_p2m_elem_type(unsigned long pfn)
+{
+ unsigned long mfn;
- if (p2m_top[topidx] == p2m_mid_missing) {
- unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_mid_init(mid, p2m_missing);
+ if (pfn >= xen_p2m_size)
+ return P2M_TYPE_IDENTITY;
- p2m_top[topidx] = mid;
- }
+ mfn = xen_p2m_addr[pfn];
- /*
- * As long as the mfn_list has enough entries to completely
- * fill a p2m page, pointing into the array is ok. But if
- * not the entries beyond the last pfn will be undefined.
- */
- if (unlikely(pfn + P2M_PER_PAGE > max_pfn)) {
- unsigned long p2midx;
+ if (mfn == INVALID_P2M_ENTRY)
+ return P2M_TYPE_MISSING;
- p2midx = max_pfn % P2M_PER_PAGE;
- for ( ; p2midx < P2M_PER_PAGE; p2midx++)
- mfn_list[pfn + p2midx] = INVALID_P2M_ENTRY;
- }
- p2m_top[topidx][mididx] = &mfn_list[pfn];
- }
+ if (mfn & IDENTITY_FRAME_BIT)
+ return P2M_TYPE_IDENTITY;
- m2p_override_init();
+ return P2M_TYPE_PFN;
}
-#ifdef CONFIG_X86_64
-#include <linux/bootmem.h>
-unsigned long __init xen_revector_p2m_tree(void)
+
+static void __init xen_rebuild_p2m_list(unsigned long *p2m)
{
- unsigned long va_start;
- unsigned long va_end;
+ unsigned int i, chunk;
unsigned long pfn;
- unsigned long pfn_free = 0;
- unsigned long *mfn_list = NULL;
- unsigned long size;
-
- va_start = xen_start_info->mfn_list;
- /*We copy in increments of P2M_PER_PAGE * sizeof(unsigned long),
- * so make sure it is rounded up to that */
- size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
- va_end = va_start + size;
-
- /* If we were revectored already, don't do it again. */
- if (va_start <= __START_KERNEL_map && va_start >= __PAGE_OFFSET)
- return 0;
+ unsigned long *mfns;
+ pte_t *ptep;
+ pmd_t *pmdp;
+ int type;
- mfn_list = alloc_bootmem_align(size, PAGE_SIZE);
- if (!mfn_list) {
- pr_warn("Could not allocate space for a new P2M tree!\n");
- return xen_start_info->mfn_list;
- }
- /* Fill it out with INVALID_P2M_ENTRY value */
- memset(mfn_list, 0xFF, size);
+ p2m_missing = alloc_p2m_page();
+ p2m_init(p2m_missing);
+ p2m_identity = alloc_p2m_page();
+ p2m_init(p2m_identity);
- for (pfn = 0; pfn < ALIGN(MAX_DOMAIN_PAGES, P2M_PER_PAGE); pfn += P2M_PER_PAGE) {
- unsigned topidx = p2m_top_index(pfn);
- unsigned mididx;
- unsigned long *mid_p;
+ p2m_missing_pte = alloc_p2m_page();
+ paravirt_alloc_pte(&init_mm, __pa(p2m_missing_pte) >> PAGE_SHIFT);
+ p2m_identity_pte = alloc_p2m_page();
+ paravirt_alloc_pte(&init_mm, __pa(p2m_identity_pte) >> PAGE_SHIFT);
+ for (i = 0; i < PTRS_PER_PTE; i++) {
+ set_pte(p2m_missing_pte + i,
+ pfn_pte(PFN_DOWN(__pa(p2m_missing)), PAGE_KERNEL_RO));
+ set_pte(p2m_identity_pte + i,
+ pfn_pte(PFN_DOWN(__pa(p2m_identity)), PAGE_KERNEL_RO));
+ }
- if (!p2m_top[topidx])
+ for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += chunk) {
+ /*
+ * Try to map missing/identity PMDs or p2m-pages if possible.
+ * We have to respect the structure of the mfn_list_list
+ * which will be built just afterwards.
+ * Chunk size to test is one p2m page if we are in the middle
+ * of a mfn_list_list mid page and the complete mid page area
+ * if we are at index 0 of the mid page. Please note that a
+ * mid page might cover more than one PMD, e.g. on 32 bit PAE
+ * kernels.
+ */
+ chunk = (pfn & (P2M_PER_PAGE * P2M_MID_PER_PAGE - 1)) ?
+ P2M_PER_PAGE : P2M_PER_PAGE * P2M_MID_PER_PAGE;
+
+ type = xen_p2m_elem_type(pfn);
+ i = 0;
+ if (type != P2M_TYPE_PFN)
+ for (i = 1; i < chunk; i++)
+ if (xen_p2m_elem_type(pfn + i) != type)
+ break;
+ if (i < chunk)
+ /* Reset to minimal chunk size. */
+ chunk = P2M_PER_PAGE;
+
+ if (type == P2M_TYPE_PFN || i < chunk) {
+ /* Use initial p2m page contents. */
+#ifdef CONFIG_X86_64
+ mfns = alloc_p2m_page();
+ copy_page(mfns, xen_p2m_addr + pfn);
+#else
+ mfns = xen_p2m_addr + pfn;
+#endif
+ ptep = populate_extra_pte((unsigned long)(p2m + pfn));
+ set_pte(ptep,
+ pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL));
continue;
+ }
- if (p2m_top[topidx] == p2m_mid_missing)
+ if (chunk == P2M_PER_PAGE) {
+ /* Map complete missing or identity p2m-page. */
+ mfns = (type == P2M_TYPE_MISSING) ?
+ p2m_missing : p2m_identity;
+ ptep = populate_extra_pte((unsigned long)(p2m + pfn));
+ set_pte(ptep,
+ pfn_pte(PFN_DOWN(__pa(mfns)), PAGE_KERNEL_RO));
continue;
+ }
- mididx = p2m_mid_index(pfn);
- mid_p = p2m_top[topidx][mididx];
- if (!mid_p)
- continue;
- if ((mid_p == p2m_missing) || (mid_p == p2m_identity))
- continue;
+ /* Complete missing or identity PMD(s) can be mapped. */
+ ptep = (type == P2M_TYPE_MISSING) ?
+ p2m_missing_pte : p2m_identity_pte;
+ for (i = 0; i < PMDS_PER_MID_PAGE; i++) {
+ pmdp = populate_extra_pmd(
+ (unsigned long)(p2m + pfn + i * PTRS_PER_PTE));
+ set_pmd(pmdp, __pmd(__pa(ptep) | _KERNPG_TABLE));
+ }
+ }
+}
- if ((unsigned long)mid_p == INVALID_P2M_ENTRY)
- continue;
+void __init xen_vmalloc_p2m_tree(void)
+{
+ static struct vm_struct vm;
- /* The old va. Rebase it on mfn_list */
- if (mid_p >= (unsigned long *)va_start && mid_p <= (unsigned long *)va_end) {
- unsigned long *new;
+ vm.flags = VM_ALLOC;
+ vm.size = ALIGN(sizeof(unsigned long) * xen_max_p2m_pfn,
+ PMD_SIZE * PMDS_PER_MID_PAGE);
+ vm_area_register_early(&vm, PMD_SIZE * PMDS_PER_MID_PAGE);
+ pr_notice("p2m virtual area at %p, size is %lx\n", vm.addr, vm.size);
- if (pfn_free > (size / sizeof(unsigned long))) {
- WARN(1, "Only allocated for %ld pages, but we want %ld!\n",
- size / sizeof(unsigned long), pfn_free);
- return 0;
- }
- new = &mfn_list[pfn_free];
+ xen_max_p2m_pfn = vm.size / sizeof(unsigned long);
- copy_page(new, mid_p);
- p2m_top[topidx][mididx] = &mfn_list[pfn_free];
- p2m_top_mfn_p[topidx][mididx] = virt_to_mfn(&mfn_list[pfn_free]);
+ xen_rebuild_p2m_list(vm.addr);
- pfn_free += P2M_PER_PAGE;
+ xen_p2m_addr = vm.addr;
+ xen_p2m_size = xen_max_p2m_pfn;
- }
- /* This should be the leafs allocated for identity from _brk. */
- }
- return (unsigned long)mfn_list;
+ xen_inv_extra_mem();
+ m2p_override_init();
}
-#else
-unsigned long __init xen_revector_p2m_tree(void)
-{
- return 0;
-}
-#endif
+
unsigned long get_phys_to_machine(unsigned long pfn)
{
- unsigned topidx, mididx, idx;
+ pte_t *ptep;
+ unsigned int level;
+
+ if (unlikely(pfn >= xen_p2m_size)) {
+ if (pfn < xen_max_p2m_pfn)
+ return xen_chk_extra_mem(pfn);
- if (unlikely(pfn >= MAX_P2M_PFN))
return IDENTITY_FRAME(pfn);
+ }
- topidx = p2m_top_index(pfn);
- mididx = p2m_mid_index(pfn);
- idx = p2m_index(pfn);
+ ptep = lookup_address((unsigned long)(xen_p2m_addr + pfn), &level);
+ BUG_ON(!ptep || level != PG_LEVEL_4K);
/*
* The INVALID_P2M_ENTRY is filled in both p2m_*identity
* and in p2m_*missing, so returning the INVALID_P2M_ENTRY
* would be wrong.
*/
- if (p2m_top[topidx][mididx] == p2m_identity)
+ if (pte_pfn(*ptep) == PFN_DOWN(__pa(p2m_identity)))
return IDENTITY_FRAME(pfn);
- return p2m_top[topidx][mididx][idx];
+ return xen_p2m_addr[pfn];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);
-static void *alloc_p2m_page(void)
+/*
+ * Allocate new pmd(s). It is checked whether the old pmd is still in place.
+ * If not, nothing is changed. This is okay as the only reason for allocating
+ * a new pmd is to replace p2m_missing_pte or p2m_identity_pte by a individual
+ * pmd. In case of PAE/x86-32 there are multiple pmds to allocate!
+ */
+static pte_t *alloc_p2m_pmd(unsigned long addr, pte_t *ptep, pte_t *pte_pg)
{
- return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
-}
+ pte_t *ptechk;
+ pte_t *pteret = ptep;
+ pte_t *pte_newpg[PMDS_PER_MID_PAGE];
+ pmd_t *pmdp;
+ unsigned int level;
+ unsigned long flags;
+ unsigned long vaddr;
+ int i;
-static void free_p2m_page(void *p)
-{
- free_page((unsigned long)p);
+ /* Do all allocations first to bail out in error case. */
+ for (i = 0; i < PMDS_PER_MID_PAGE; i++) {
+ pte_newpg[i] = alloc_p2m_page();
+ if (!pte_newpg[i]) {
+ for (i--; i >= 0; i--)
+ free_p2m_page(pte_newpg[i]);
+
+ return NULL;
+ }
+ }
+
+ vaddr = addr & ~(PMD_SIZE * PMDS_PER_MID_PAGE - 1);
+
+ for (i = 0; i < PMDS_PER_MID_PAGE; i++) {
+ copy_page(pte_newpg[i], pte_pg);
+ paravirt_alloc_pte(&init_mm, __pa(pte_newpg[i]) >> PAGE_SHIFT);
+
+ pmdp = lookup_pmd_address(vaddr);
+ BUG_ON(!pmdp);
+
+ spin_lock_irqsave(&p2m_update_lock, flags);
+
+ ptechk = lookup_address(vaddr, &level);
+ if (ptechk == pte_pg) {
+ set_pmd(pmdp,
+ __pmd(__pa(pte_newpg[i]) | _KERNPG_TABLE));
+ if (vaddr == (addr & ~(PMD_SIZE - 1)))
+ pteret = pte_offset_kernel(pmdp, addr);
+ pte_newpg[i] = NULL;
+ }
+
+ spin_unlock_irqrestore(&p2m_update_lock, flags);
+
+ if (pte_newpg[i]) {
+ paravirt_release_pte(__pa(pte_newpg[i]) >> PAGE_SHIFT);
+ free_p2m_page(pte_newpg[i]);
+ }
+
+ vaddr += PMD_SIZE;
+ }
+
+ return pteret;
}
/*
@@ -545,269 +501,99 @@ static void free_p2m_page(void *p)
static bool alloc_p2m(unsigned long pfn)
{
unsigned topidx, mididx;
- unsigned long ***top_p, **mid;
unsigned long *top_mfn_p, *mid_mfn;
+ pte_t *ptep, *pte_pg;
+ unsigned int level;
+ unsigned long flags;
+ unsigned long addr = (unsigned long)(xen_p2m_addr + pfn);
+ unsigned long p2m_pfn;
topidx = p2m_top_index(pfn);
mididx = p2m_mid_index(pfn);
- top_p = &p2m_top[topidx];
- mid = *top_p;
+ ptep = lookup_address(addr, &level);
+ BUG_ON(!ptep || level != PG_LEVEL_4K);
+ pte_pg = (pte_t *)((unsigned long)ptep & ~(PAGE_SIZE - 1));
- if (mid == p2m_mid_missing) {
- /* Mid level is missing, allocate a new one */
- mid = alloc_p2m_page();
- if (!mid)
+ if (pte_pg == p2m_missing_pte || pte_pg == p2m_identity_pte) {
+ /* PMD level is missing, allocate a new one */
+ ptep = alloc_p2m_pmd(addr, ptep, pte_pg);
+ if (!ptep)
return false;
-
- p2m_mid_init(mid, p2m_missing);
-
- if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
- free_p2m_page(mid);
}
- top_mfn_p = &p2m_top_mfn[topidx];
- mid_mfn = p2m_top_mfn_p[topidx];
+ if (p2m_top_mfn) {
+ top_mfn_p = &p2m_top_mfn[topidx];
+ mid_mfn = ACCESS_ONCE(p2m_top_mfn_p[topidx]);
- BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
+ BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
- if (mid_mfn == p2m_mid_missing_mfn) {
- /* Separately check the mid mfn level */
- unsigned long missing_mfn;
- unsigned long mid_mfn_mfn;
+ if (mid_mfn == p2m_mid_missing_mfn) {
+ /* Separately check the mid mfn level */
+ unsigned long missing_mfn;
+ unsigned long mid_mfn_mfn;
+ unsigned long old_mfn;
- mid_mfn = alloc_p2m_page();
- if (!mid_mfn)
- return false;
+ mid_mfn = alloc_p2m_page();
+ if (!mid_mfn)
+ return false;
- p2m_mid_mfn_init(mid_mfn, p2m_missing);
+ p2m_mid_mfn_init(mid_mfn, p2m_missing);
- missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
- mid_mfn_mfn = virt_to_mfn(mid_mfn);
- if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
- free_p2m_page(mid_mfn);
- else
- p2m_top_mfn_p[topidx] = mid_mfn;
+ missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
+ mid_mfn_mfn = virt_to_mfn(mid_mfn);
+ old_mfn = cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn);
+ if (old_mfn != missing_mfn) {
+ free_p2m_page(mid_mfn);
+ mid_mfn = mfn_to_virt(old_mfn);
+ } else {
+ p2m_top_mfn_p[topidx] = mid_mfn;
+ }
+ }
+ } else {
+ mid_mfn = NULL;
}
- if (p2m_top[topidx][mididx] == p2m_identity ||
- p2m_top[topidx][mididx] == p2m_missing) {
+ p2m_pfn = pte_pfn(ACCESS_ONCE(*ptep));
+ if (p2m_pfn == PFN_DOWN(__pa(p2m_identity)) ||
+ p2m_pfn == PFN_DOWN(__pa(p2m_missing))) {
/* p2m leaf page is missing */
unsigned long *p2m;
- unsigned long *p2m_orig = p2m_top[topidx][mididx];
p2m = alloc_p2m_page();
if (!p2m)
return false;
- p2m_init(p2m);
-
- if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig)
- free_p2m_page(p2m);
+ if (p2m_pfn == PFN_DOWN(__pa(p2m_missing)))
+ p2m_init(p2m);
else
- mid_mfn[mididx] = virt_to_mfn(p2m);
- }
-
- return true;
-}
-
-static bool __init early_alloc_p2m(unsigned long pfn, bool check_boundary)
-{
- unsigned topidx, mididx, idx;
- unsigned long *p2m;
- unsigned long *mid_mfn_p;
-
- topidx = p2m_top_index(pfn);
- mididx = p2m_mid_index(pfn);
- idx = p2m_index(pfn);
-
- /* Pfff.. No boundary cross-over, lets get out. */
- if (!idx && check_boundary)
- return false;
-
- WARN(p2m_top[topidx][mididx] == p2m_identity,
- "P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n",
- topidx, mididx);
-
- /*
- * Could be done by xen_build_dynamic_phys_to_machine..
- */
- if (p2m_top[topidx][mididx] != p2m_missing)
- return false;
-
- /* Boundary cross-over for the edges: */
- p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_init_identity(p2m, pfn);
- p2m_init(p2m);
+ spin_lock_irqsave(&p2m_update_lock, flags);
- p2m_top[topidx][mididx] = p2m;
-
- /* For save/restore we need to MFN of the P2M saved */
-
- mid_mfn_p = p2m_top_mfn_p[topidx];
- WARN(mid_mfn_p[mididx] != virt_to_mfn(p2m_missing),
- "P2M_TOP_P[%d][%d] != MFN of p2m_missing!\n",
- topidx, mididx);
- mid_mfn_p[mididx] = virt_to_mfn(p2m);
-
- return true;
-}
-
-static bool __init early_alloc_p2m_middle(unsigned long pfn)
-{
- unsigned topidx = p2m_top_index(pfn);
- unsigned long *mid_mfn_p;
- unsigned long **mid;
-
- mid = p2m_top[topidx];
- mid_mfn_p = p2m_top_mfn_p[topidx];
- if (mid == p2m_mid_missing) {
- mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
-
- p2m_mid_init(mid, p2m_missing);
-
- p2m_top[topidx] = mid;
-
- BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
- }
- /* And the save/restore P2M tables.. */
- if (mid_mfn_p == p2m_mid_missing_mfn) {
- mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
- p2m_mid_mfn_init(mid_mfn_p, p2m_missing);
-
- p2m_top_mfn_p[topidx] = mid_mfn_p;
- p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
- /* Note: we don't set mid_mfn_p[midix] here,
- * look in early_alloc_p2m() */
- }
- return true;
-}
-
-/*
- * Skim over the P2M tree looking at pages that are either filled with
- * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and
- * replace the P2M leaf with a p2m_missing or p2m_identity.
- * Stick the old page in the new P2M tree location.
- */
-bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn)
-{
- unsigned topidx;
- unsigned mididx;
- unsigned ident_pfns;
- unsigned inv_pfns;
- unsigned long *p2m;
- unsigned long *mid_mfn_p;
- unsigned idx;
- unsigned long pfn;
-
- /* We only look when this entails a P2M middle layer */
- if (p2m_index(set_pfn))
- return false;
-
- for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) {
- topidx = p2m_top_index(pfn);
-
- if (!p2m_top[topidx])
- continue;
-
- if (p2m_top[topidx] == p2m_mid_missing)
- continue;
-
- mididx = p2m_mid_index(pfn);
- p2m = p2m_top[topidx][mididx];
- if (!p2m)
- continue;
-
- if ((p2m == p2m_missing) || (p2m == p2m_identity))
- continue;
-
- if ((unsigned long)p2m == INVALID_P2M_ENTRY)
- continue;
-
- ident_pfns = 0;
- inv_pfns = 0;
- for (idx = 0; idx < P2M_PER_PAGE; idx++) {
- /* IDENTITY_PFNs are 1:1 */
- if (p2m[idx] == IDENTITY_FRAME(pfn + idx))
- ident_pfns++;
- else if (p2m[idx] == INVALID_P2M_ENTRY)
- inv_pfns++;
- else
- break;
+ if (pte_pfn(*ptep) == p2m_pfn) {
+ set_pte(ptep,
+ pfn_pte(PFN_DOWN(__pa(p2m)), PAGE_KERNEL));
+ if (mid_mfn)
+ mid_mfn[mididx] = virt_to_mfn(p2m);
+ p2m = NULL;
}
- if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE))
- goto found;
- }
- return false;
-found:
- /* Found one, replace old with p2m_identity or p2m_missing */
- p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing);
- /* And the other for save/restore.. */
- mid_mfn_p = p2m_top_mfn_p[topidx];
- /* NOTE: Even if it is a p2m_identity it should still be point to
- * a page filled with INVALID_P2M_ENTRY entries. */
- mid_mfn_p[mididx] = virt_to_mfn(p2m_missing);
-
- /* Reset where we want to stick the old page in. */
- topidx = p2m_top_index(set_pfn);
- mididx = p2m_mid_index(set_pfn);
-
- /* This shouldn't happen */
- if (WARN_ON(p2m_top[topidx] == p2m_mid_missing))
- early_alloc_p2m_middle(set_pfn);
-
- if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing))
- return false;
-
- p2m_init(p2m);
- p2m_top[topidx][mididx] = p2m;
- mid_mfn_p = p2m_top_mfn_p[topidx];
- mid_mfn_p[mididx] = virt_to_mfn(p2m);
-
- return true;
-}
-bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn)
-{
- if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
- if (!early_alloc_p2m_middle(pfn))
- return false;
- if (early_can_reuse_p2m_middle(pfn, mfn))
- return __set_phys_to_machine(pfn, mfn);
+ spin_unlock_irqrestore(&p2m_update_lock, flags);
- if (!early_alloc_p2m(pfn, false /* boundary crossover OK!*/))
- return false;
-
- if (!__set_phys_to_machine(pfn, mfn))
- return false;
+ if (p2m)
+ free_p2m_page(p2m);
}
return true;
}
-static void __init early_split_p2m(unsigned long pfn)
-{
- unsigned long mididx, idx;
-
- mididx = p2m_mid_index(pfn);
- idx = p2m_index(pfn);
-
- /*
- * Allocate new middle and leaf pages if this pfn lies in the
- * middle of one.
- */
- if (mididx || idx)
- early_alloc_p2m_middle(pfn);
- if (idx)
- early_alloc_p2m(pfn, false);
-}
-
unsigned long __init set_phys_range_identity(unsigned long pfn_s,
unsigned long pfn_e)
{
unsigned long pfn;
- if (unlikely(pfn_s >= MAX_P2M_PFN))
+ if (unlikely(pfn_s >= xen_p2m_size))
return 0;
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
@@ -816,101 +602,51 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s,
if (pfn_s > pfn_e)
return 0;
- if (pfn_e > MAX_P2M_PFN)
- pfn_e = MAX_P2M_PFN;
-
- early_split_p2m(pfn_s);
- early_split_p2m(pfn_e);
-
- for (pfn = pfn_s; pfn < pfn_e;) {
- unsigned topidx = p2m_top_index(pfn);
- unsigned mididx = p2m_mid_index(pfn);
-
- if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
- break;
- pfn++;
-
- /*
- * If the PFN was set to a middle or leaf identity
- * page the remainder must also be identity, so skip
- * ahead to the next middle or leaf entry.
- */
- if (p2m_top[topidx] == p2m_mid_identity)
- pfn = ALIGN(pfn, P2M_MID_PER_PAGE * P2M_PER_PAGE);
- else if (p2m_top[topidx][mididx] == p2m_identity)
- pfn = ALIGN(pfn, P2M_PER_PAGE);
- }
+ if (pfn_e > xen_p2m_size)
+ pfn_e = xen_p2m_size;
- WARN((pfn - pfn_s) != (pfn_e - pfn_s),
- "Identity mapping failed. We are %ld short of 1-1 mappings!\n",
- (pfn_e - pfn_s) - (pfn - pfn_s));
+ for (pfn = pfn_s; pfn < pfn_e; pfn++)
+ xen_p2m_addr[pfn] = IDENTITY_FRAME(pfn);
return pfn - pfn_s;
}
-/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
- unsigned topidx, mididx, idx;
+ pte_t *ptep;
+ unsigned int level;
/* don't track P2M changes in autotranslate guests */
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
return true;
- if (unlikely(pfn >= MAX_P2M_PFN)) {
+ if (unlikely(pfn >= xen_p2m_size)) {
BUG_ON(mfn != INVALID_P2M_ENTRY);
return true;
}
- topidx = p2m_top_index(pfn);
- mididx = p2m_mid_index(pfn);
- idx = p2m_index(pfn);
-
- /* For sparse holes were the p2m leaf has real PFN along with
- * PCI holes, stick in the PFN as the MFN value.
- *
- * set_phys_range_identity() will have allocated new middle
- * and leaf pages as required so an existing p2m_mid_missing
- * or p2m_missing mean that whole range will be identity so
- * these can be switched to p2m_mid_identity or p2m_identity.
- */
- if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
- if (p2m_top[topidx] == p2m_mid_identity)
- return true;
-
- if (p2m_top[topidx] == p2m_mid_missing) {
- WARN_ON(cmpxchg(&p2m_top[topidx], p2m_mid_missing,
- p2m_mid_identity) != p2m_mid_missing);
- return true;
- }
-
- if (p2m_top[topidx][mididx] == p2m_identity)
- return true;
+ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn)))
+ return true;
- /* Swap over from MISSING to IDENTITY if needed. */
- if (p2m_top[topidx][mididx] == p2m_missing) {
- WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing,
- p2m_identity) != p2m_missing);
- return true;
- }
- }
+ ptep = lookup_address((unsigned long)(xen_p2m_addr + pfn), &level);
+ BUG_ON(!ptep || level != PG_LEVEL_4K);
- if (p2m_top[topidx][mididx] == p2m_missing)
+ if (pte_pfn(*ptep) == PFN_DOWN(__pa(p2m_missing)))
return mfn == INVALID_P2M_ENTRY;
- p2m_top[topidx][mididx][idx] = mfn;
+ if (pte_pfn(*ptep) == PFN_DOWN(__pa(p2m_identity)))
+ return mfn == IDENTITY_FRAME(pfn);
- return true;
+ return false;
}
bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
- if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
+ if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
if (!alloc_p2m(pfn))
return false;
- if (!__set_phys_to_machine(pfn, mfn))
- return false;
+ return __set_phys_to_machine(pfn, mfn);
}
return true;
@@ -919,15 +655,16 @@ bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
#define M2P_OVERRIDE_HASH_SHIFT 10
#define M2P_OVERRIDE_HASH (1 << M2P_OVERRIDE_HASH_SHIFT)
-static RESERVE_BRK_ARRAY(struct list_head, m2p_overrides, M2P_OVERRIDE_HASH);
+static struct list_head *m2p_overrides;
static DEFINE_SPINLOCK(m2p_override_lock);
static void __init m2p_override_init(void)
{
unsigned i;
- m2p_overrides = extend_brk(sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH,
- sizeof(unsigned long));
+ m2p_overrides = alloc_bootmem_align(
+ sizeof(*m2p_overrides) * M2P_OVERRIDE_HASH,
+ sizeof(unsigned long));
for (i = 0; i < M2P_OVERRIDE_HASH; i++)
INIT_LIST_HEAD(&m2p_overrides[i]);
@@ -938,68 +675,9 @@ static unsigned long mfn_hash(unsigned long mfn)
return hash_long(mfn, M2P_OVERRIDE_HASH_SHIFT);
}
-int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
- struct gnttab_map_grant_ref *kmap_ops,
- struct page **pages, unsigned int count)
-{
- int i, ret = 0;
- bool lazy = false;
- pte_t *pte;
-
- if (xen_feature(XENFEAT_auto_translated_physmap))
- return 0;
-
- if (kmap_ops &&
- !in_interrupt() &&
- paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
- arch_enter_lazy_mmu_mode();
- lazy = true;
- }
-
- for (i = 0; i < count; i++) {
- unsigned long mfn, pfn;
-
- /* Do not add to override if the map failed. */
- if (map_ops[i].status)
- continue;
-
- if (map_ops[i].flags & GNTMAP_contains_pte) {
- pte = (pte_t *) (mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
- (map_ops[i].host_addr & ~PAGE_MASK));
- mfn = pte_mfn(*pte);
- } else {
- mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
- }
- pfn = page_to_pfn(pages[i]);
-
- WARN_ON(PagePrivate(pages[i]));
- SetPagePrivate(pages[i]);
- set_page_private(pages[i], mfn);
- pages[i]->index = pfn_to_mfn(pfn);
-
- if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
- ret = -ENOMEM;
- goto out;
- }
-
- if (kmap_ops) {
- ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
- if (ret)
- goto out;
- }
- }
-
-out:
- if (lazy)
- arch_leave_lazy_mmu_mode();
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
-
/* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page,
- struct gnttab_map_grant_ref *kmap_op)
+static int m2p_add_override(unsigned long mfn, struct page *page,
+ struct gnttab_map_grant_ref *kmap_op)
{
unsigned long flags;
unsigned long pfn;
@@ -1012,7 +690,7 @@ int m2p_add_override(unsigned long mfn, struct page *page,
address = (unsigned long)__va(pfn << PAGE_SHIFT);
ptep = lookup_address(address, &level);
if (WARN(ptep == NULL || level != PG_LEVEL_4K,
- "m2p_add_override: pfn %lx not mapped", pfn))
+ "m2p_add_override: pfn %lx not mapped", pfn))
return -EINVAL;
}
@@ -1046,19 +724,19 @@ int m2p_add_override(unsigned long mfn, struct page *page,
* because mfn_to_pfn (that ends up being called by GUPF) will
* return the backend pfn rather than the frontend pfn. */
pfn = mfn_to_pfn_no_overrides(mfn);
- if (get_phys_to_machine(pfn) == mfn)
+ if (__pfn_to_mfn(pfn) == mfn)
set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
return 0;
}
-EXPORT_SYMBOL_GPL(m2p_add_override);
-int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
- struct gnttab_map_grant_ref *kmap_ops,
- struct page **pages, unsigned int count)
+int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
+ struct gnttab_map_grant_ref *kmap_ops,
+ struct page **pages, unsigned int count)
{
int i, ret = 0;
bool lazy = false;
+ pte_t *pte;
if (xen_feature(XENFEAT_auto_translated_physmap))
return 0;
@@ -1071,35 +749,75 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
}
for (i = 0; i < count; i++) {
- unsigned long mfn = get_phys_to_machine(page_to_pfn(pages[i]));
- unsigned long pfn = page_to_pfn(pages[i]);
+ unsigned long mfn, pfn;
- if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) {
- ret = -EINVAL;
- goto out;
+ /* Do not add to override if the map failed. */
+ if (map_ops[i].status)
+ continue;
+
+ if (map_ops[i].flags & GNTMAP_contains_pte) {
+ pte = (pte_t *)(mfn_to_virt(PFN_DOWN(map_ops[i].host_addr)) +
+ (map_ops[i].host_addr & ~PAGE_MASK));
+ mfn = pte_mfn(*pte);
+ } else {
+ mfn = PFN_DOWN(map_ops[i].dev_bus_addr);
}
+ pfn = page_to_pfn(pages[i]);
- set_page_private(pages[i], INVALID_P2M_ENTRY);
- WARN_ON(!PagePrivate(pages[i]));
- ClearPagePrivate(pages[i]);
- set_phys_to_machine(pfn, pages[i]->index);
+ WARN_ON(PagePrivate(pages[i]));
+ SetPagePrivate(pages[i]);
+ set_page_private(pages[i], mfn);
+ pages[i]->index = pfn_to_mfn(pfn);
- if (kmap_ops)
- ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
- if (ret)
+ if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn)))) {
+ ret = -ENOMEM;
goto out;
+ }
+
+ if (kmap_ops) {
+ ret = m2p_add_override(mfn, pages[i], &kmap_ops[i]);
+ if (ret)
+ goto out;
+ }
}
out:
if (lazy)
arch_leave_lazy_mmu_mode();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
+
+static struct page *m2p_find_override(unsigned long mfn)
+{
+ unsigned long flags;
+ struct list_head *bucket;
+ struct page *p, *ret;
+
+ if (unlikely(!m2p_overrides))
+ return NULL;
+
+ ret = NULL;
+ bucket = &m2p_overrides[mfn_hash(mfn)];
+
+ spin_lock_irqsave(&m2p_override_lock, flags);
+
+ list_for_each_entry(p, bucket, lru) {
+ if (page_private(p) == mfn) {
+ ret = p;
+ break;
+ }
+ }
+
+ spin_unlock_irqrestore(&m2p_override_lock, flags);
+
return ret;
}
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
-int m2p_remove_override(struct page *page,
- struct gnttab_map_grant_ref *kmap_op,
- unsigned long mfn)
+static int m2p_remove_override(struct page *page,
+ struct gnttab_map_grant_ref *kmap_op,
+ unsigned long mfn)
{
unsigned long flags;
unsigned long pfn;
@@ -1114,7 +832,7 @@ int m2p_remove_override(struct page *page,
ptep = lookup_address(address, &level);
if (WARN(ptep == NULL || level != PG_LEVEL_4K,
- "m2p_remove_override: pfn %lx not mapped", pfn))
+ "m2p_remove_override: pfn %lx not mapped", pfn))
return -EINVAL;
}
@@ -1144,9 +862,8 @@ int m2p_remove_override(struct page *page,
* hypercall actually returned an error.
*/
if (kmap_op->handle == GNTST_general_error) {
- printk(KERN_WARNING "m2p_remove_override: "
- "pfn %lx mfn %lx, failed to modify kernel mappings",
- pfn, mfn);
+ pr_warn("m2p_remove_override: pfn %lx mfn %lx, failed to modify kernel mappings",
+ pfn, mfn);
put_balloon_scratch_page();
return -1;
}
@@ -1154,14 +871,14 @@ int m2p_remove_override(struct page *page,
xen_mc_batch();
mcs = __xen_mc_entry(
- sizeof(struct gnttab_unmap_and_replace));
+ sizeof(struct gnttab_unmap_and_replace));
unmap_op = mcs.args;
unmap_op->host_addr = kmap_op->host_addr;
unmap_op->new_addr = scratch_page_address;
unmap_op->handle = kmap_op->handle;
MULTI_grant_table_op(mcs.mc,
- GNTTABOP_unmap_and_replace, unmap_op, 1);
+ GNTTABOP_unmap_and_replace, unmap_op, 1);
mcs = __xen_mc_entry(0);
MULTI_update_va_mapping(mcs.mc, scratch_page_address,
@@ -1187,35 +904,56 @@ int m2p_remove_override(struct page *page,
* pfn again. */
mfn &= ~FOREIGN_FRAME_BIT;
pfn = mfn_to_pfn_no_overrides(mfn);
- if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+ if (__pfn_to_mfn(pfn) == FOREIGN_FRAME(mfn) &&
m2p_find_override(mfn) == NULL)
set_phys_to_machine(pfn, mfn);
return 0;
}
-EXPORT_SYMBOL_GPL(m2p_remove_override);
-struct page *m2p_find_override(unsigned long mfn)
+int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
+ struct gnttab_map_grant_ref *kmap_ops,
+ struct page **pages, unsigned int count)
{
- unsigned long flags;
- struct list_head *bucket = &m2p_overrides[mfn_hash(mfn)];
- struct page *p, *ret;
+ int i, ret = 0;
+ bool lazy = false;
- ret = NULL;
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return 0;
- spin_lock_irqsave(&m2p_override_lock, flags);
+ if (kmap_ops &&
+ !in_interrupt() &&
+ paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE) {
+ arch_enter_lazy_mmu_mode();
+ lazy = true;
+ }
- list_for_each_entry(p, bucket, lru) {
- if (page_private(p) == mfn) {
- ret = p;
- break;
+ for (i = 0; i < count; i++) {
+ unsigned long mfn = __pfn_to_mfn(page_to_pfn(pages[i]));
+ unsigned long pfn = page_to_pfn(pages[i]);
+
+ if (mfn == INVALID_P2M_ENTRY || !(mfn & FOREIGN_FRAME_BIT)) {
+ ret = -EINVAL;
+ goto out;
}
- }
- spin_unlock_irqrestore(&m2p_override_lock, flags);
+ set_page_private(pages[i], INVALID_P2M_ENTRY);
+ WARN_ON(!PagePrivate(pages[i]));
+ ClearPagePrivate(pages[i]);
+ set_phys_to_machine(pfn, pages[i]->index);
+ if (kmap_ops)
+ ret = m2p_remove_override(pages[i], &kmap_ops[i], mfn);
+ if (ret)
+ goto out;
+ }
+
+out:
+ if (lazy)
+ arch_leave_lazy_mmu_mode();
return ret;
}
+EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
{
@@ -1234,79 +972,29 @@ EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
#include "debugfs.h"
static int p2m_dump_show(struct seq_file *m, void *v)
{
- static const char * const level_name[] = { "top", "middle",
- "entry", "abnormal", "error"};
-#define TYPE_IDENTITY 0
-#define TYPE_MISSING 1
-#define TYPE_PFN 2
-#define TYPE_UNKNOWN 3
static const char * const type_name[] = {
- [TYPE_IDENTITY] = "identity",
- [TYPE_MISSING] = "missing",
- [TYPE_PFN] = "pfn",
- [TYPE_UNKNOWN] = "abnormal"};
- unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
- unsigned int uninitialized_var(prev_level);
- unsigned int uninitialized_var(prev_type);
-
- if (!p2m_top)
- return 0;
-
- for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) {
- unsigned topidx = p2m_top_index(pfn);
- unsigned mididx = p2m_mid_index(pfn);
- unsigned idx = p2m_index(pfn);
- unsigned lvl, type;
-
- lvl = 4;
- type = TYPE_UNKNOWN;
- if (p2m_top[topidx] == p2m_mid_missing) {
- lvl = 0; type = TYPE_MISSING;
- } else if (p2m_top[topidx] == NULL) {
- lvl = 0; type = TYPE_UNKNOWN;
- } else if (p2m_top[topidx][mididx] == NULL) {
- lvl = 1; type = TYPE_UNKNOWN;
- } else if (p2m_top[topidx][mididx] == p2m_identity) {
- lvl = 1; type = TYPE_IDENTITY;
- } else if (p2m_top[topidx][mididx] == p2m_missing) {
- lvl = 1; type = TYPE_MISSING;
- } else if (p2m_top[topidx][mididx][idx] == 0) {
- lvl = 2; type = TYPE_UNKNOWN;
- } else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) {
- lvl = 2; type = TYPE_IDENTITY;
- } else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) {
- lvl = 2; type = TYPE_MISSING;
- } else if (p2m_top[topidx][mididx][idx] == pfn) {
- lvl = 2; type = TYPE_PFN;
- } else if (p2m_top[topidx][mididx][idx] != pfn) {
- lvl = 2; type = TYPE_PFN;
- }
- if (pfn == 0) {
- prev_level = lvl;
- prev_type = type;
- }
- if (pfn == MAX_DOMAIN_PAGES-1) {
- lvl = 3;
- type = TYPE_UNKNOWN;
- }
- if (prev_type != type) {
- seq_printf(m, " [0x%lx->0x%lx] %s\n",
- prev_pfn_type, pfn, type_name[prev_type]);
- prev_pfn_type = pfn;
+ [P2M_TYPE_IDENTITY] = "identity",
+ [P2M_TYPE_MISSING] = "missing",
+ [P2M_TYPE_PFN] = "pfn",
+ [P2M_TYPE_UNKNOWN] = "abnormal"};
+ unsigned long pfn, first_pfn;
+ int type, prev_type;
+
+ prev_type = xen_p2m_elem_type(0);
+ first_pfn = 0;
+
+ for (pfn = 0; pfn < xen_p2m_size; pfn++) {
+ type = xen_p2m_elem_type(pfn);
+ if (type != prev_type) {
+ seq_printf(m, " [0x%lx->0x%lx] %s\n", first_pfn, pfn,
+ type_name[prev_type]);
prev_type = type;
- }
- if (prev_level != lvl) {
- seq_printf(m, " [0x%lx->0x%lx] level %s\n",
- prev_pfn_level, pfn, level_name[prev_level]);
- prev_pfn_level = pfn;
- prev_level = lvl;
+ first_pfn = pfn;
}
}
+ seq_printf(m, " [0x%lx->0x%lx] %s\n", first_pfn, pfn,
+ type_name[prev_type]);
return 0;
-#undef TYPE_IDENTITY
-#undef TYPE_MISSING
-#undef TYPE_PFN
-#undef TYPE_UNKNOWN
}
static int p2m_dump_open(struct inode *inode, struct file *filp)
diff --git a/arch/x86/xen/p2m.h b/arch/x86/xen/p2m.h
new file mode 100644
index 000000000000..ad8aee24ab72
--- /dev/null
+++ b/arch/x86/xen/p2m.h
@@ -0,0 +1,15 @@
+#ifndef _XEN_P2M_H
+#define _XEN_P2M_H
+
+#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
+#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *))
+#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **))
+
+#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
+
+#define MAX_REMAP_RANGES 10
+
+extern unsigned long __init set_phys_range_identity(unsigned long pfn_s,
+ unsigned long pfn_e);
+
+#endif /* _XEN_P2M_H */
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 2e555163c2fe..dfd77dec8e2b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -29,6 +29,8 @@
#include <xen/features.h>
#include "xen-ops.h"
#include "vdso.h"
+#include "p2m.h"
+#include "mmu.h"
/* These are code, but not functions. Defined in entry.S */
extern const char xen_hypervisor_callback[];
@@ -46,6 +48,20 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata;
/* Number of pages released from the initial allocation. */
unsigned long xen_released_pages;
+/*
+ * Buffer used to remap identity mapped pages. We only need the virtual space.
+ * The physical page behind this address is remapped as needed to different
+ * buffer pages.
+ */
+#define REMAP_SIZE (P2M_PER_PAGE - 3)
+static struct {
+ unsigned long next_area_mfn;
+ unsigned long target_pfn;
+ unsigned long size;
+ unsigned long mfns[REMAP_SIZE];
+} xen_remap_buf __initdata __aligned(PAGE_SIZE);
+static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
+
/*
* The maximum amount of extra memory compared to the base size. The
* main scaling factor is the size of struct page. At extreme ratios
@@ -60,7 +76,6 @@ unsigned long xen_released_pages;
static void __init xen_add_extra_mem(u64 start, u64 size)
{
- unsigned long pfn;
int i;
for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
@@ -80,178 +95,351 @@ static void __init xen_add_extra_mem(u64 start, u64 size)
printk(KERN_WARNING "Warning: not enough extra memory regions\n");
memblock_reserve(start, size);
+}
- xen_max_p2m_pfn = PFN_DOWN(start + size);
- for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) {
- unsigned long mfn = pfn_to_mfn(pfn);
+static void __init xen_del_extra_mem(u64 start, u64 size)
+{
+ int i;
+ u64 start_r, size_r;
+
+ for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+ start_r = xen_extra_mem[i].start;
+ size_r = xen_extra_mem[i].size;
+
+ /* Start of region. */
+ if (start_r == start) {
+ BUG_ON(size > size_r);
+ xen_extra_mem[i].start += size;
+ xen_extra_mem[i].size -= size;
+ break;
+ }
+ /* End of region. */
+ if (start_r + size_r == start + size) {
+ BUG_ON(size > size_r);
+ xen_extra_mem[i].size -= size;
+ break;
+ }
+ /* Mid of region. */
+ if (start > start_r && start < start_r + size_r) {
+ BUG_ON(start + size > start_r + size_r);
+ xen_extra_mem[i].size = start - start_r;
+ /* Calling memblock_reserve() again is okay. */
+ xen_add_extra_mem(start + size, start_r + size_r -
+ (start + size));
+ break;
+ }
+ }
+ memblock_free(start, size);
+}
+
+/*
+ * Called during boot before the p2m list can take entries beyond the
+ * hypervisor supplied p2m list. Entries in extra mem are to be regarded as
+ * invalid.
+ */
+unsigned long __ref xen_chk_extra_mem(unsigned long pfn)
+{
+ int i;
+ unsigned long addr = PFN_PHYS(pfn);
+
+ for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+ if (addr >= xen_extra_mem[i].start &&
+ addr < xen_extra_mem[i].start + xen_extra_mem[i].size)
+ return INVALID_P2M_ENTRY;
+ }
- if (WARN_ONCE(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn))
+ return IDENTITY_FRAME(pfn);
+}
+
+/*
+ * Mark all pfns of extra mem as invalid in p2m list.
+ */
+void __init xen_inv_extra_mem(void)
+{
+ unsigned long pfn, pfn_s, pfn_e;
+ int i;
+
+ for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
+ pfn_s = PFN_DOWN(xen_extra_mem[i].start);
+ pfn_e = PFN_UP(xen_extra_mem[i].start + xen_extra_mem[i].size);
+ for (pfn = pfn_s; pfn < pfn_e; pfn++)
+ set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ }
+}
+
+/*
+ * Finds the next RAM pfn available in the E820 map after min_pfn.
+ * This function updates min_pfn with the pfn found and returns
+ * the size of that range or zero if not found.
+ */
+static unsigned long __init xen_find_pfn_range(
+ const struct e820entry *list, size_t map_size,
+ unsigned long *min_pfn)
+{
+ const struct e820entry *entry;
+ unsigned int i;
+ unsigned long done = 0;
+
+ for (i = 0, entry = list; i < map_size; i++, entry++) {
+ unsigned long s_pfn;
+ unsigned long e_pfn;
+
+ if (entry->type != E820_RAM)
continue;
- WARN_ONCE(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n",
- pfn, mfn);
- __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ e_pfn = PFN_DOWN(entry->addr + entry->size);
+
+ /* We only care about E820 after this */
+ if (e_pfn < *min_pfn)
+ continue;
+
+ s_pfn = PFN_UP(entry->addr);
+
+ /* If min_pfn falls within the E820 entry, we want to start
+ * at the min_pfn PFN.
+ */
+ if (s_pfn <= *min_pfn) {
+ done = e_pfn - *min_pfn;
+ } else {
+ done = e_pfn - s_pfn;
+ *min_pfn = s_pfn;
+ }
+ break;
}
+
+ return done;
}
-static unsigned long __init xen_do_chunk(unsigned long start,
- unsigned long end, bool release)
+static int __init xen_free_mfn(unsigned long mfn)
{
struct xen_memory_reservation reservation = {
.address_bits = 0,
.extent_order = 0,
.domid = DOMID_SELF
};
+
+ set_xen_guest_handle(reservation.extent_start, &mfn);
+ reservation.nr_extents = 1;
+
+ return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+}
+
+/*
+ * This releases a chunk of memory and then does the identity map. It's used
+ * as a fallback if the remapping fails.
+ */
+static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
+ unsigned long end_pfn, unsigned long nr_pages, unsigned long *identity,
+ unsigned long *released)
+{
unsigned long len = 0;
- unsigned long pfn;
+ unsigned long pfn, end;
int ret;
- for (pfn = start; pfn < end; pfn++) {
- unsigned long frame;
+ WARN_ON(start_pfn > end_pfn);
+
+ end = min(end_pfn, nr_pages);
+ for (pfn = start_pfn; pfn < end; pfn++) {
unsigned long mfn = pfn_to_mfn(pfn);
- if (release) {
- /* Make sure pfn exists to start with */
- if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
- continue;
- frame = mfn;
- } else {
- if (mfn != INVALID_P2M_ENTRY)
- continue;
- frame = pfn;
- }
- set_xen_guest_handle(reservation.extent_start, &frame);
- reservation.nr_extents = 1;
+ /* Make sure pfn exists to start with */
+ if (mfn == INVALID_P2M_ENTRY || mfn_to_pfn(mfn) != pfn)
+ continue;
- ret = HYPERVISOR_memory_op(release ? XENMEM_decrease_reservation : XENMEM_populate_physmap,
- &reservation);
- WARN(ret != 1, "Failed to %s pfn %lx err=%d\n",
- release ? "release" : "populate", pfn, ret);
+ ret = xen_free_mfn(mfn);
+ WARN(ret != 1, "Failed to release pfn %lx err=%d\n", pfn, ret);
if (ret == 1) {
- if (!early_set_phys_to_machine(pfn, release ? INVALID_P2M_ENTRY : frame)) {
- if (release)
- break;
- set_xen_guest_handle(reservation.extent_start, &frame);
- reservation.nr_extents = 1;
- ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation,
- &reservation);
+ if (!__set_phys_to_machine(pfn, INVALID_P2M_ENTRY))
break;
- }
len++;
} else
break;
}
- if (len)
- printk(KERN_INFO "%s %lx-%lx pfn range: %lu pages %s\n",
- release ? "Freeing" : "Populating",
- start, end, len,
- release ? "freed" : "added");
- return len;
+ /* Need to release pages first */
+ *released += len;
+ *identity += set_phys_range_identity(start_pfn, end_pfn);
}
-static unsigned long __init xen_release_chunk(unsigned long start,
- unsigned long end)
+/*
+ * Helper function to update the p2m and m2p tables and kernel mapping.
+ */
+static void __init xen_update_mem_tables(unsigned long pfn, unsigned long mfn)
{
- return xen_do_chunk(start, end, true);
+ struct mmu_update update = {
+ .ptr = ((unsigned long long)mfn << PAGE_SHIFT) | MMU_MACHPHYS_UPDATE,
+ .val = pfn
+ };
+
+ /* Update p2m */
+ if (!set_phys_to_machine(pfn, mfn)) {
+ WARN(1, "Failed to set p2m mapping for pfn=%ld mfn=%ld\n",
+ pfn, mfn);
+ BUG();
+ }
+
+ /* Update m2p */
+ if (HYPERVISOR_mmu_update(&update, 1, NULL, DOMID_SELF) < 0) {
+ WARN(1, "Failed to set m2p mapping for mfn=%ld pfn=%ld\n",
+ mfn, pfn);
+ BUG();
+ }
+
+ /* Update kernel mapping, but not for highmem. */
+ if ((pfn << PAGE_SHIFT) >= __pa(high_memory))
+ return;
+
+ if (HYPERVISOR_update_va_mapping((unsigned long)__va(pfn << PAGE_SHIFT),
+ mfn_pte(mfn, PAGE_KERNEL), 0)) {
+ WARN(1, "Failed to update kernel mapping for mfn=%ld pfn=%ld\n",
+ mfn, pfn);
+ BUG();
+ }
}
-static unsigned long __init xen_populate_chunk(
- const struct e820entry *list, size_t map_size,
- unsigned long max_pfn, unsigned long *last_pfn,
- unsigned long credits_left)
+/*
+ * This function updates the p2m and m2p tables with an identity map from
+ * start_pfn to start_pfn+size and prepares remapping the underlying RAM of the
+ * original allocation at remap_pfn. The information needed for remapping is
+ * saved in the memory itself to avoid the need for allocating buffers. The
+ * complete remap information is contained in a list of MFNs each containing
+ * up to REMAP_SIZE MFNs and the start target PFN for doing the remap.
+ * This enables us to preserve the original mfn sequence while doing the
+ * remapping at a time when the memory management is capable of allocating
+ * virtual and physical memory in arbitrary amounts, see 'xen_remap_memory' and
+ * its callers.
+ */
+static void __init xen_do_set_identity_and_remap_chunk(
+ unsigned long start_pfn, unsigned long size, unsigned long remap_pfn)
{
- const struct e820entry *entry;
- unsigned int i;
- unsigned long done = 0;
- unsigned long dest_pfn;
+ unsigned long buf = (unsigned long)&xen_remap_buf;
+ unsigned long mfn_save, mfn;
+ unsigned long ident_pfn_iter, remap_pfn_iter;
+ unsigned long ident_end_pfn = start_pfn + size;
+ unsigned long left = size;
+ unsigned long ident_cnt = 0;
+ unsigned int i, chunk;
- for (i = 0, entry = list; i < map_size; i++, entry++) {
- unsigned long s_pfn;
- unsigned long e_pfn;
- unsigned long pfns;
- long capacity;
+ WARN_ON(size == 0);
- if (credits_left <= 0)
- break;
+ BUG_ON(xen_feature(XENFEAT_auto_translated_physmap));
- if (entry->type != E820_RAM)
- continue;
+ mfn_save = virt_to_mfn(buf);
- e_pfn = PFN_DOWN(entry->addr + entry->size);
+ for (ident_pfn_iter = start_pfn, remap_pfn_iter = remap_pfn;
+ ident_pfn_iter < ident_end_pfn;
+ ident_pfn_iter += REMAP_SIZE, remap_pfn_iter += REMAP_SIZE) {
+ chunk = (left < REMAP_SIZE) ? left : REMAP_SIZE;
- /* We only care about E820 after the xen_start_info->nr_pages */
- if (e_pfn <= max_pfn)
- continue;
+ /* Map first pfn to xen_remap_buf */
+ mfn = pfn_to_mfn(ident_pfn_iter);
+ set_pte_mfn(buf, mfn, PAGE_KERNEL);
- s_pfn = PFN_UP(entry->addr);
- /* If the E820 falls within the nr_pages, we want to start
- * at the nr_pages PFN.
- * If that would mean going past the E820 entry, skip it
- */
- if (s_pfn <= max_pfn) {
- capacity = e_pfn - max_pfn;
- dest_pfn = max_pfn;
- } else {
- capacity = e_pfn - s_pfn;
- dest_pfn = s_pfn;
- }
+ /* Save mapping information in page */
+ xen_remap_buf.next_area_mfn = xen_remap_mfn;
+ xen_remap_buf.target_pfn = remap_pfn_iter;
+ xen_remap_buf.size = chunk;
+ for (i = 0; i < chunk; i++)
+ xen_remap_buf.mfns[i] = pfn_to_mfn(ident_pfn_iter + i);
- if (credits_left < capacity)
- capacity = credits_left;
+ /* Put remap buf into list. */
+ xen_remap_mfn = mfn;
- pfns = xen_do_chunk(dest_pfn, dest_pfn + capacity, false);
- done += pfns;
- *last_pfn = (dest_pfn + pfns);
- if (pfns < capacity)
- break;
- credits_left -= pfns;
+ /* Set identity map */
+ ident_cnt += set_phys_range_identity(ident_pfn_iter,
+ ident_pfn_iter + chunk);
+
+ left -= chunk;
}
- return done;
+
+ /* Restore old xen_remap_buf mapping */
+ set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
}
-static void __init xen_set_identity_and_release_chunk(
- unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
- unsigned long *released, unsigned long *identity)
+/*
+ * This function takes a contiguous pfn range that needs to be identity mapped
+ * and:
+ *
+ * 1) Finds a new range of pfns to use to remap based on E820 and remap_pfn.
+ * 2) Calls the do_ function to actually do the mapping/remapping work.
+ *
+ * The goal is to not allocate additional memory but to remap the existing
+ * pages. In the case of an error the underlying memory is simply released back
+ * to Xen and not remapped.
+ */
+static unsigned long __init xen_set_identity_and_remap_chunk(
+ const struct e820entry *list, size_t map_size, unsigned long start_pfn,
+ unsigned long end_pfn, unsigned long nr_pages, unsigned long remap_pfn,
+ unsigned long *identity, unsigned long *released)
{
unsigned long pfn;
+ unsigned long i = 0;
+ unsigned long n = end_pfn - start_pfn;
+
+ while (i < n) {
+ unsigned long cur_pfn = start_pfn + i;
+ unsigned long left = n - i;
+ unsigned long size = left;
+ unsigned long remap_range_size;
+
+ /* Do not remap pages beyond the current allocation */
+ if (cur_pfn >= nr_pages) {
+ /* Identity map remaining pages */
+ *identity += set_phys_range_identity(cur_pfn,
+ cur_pfn + size);
+ break;
+ }
+ if (cur_pfn + size > nr_pages)
+ size = nr_pages - cur_pfn;
+
+ remap_range_size = xen_find_pfn_range(list, map_size,
+ &remap_pfn);
+ if (!remap_range_size) {
+ pr_warning("Unable to find available pfn range, not remapping identity pages\n");
+ xen_set_identity_and_release_chunk(cur_pfn,
+ cur_pfn + left, nr_pages, identity, released);
+ break;
+ }
+ /* Adjust size to fit in current e820 RAM region */
+ if (size > remap_range_size)
+ size = remap_range_size;
- /*
- * If the PFNs are currently mapped, clear the mappings
- * (except for the ISA region which must be 1:1 mapped) to
- * release the refcounts (in Xen) on the original frames.
- */
- for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
- pte_t pte = __pte_ma(0);
-
- if (pfn < PFN_UP(ISA_END_ADDRESS))
- pte = mfn_pte(pfn, PAGE_KERNEL_IO);
+ xen_do_set_identity_and_remap_chunk(cur_pfn, size, remap_pfn);
- (void)HYPERVISOR_update_va_mapping(
- (unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
+ /* Update variables to reflect new mappings. */
+ i += size;
+ remap_pfn += size;
+ *identity += size;
}
- if (start_pfn < nr_pages)
- *released += xen_release_chunk(
- start_pfn, min(end_pfn, nr_pages));
+ /*
+ * If the PFNs are currently mapped, the VA mapping also needs
+ * to be updated to be 1:1.
+ */
+ for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+ (void)HYPERVISOR_update_va_mapping(
+ (unsigned long)__va(pfn << PAGE_SHIFT),
+ mfn_pte(pfn, PAGE_KERNEL_IO), 0);
- *identity += set_phys_range_identity(start_pfn, end_pfn);
+ return remap_pfn;
}
-static unsigned long __init xen_set_identity_and_release(
- const struct e820entry *list, size_t map_size, unsigned long nr_pages)
+static void __init xen_set_identity_and_remap(
+ const struct e820entry *list, size_t map_size, unsigned long nr_pages,
+ unsigned long *released)
{
phys_addr_t start = 0;
- unsigned long released = 0;
unsigned long identity = 0;
+ unsigned long last_pfn = nr_pages;
const struct e820entry *entry;
+ unsigned long num_released = 0;
int i;
/*
* Combine non-RAM regions and gaps until a RAM region (or the
* end of the map) is reached, then set the 1:1 map and
- * release the pages (if available) in those non-RAM regions.
+ * remap the memory in those non-RAM regions.
*
* The combined non-RAM regions are rounded to a whole number
* of pages so any partial pages are accessible via the 1:1
@@ -269,20 +457,72 @@ static unsigned long __init xen_set_identity_and_release(
end_pfn = PFN_UP(entry->addr);
if (start_pfn < end_pfn)
- xen_set_identity_and_release_chunk(
- start_pfn, end_pfn, nr_pages,
- &released, &identity);
-
+ last_pfn = xen_set_identity_and_remap_chunk(
+ list, map_size, start_pfn,
+ end_pfn, nr_pages, last_pfn,
+ &identity, &num_released);
start = end;
}
}
- if (released)
- printk(KERN_INFO "Released %lu pages of unused memory\n", released);
- if (identity)
- printk(KERN_INFO "Set %ld page(s) to 1-1 mapping\n", identity);
+ *released = num_released;
- return released;
+ pr_info("Set %ld page(s) to 1-1 mapping\n", identity);
+ pr_info("Released %ld page(s)\n", num_released);
+}
+
+/*
+ * Remap the memory prepared in xen_do_set_identity_and_remap_chunk().
+ * The remap information (which mfn remap to which pfn) is contained in the
+ * to be remapped memory itself in a linked list anchored at xen_remap_mfn.
+ * This scheme allows to remap the different chunks in arbitrary order while
+ * the resulting mapping will be independant from the order.
+ */
+void __init xen_remap_memory(void)
+{
+ unsigned long buf = (unsigned long)&xen_remap_buf;
+ unsigned long mfn_save, mfn, pfn;
+ unsigned long remapped = 0;
+ unsigned int i;
+ unsigned long pfn_s = ~0UL;
+ unsigned long len = 0;
+
+ mfn_save = virt_to_mfn(buf);
+
+ while (xen_remap_mfn != INVALID_P2M_ENTRY) {
+ /* Map the remap information */
+ set_pte_mfn(buf, xen_remap_mfn, PAGE_KERNEL);
+
+ BUG_ON(xen_remap_mfn != xen_remap_buf.mfns[0]);
+
+ pfn = xen_remap_buf.target_pfn;
+ for (i = 0; i < xen_remap_buf.size; i++) {
+ mfn = xen_remap_buf.mfns[i];
+ xen_update_mem_tables(pfn, mfn);
+ remapped++;
+ pfn++;
+ }
+ if (pfn_s == ~0UL || pfn == pfn_s) {
+ pfn_s = xen_remap_buf.target_pfn;
+ len += xen_remap_buf.size;
+ } else if (pfn_s + len == xen_remap_buf.target_pfn) {
+ len += xen_remap_buf.size;
+ } else {
+ xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+ pfn_s = xen_remap_buf.target_pfn;
+ len = xen_remap_buf.size;
+ }
+
+ mfn = xen_remap_mfn;
+ xen_remap_mfn = xen_remap_buf.next_area_mfn;
+ }
+
+ if (pfn_s != ~0UL && len)
+ xen_del_extra_mem(PFN_PHYS(pfn_s), PFN_PHYS(len));
+
+ set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
+
+ pr_info("Remapped %ld page(s)\n", remapped);
}
static unsigned long __init xen_get_max_pages(void)
@@ -345,9 +585,7 @@ char * __init xen_memory_setup(void)
int rc;
struct xen_memory_map memmap;
unsigned long max_pages;
- unsigned long last_pfn = 0;
unsigned long extra_pages = 0;
- unsigned long populated;
int i;
int op;
@@ -372,6 +610,7 @@ char * __init xen_memory_setup(void)
rc = 0;
}
BUG_ON(rc);
+ BUG_ON(memmap.nr_entries == 0);
/*
* Xen won't allow a 1:1 mapping to be created to UNUSABLE
@@ -392,26 +631,14 @@ char * __init xen_memory_setup(void)
extra_pages += max_pages - max_pfn;
/*
- * Set P2M for all non-RAM pages and E820 gaps to be identity
- * type PFNs. Any RAM pages that would be made inaccesible by
- * this are first released.
+ * Set identity map on non-RAM pages and prepare remapping the
+ * underlying RAM.
*/
- xen_released_pages = xen_set_identity_and_release(
- map, memmap.nr_entries, max_pfn);
-
- /*
- * Populate back the non-RAM pages and E820 gaps that had been
- * released. */
- populated = xen_populate_chunk(map, memmap.nr_entries,
- max_pfn, &last_pfn, xen_released_pages);
+ xen_set_identity_and_remap(map, memmap.nr_entries, max_pfn,
+ &xen_released_pages);
- xen_released_pages -= populated;
extra_pages += xen_released_pages;
- if (last_pfn > max_pfn) {
- max_pfn = min(MAX_DOMAIN_PAGES, last_pfn);
- mem_end = PFN_PHYS(max_pfn);
- }
/*
* Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size. On non-highmem systems, the base
@@ -438,6 +665,7 @@ char * __init xen_memory_setup(void)
size = min(size, (u64)extra_pages * PAGE_SIZE);
extra_pages -= size / PAGE_SIZE;
xen_add_extra_mem(addr, size);
+ xen_max_p2m_pfn = PFN_DOWN(addr + size);
} else
type = E820_UNUSABLE;
}
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 7005974c3ff3..4c071aeb8417 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -37,6 +37,7 @@
#include <xen/hvc-console.h>
#include "xen-ops.h"
#include "mmu.h"
+#include "smp.h"
cpumask_var_t xen_cpu_initialized_map;
@@ -99,10 +100,14 @@ static void cpu_bringup(void)
wmb(); /* make sure everything is out */
}
-/* Note: cpu parameter is only relevant for PVH */
-static void cpu_bringup_and_idle(int cpu)
+/*
+ * Note: cpu parameter is only relevant for PVH. The reason for passing it
+ * is we can't do smp_processor_id until the percpu segments are loaded, for
+ * which we need the cpu number! So we pass it in rdi as first parameter.
+ */
+asmlinkage __visible void cpu_bringup_and_idle(int cpu)
{
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_XEN_PVH
if (xen_feature(XENFEAT_auto_translated_physmap) &&
xen_feature(XENFEAT_supervisor_mode_kernel))
xen_pvh_secondary_vcpu_init(cpu);
@@ -360,6 +365,8 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
struct desc_struct *gdt;
unsigned long gdt_mfn;
+ /* used to tell cpu_init() that it can proceed with initialization */
+ cpumask_set_cpu(cpu, cpu_callout_mask);
if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
return 0;
@@ -374,11 +381,10 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
ctxt->user_regs.fs = __KERNEL_PERCPU;
ctxt->user_regs.gs = __KERNEL_STACK_CANARY;
#endif
- ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
-
memset(&ctxt->fpu_ctxt, 0, sizeof(ctxt->fpu_ctxt));
if (!xen_feature(XENFEAT_auto_translated_physmap)) {
+ ctxt->user_regs.eip = (unsigned long)cpu_bringup_and_idle;
ctxt->flags = VGCF_IN_KERNEL;
ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
ctxt->user_regs.ds = __USER_DS;
@@ -413,15 +419,18 @@ cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
(unsigned long)xen_failsafe_callback;
ctxt->user_regs.cs = __KERNEL_CS;
per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
-#ifdef CONFIG_X86_32
}
-#else
- } else
- /* N.B. The user_regs.eip (cpu_bringup_and_idle) is called with
- * %rdi having the cpu number - which means are passing in
- * as the first parameter the cpu. Subtle!
+#ifdef CONFIG_XEN_PVH
+ else {
+ /*
+ * The vcpu comes on kernel page tables which have the NX pte
+ * bit set. This means before DS/SS is touched, NX in
+ * EFER must be set. Hence the following assembly glue code.
*/
+ ctxt->user_regs.eip = (unsigned long)xen_pvh_early_cpu_init;
ctxt->user_regs.rdi = cpu;
+ ctxt->user_regs.rsi = true; /* entry == true */
+ }
#endif
ctxt->user_regs.esp = idle->thread.sp0 - sizeof(struct pt_regs);
ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_mfn(swapper_pg_dir));
@@ -501,6 +510,9 @@ static void xen_cpu_die(unsigned int cpu)
current->state = TASK_UNINTERRUPTIBLE;
schedule_timeout(HZ/10);
}
+
+ cpu_die_common(cpu);
+
xen_smp_intr_free(cpu);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h
index c7c2d89efd76..963d62a35c82 100644
--- a/arch/x86/xen/smp.h
+++ b/arch/x86/xen/smp.h
@@ -8,4 +8,12 @@ extern void xen_send_IPI_allbutself(int vector);
extern void xen_send_IPI_all(int vector);
extern void xen_send_IPI_self(int vector);
+#ifdef CONFIG_XEN_PVH
+extern void xen_pvh_early_cpu_init(int cpu, bool entry);
+#else
+static inline void xen_pvh_early_cpu_init(int cpu, bool entry)
+{
+}
+#endif
+
#endif
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 0ba5f3b967f0..23b45eb9a89c 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -109,7 +109,7 @@ static bool xen_pvspin = true;
__visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
int irq = __this_cpu_read(lock_kicker_irq);
- struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+ struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
int cpu = smp_processor_id();
u64 start;
unsigned long flags;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 5718b0b58b60..f473d268d387 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -80,7 +80,7 @@ static void get_runstate_snapshot(struct vcpu_runstate_info *res)
BUG_ON(preemptible());
- state = &__get_cpu_var(xen_runstate);
+ state = this_cpu_ptr(&xen_runstate);
/*
* The runstate info is always updated by the hypervisor on
@@ -123,7 +123,7 @@ static void do_stolen_accounting(void)
WARN_ON(state.state != RUNSTATE_running);
- snap = &__get_cpu_var(xen_runstate_snapshot);
+ snap = this_cpu_ptr(&xen_runstate_snapshot);
/* work out how much time the VCPU has not been runn*ing* */
runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
@@ -158,7 +158,7 @@ cycle_t xen_clocksource_read(void)
cycle_t ret;
preempt_disable_notrace();
- src = &__get_cpu_var(xen_vcpu)->time;
+ src = &__this_cpu_read(xen_vcpu)->time;
ret = pvclock_clocksource_read(src);
preempt_enable_notrace();
return ret;
@@ -397,7 +397,7 @@ static DEFINE_PER_CPU(struct xen_clock_event_device, xen_clock_events) = { .evt.
static irqreturn_t xen_timer_interrupt(int irq, void *dev_id)
{
- struct clock_event_device *evt = &__get_cpu_var(xen_clock_events).evt;
+ struct clock_event_device *evt = this_cpu_ptr(&xen_clock_events.evt);
irqreturn_t ret;
ret = IRQ_NONE;
@@ -460,7 +460,7 @@ void xen_setup_cpu_clockevents(void)
{
BUG_ON(preemptible());
- clockevents_register_device(&__get_cpu_var(xen_clock_events).evt);
+ clockevents_register_device(this_cpu_ptr(&xen_clock_events.evt));
}
void xen_timer_resume(void)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 485b69585540..674b222544b7 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -47,6 +47,41 @@ ENTRY(startup_xen)
__FINIT
+#ifdef CONFIG_XEN_PVH
+/*
+ * xen_pvh_early_cpu_init() - early PVH VCPU initialization
+ * @cpu: this cpu number (%rdi)
+ * @entry: true if this is a secondary vcpu coming up on this entry
+ * point, false if this is the boot CPU being initialized for
+ * the first time (%rsi)
+ *
+ * Note: This is called as a function on the boot CPU, and is the entry point
+ * on the secondary CPU.
+ */
+ENTRY(xen_pvh_early_cpu_init)
+ mov %rsi, %r11
+
+ /* Gather features to see if NX implemented. */
+ mov $0x80000001, %eax
+ cpuid
+ mov %edx, %esi
+
+ mov $MSR_EFER, %ecx
+ rdmsr
+ bts $_EFER_SCE, %eax
+
+ bt $20, %esi
+ jnc 1f /* No NX, skip setting it */
+ bts $_EFER_NX, %eax
+1: wrmsr
+#ifdef CONFIG_SMP
+ cmp $0, %r11b
+ jne cpu_bringup_and_idle
+#endif
+ ret
+
+#endif /* CONFIG_XEN_PVH */
+
.pushsection .text
.balign PAGE_SIZE
ENTRY(hypercall_page)
@@ -124,6 +159,7 @@ NEXT_HYPERCALL(arch_6)
ELFNOTE(Xen, XEN_ELFNOTE_L1_MFN_VALID,
.quad _PAGE_PRESENT; .quad _PAGE_PRESENT)
ELFNOTE(Xen, XEN_ELFNOTE_SUSPEND_CANCEL, .long 1)
+ ELFNOTE(Xen, XEN_ELFNOTE_MOD_START_PFN, .long 1)
ELFNOTE(Xen, XEN_ELFNOTE_HV_START_LOW, _ASM_PTR __HYPERVISOR_VIRT_START)
ELFNOTE(Xen, XEN_ELFNOTE_PADDR_OFFSET, _ASM_PTR 0)
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 28c7e0be56e4..5686bd9d58cc 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -29,12 +29,13 @@ void xen_build_mfn_list_list(void);
void xen_setup_machphys_mapping(void);
void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
void xen_reserve_top(void);
-extern unsigned long xen_max_p2m_pfn;
void xen_mm_pin_all(void);
void xen_mm_unpin_all(void);
-void xen_set_pat(u64);
+unsigned long __ref xen_chk_extra_mem(unsigned long pfn);
+void __init xen_inv_extra_mem(void);
+void __init xen_remap_memory(void);
char * __init xen_memory_setup(void);
char * xen_auto_xlated_memory_setup(void);
void __init xen_arch_setup(void);
@@ -47,7 +48,7 @@ void xen_hvm_init_shared_info(void);
void xen_unplug_emulated_devices(void);
void __init xen_build_dynamic_phys_to_machine(void);
-unsigned long __init xen_revector_p2m_tree(void);
+void __init xen_vmalloc_p2m_tree(void);
void xen_init_irq_ops(void);
void xen_setup_timer(int cpu);