diff options
499 files changed, 7315 insertions, 2595 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst index b2598cc9834c..7242cbda15dd 100644 --- a/Documentation/admin-guide/kernel-parameters.rst +++ b/Documentation/admin-guide/kernel-parameters.rst @@ -109,6 +109,7 @@ parameter is applicable:: IPV6 IPv6 support is enabled. ISAPNP ISA PnP code is enabled. ISDN Appropriate ISDN support is enabled. + ISOL CPU Isolation is enabled. JOY Appropriate joystick support is enabled. KGDB Kernel debugger support is enabled. KVM Kernel Virtual Machine support is enabled. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6571fbfdb2a1..af7104aaffd9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -328,11 +328,15 @@ not play well with APC CPU idle - disable it if you have APC and your system crashes randomly. - apic= [APIC,X86-32] Advanced Programmable Interrupt Controller + apic= [APIC,X86] Advanced Programmable Interrupt Controller Change the output verbosity whilst booting Format: { quiet (default) | verbose | debug } Change the amount of debugging information output when initialising the APIC and IO-APIC components. + For X86-32, this can also be used to specify an APIC + driver name. + Format: apic=driver_name + Examples: apic=bigsmp apic_extnmi= [APIC,X86] External NMI delivery setting Format: { bsp (default) | all | none } @@ -1737,7 +1741,7 @@ isapnp= [ISAPNP] Format: <RDP>,<reset>,<pci_scan>,<verbosity> - isolcpus= [KNL,SMP] Isolate a given set of CPUs from disturbance. + isolcpus= [KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance. [Deprecated - use cpusets instead] Format: [flag-list,]<cpu-list> @@ -2662,7 +2666,7 @@ Valid arguments: on, off Default: on - nohz_full= [KNL,BOOT] + nohz_full= [KNL,BOOT,SMP,ISOL] The argument is a cpu list, as described above. In kernels built with CONFIG_NO_HZ_FULL=y, set the specified list of CPUs whose tick will be stopped @@ -2708,6 +2712,8 @@ steal time is computed, but won't influence scheduler behaviour + nopti [X86-64] Disable kernel page table isolation + nolapic [X86-32,APIC] Do not enable or use the local APIC. nolapic_timer [X86-32,APIC] Do not use the local APIC timer. @@ -3282,6 +3288,12 @@ pt. [PARIDE] See Documentation/blockdev/paride.txt. + pti= [X86_64] + Control user/kernel address space isolation: + on - enable + off - disable + auto - default setting + pty.legacy_count= [KNL] Number of legacy pty's. Overwrites compiled-in default number. diff --git a/Documentation/admin-guide/thunderbolt.rst b/Documentation/admin-guide/thunderbolt.rst index de50a8561774..9b55952039a6 100644 --- a/Documentation/admin-guide/thunderbolt.rst +++ b/Documentation/admin-guide/thunderbolt.rst @@ -230,7 +230,7 @@ If supported by your machine this will be exposed by the WMI bus with a sysfs attribute called "force_power". For example the intel-wmi-thunderbolt driver exposes this attribute in: - /sys/devices/platform/PNP0C14:00/wmi_bus/wmi_bus-PNP0C14:00/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power + /sys/bus/wmi/devices/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power To force the power to on, write 1 to this attribute file. To disable force power, write 0 to this attribute file. diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt index 376fa2f50e6b..956bb046e599 100644 --- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt +++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt @@ -13,7 +13,6 @@ Required properties: at25df321a at25df641 at26df081a - en25s64 mr25h128 mr25h256 mr25h10 @@ -33,7 +32,6 @@ Required properties: s25fl008k s25fl064k sst25vf040b - sst25wf040b m25p40 m25p80 m25p16 diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt index 5ca5a709b6aa..3ab9dfef38d1 100644 --- a/Documentation/devicetree/bindings/sound/da7218.txt +++ b/Documentation/devicetree/bindings/sound/da7218.txt @@ -73,7 +73,7 @@ Example: compatible = "dlg,da7218"; reg = <0x1a>; interrupt-parent = <&gpio6>; - interrupts = <11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; wakeup-source; VDD-supply = <®_audio>; diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt index cf61681826b6..5b54d2d045c3 100644 --- a/Documentation/devicetree/bindings/sound/da7219.txt +++ b/Documentation/devicetree/bindings/sound/da7219.txt @@ -77,7 +77,7 @@ Example: reg = <0x1a>; interrupt-parent = <&gpio6>; - interrupts = <11 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; VDD-supply = <®_audio>; VDDMIC-supply = <®_audio>; diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt index 5bf13960f7f4..e3c48b20b1a6 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt @@ -12,24 +12,30 @@ Required properties: - "fsl,imx53-ecspi" for SPI compatible with the one integrated on i.MX53 and later Soc - reg : Offset and length of the register set for the device - interrupts : Should contain CSPI/eCSPI interrupt -- cs-gpios : Specifies the gpio pins to be used for chipselects. - clocks : Clock specifiers for both ipg and per clocks. - clock-names : Clock names should include both "ipg" and "per" See the clock consumer binding, Documentation/devicetree/bindings/clock/clock-bindings.txt -- dmas: DMA specifiers for tx and rx dma. See the DMA client binding, - Documentation/devicetree/bindings/dma/dma.txt -- dma-names: DMA request names should include "tx" and "rx" if present. -Obsolete properties: -- fsl,spi-num-chipselects : Contains the number of the chipselect +Recommended properties: +- cs-gpios : GPIOs to use as chip selects, see spi-bus.txt. While the native chip +select lines can be used, they appear to always generate a pulse between each +word of a transfer. Most use cases will require GPIO based chip selects to +generate a valid transaction. Optional properties: +- num-cs : Number of total chip selects, see spi-bus.txt. +- dmas: DMA specifiers for tx and rx dma. See the DMA client binding, +Documentation/devicetree/bindings/dma/dma.txt. +- dma-names: DMA request names, if present, should include "tx" and "rx". - fsl,spi-rdy-drctl: Integer, representing the value of DRCTL, the register controlling the SPI_READY handling. Note that to enable the DRCTL consideration, the SPI_READY mode-flag needs to be set too. Valid values are: 0 (disabled), 1 (edge-triggered burst) and 2 (level-triggered burst). +Obsolete properties: +- fsl,spi-num-chipselects : Contains the number of the chipselect + Example: ecspi@70010000 { diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 3448e675b462..ad41b3813f0a 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -1,6 +1,4 @@ -<previous description obsolete, deleted> - Virtual memory map with 4 level page tables: 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm @@ -14,13 +12,16 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) ... unused hole ... ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB) ... unused hole ... +fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI +fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ... unused hole ... ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space ... unused hole ... ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0 -ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable) -ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls +ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space (variable) +[fixmap start] - ffffffffff5fffff kernel-internal fixmap range +ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole Virtual memory map with 5 level page tables: @@ -29,26 +30,29 @@ Virtual memory map with 5 level page tables: hole caused by [56:63] sign extension ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory -ff90000000000000 - ff91ffffffffffff (=49 bits) hole -ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space +ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI +ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB) ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB) ... unused hole ... ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB) ... unused hole ... +fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ... unused hole ... ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space ... unused hole ... ffffffff80000000 - ffffffff9fffffff (=512 MB) kernel text mapping, from phys 0 -ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space -ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls +ffffffffa0000000 - [fixmap start] (~1526 MB) module mapping space +[fixmap start] - ffffffffff5fffff kernel-internal fixmap range +ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole Architecture defines a 64-bit virtual address. Implementations can support less. Currently supported are 48- and 57-bit virtual addresses. Bits 63 -through to the most-significant implemented bit are set to either all ones -or all zero. This causes hole between user space and kernel addresses. +through to the most-significant implemented bit are sign extended. +This causes hole between user space and kernel addresses if you interpret them +as unsigned. The direct mapping covers all memory in the system up to the highest memory address (this means in some cases it can also include PCI memory @@ -58,9 +62,6 @@ vmalloc space is lazily synchronized into the different PML4/PML5 pages of the processes using the page fault handler, with init_top_pgt as reference. -Current X86-64 implementations support up to 46 bits of address space (64 TB), -which is our current limit. This expands into MBZ space in the page tables. - We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual memory window (this size is arbitrary, it can be raised later if needed). The mappings are not part of any other kernel PGD and are only available @@ -72,5 +73,3 @@ following fixmap section. Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all physical memory, vmalloc/ioremap space and virtual memory map are randomized. Their order is preserved but their base will be offset early at boot time. - --Andi Kleen, Jul 2004 diff --git a/MAINTAINERS b/MAINTAINERS index a6e86e20761e..b46c9cea5ae5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2621,24 +2621,22 @@ F: fs/bfs/ F: include/uapi/linux/bfs_fs.h BLACKFIN ARCHITECTURE -M: Steven Miao <realmz6@gmail.com> L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) T: git git://git.code.sf.net/p/adi-linux/code W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: arch/blackfin/ BLACKFIN EMAC DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/net/ethernet/adi/ BLACKFIN MEDIA DRIVER -M: Scott Jiang <scott.jiang.linux@gmail.com> L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org/ -S: Supported +S: Orphan F: drivers/media/platform/blackfin/ F: drivers/media/i2c/adv7183* F: drivers/media/i2c/vs6624* @@ -2646,25 +2644,25 @@ F: drivers/media/i2c/vs6624* BLACKFIN RTC DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/rtc/rtc-bfin.c BLACKFIN SDH DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/mmc/host/bfin_sdh.c BLACKFIN SERIAL DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/tty/serial/bfin_uart.c BLACKFIN WATCHDOG DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/watchdog/bfin_wdt.c BLINKM RGB LED DRIVER @@ -13493,6 +13491,7 @@ M: Mika Westerberg <mika.westerberg@linux.intel.com> M: Yehezkel Bernat <yehezkel.bernat@intel.com> T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git S: Maintained +F: Documentation/admin-guide/thunderbolt.rst F: drivers/thunderbolt/ F: include/linux/thunderbolt.h @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Fearless Coyote # *DOCUMENTATION* @@ -789,6 +789,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign) # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) +# Make sure -fstack-check isn't enabled (like gentoo apparently did) +KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,) + # conserve stack if available KBUILD_CFLAGS += $(call cc-option,-fconserve-stack) diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S index 1712f132b80d..b83fdc06286a 100644 --- a/arch/arm/lib/csumpartialcopyuser.S +++ b/arch/arm/lib/csumpartialcopyuser.S @@ -85,7 +85,11 @@ .pushsection .text.fixup,"ax" .align 4 9001: mov r4, #-EFAULT +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + ldr r5, [sp, #9*4] @ *err_ptr +#else ldr r5, [sp, #8*4] @ *err_ptr +#endif str r4, [r5] ldmia sp, {r1, r2} @ retrieve dst, len add r2, r2, r1 diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 321c9c05dd9e..f4363d40e2cd 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -74,6 +74,9 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1) { u64 reg; + /* Clear pmscr in case of early return */ + *pmscr_el1 = 0; + /* SPE present on this CPU? */ if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1), ID_AA64DFR0_PMSVER_SHIFT)) diff --git a/arch/parisc/boot/compressed/misc.c b/arch/parisc/boot/compressed/misc.c index 9345b44b86f0..f57118e1f6b4 100644 --- a/arch/parisc/boot/compressed/misc.c +++ b/arch/parisc/boot/compressed/misc.c @@ -123,8 +123,8 @@ int puts(const char *s) while ((nuline = strchr(s, '\n')) != NULL) { if (nuline != s) pdc_iodc_print(s, nuline - s); - pdc_iodc_print("\r\n", 2); - s = nuline + 1; + pdc_iodc_print("\r\n", 2); + s = nuline + 1; } if (*s != '\0') pdc_iodc_print(s, strlen(s)); diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h index c980a02a52bc..598c8d60fa5e 100644 --- a/arch/parisc/include/asm/thread_info.h +++ b/arch/parisc/include/asm/thread_info.h @@ -35,7 +35,12 @@ struct thread_info { /* thread information allocation */ +#ifdef CONFIG_IRQSTACKS +#define THREAD_SIZE_ORDER 2 /* PA-RISC requires at least 16k stack */ +#else #define THREAD_SIZE_ORDER 3 /* PA-RISC requires at least 32k stack */ +#endif + /* Be sure to hunt all references to this down when you change the size of * the kernel stack */ #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index a4fd296c958e..f3cecf5117cf 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -878,9 +878,6 @@ ENTRY_CFI(syscall_exit_rfi) STREG %r19,PT_SR7(%r16) intr_return: - /* NOTE: Need to enable interrupts incase we schedule. */ - ssm PSW_SM_I, %r0 - /* check for reschedule */ mfctl %cr30,%r1 LDREG TI_FLAGS(%r1),%r19 /* sched.h: TIF_NEED_RESCHED */ @@ -907,6 +904,11 @@ intr_check_sig: LDREG PT_IASQ1(%r16), %r20 cmpib,COND(=),n 0,%r20,intr_restore /* backward */ + /* NOTE: We need to enable interrupts if we have to deliver + * signals. We used to do this earlier but it caused kernel + * stack overflows. */ + ssm PSW_SM_I, %r0 + copy %r0, %r25 /* long in_syscall = 0 */ #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ @@ -958,6 +960,10 @@ intr_do_resched: cmpib,COND(=) 0, %r20, intr_do_preempt nop + /* NOTE: We need to enable interrupts if we schedule. We used + * to do this earlier but it caused kernel stack overflows. */ + ssm PSW_SM_I, %r0 + #ifdef CONFIG_64BIT ldo -16(%r30),%r29 /* Reference param save area */ #endif diff --git a/arch/parisc/kernel/hpmc.S b/arch/parisc/kernel/hpmc.S index e3a8e5e4d5de..8d072c44f300 100644 --- a/arch/parisc/kernel/hpmc.S +++ b/arch/parisc/kernel/hpmc.S @@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc) __INITRODATA + .align 4 .export os_hpmc_size os_hpmc_size: .word .os_hpmc_end-.os_hpmc diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c index 5a657986ebbf..143f90e2f9f3 100644 --- a/arch/parisc/kernel/unwind.c +++ b/arch/parisc/kernel/unwind.c @@ -15,7 +15,6 @@ #include <linux/slab.h> #include <linux/kallsyms.h> #include <linux/sort.h> -#include <linux/sched.h> #include <linux/uaccess.h> #include <asm/assembly.h> diff --git a/arch/parisc/lib/delay.c b/arch/parisc/lib/delay.c index 7eab4bb8abe6..66e506520505 100644 --- a/arch/parisc/lib/delay.c +++ b/arch/parisc/lib/delay.c @@ -16,9 +16,7 @@ #include <linux/preempt.h> #include <linux/init.h> -#include <asm/processor.h> #include <asm/delay.h> - #include <asm/special_insns.h> /* for mfctl() */ #include <asm/processor.h> /* for boot_cpu_data */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 6177d43f0ce8..e2a2b8400490 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -160,9 +160,10 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, #endif } -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) { + return 0; } #ifndef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 5acb5a176dbe..72be0c32e902 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1403,7 +1403,7 @@ void show_regs(struct pt_regs * regs) printk("NIP: "REG" LR: "REG" CTR: "REG"\n", regs->nip, regs->link, regs->ctr); - printk("REGS: %p TRAP: %04lx %s (%s)\n", + printk("REGS: %px TRAP: %04lx %s (%s)\n", regs, regs->trap, print_tainted(), init_utsname()->release); printk("MSR: "REG" ", regs->msr); print_msr_bits(regs->msr); diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index bf457843e032..0d750d274c4e 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -725,7 +725,8 @@ u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu) /* Return the per-cpu state for state saving/migration */ return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT | - (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT; + (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT | + (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT; } int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) @@ -1558,7 +1559,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) /* * Restore P and Q. If the interrupt was pending, we - * force both P and Q, which will trigger a resend. + * force Q and !P, which will trigger a resend. * * That means that a guest that had both an interrupt * pending (queued) and Q set will restore with only @@ -1566,7 +1567,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr) * is perfectly fine as coalescing interrupts that haven't * been presented yet is always allowed. */ - if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING) + if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING)) state->old_p = true; if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING) state->old_q = true; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 46d74e81aff1..d183b4801bdb 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -763,7 +763,8 @@ emit_clear: func = (u8 *) __bpf_call_base + imm; /* Save skb pointer if we need to re-cache skb data */ - if (bpf_helper_changes_pkt_data(func)) + if ((ctx->seen & SEEN_SKB) && + bpf_helper_changes_pkt_data(func)) PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_func_call(image, ctx, (u64)func); @@ -772,7 +773,8 @@ emit_clear: PPC_MR(b2p[BPF_REG_0], 3); /* refresh skb cache */ - if (bpf_helper_changes_pkt_data(func)) { + if ((ctx->seen & SEEN_SKB) && + bpf_helper_changes_pkt_data(func)) { /* reload skb pointer to r3 */ PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx)); bpf_jit_emit_skb_loads(image, ctx); diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 153812966365..fce545774d50 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -410,8 +410,12 @@ static __u64 power_pmu_bhrb_to(u64 addr) int ret; __u64 target; - if (is_kernel_addr(addr)) - return branch_target((unsigned int *)addr); + if (is_kernel_addr(addr)) { + if (probe_kernel_read(&instr, (void *)addr, sizeof(instr))) + return 0; + + return branch_target(&instr); + } /* Userspace: need copy instruction here then translate it */ pagefault_disable(); diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 0ead3cd73caa..be4e7f84f70a 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -310,6 +310,19 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu) return 0; /* + * Check whether nest_imc is registered. We could end up here if the + * cpuhotplug callback registration fails. i.e, callback invokes the + * offline path for all successfully registered nodes. At this stage, + * nest_imc pmu will not be registered and we should return here. + * + * We return with a zero since this is not an offline failure. And + * cpuhp_setup_state() returns the actual failure reason to the caller, + * which in turn will call the cleanup routine. + */ + if (!nest_pmus) + return 0; + + /* * Now that this cpu is one of the designated, * find a next cpu a) which is online and b) in same chip. */ @@ -1171,6 +1184,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) if (nest_pmus == 1) { cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE); kfree(nest_imc_refc); + kfree(per_nest_pmu_arr); } if (nest_pmus > 0) @@ -1195,7 +1209,6 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr) kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs); kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]); kfree(pmu_ptr); - kfree(per_nest_pmu_arr); return; } @@ -1309,6 +1322,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id ret = nest_pmu_cpumask_init(); if (ret) { mutex_unlock(&nest_init_lock); + kfree(nest_imc_refc); + kfree(per_nest_pmu_arr); goto err_free; } } diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 44cbf4c12ea1..df95102e732c 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -354,6 +354,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev) } static struct lock_class_key fsl_msi_irq_class; +static struct lock_class_key fsl_msi_irq_request_class; static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev, int offset, int irq_index) @@ -373,7 +374,8 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev, dev_err(&dev->dev, "No memory for MSI cascade data\n"); return -ENOMEM; } - irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class); + irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class, + &fsl_msi_irq_request_class); cascade_data->index = offset; cascade_data->msi_data = msi; cascade_data->virq = virt_msir; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index e81c16838b90..9557d8b516df 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -55,8 +55,7 @@ struct bpf_jit { #define SEEN_LITERAL 8 /* code uses literals */ #define SEEN_FUNC 16 /* calls C functions */ #define SEEN_TAIL_CALL 32 /* code uses tail calls */ -#define SEEN_SKB_CHANGE 64 /* code changes skb data */ -#define SEEN_REG_AX 128 /* code uses constant blinding */ +#define SEEN_REG_AX 64 /* code uses constant blinding */ #define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB) /* @@ -448,12 +447,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, 152); } - if (jit->seen & SEEN_SKB) + if (jit->seen & SEEN_SKB) { emit_load_skb_data_hlen(jit); - if (jit->seen & SEEN_SKB_CHANGE) /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15, STK_OFF_SKBP); + } } /* @@ -983,8 +982,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT2(0x0d00, REG_14, REG_W1); /* lgr %b0,%r2: load return value into %b0 */ EMIT4(0xb9040000, BPF_REG_0, REG_2); - if (bpf_helper_changes_pkt_data((void *)func)) { - jit->seen |= SEEN_SKB_CHANGE; + if ((jit->seen & SEEN_SKB) && + bpf_helper_changes_pkt_data((void *)func)) { /* lg %b1,ST_OFF_SKBP(%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0, REG_15, STK_OFF_SKBP); diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S index e5547b22cd18..0ddbbb031822 100644 --- a/arch/sparc/lib/hweight.S +++ b/arch/sparc/lib/hweight.S @@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32) .previous ENTRY(__arch_hweight64) - sethi %hi(__sw_hweight16), %g1 - jmpl %g1 + %lo(__sw_hweight16), %g0 + sethi %hi(__sw_hweight64), %g1 + jmpl %g1 + %lo(__sw_hweight64), %g0 nop ENDPROC(__arch_hweight64) EXPORT_SYMBOL(__arch_hweight64) diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index be3136f142a9..a8103a84b4ac 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->pc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 815c03d7a765..41363f46797b 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->tpc, (void *)regs->u_regs[UREG_I7], diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 5765e7e711f7..ff5f9cb3039a 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -1245,14 +1245,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) u8 *func = ((u8 *)__bpf_call_base) + imm; ctx->saw_call = true; + if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func)) + emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx); emit_call((u32 *)func, ctx); emit_nop(ctx); emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx); - if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind) - load_skb_regs(ctx, bpf2sparc[BPF_REG_6]); + if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func)) + load_skb_regs(ctx, L7); break; } diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h index b668e351fd6c..fca34b2177e2 100644 --- a/arch/um/include/asm/mmu_context.h +++ b/arch/um/include/asm/mmu_context.h @@ -15,9 +15,10 @@ extern void uml_setup_stubs(struct mm_struct *mm); /* * Needed since we do not use the asm-generic/mm_hooks.h: */ -static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { uml_setup_stubs(mm); + return 0; } extern void arch_exit_mmap(struct mm_struct *mm); static inline void arch_unmap(struct mm_struct *mm, diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index 4e6fcb32620f..428644175956 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs) if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi), (void *)UPT_IP(regs), (void *)UPT_SP(regs), diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index 59b06b48f27d..5c205a9cb5a6 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -81,9 +81,10 @@ do { \ } \ } while (0) -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) { + return 0; } static inline void arch_unmap(struct mm_struct *mm, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 8eed3f94bfc7..d4fc98c50378 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -926,7 +926,8 @@ config MAXSMP config NR_CPUS int "Maximum number of CPUs" if SMP && !MAXSMP range 2 8 if SMP && X86_32 && !X86_BIGSMP - range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK + range 2 64 if SMP && X86_32 && X86_BIGSMP + range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64 range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64 default "1" if !SMP default "8192" if MAXSMP diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c index d5364ca2e3f9..b5e5e02f8cde 100644 --- a/arch/x86/boot/compressed/pagetable.c +++ b/arch/x86/boot/compressed/pagetable.c @@ -23,6 +23,9 @@ */ #undef CONFIG_AMD_MEM_ENCRYPT +/* No PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_PAGE_TABLE_ISOLATION + #include "misc.h" /* These actually do the work of building the kernel identity maps. */ diff --git a/arch/x86/boot/genimage.sh b/arch/x86/boot/genimage.sh index c9e8499fbfe7..6a10d52a4145 100644 --- a/arch/x86/boot/genimage.sh +++ b/arch/x86/boot/genimage.sh @@ -80,39 +80,43 @@ genfdimage288() { mcopy $FBZIMAGE w:linux } -genisoimage() { +geniso() { tmp_dir=`dirname $FIMAGE`/isoimage rm -rf $tmp_dir mkdir $tmp_dir - for i in lib lib64 share end ; do + for i in lib lib64 share ; do for j in syslinux ISOLINUX ; do if [ -f /usr/$i/$j/isolinux.bin ] ; then isolinux=/usr/$i/$j/isolinux.bin - cp $isolinux $tmp_dir fi done for j in syslinux syslinux/modules/bios ; do if [ -f /usr/$i/$j/ldlinux.c32 ]; then ldlinux=/usr/$i/$j/ldlinux.c32 - cp $ldlinux $tmp_dir fi done if [ -n "$isolinux" -a -n "$ldlinux" ] ; then break fi - if [ $i = end -a -z "$isolinux" ] ; then - echo 'Need an isolinux.bin file, please install syslinux/isolinux.' - exit 1 - fi done + if [ -z "$isolinux" ] ; then + echo 'Need an isolinux.bin file, please install syslinux/isolinux.' + exit 1 + fi + if [ -z "$ldlinux" ] ; then + echo 'Need an ldlinux.c32 file, please install syslinux/isolinux.' + exit 1 + fi + cp $isolinux $tmp_dir + cp $ldlinux $tmp_dir cp $FBZIMAGE $tmp_dir/linux echo "$KCMDLINE" > $tmp_dir/isolinux.cfg if [ -f "$FDINITRD" ] ; then cp "$FDINITRD" $tmp_dir/initrd.img fi - mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \ - -c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \ - $tmp_dir + genisoimage -J -r -input-charset=utf-8 -quiet -o $FIMAGE \ + -b isolinux.bin -c boot.cat -no-emul-boot -boot-load-size 4 \ + -boot-info-table $tmp_dir isohybrid $FIMAGE 2>/dev/null || true rm -rf $tmp_dir } @@ -121,6 +125,6 @@ case $1 in bzdisk) genbzdisk;; fdimage144) genfdimage144;; fdimage288) genfdimage288;; - isoimage) genisoimage;; + isoimage) geniso;; *) echo 'Unknown image format'; exit 1; esac diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3fd8bc560fae..45a63e00a6af 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,6 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/jump_label.h> #include <asm/unwind_hints.h> +#include <asm/cpufeatures.h> +#include <asm/page_types.h> +#include <asm/percpu.h> +#include <asm/asm-offsets.h> +#include <asm/processor-flags.h> /* @@ -187,6 +192,146 @@ For 32-bit we have the following conventions - kernel is built with #endif .endm +#ifdef CONFIG_PAGE_TABLE_ISOLATION + +/* + * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two + * halves: + */ +#define PTI_SWITCH_PGTABLES_MASK (1<<PAGE_SHIFT) +#define PTI_SWITCH_MASK (PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT)) + +.macro SET_NOFLUSH_BIT reg:req + bts $X86_CR3_PCID_NOFLUSH_BIT, \reg +.endm + +.macro ADJUST_KERNEL_CR3 reg:req + ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID + /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ + andq $(~PTI_SWITCH_MASK), \reg +.endm + +.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + mov %cr3, \scratch_reg + ADJUST_KERNEL_CR3 \scratch_reg + mov \scratch_reg, %cr3 +.Lend_\@: +.endm + +#define THIS_CPU_user_pcid_flush_mask \ + PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask + +.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + mov %cr3, \scratch_reg + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID + + /* + * Test if the ASID needs a flush. + */ + movq \scratch_reg, \scratch_reg2 + andq $(0x7FF), \scratch_reg /* mask ASID */ + bt \scratch_reg, THIS_CPU_user_pcid_flush_mask + jnc .Lnoflush_\@ + + /* Flush needed, clear the bit */ + btr \scratch_reg, THIS_CPU_user_pcid_flush_mask + movq \scratch_reg2, \scratch_reg + jmp .Lwrcr3_\@ + +.Lnoflush_\@: + movq \scratch_reg2, \scratch_reg + SET_NOFLUSH_BIT \scratch_reg + +.Lwrcr3_\@: + /* Flip the PGD and ASID to the user version */ + orq $(PTI_SWITCH_MASK), \scratch_reg + mov \scratch_reg, %cr3 +.Lend_\@: +.endm + +.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req + pushq %rax + SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax + popq %rax +.endm + +.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req + ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI + movq %cr3, \scratch_reg + movq \scratch_reg, \save_reg + /* + * Is the "switch mask" all zero? That means that both of + * these are zero: + * + * 1. The user/kernel PCID bit, and + * 2. The user/kernel "bit" that points CR3 to the + * bottom half of the 8k PGD + * + * That indicates a kernel CR3 value, not a user CR3. + */ + testq $(PTI_SWITCH_MASK), \scratch_reg + jz .Ldone_\@ + + ADJUST_KERNEL_CR3 \scratch_reg + movq \scratch_reg, %cr3 + +.Ldone_\@: +.endm + +.macro RESTORE_CR3 scratch_reg:req save_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID + + /* + * KERNEL pages can always resume with NOFLUSH as we do + * explicit flushes. + */ + bt $X86_CR3_PTI_SWITCH_BIT, \save_reg + jnc .Lnoflush_\@ + + /* + * Check if there's a pending flush for the user ASID we're + * about to set. + */ + movq \save_reg, \scratch_reg + andq $(0x7FF), \scratch_reg + bt \scratch_reg, THIS_CPU_user_pcid_flush_mask + jnc .Lnoflush_\@ + + btr \scratch_reg, THIS_CPU_user_pcid_flush_mask + jmp .Lwrcr3_\@ + +.Lnoflush_\@: + SET_NOFLUSH_BIT \save_reg + +.Lwrcr3_\@: + /* + * The CR3 write could be avoided when not changing its value, + * but would require a CR3 read *and* a scratch register. + */ + movq \save_reg, %cr3 +.Lend_\@: +.endm + +#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */ + +.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req +.endm +.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req +.endm +.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req +.endm +.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req +.endm +.macro RESTORE_CR3 scratch_reg:req save_reg:req +.endm + +#endif + #endif /* CONFIG_X86_64 */ /* diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4838037f97f6..ace8f321a5a1 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -941,9 +941,10 @@ ENTRY(debug) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) - subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ - cmpl $SIZEOF_SYSENTER_stack, %ecx + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx + subl %eax, %ecx /* ecx = (end of entry_stack) - esp */ + cmpl $SIZEOF_entry_stack, %ecx jb .Ldebug_from_sysenter_stack TRACE_IRQS_OFF @@ -984,9 +985,10 @@ ENTRY(nmi) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) - subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ - cmpl $SIZEOF_SYSENTER_stack, %ecx + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx + subl %eax, %ecx /* ecx = (end of entry_stack) - esp */ + cmpl $SIZEOF_entry_stack, %ecx jb .Lnmi_from_sysenter_stack /* Not on SYSENTER stack. */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f81d50d7ceac..f048e384ff54 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -23,7 +23,6 @@ #include <asm/segment.h> #include <asm/cache.h> #include <asm/errno.h> -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/msr.h> #include <asm/unistd.h> @@ -40,6 +39,8 @@ #include <asm/frame.h> #include <linux/err.h> +#include "calling.h" + .code64 .section .entry.text, "ax" @@ -140,6 +141,67 @@ END(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ + .pushsection .entry_trampoline, "ax" + +/* + * The code in here gets remapped into cpu_entry_area's trampoline. This means + * that the assembler and linker have the wrong idea as to where this code + * lives (and, in fact, it's mapped more than once, so it's not even at a + * fixed address). So we can't reference any symbols outside the entry + * trampoline and expect it to work. + * + * Instead, we carefully abuse %rip-relative addressing. + * _entry_trampoline(%rip) refers to the start of the remapped) entry + * trampoline. We can thus find cpu_entry_area with this macro: + */ + +#define CPU_ENTRY_AREA \ + _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) + +/* The top word of the SYSENTER stack is hot and is usable as scratch space. */ +#define RSP_SCRATCH CPU_ENTRY_AREA_entry_stack + \ + SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA + +ENTRY(entry_SYSCALL_64_trampoline) + UNWIND_HINT_EMPTY + swapgs + + /* Stash the user RSP. */ + movq %rsp, RSP_SCRATCH + + /* Note: using %rsp as a scratch reg. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp + + /* Load the top of the task stack into RSP */ + movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp + + /* Start building the simulated IRET frame. */ + pushq $__USER_DS /* pt_regs->ss */ + pushq RSP_SCRATCH /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + + /* + * x86 lacks a near absolute jump, and we can't jump to the real + * entry text with a relative jump. We could push the target + * address and then use retq, but this destroys the pipeline on + * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead, + * spill RDI and restore it in a second-stage trampoline. + */ + pushq %rdi + movq $entry_SYSCALL_64_stage2, %rdi + jmp *%rdi +END(entry_SYSCALL_64_trampoline) + + .popsection + +ENTRY(entry_SYSCALL_64_stage2) + UNWIND_HINT_EMPTY + popq %rdi + jmp entry_SYSCALL_64_after_hwframe +END(entry_SYSCALL_64_stage2) + ENTRY(entry_SYSCALL_64) UNWIND_HINT_EMPTY /* @@ -149,6 +211,10 @@ ENTRY(entry_SYSCALL_64) */ swapgs + /* + * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it + * is not required to switch CR3. + */ movq %rsp, PER_CPU_VAR(rsp_scratch) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp @@ -330,8 +396,25 @@ syscall_return_via_sysret: popq %rsi /* skip rcx */ popq %rdx popq %rsi + + /* + * Now all regs are restored except RSP and RDI. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + pushq RSP-RDI(%rdi) /* RSP */ + pushq (%rdi) /* RDI */ + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + popq %rdi - movq RSP-ORIG_RAX(%rsp), %rsp + popq %rsp USERGS_SYSRET64 END(entry_SYSCALL_64) @@ -466,12 +549,13 @@ END(irq_entries_start) .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY - pushfq - testl $X86_EFLAGS_IF, (%rsp) + pushq %rax + SAVE_FLAGS(CLBR_RAX) + testl $X86_EFLAGS_IF, %eax jz .Lokay_\@ ud2 .Lokay_\@: - addq $8, %rsp + popq %rax #endif .endm @@ -563,6 +647,13 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + + testb $3, CS-ORIG_RAX(%rsp) + jz 1f + SWAPGS + call switch_to_thread_stack +1: + ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS @@ -572,12 +663,8 @@ END(irq_entries_start) jz 1f /* - * IRQ from user mode. Switch to kernel gsbase and inform context - * tracking that we're in kernel mode. - */ - SWAPGS - - /* + * IRQ from user mode. + * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode * (which can take locks). Since TRACE_IRQS_OFF idempotent, @@ -630,10 +717,43 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - SWAPGS POP_EXTRA_REGS - POP_C_REGS - addq $8, %rsp /* skip regs->orig_ax */ + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + + /* + * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + + /* Copy the IRET frame to the trampoline stack. */ + pushq 6*8(%rdi) /* SS */ + pushq 5*8(%rdi) /* RSP */ + pushq 4*8(%rdi) /* EFLAGS */ + pushq 3*8(%rdi) /* CS */ + pushq 2*8(%rdi) /* RIP */ + + /* Push user RDI on the trampoline stack. */ + pushq (%rdi) + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + + /* Restore RDI. */ + popq %rdi + SWAPGS INTERRUPT_RETURN @@ -713,7 +833,9 @@ native_irq_return_ldt: */ pushq %rdi /* Stash user RDI */ - SWAPGS + SWAPGS /* to kernel GS */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */ + movq PER_CPU_VAR(espfix_waddr), %rdi movq %rax, (0*8)(%rdi) /* user RAX */ movq (1*8)(%rsp), %rax /* user RIP */ @@ -729,7 +851,6 @@ native_irq_return_ldt: /* Now RAX == RSP. */ andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */ - popq %rdi /* Restore user RDI */ /* * espfix_stack[31:16] == 0. The page tables are set up such that @@ -740,7 +861,11 @@ native_irq_return_ldt: * still points to an RO alias of the ESPFIX stack. */ orq PER_CPU_VAR(espfix_stack), %rax - SWAPGS + + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + SWAPGS /* to user GS */ + popq %rdi /* Restore user RDI */ + movq %rax, %rsp UNWIND_HINT_IRET_REGS offset=8 @@ -829,7 +954,35 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) + +/* + * Switch to the thread stack. This is called with the IRET frame and + * orig_ax on the stack. (That is, RDI..R12 are not on the stack and + * space has not been allocated for them.) + */ +ENTRY(switch_to_thread_stack) + UNWIND_HINT_FUNC + + pushq %rdi + /* Need to switch before accessing the thread stack. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi + ret +END(switch_to_thread_stack) .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) @@ -848,11 +1001,12 @@ ENTRY(\sym) ALLOC_PT_GPREGS_ON_STACK - .if \paranoid - .if \paranoid == 1 + .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ - jnz 1f + jnz .Lfrom_usermode_switch_stack_\@ .endif + + .if \paranoid call paranoid_entry .else call error_entry @@ -894,20 +1048,15 @@ ENTRY(\sym) jmp error_exit .endif - .if \paranoid == 1 + .if \paranoid < 2 /* - * Paranoid entry from userspace. Switch stacks and treat it + * Entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ -1: +.Lfrom_usermode_switch_stack_\@: call error_entry - - movq %rsp, %rdi /* pt_regs pointer */ - call sync_regs - movq %rax, %rsp /* switch stack */ - movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code @@ -1119,7 +1268,11 @@ ENTRY(paranoid_entry) js 1f /* negative -> in kernel */ SWAPGS xorl %ebx, %ebx -1: ret + +1: + SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + + ret END(paranoid_entry) /* @@ -1141,6 +1294,7 @@ ENTRY(paranoid_exit) testl %ebx, %ebx /* swapgs needed? */ jnz .Lparanoid_exit_no_swapgs TRACE_IRQS_IRETQ + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 SWAPGS_UNSAFE_STACK jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: @@ -1168,8 +1322,18 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS + /* We have user CR3. Change to kernel CR3. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ + popq %r12 /* save return addr in %12 */ + movq %rsp, %rdi /* arg0 = pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ + ENCODE_FRAME_POINTER + pushq %r12 + /* * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode @@ -1206,6 +1370,7 @@ ENTRY(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done .Lbstep_iret: @@ -1215,10 +1380,11 @@ ENTRY(error_entry) .Lerror_bad_iret: /* - * We came from an IRET to user mode, so we have user gsbase. - * Switch to kernel gsbase: + * We came from an IRET to user mode, so we have user + * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* * Pretend that the exception came from user mode: set up pt_regs @@ -1250,6 +1416,10 @@ END(error_exit) /* * Runs on exception stack. Xen PV does not go through this path at all, * so we can use real assembly here. + * + * Registers: + * %r14: Used to save/restore the CR3 of the interrupted context + * when PAGE_TABLE_ISOLATION is in use. Do not clobber. */ ENTRY(nmi) UNWIND_HINT_IRET_REGS @@ -1313,6 +1483,7 @@ ENTRY(nmi) swapgs cld + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp UNWIND_HINT_IRET_REGS base=%rdx offset=8 @@ -1565,6 +1736,8 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi + RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 + testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 568e130d932c..40f17009ec20 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -48,7 +48,11 @@ */ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ - SWAPGS_UNSAFE_STACK + SWAPGS + + /* We are about to clobber %rsp anyway, clobbering here is OK */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* @@ -216,6 +220,12 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq $0 /* pt_regs->r15 = 0 */ /* + * We just saved %rdi so it is safe to clobber. It is not + * preserved during the C calls inside TRACE_IRQS_OFF anyway. + */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + + /* * User mode is traced as though IRQs are on, and SYSENTER * turned them off. */ @@ -256,10 +266,22 @@ sysret32_from_system_call: * when the system call started, which is already known to user * code. We zero R8-R10 to avoid info leaks. */ + movq RSP-ORIG_RAX(%rsp), %rsp + + /* + * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored + * on the process stack which is not mapped to userspace and + * not readable after we SWITCH_TO_USER_CR3. Delay the CR3 + * switch until after after the last reference to the process + * stack. + * + * %r8/%r9 are zeroed before the sysret, thus safe to clobber. + */ + SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 + xorq %r8, %r8 xorq %r9, %r9 xorq %r10, %r10 - movq RSP-ORIG_RAX(%rsp), %rsp swapgs sysretl END(entry_SYSCALL_compat) @@ -306,8 +328,11 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax - /* Construct struct pt_regs on stack (iret frame is already on stack) */ pushq %rax /* pt_regs->orig_ax */ + + /* switch to thread stack expects orig_ax to be pushed */ + call switch_to_thread_stack + pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index f279ba2643dc..577fa8adb785 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -37,6 +37,7 @@ #include <asm/unistd.h> #include <asm/fixmap.h> #include <asm/traps.h> +#include <asm/paravirt.h> #define CREATE_TRACE_POINTS #include "vsyscall_trace.h" @@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address) WARN_ON_ONCE(address != regs->ip); + /* This should be unreachable in NATIVE mode. */ + if (WARN_ON(vsyscall_mode == NATIVE)) + return false; + if (vsyscall_mode == NONE) { warn_bad_vsyscall(KERN_INFO, regs, "vsyscall attempted with vsyscall=none"); @@ -329,16 +334,47 @@ int in_gate_area_no_mm(unsigned long addr) return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR; } +/* + * The VSYSCALL page is the only user-accessible page in the kernel address + * range. Normally, the kernel page tables can have _PAGE_USER clear, but + * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls + * are enabled. + * + * Some day we may create a "minimal" vsyscall mode in which we emulate + * vsyscalls but leave the page not present. If so, we skip calling + * this. + */ +void __init set_vsyscall_pgtable_user_bits(pgd_t *root) +{ + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset_pgd(root, VSYSCALL_ADDR); + set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER)); + p4d = p4d_offset(pgd, VSYSCALL_ADDR); +#if CONFIG_PGTABLE_LEVELS >= 5 + p4d->p4d |= _PAGE_USER; +#endif + pud = pud_offset(p4d, VSYSCALL_ADDR); + set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER)); + pmd = pmd_offset(pud, VSYSCALL_ADDR); + set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER)); +} + void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - if (vsyscall_mode != NONE) + if (vsyscall_mode != NONE) { __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, vsyscall_mode == NATIVE ? PAGE_KERNEL_VSYSCALL : PAGE_KERNEL_VVAR); + set_vsyscall_pgtable_user_bits(swapper_pg_dir); + } BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != (unsigned long)VSYSCALL_ADDR); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 09c26a4f139c..731153a4681e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3847,6 +3847,8 @@ static struct attribute *intel_pmu_attrs[] = { __init int intel_pmu_init(void) { + struct attribute **extra_attr = NULL; + struct attribute **to_free = NULL; union cpuid10_edx edx; union cpuid10_eax eax; union cpuid10_ebx ebx; @@ -3854,7 +3856,6 @@ __init int intel_pmu_init(void) unsigned int unused; struct extra_reg *er; int version, i; - struct attribute **extra_attr = NULL; char *name; if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) { @@ -4294,6 +4295,7 @@ __init int intel_pmu_init(void) extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; extra_attr = merge_attr(extra_attr, skl_format_attr); + to_free = extra_attr; x86_pmu.cpu_events = get_hsw_events_attrs(); intel_pmu_pebs_data_source_skl( boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X); @@ -4401,6 +4403,7 @@ __init int intel_pmu_init(void) pr_cont("full-width counters, "); } + kfree(to_free); return 0; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 3674a4b6f8bd..8f0aace08b87 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -3,16 +3,18 @@ #include <linux/types.h> #include <linux/slab.h> +#include <asm/cpu_entry_area.h> #include <asm/perf_event.h> #include <asm/insn.h> #include "../perf_event.h" +/* Waste a full page so it can be mapped into the cpu_entry_area */ +DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + /* The size of a BTS record in bytes: */ #define BTS_RECORD_SIZE 24 -#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) -#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) #define PEBS_FIXUP_SIZE PAGE_SIZE /* @@ -279,17 +281,52 @@ void fini_debug_store_on_cpu(int cpu) static DEFINE_PER_CPU(void *, insn_buffer); -static int alloc_pebs_buffer(int cpu) +static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + phys_addr_t pa; + size_t msz = 0; + + pa = virt_to_phys(addr); + for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE) + cea_set_pte(cea, pa, prot); +} + +static void ds_clear_cea(void *cea, size_t size) +{ + size_t msz = 0; + + for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE) + cea_set_pte(cea, 0, PAGE_NONE); +} + +static void *dsalloc_pages(size_t size, gfp_t flags, int cpu) +{ + unsigned int order = get_order(size); int node = cpu_to_node(cpu); - int max; - void *buffer, *ibuffer; + struct page *page; + + page = __alloc_pages_node(node, flags | __GFP_ZERO, order); + return page ? page_address(page) : NULL; +} + +static void dsfree_pages(const void *buffer, size_t size) +{ + if (buffer) + free_pages((unsigned long)buffer, get_order(size)); +} + +static int alloc_pebs_buffer(int cpu) +{ + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + size_t bsiz = x86_pmu.pebs_buffer_size; + int max, node = cpu_to_node(cpu); + void *buffer, *ibuffer, *cea; if (!x86_pmu.pebs) return 0; - buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node); + buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu); if (unlikely(!buffer)) return -ENOMEM; @@ -300,25 +337,27 @@ static int alloc_pebs_buffer(int cpu) if (x86_pmu.intel_cap.pebs_format < 2) { ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node); if (!ibuffer) { - kfree(buffer); + dsfree_pages(buffer, bsiz); return -ENOMEM; } per_cpu(insn_buffer, cpu) = ibuffer; } - - max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size; - - ds->pebs_buffer_base = (u64)(unsigned long)buffer; + hwev->ds_pebs_vaddr = buffer; + /* Update the cpu entry area mapping */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; + ds->pebs_buffer_base = (unsigned long) cea; + ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL); ds->pebs_index = ds->pebs_buffer_base; - ds->pebs_absolute_maximum = ds->pebs_buffer_base + - max * x86_pmu.pebs_record_size; - + max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size); + ds->pebs_absolute_maximum = ds->pebs_buffer_base + max; return 0; } static void release_pebs_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + void *cea; if (!ds || !x86_pmu.pebs) return; @@ -326,73 +365,70 @@ static void release_pebs_buffer(int cpu) kfree(per_cpu(insn_buffer, cpu)); per_cpu(insn_buffer, cpu) = NULL; - kfree((void *)(unsigned long)ds->pebs_buffer_base); + /* Clear the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; + ds_clear_cea(cea, x86_pmu.pebs_buffer_size); ds->pebs_buffer_base = 0; + dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size); + hwev->ds_pebs_vaddr = NULL; } static int alloc_bts_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - int node = cpu_to_node(cpu); - int max, thresh; - void *buffer; + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + void *buffer, *cea; + int max; if (!x86_pmu.bts) return 0; - buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node); + buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu); if (unlikely(!buffer)) { WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__); return -ENOMEM; } - - max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE; - thresh = max / 16; - - ds->bts_buffer_base = (u64)(unsigned long)buffer; + hwev->ds_bts_vaddr = buffer; + /* Update the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer; + ds->bts_buffer_base = (unsigned long) cea; + ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL); ds->bts_index = ds->bts_buffer_base; - ds->bts_absolute_maximum = ds->bts_buffer_base + - max * BTS_RECORD_SIZE; - ds->bts_interrupt_threshold = ds->bts_absolute_maximum - - thresh * BTS_RECORD_SIZE; - + max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE); + ds->bts_absolute_maximum = ds->bts_buffer_base + max; + ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16); return 0; } static void release_bts_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; + struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); + struct debug_store *ds = hwev->ds; + void *cea; if (!ds || !x86_pmu.bts) return; - kfree((void *)(unsigned long)ds->bts_buffer_base); + /* Clear the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer; + ds_clear_cea(cea, BTS_BUFFER_SIZE); ds->bts_buffer_base = 0; + dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE); + hwev->ds_bts_vaddr = NULL; } static int alloc_ds_buffer(int cpu) { - int node = cpu_to_node(cpu); - struct debug_store *ds; - - ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); - if (unlikely(!ds)) - return -ENOMEM; + struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store; + memset(ds, 0, sizeof(*ds)); per_cpu(cpu_hw_events, cpu).ds = ds; - return 0; } static void release_ds_buffer(int cpu) { - struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds; - - if (!ds) - return; - per_cpu(cpu_hw_events, cpu).ds = NULL; - kfree(ds); } void release_ds_buffers(void) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index f7aaadf9331f..8e4ea143ed96 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -14,6 +14,8 @@ #include <linux/perf_event.h> +#include <asm/intel_ds.h> + /* To enable MSR tracing please use the generic trace points. */ /* @@ -77,8 +79,6 @@ struct amd_nb { struct event_constraint event_constraints[X86_PMC_IDX_MAX]; }; -/* The maximal number of PEBS events: */ -#define MAX_PEBS_EVENTS 8 #define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1) /* @@ -95,23 +95,6 @@ struct amd_nb { PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER) -/* - * A debug store configuration. - * - * We only support architectures that use 64bit fields. - */ -struct debug_store { - u64 bts_buffer_base; - u64 bts_index; - u64 bts_absolute_maximum; - u64 bts_interrupt_threshold; - u64 pebs_buffer_base; - u64 pebs_index; - u64 pebs_absolute_maximum; - u64 pebs_interrupt_threshold; - u64 pebs_event_reset[MAX_PEBS_EVENTS]; -}; - #define PEBS_REGS \ (PERF_REG_X86_AX | \ PERF_REG_X86_BX | \ @@ -216,6 +199,8 @@ struct cpu_hw_events { * Intel DebugStore bits */ struct debug_store *ds; + void *ds_pebs_vaddr; + void *ds_bts_vaddr; u64 pebs_enabled; int n_pebs; int n_large_pebs; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 219faaec51df..386a6900e206 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -136,6 +136,7 @@ #endif #ifndef __ASSEMBLY__ +#ifndef __BPF__ /* * This output constraint should be used for any inline asm which has a "call" * instruction. Otherwise the asm may be inserted before the frame pointer @@ -145,5 +146,6 @@ register unsigned long current_stack_pointer asm(_ASM_SP); #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) #endif +#endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h new file mode 100644 index 000000000000..4a7884b8dca5 --- /dev/null +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -0,0 +1,81 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef _ASM_X86_CPU_ENTRY_AREA_H +#define _ASM_X86_CPU_ENTRY_AREA_H + +#include <linux/percpu-defs.h> +#include <asm/processor.h> +#include <asm/intel_ds.h> + +/* + * cpu_entry_area is a percpu region that contains things needed by the CPU + * and early entry/exit code. Real types aren't used for all fields here + * to avoid circular header dependencies. + * + * Every field is a virtual alias of some other allocated backing store. + * There is no direct allocation of a struct cpu_entry_area. + */ +struct cpu_entry_area { + char gdt[PAGE_SIZE]; + + /* + * The GDT is just below entry_stack and thus serves (on x86_64) as + * a a read-only guard page. + */ + struct entry_stack_page entry_stack_page; + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. + */ + struct tss_struct tss; + + char entry_trampoline[PAGE_SIZE]; + +#ifdef CONFIG_X86_64 + /* + * Exception stacks used for IST entries. + * + * In the future, this should have a separate slot for each stack + * with guard pages between them. + */ + char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; +#endif +#ifdef CONFIG_CPU_SUP_INTEL + /* + * Per CPU debug store for Intel performance monitoring. Wastes a + * full page at the moment. + */ + struct debug_store cpu_debug_store; + /* + * The actual PEBS/BTS buffers must be mapped to user space + * Reserve enough fixmap PTEs. + */ + struct debug_store_buffers cpu_debug_buffers; +#endif +}; + +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) + +DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); + +extern void setup_cpu_entry_areas(void); +extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); + +#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE +#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) + +#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +#define CPU_ENTRY_AREA_MAP_SIZE \ + (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE) + +extern struct cpu_entry_area *get_cpu_entry_area(int cpu); + +static inline struct entry_stack *cpu_entry_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->entry_stack_page.stack; +} + +#endif diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index bf6a76202a77..ea9a7dde62e5 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); set_bit(bit, (unsigned long *)cpu_caps_set); \ } while (0) +#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) + #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS) /* * Static testing of CPU features. Used the same as boot_cpu_has(). diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 800104c8a3ed..07cdd1715705 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -197,11 +197,12 @@ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ - +#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ #define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */ @@ -340,5 +341,6 @@ #define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ #define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 4011cb03ef08..13c5ee878a47 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -7,6 +7,7 @@ #include <asm/mmu.h> #include <asm/fixmap.h> #include <asm/irq_vectors.h> +#include <asm/cpu_entry_area.h> #include <linux/smp.h> #include <linux/percpu.h> @@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in desc->type = (info->read_exec_only ^ 1) << 1; desc->type |= info->contents << 2; + /* Set the ACCESS bit so it can be mapped RO */ + desc->type |= 1; desc->s = 1; desc->dpl = 0x3; @@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void) return this_cpu_ptr(&gdt_page)->gdt; } -/* Get the fixmap index for a specific processor */ -static inline unsigned int get_cpu_gdt_ro_index(int cpu) -{ - return FIX_GDT_REMAP_BEGIN + cpu; -} - /* Provide the fixmap address of the remapped GDT */ static inline struct desc_struct *get_cpu_gdt_ro(int cpu) { - unsigned int idx = get_cpu_gdt_ro_index(cpu); - return (struct desc_struct *)__fix_to_virt(idx); + return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; } /* Provide the current read-only GDT */ @@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr, #endif } -static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr) +static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) { struct desc_struct *d = get_cpu_gdt_rw(cpu); tss_desc tss; diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 14d6d5007314..b027633e7300 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -50,6 +50,12 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define DISABLE_PTI 0 +#else +# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -60,7 +66,7 @@ #define DISABLED_MASK4 (DISABLE_PCID) #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 -#define DISABLED_MASK7 0 +#define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 #define DISABLED_MASK9 (DISABLE_MPX) #define DISABLED_MASK10 0 diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h index 0211029076ea..6777480d8a42 100644 --- a/arch/x86/include/asm/espfix.h +++ b/arch/x86/include/asm/espfix.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_ESPFIX_H #define _ASM_X86_ESPFIX_H -#ifdef CONFIG_X86_64 +#ifdef CONFIG_X86_ESPFIX64 #include <asm/percpu.h> @@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); extern void init_espfix_bsp(void); extern void init_espfix_ap(int cpu); - -#endif /* CONFIG_X86_64 */ +#else +static inline void init_espfix_ap(int cpu) { } +#endif #endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b0c505fe9a95..64c4a30e0d39 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP; PAGE_SIZE) #endif - /* * Here we define all the compile-time 'special' virtual * addresses. The point is to have a constant address at @@ -84,7 +83,6 @@ enum fixed_addresses { FIX_IO_APIC_BASE_0, FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, #endif - FIX_RO_IDT, /* Virtual mapping for read-only IDT */ #ifdef CONFIG_X86_32 FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, @@ -100,9 +98,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_INTEL_MID FIX_LNW_VRTC, #endif - /* Fixmap entries to remap the GDTs, one per processor. */ - FIX_GDT_REMAP_BEGIN, - FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1, #ifdef CONFIG_ACPI_APEI_GHES /* Used for GHES mapping from assorted contexts */ @@ -143,7 +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_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) extern int fixmaps_set; diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 1b0a5abcd8ae..96aa6b9884dc 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -20,16 +20,7 @@ #ifndef _ASM_X86_HYPERVISOR_H #define _ASM_X86_HYPERVISOR_H -#ifdef CONFIG_HYPERVISOR_GUEST - -#include <asm/kvm_para.h> -#include <asm/x86_init.h> -#include <asm/xen/hypervisor.h> - -/* - * x86 hypervisor information - */ - +/* x86 hypervisor types */ enum x86_hypervisor_type { X86_HYPER_NATIVE = 0, X86_HYPER_VMWARE, @@ -39,6 +30,12 @@ enum x86_hypervisor_type { X86_HYPER_KVM, }; +#ifdef CONFIG_HYPERVISOR_GUEST + +#include <asm/kvm_para.h> +#include <asm/x86_init.h> +#include <asm/xen/hypervisor.h> + struct hypervisor_x86 { /* Hypervisor name */ const char *name; @@ -58,7 +55,15 @@ struct hypervisor_x86 { extern enum x86_hypervisor_type x86_hyper_type; extern void init_hypervisor_platform(void); +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return x86_hyper_type == type; +} #else static inline void init_hypervisor_platform(void) { } +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return type == X86_HYPER_NATIVE; +} #endif /* CONFIG_HYPERVISOR_GUEST */ #endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h new file mode 100644 index 000000000000..62a9f4966b42 --- /dev/null +++ b/arch/x86/include/asm/intel_ds.h @@ -0,0 +1,36 @@ +#ifndef _ASM_INTEL_DS_H +#define _ASM_INTEL_DS_H + +#include <linux/percpu-defs.h> + +#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) +#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4) + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS 8 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS]; +} __aligned(PAGE_SIZE); + +DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + +struct debug_store_buffers { + char bts_buffer[BTS_BUFFER_SIZE]; + char pebs_buffer[PEBS_BUFFER_SIZE]; +}; + +#endif diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h new file mode 100644 index 000000000000..989cfa86de85 --- /dev/null +++ b/arch/x86/include/asm/invpcid.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INVPCID +#define _ASM_X86_INVPCID + +static inline void __invpcid(unsigned long pcid, unsigned long addr, + unsigned long type) +{ + struct { u64 d[2]; } desc = { { pcid, addr } }; + + /* + * The memory clobber is because the whole point is to invalidate + * stale TLB entries and, especially if we're flushing global + * mappings, we don't want the compiler to reorder any subsequent + * memory accesses before the TLB flush. + * + * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and + * invpcid (%rcx), %rax in long mode. + */ + asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01" + : : "m" (desc), "a" (type), "c" (&desc) : "memory"); +} + +#define INVPCID_TYPE_INDIV_ADDR 0 +#define INVPCID_TYPE_SINGLE_CTXT 1 +#define INVPCID_TYPE_ALL_INCL_GLOBAL 2 +#define INVPCID_TYPE_ALL_NON_GLOBAL 3 + +/* Flush all mappings for a given pcid and addr, not including globals. */ +static inline void invpcid_flush_one(unsigned long pcid, + unsigned long addr) +{ + __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR); +} + +/* Flush all mappings for a given PCID, not including globals. */ +static inline void invpcid_flush_single_context(unsigned long pcid) +{ + __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT); +} + +/* Flush all mappings, including globals, for all PCIDs. */ +static inline void invpcid_flush_all(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL); +} + +/* Flush all mappings for all PCIDs except globals. */ +static inline void invpcid_flush_all_nonglobals(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); +} + +#endif /* _ASM_X86_INVPCID */ diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index 139feef467f7..c066ffae222b 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -44,7 +44,7 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs); extern int mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool early); + struct irq_data *irq_data, bool reserve); extern void mp_irqdomain_deactivate(struct irq_domain *domain, struct irq_data *irq_data); extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c8ef23f2c28f..89f08955fff7 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void) swapgs; \ sysretl +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(x) pushfq; popq %rax +#endif #else #define INTERRUPT_RETURN iret #define ENABLE_INTERRUPTS_SYSEXIT sti; sysexit diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index f86a8caa561e..395c9631e000 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, int all); +extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 9ea26f167497..5ff3e8af2c20 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -3,6 +3,7 @@ #define _ASM_X86_MMU_H #include <linux/spinlock.h> +#include <linux/rwsem.h> #include <linux/mutex.h> #include <linux/atomic.h> @@ -27,7 +28,8 @@ typedef struct { atomic64_t tlb_gen; #ifdef CONFIG_MODIFY_LDT_SYSCALL - struct ldt_struct *ldt; + struct rw_semaphore ldt_usr_sem; + struct ldt_struct *ldt; #endif #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 6d16d15d09a0..c931b88982a0 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -50,22 +50,53 @@ struct ldt_struct { * call gates. On native, we could merge the ldt_struct and LDT * allocations, but it's not worth trying to optimize. */ - struct desc_struct *entries; - unsigned int nr_entries; + struct desc_struct *entries; + unsigned int nr_entries; + + /* + * If PTI is in use, then the entries array is not mapped while we're + * in user mode. The whole array will be aliased at the addressed + * given by ldt_slot_va(slot). We use two slots so that we can allocate + * and map, and enable a new LDT without invalidating the mapping + * of an older, still-in-use LDT. + * + * slot will be -1 if this LDT doesn't have an alias mapping. + */ + int slot; }; +/* This is a multiple of PAGE_SIZE. */ +#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) + +static inline void *ldt_slot_va(int slot) +{ +#ifdef CONFIG_X86_64 + return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot); +#else + BUG(); +#endif +} + /* * Used for LDT copy/destruction. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm); +static inline void init_new_context_ldt(struct mm_struct *mm) +{ + mm->context.ldt = NULL; + init_rwsem(&mm->context.ldt_usr_sem); +} +int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); void destroy_context_ldt(struct mm_struct *mm); +void ldt_arch_exit_mmap(struct mm_struct *mm); #else /* CONFIG_MODIFY_LDT_SYSCALL */ -static inline int init_new_context_ldt(struct task_struct *tsk, - struct mm_struct *mm) +static inline void init_new_context_ldt(struct mm_struct *mm) { } +static inline int ldt_dup_context(struct mm_struct *oldmm, + struct mm_struct *mm) { return 0; } -static inline void destroy_context_ldt(struct mm_struct *mm) {} +static inline void destroy_context_ldt(struct mm_struct *mm) { } +static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } #endif static inline void load_mm_ldt(struct mm_struct *mm) @@ -90,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm) * that we can see. */ - if (unlikely(ldt)) - set_ldt(ldt->entries, ldt->nr_entries); - else + if (unlikely(ldt)) { + if (static_cpu_has(X86_FEATURE_PTI)) { + if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) { + /* + * Whoops -- either the new LDT isn't mapped + * (if slot == -1) or is mapped into a bogus + * slot (if slot > 1). + */ + clear_LDT(); + return; + } + + /* + * If page table isolation is enabled, ldt->entries + * will not be mapped in the userspace pagetables. + * Tell the CPU to access the LDT through the alias + * at ldt_slot_va(ldt->slot). + */ + set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries); + } else { + set_ldt(ldt->entries, ldt->nr_entries); + } + } else { clear_LDT(); + } #else clear_LDT(); #endif @@ -132,18 +184,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { + mutex_init(&mm->context.lock); + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); - #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { /* pkey 0 is the default and always allocated */ mm->context.pkey_allocation_map = 0x1; /* -1 means unallocated or invalid */ mm->context.execute_only_pkey = -1; } - #endif - return init_new_context_ldt(tsk, mm); +#endif + init_new_context_ldt(mm); + return 0; } static inline void destroy_context(struct mm_struct *mm) { @@ -176,15 +231,16 @@ do { \ } while (0) #endif -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { paravirt_arch_dup_mmap(oldmm, mm); + return ldt_dup_context(oldmm, mm); } static inline void arch_exit_mmap(struct mm_struct *mm) { paravirt_arch_exit_mmap(mm); + ldt_arch_exit_mmap(mm); } #ifdef CONFIG_X86_64 @@ -282,33 +338,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, } /* - * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID - * bits. This serves two purposes. It prevents a nasty situation in - * which PCID-unaware code saves CR3, loads some other value (with PCID - * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if - * the saved ASID was nonzero. It also means that any bugs involving - * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger - * deterministically. - */ - -static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid) -{ - if (static_cpu_has(X86_FEATURE_PCID)) { - VM_WARN_ON_ONCE(asid > 4094); - return __sme_pa(mm->pgd) | (asid + 1); - } else { - VM_WARN_ON_ONCE(asid != 0); - return __sme_pa(mm->pgd); - } -} - -static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) -{ - VM_WARN_ON_ONCE(asid > 4094); - return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH; -} - -/* * This can be used from process context to figure out what the value of * CR3 is without needing to do a (slow) __read_cr3(). * @@ -317,7 +346,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid) */ static inline unsigned long __get_current_cr3_fast(void) { - unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm), + unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd, this_cpu_read(cpu_tlbstate.loaded_mm_asid)); /* For now, be very restrictive about when this can be called. */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 283efcaac8af..892df375b615 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -927,6 +927,15 @@ extern void default_banner(void); PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \ CLBR_NONE, \ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64)) + +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS(clobbers) \ + PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \ + PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ + call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \ + PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) +#endif + #endif /* CONFIG_X86_32 */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index 4b5e1eafada7..aff42e1da6ee 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {} */ extern gfp_t __userpte_alloc_gfp; +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Instead of one PGD, we acquire two PGDs. Being order-1, it is + * both 8k in size and 8k-aligned. That lets us just flip bit 12 + * in a pointer to swap between the two 4k halves. + */ +#define PGD_ALLOCATION_ORDER 1 +#else +#define PGD_ALLOCATION_ORDER 0 +#endif + /* * Allocate and free page tables. */ diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 95e2dfd75521..e42b8943cb1a 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD]; int __init __early_make_pgtable(unsigned long address, pmdval_t pmd); void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd); +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user); void ptdump_walk_pgd_level_checkwx(void); #ifdef CONFIG_DEBUG_WX @@ -841,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) static inline int p4d_bad(p4d_t p4d) { - return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; + unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; + + if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + ignore_flags |= _PAGE_NX; + + return (p4d_flags(p4d) & ~ignore_flags) != 0; } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ @@ -875,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) static inline int pgd_bad(pgd_t pgd) { - return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE; + unsigned long ignore_flags = _PAGE_USER; + + if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + ignore_flags |= _PAGE_NX; + + return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; } static inline int pgd_none(pgd_t pgd) @@ -904,7 +915,11 @@ static inline int pgd_none(pgd_t pgd) * pgd_offset() returns a (pgd_t *) * pgd_index() is used get the offset into the pgd page's array of pgd_t's; */ -#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address))) +#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address))) +/* + * a shortcut to get a pgd_t in a given mm + */ +#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address)) /* * a shortcut which implies the use of the kernel's pgd, instead * of a process's @@ -1106,7 +1121,14 @@ static inline int pud_write(pud_t pud) */ static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { - memcpy(dst, src, count * sizeof(pgd_t)); + memcpy(dst, src, count * sizeof(pgd_t)); +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + /* Clone the user space pgd as well */ + memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), + count * sizeof(pgd_t)); +#endif } #define PTE_SHIFT ilog2(PTRS_PER_PTE) diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index f2ca9b28fd68..ce245b0cdfca 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ #define LAST_PKMAP 1024 #endif -#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \ - & PMD_MASK) +/* + * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c + * to avoid include recursion hell + */ +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) + +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) + +#define PKMAP_BASE \ + ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) #else -# define VMALLOC_END (FIXADDR_START - 2 * PAGE_SIZE) +# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE) #endif #define MODULES_VADDR VMALLOC_START diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e9f05331e732..81462e9a34f6 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp) #endif } +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and + * the user one is in the last 4k. To switch between them, you + * just need to flip the 12th bit in their addresses. + */ +#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT + +/* + * This generates better code than the inline assembly in + * __set_bit(). + */ +static inline void *ptr_set_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr |= BIT(bit); + return (void *)__ptr; +} +static inline void *ptr_clear_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr &= ~BIT(bit); + return (void *)__ptr; +} + +static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) +{ + return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) +{ + return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) +{ + return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) +{ + return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} +#endif /* CONFIG_PAGE_TABLE_ISOLATION */ + +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * + * Returns true for parts of the PGD that map userspace and + * false for the parts that map the kernel. + */ +static inline bool pgdp_maps_userspace(void *__ptr) +{ + unsigned long ptr = (unsigned long)__ptr; + + return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2); +} + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd); + +/* + * Take a PGD location (pgdp) and a pgd value that needs to be set there. + * Populates the user and returns the resulting PGD that must be set in + * the kernel copy of the page tables. + */ +static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + return pgd; + return __pti_set_user_pgd(pgdp, pgd); +} +#else +static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +#endif + static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { +#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL) + p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd); +#else *p4dp = p4d; +#endif } static inline void native_p4d_clear(p4d_t *p4d) @@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { +#ifdef CONFIG_PAGE_TABLE_ISOLATION + *pgdp = pti_set_user_pgd(pgdp, pgd); +#else *pgdp = pgd; +#endif } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 6d5f45dcd4a1..b97a539bcdee 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -76,32 +76,45 @@ typedef struct { pteval_t pte; } pte_t; #define PGDIR_MASK (~(PGDIR_SIZE - 1)) /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ -#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) +#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) + #ifdef CONFIG_X86_5LEVEL -#define VMALLOC_SIZE_TB _AC(16384, UL) -#define __VMALLOC_BASE _AC(0xff92000000000000, UL) -#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +# define VMALLOC_SIZE_TB _AC(12800, UL) +# define __VMALLOC_BASE _AC(0xffa0000000000000, UL) +# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +# define LDT_PGD_ENTRY _AC(-112, UL) +# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #else -#define VMALLOC_SIZE_TB _AC(32, UL) -#define __VMALLOC_BASE _AC(0xffffc90000000000, UL) -#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +# define VMALLOC_SIZE_TB _AC(32, UL) +# define __VMALLOC_BASE _AC(0xffffc90000000000, UL) +# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +# define LDT_PGD_ENTRY _AC(-4, UL) +# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #endif + #ifdef CONFIG_RANDOMIZE_MEMORY -#define VMALLOC_START vmalloc_base -#define VMEMMAP_START vmemmap_base +# define VMALLOC_START vmalloc_base +# define VMEMMAP_START vmemmap_base #else -#define VMALLOC_START __VMALLOC_BASE -#define VMEMMAP_START __VMEMMAP_BASE +# define VMALLOC_START __VMALLOC_BASE +# define VMEMMAP_START __VMEMMAP_BASE #endif /* CONFIG_RANDOMIZE_MEMORY */ -#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) -#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) + +#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) + +#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) /* The module sections ends with the start of the fixmap */ -#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) -#define MODULES_LEN (MODULES_END - MODULES_VADDR) -#define ESPFIX_PGD_ENTRY _AC(-2, UL) -#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) -#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) -#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) +#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) +#define MODULES_LEN (MODULES_END - MODULES_VADDR) + +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) + +#define CPU_ENTRY_AREA_PGD _AC(-3, UL) +#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_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/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 43212a43ee69..6a60fea90b9d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -38,6 +38,11 @@ #define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull) #define CR3_PCID_MASK 0xFFFull #define CR3_NOFLUSH BIT_ULL(63) + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define X86_CR3_PTI_SWITCH_BIT 11 +#endif + #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index cc16fa882e3e..d3a67fba200a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -163,9 +163,9 @@ enum cpuid_regs_idx { extern struct cpuinfo_x86 boot_cpu_data; extern struct cpuinfo_x86 new_cpu_data; -extern struct tss_struct doublefault_tss; -extern __u32 cpu_caps_cleared[NCAPINTS]; -extern __u32 cpu_caps_set[NCAPINTS]; +extern struct x86_hw_tss doublefault_tss; +extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; #ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); @@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir) write_cr3(__sme_pa(pgdir)); } +/* + * Note that while the legacy 'TSS' name comes from 'Task State Segment', + * on modern x86 CPUs the TSS also holds information important to 64-bit mode, + * unrelated to the task-switch mechanism: + */ #ifdef CONFIG_X86_32 /* This is the TSS defined by the hardware. */ struct x86_hw_tss { @@ -305,7 +310,13 @@ struct x86_hw_tss { struct x86_hw_tss { u32 reserved1; u64 sp0; + + /* + * We store cpu_current_top_of_stack in sp1 so it's always accessible. + * Linux does not use ring 1, so sp1 is not otherwise needed. + */ u64 sp1; + u64 sp2; u64 reserved2; u64 ist[7]; @@ -323,12 +334,22 @@ struct x86_hw_tss { #define IO_BITMAP_BITS 65536 #define IO_BITMAP_BYTES (IO_BITMAP_BITS/8) #define IO_BITMAP_LONGS (IO_BITMAP_BYTES/sizeof(long)) -#define IO_BITMAP_OFFSET offsetof(struct tss_struct, io_bitmap) +#define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) #define INVALID_IO_BITMAP_OFFSET 0x8000 +struct entry_stack { + unsigned long words[64]; +}; + +struct entry_stack_page { + struct entry_stack stack; +} __aligned(PAGE_SIZE); + struct tss_struct { /* - * The hardware state: + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. */ struct x86_hw_tss x86_tss; @@ -339,18 +360,9 @@ struct tss_struct { * be within the limit. */ unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; +} __aligned(PAGE_SIZE); -#ifdef CONFIG_X86_32 - /* - * Space for the temporary SYSENTER stack. - */ - unsigned long SYSENTER_stack_canary; - unsigned long SYSENTER_stack[64]; -#endif - -} ____cacheline_aligned; - -DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); /* * sizeof(unsigned long) coming from an extra "long" at the end @@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); +#else +/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ +#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 #endif /* @@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask) static inline void native_load_sp0(unsigned long sp0) { - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } static inline void native_swapgs(void) @@ -535,12 +550,12 @@ static inline void native_swapgs(void) static inline unsigned long current_top_of_stack(void) { -#ifdef CONFIG_X86_64 - return this_cpu_read_stable(cpu_tss.x86_tss.sp0); -#else - /* sp0 on x86_32 is special in and around vm86 mode. */ + /* + * We can't read directly from tss.sp0: sp0 on x86_32 is special in + * and around vm86 mode and sp0 on x86_64 is special because of the + * entry trampoline. + */ return this_cpu_read_stable(cpu_current_top_of_stack); -#endif } static inline bool on_thread_stack(void) @@ -837,13 +852,22 @@ static inline void spin_lock_prefetch(const void *x) #else /* - * 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. + * User space process size. This is the first address outside the user range. + * There are a few constraints that determine this: + * + * On Intel CPUs, if a SYSCALL instruction is at the highest canonical + * 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 executable + * from being mapped at the maximum canonical address. + * + * On AMD CPUs in the Ryzen family, there's a nasty bug in which the + * CPUs malfunction if they execute code from the highest canonical page. + * They'll speculate right off the end of the canonical space, and + * bad things happen. This is worked around in the same way as the + * Intel problem. + * + * With page table isolation enabled, we map the LDT in ... [stay tuned] */ #define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE) diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h new file mode 100644 index 000000000000..0b5ef05b2d2d --- /dev/null +++ b/arch/x86/include/asm/pti.h @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _ASM_X86_PTI_H +#define _ASM_X86_PTI_H +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +extern void pti_init(void); +extern void pti_check_boottime_disable(void); +#else +static inline void pti_check_boottime_disable(void) { } +#endif + +#endif /* __ASSEMBLY__ */ +#endif /* _ASM_X86_PTI_H */ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 8da111b3c342..f73706878772 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -16,6 +16,7 @@ enum stack_type { STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, + STACK_TYPE_ENTRY, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; @@ -28,6 +29,8 @@ struct stack_info { bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); +bool in_entry_stack(unsigned long *stack, struct stack_info *info); + int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8c6bd6863db9..eb5f7999a893 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -16,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss); /* This runs runs on the previous thread's stack. */ -static inline void prepare_switch_to(struct task_struct *prev, - struct task_struct *next) +static inline void prepare_switch_to(struct task_struct *next) { #ifdef CONFIG_VMAP_STACK /* @@ -70,7 +69,7 @@ struct fork_frame { #define switch_to(prev, next, last) \ do { \ - prepare_switch_to(prev, next); \ + prepare_switch_to(next); \ \ ((last) = __switch_to_asm((prev), (next))); \ } while (0) @@ -79,10 +78,10 @@ do { \ static inline void refresh_sysenter_cs(struct thread_struct *thread) { /* Only happens when SEP is enabled, no need to test "SEP"arately: */ - if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs)) + if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs)) return; - this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs); + this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs); wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); } #endif @@ -90,10 +89,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread) /* This is used when switching tasks or entering/exiting vm86 mode. */ static inline void update_sp0(struct task_struct *task) { + /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 load_sp0(task->thread.sp0); #else - load_sp0(task_top_of_stack(task)); + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task_top_of_stack(task)); #endif } diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 70f425947dc5..00223333821a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack, #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss + TSS_sp0) +# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1) #endif #endif diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 877b5c1a1b12..4a08dd2ab32a 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -9,70 +9,130 @@ #include <asm/cpufeature.h> #include <asm/special_insns.h> #include <asm/smp.h> +#include <asm/invpcid.h> +#include <asm/pti.h> +#include <asm/processor-flags.h> -static inline void __invpcid(unsigned long pcid, unsigned long addr, - unsigned long type) -{ - struct { u64 d[2]; } desc = { { pcid, addr } }; +/* + * The x86 feature is called PCID (Process Context IDentifier). It is similar + * to what is traditionally called ASID on the RISC processors. + * + * We don't use the traditional ASID implementation, where each process/mm gets + * its own ASID and flush/restart when we run out of ASID space. + * + * Instead we have a small per-cpu array of ASIDs and cache the last few mm's + * that came by on this CPU, allowing cheaper switch_mm between processes on + * this CPU. + * + * We end up with different spaces for different things. To avoid confusion we + * use different names for each of them: + * + * ASID - [0, TLB_NR_DYN_ASIDS-1] + * the canonical identifier for an mm + * + * kPCID - [1, TLB_NR_DYN_ASIDS] + * the value we write into the PCID part of CR3; corresponds to the + * ASID+1, because PCID 0 is special. + * + * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS] + * for KPTI each mm has two address spaces and thus needs two + * PCID values, but we can still do with a single ASID denomination + * for each mm. Corresponds to kPCID + 2048. + * + */ - /* - * The memory clobber is because the whole point is to invalidate - * stale TLB entries and, especially if we're flushing global - * mappings, we don't want the compiler to reorder any subsequent - * memory accesses before the TLB flush. - * - * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and - * invpcid (%rcx), %rax in long mode. - */ - asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01" - : : "m" (desc), "a" (type), "c" (&desc) : "memory"); -} +/* There are 12 bits of space for ASIDS in CR3 */ +#define CR3_HW_ASID_BITS 12 -#define INVPCID_TYPE_INDIV_ADDR 0 -#define INVPCID_TYPE_SINGLE_CTXT 1 -#define INVPCID_TYPE_ALL_INCL_GLOBAL 2 -#define INVPCID_TYPE_ALL_NON_GLOBAL 3 +/* + * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for + * user/kernel switches + */ +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define PTI_CONSUMED_PCID_BITS 1 +#else +# define PTI_CONSUMED_PCID_BITS 0 +#endif -/* Flush all mappings for a given pcid and addr, not including globals. */ -static inline void invpcid_flush_one(unsigned long pcid, - unsigned long addr) -{ - __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR); -} +#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS) + +/* + * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account + * for them being zero-based. Another -1 is because PCID 0 is reserved for + * use by non-PCID-aware users. + */ +#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2) + +/* + * 6 because 6 should be plenty and struct tlb_state will fit in two cache + * lines. + */ +#define TLB_NR_DYN_ASIDS 6 -/* Flush all mappings for a given PCID, not including globals. */ -static inline void invpcid_flush_single_context(unsigned long pcid) +/* + * Given @asid, compute kPCID + */ +static inline u16 kern_pcid(u16 asid) { - __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT); + VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * Make sure that the dynamic ASID space does not confict with the + * bit we are using to switch between user and kernel ASIDs. + */ + BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT)); + + /* + * The ASID being passed in here should have respected the + * MAX_ASID_AVAILABLE and thus never have the switch bit set. + */ + VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT)); +#endif + /* + * The dynamically-assigned ASIDs that get passed in are small + * (<TLB_NR_DYN_ASIDS). They never have the high switch bit set, + * so do not bother to clear it. + * + * If PCID is on, ASID-aware code paths put the ASID+1 into the + * PCID bits. This serves two purposes. It prevents a nasty + * situation in which PCID-unaware code saves CR3, loads some other + * value (with PCID == 0), and then restores CR3, thus corrupting + * the TLB for ASID 0 if the saved ASID was nonzero. It also means + * that any bugs involving loading a PCID-enabled CR3 with + * CR4.PCIDE off will trigger deterministically. + */ + return asid + 1; } -/* Flush all mappings, including globals, for all PCIDs. */ -static inline void invpcid_flush_all(void) +/* + * Given @asid, compute uPCID + */ +static inline u16 user_pcid(u16 asid) { - __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL); + u16 ret = kern_pcid(asid); +#ifdef CONFIG_PAGE_TABLE_ISOLATION + ret |= 1 << X86_CR3_PTI_SWITCH_BIT; +#endif + return ret; } -/* Flush all mappings for all PCIDs except globals. */ -static inline void invpcid_flush_all_nonglobals(void) +struct pgd_t; +static inline unsigned long build_cr3(pgd_t *pgd, u16 asid) { - __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); + if (static_cpu_has(X86_FEATURE_PCID)) { + return __sme_pa(pgd) | kern_pcid(asid); + } else { + VM_WARN_ON_ONCE(asid != 0); + return __sme_pa(pgd); + } } -static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) +static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid) { - u64 new_tlb_gen; - - /* - * Bump the generation count. This also serves as a full barrier - * that synchronizes with switch_mm(): callers are required to order - * their read of mm_cpumask after their writes to the paging - * structures. - */ - smp_mb__before_atomic(); - new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen); - smp_mb__after_atomic(); - - return new_tlb_gen; + VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); + VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID)); + return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH; } #ifdef CONFIG_PARAVIRT @@ -99,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void) return !static_cpu_has(X86_FEATURE_PCID); } -/* - * 6 because 6 should be plenty and struct tlb_state will fit in - * two cache lines. - */ -#define TLB_NR_DYN_ASIDS 6 - struct tlb_context { u64 ctx_id; u64 tlb_gen; @@ -139,6 +193,24 @@ struct tlb_state { bool is_lazy; /* + * If set we changed the page tables in such a way that we + * needed an invalidation of all contexts (aka. PCIDs / ASIDs). + * This tells us to go invalidate all the non-loaded ctxs[] + * on the next context switch. + * + * The current ctx was kept up-to-date as it ran and does not + * need to be invalidated. + */ + bool invalidate_other; + + /* + * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate + * the corresponding user PCID needs a flush next time we + * switch to it; see SWITCH_TO_USER_CR3. + */ + unsigned short user_pcid_flush_mask; + + /* * Access to this CR4 shadow and to H/W CR4 is protected by * disabling interrupts when modifying either one. */ @@ -219,6 +291,14 @@ static inline unsigned long cr4_read_shadow(void) } /* + * Mark all other ASIDs as invalid, preserves the current. + */ +static inline void invalidate_other_asid(void) +{ + this_cpu_write(cpu_tlbstate.invalidate_other, true); +} + +/* * Save some of cr4 feature set we're using (e.g. Pentium 4MB * enable and PPro Global page enable), so that any CPU's that boot * up after us can get the correct flags. This should only be used @@ -237,37 +317,63 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) extern void initialize_tlbstate_and_flush(void); -static inline void __native_flush_tlb(void) +/* + * Given an ASID, flush the corresponding user ASID. We can delay this + * until the next time we switch to it. + * + * See SWITCH_TO_USER_CR3. + */ +static inline void invalidate_user_asid(u16 asid) { + /* There is no user ASID if address space separation is off */ + if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + return; + /* - * If current->mm == NULL then we borrow a mm which may change during a - * task switch and therefore we must not be preempted while we write CR3 - * back: + * We only have a single ASID if PCID is off and the CR3 + * write will have flushed it. */ - preempt_disable(); - native_write_cr3(__native_read_cr3()); - preempt_enable(); + if (!cpu_feature_enabled(X86_FEATURE_PCID)) + return; + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + __set_bit(kern_pcid(asid), + (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask)); } -static inline void __native_flush_tlb_global_irq_disabled(void) +/* + * flush the entire current user mapping + */ +static inline void __native_flush_tlb(void) { - unsigned long cr4; + /* + * Preemption or interrupts must be disabled to protect the access + * to the per CPU variable and to prevent being preempted between + * read_cr3() and write_cr3(). + */ + WARN_ON_ONCE(preemptible()); - cr4 = this_cpu_read(cpu_tlbstate.cr4); - /* clear PGE */ - native_write_cr4(cr4 & ~X86_CR4_PGE); - /* write old PGE again and flush TLBs */ - native_write_cr4(cr4); + invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid)); + + /* If current->mm == NULL then the read_cr3() "borrows" an mm */ + native_write_cr3(__native_read_cr3()); } +/* + * flush everything + */ static inline void __native_flush_tlb_global(void) { - unsigned long flags; + unsigned long cr4, flags; if (static_cpu_has(X86_FEATURE_INVPCID)) { /* * Using INVPCID is considerably faster than a pair of writes * to CR4 sandwiched inside an IRQ flag save/restore. + * + * Note, this works with CR4.PCIDE=0 or 1. */ invpcid_flush_all(); return; @@ -280,36 +386,69 @@ static inline void __native_flush_tlb_global(void) */ raw_local_irq_save(flags); - __native_flush_tlb_global_irq_disabled(); + cr4 = this_cpu_read(cpu_tlbstate.cr4); + /* toggle PGE */ + native_write_cr4(cr4 ^ X86_CR4_PGE); + /* write old PGE again and flush TLBs */ + native_write_cr4(cr4); raw_local_irq_restore(flags); } +/* + * flush one page in the user mapping + */ static inline void __native_flush_tlb_single(unsigned long addr) { + u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + /* + * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1. + * Just use invalidate_user_asid() in case we are called early. + */ + if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) + invalidate_user_asid(loaded_mm_asid); + else + invpcid_flush_one(user_pcid(loaded_mm_asid), addr); } +/* + * flush everything + */ static inline void __flush_tlb_all(void) { - if (boot_cpu_has(X86_FEATURE_PGE)) + if (boot_cpu_has(X86_FEATURE_PGE)) { __flush_tlb_global(); - else + } else { + /* + * !PGE -> !PCID (setup_pcid()), thus every flush is total. + */ __flush_tlb(); - - /* - * Note: if we somehow had PCID but not PGE, then this wouldn't work -- - * we'd end up flushing kernel translations for the current ASID but - * we might fail to flush kernel translations for other cached ASIDs. - * - * To avoid this issue, we force PCID off if PGE is off. - */ + } } +/* + * flush one page in the kernel mapping + */ static inline void __flush_tlb_one(unsigned long addr) { count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE); __flush_tlb_single(addr); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + /* + * __flush_tlb_single() will have cleared the TLB entry for this ASID, + * but since kernel space is replicated across all, we must also + * invalidate all others. + */ + invalidate_other_asid(); } #define TLB_FLUSH_ALL -1UL @@ -370,6 +509,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) void native_flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info); +static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) +{ + /* + * Bump the generation count. This also serves as a full barrier + * that synchronizes with switch_mm(): callers are required to order + * their read of mm_cpumask after their writes to the paging + * structures. + */ + return atomic64_inc_return(&mm->context.tlb_gen); +} + static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch, struct mm_struct *mm) { diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 84b9ec0c1bc0..22647a642e98 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -283,34 +283,34 @@ TRACE_EVENT(vector_alloc_managed, DECLARE_EVENT_CLASS(vector_activate, TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve, - bool early), + bool reserve), - TP_ARGS(irq, is_managed, can_reserve, early), + TP_ARGS(irq, is_managed, can_reserve, reserve), TP_STRUCT__entry( __field( unsigned int, irq ) __field( bool, is_managed ) __field( bool, can_reserve ) - __field( bool, early ) + __field( bool, reserve ) ), TP_fast_assign( __entry->irq = irq; __entry->is_managed = is_managed; __entry->can_reserve = can_reserve; - __entry->early = early; + __entry->reserve = reserve; ), - TP_printk("irq=%u is_managed=%d can_reserve=%d early=%d", + TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d", __entry->irq, __entry->is_managed, __entry->can_reserve, - __entry->early) + __entry->reserve) ); #define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name) \ DEFINE_EVENT_FN(vector_activate, name, \ TP_PROTO(unsigned int irq, bool is_managed, \ - bool can_reserve, bool early), \ - TP_ARGS(irq, is_managed, can_reserve, early), NULL, NULL); \ + bool can_reserve, bool reserve), \ + TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL); \ DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate); DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate); diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 1fadd310ff68..31051f35cbb7 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long); dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index e9cc6fe1fc6f..c1688c2d0a12 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -7,6 +7,9 @@ #include <asm/ptrace.h> #include <asm/stacktrace.h> +#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) +#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) + struct unwind_state { struct stack_info stack_info; unsigned long stack_mask; @@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task, } #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) +/* + * WARNING: The entire pt_regs may not be safe to dereference. In some cases, + * only the iret frame registers are accessible. Use with caution! + */ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state) { if (unwind_done(state)) diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index d9a7c659009c..b986b2ca688a 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -7,6 +7,7 @@ #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); +extern void set_vsyscall_pgtable_user_bits(pgd_t *root); /* * Called on instruction fetch fault in vsyscall page. diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 7e1e730396ae..bcba3c643e63 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -78,7 +78,12 @@ #define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT) #define X86_CR3_PCD_BIT 4 /* Page Cache Disable */ #define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT) -#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */ + +#define X86_CR3_PCID_BITS 12 +#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL)) + +#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */ +#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT) /* * Intel CPU features in CR4 diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6e272f3ea984..880441f24146 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2626,11 +2626,13 @@ static int __init apic_set_verbosity(char *arg) apic_verbosity = APIC_DEBUG; else if (strcmp("verbose", arg) == 0) apic_verbosity = APIC_VERBOSE; +#ifdef CONFIG_X86_64 else { pr_warning("APIC Verbosity level %s not recognised" " use apic=verbose or apic=debug\n", arg); return -EINVAL; } +#endif return 0; } diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index aa85690e9b64..25a87028cb3f 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -151,7 +151,7 @@ static struct apic apic_flat __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = flat_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 1, /* logical */ .disable_esr = 0, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 7b659c4480c9..5078b5ce63a7 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -110,7 +110,7 @@ struct apic apic_noop __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = noop_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 201579dc5242..8a7963421460 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2988,7 +2988,7 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, } int mp_irqdomain_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool early) + struct irq_data *irq_data, bool reserve) { unsigned long flags; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 9b18be764422..ce503c99f5c4 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -39,17 +39,13 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) ((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_REDIRECTION_CPU | MSI_ADDR_DEST_ID(cfg->dest_apicid); 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_DELIVERY_FIXED | MSI_DATA_VECTOR(cfg->vector); } diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index fa22017de806..02e8acb134f8 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,7 +105,7 @@ static struct apic apic_default __ro_after_init = { .apic_id_valid = default_apic_id_valid, .apic_id_registered = default_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, /* logical delivery broadcast to all CPUs: */ .irq_dest_mode = 1, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 750449152b04..f8b03bb8e725 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -184,6 +184,7 @@ static void reserve_irq_vector_locked(struct irq_data *irqd) irq_matrix_reserve(vector_matrix); apicd->can_reserve = true; apicd->has_reserved = true; + irqd_set_can_reserve(irqd); trace_vector_reserve(irqd->irq, 0); vector_assign_managed_shutdown(irqd); } @@ -368,8 +369,18 @@ static int activate_reserved(struct irq_data *irqd) int ret; ret = assign_irq_vector_any_locked(irqd); - if (!ret) + if (!ret) { apicd->has_reserved = false; + /* + * Core might have disabled reservation mode after + * allocating the irq descriptor. Ideally this should + * happen before allocation time, but that would require + * completely convoluted ways of transporting that + * information. + */ + if (!irqd_can_reserve(irqd)) + apicd->can_reserve = false; + } return ret; } @@ -398,21 +409,21 @@ static int activate_managed(struct irq_data *irqd) } static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd, - bool early) + bool reserve) { struct apic_chip_data *apicd = apic_chip_data(irqd); unsigned long flags; int ret = 0; trace_vector_activate(irqd->irq, apicd->is_managed, - apicd->can_reserve, early); + apicd->can_reserve, reserve); /* Nothing to do for fixed assigned vectors */ if (!apicd->can_reserve && !apicd->is_managed) return 0; raw_spin_lock_irqsave(&vector_lock, flags); - if (early || irqd_is_managed_and_shutdown(irqd)) + if (reserve || irqd_is_managed_and_shutdown(irqd)) vector_assign_managed_shutdown(irqd); else if (apicd->is_managed) ret = activate_managed(irqd); @@ -478,6 +489,7 @@ static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd, } else { /* Release the vector */ apicd->can_reserve = true; + irqd_set_can_reserve(irqd); clear_irq_vector(irqd); realloc = true; } diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 622f13ca8a94..8b04234e010b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -184,7 +184,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .apic_id_valid = x2apic_apic_id_valid, .apic_id_registered = x2apic_apic_id_registered, - .irq_delivery_mode = dest_LowestPrio, + .irq_delivery_mode = dest_Fixed, .irq_dest_mode = 1, /* logical */ .disable_esr = 0, diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 8ea78275480d..76417a9aab73 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -17,6 +17,7 @@ #include <asm/sigframe.h> #include <asm/bootparam.h> #include <asm/suspend.h> +#include <asm/tlbflush.h> #ifdef CONFIG_XEN #include <xen/interface/xen.h> @@ -93,4 +94,13 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + + /* TLB state for the entry code */ + OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); + + /* Layout info for cpu_entry_area */ + OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); + OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); + OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page); + DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack)); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index dedf428b20b6..fa1261eefa16 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -47,13 +47,8 @@ void foo(void) BLANK(); /* Offset from the sysenter stack to tss.sp0 */ - DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - - offsetofend(struct tss_struct, SYSENTER_stack)); - - /* Offset from cpu_tss to SYSENTER_stack */ - OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); - /* Size of SYSENTER_stack */ - DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); + DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - + offsetofend(struct cpu_entry_area, entry_stack_page.stack)); #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 630212fa9b9d..bf51e51d808d 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,6 +23,9 @@ int main(void) #ifdef CONFIG_PARAVIRT OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); +#ifdef CONFIG_DEBUG_ENTRY + OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl); +#endif BLANK(); #endif @@ -63,6 +66,7 @@ int main(void) OFFSET(TSS_ist, tss_struct, x86_tss.ist); OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); + OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); BLANK(); #ifdef CONFIG_CC_STACKPROTECTOR diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fa998ca8aa5a..c47de4ebf63a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -476,8 +476,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) return NULL; /* Not found */ } -__u32 cpu_caps_cleared[NCAPINTS]; -__u32 cpu_caps_set[NCAPINTS]; +__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +__u32 cpu_caps_set[NCAPINTS + NBUGINTS]; void load_percpu_segment(int cpu) { @@ -490,28 +490,23 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } -/* Setup the fixmap mapping only once per-processor */ -static inline void setup_fixmap_gdt(int cpu) -{ -#ifdef CONFIG_X86_64 - /* On 64-bit systems, we use a read-only fixmap GDT. */ - pgprot_t prot = PAGE_KERNEL_RO; -#else - /* - * On native 32-bit systems, the GDT cannot be read-only because - * our double fault handler uses a task gate, and entering through - * a task gate needs to change an available TSS to busy. If the GDT - * is read-only, that will triple fault. - * - * On Xen PV, the GDT must be read-only because the hypervisor requires - * it. - */ - pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ? - PAGE_KERNEL_RO : PAGE_KERNEL; +#ifdef CONFIG_X86_32 +/* The 32-bit entry code needs to find cpu_entry_area. */ +DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); #endif - __set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot); -} +#ifdef CONFIG_X86_64 +/* + * Special IST stacks which the CPU switches to when it calls + * an IST-marked descriptor entry. Up to 7 stacks (hardware + * limit), all of them are 4K, except the debug stack which + * is 8K. + */ +static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ +}; +#endif /* Load the original GDT from the per-cpu structure */ void load_direct_gdt(int cpu) @@ -747,7 +742,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c) { int i; - for (i = 0; i < NCAPINTS; i++) { + for (i = 0; i < NCAPINTS + NBUGINTS; i++) { c->x86_capability[i] &= ~cpu_caps_cleared[i]; c->x86_capability[i] |= cpu_caps_set[i]; } @@ -927,6 +922,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) } setup_force_cpu_cap(X86_FEATURE_ALWAYS); + + /* Assume for now that ALL x86 CPUs are insecure */ + setup_force_cpu_bug(X86_BUG_CPU_INSECURE); + fpu__init_system(c); #ifdef CONFIG_X86_32 @@ -1250,7 +1249,7 @@ void enable_sep_cpu(void) return; cpu = get_cpu(); - tss = &per_cpu(cpu_tss, cpu); + tss = &per_cpu(cpu_tss_rw, cpu); /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- @@ -1259,11 +1258,7 @@ void enable_sep_cpu(void) tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - - wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), - 0); - + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1357,25 +1352,22 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); -/* - * Special IST stacks which the CPU switches to when it calls - * an IST-marked descriptor entry. Up to 7 stacks (hardware - * limit), all of them are 4K, except the debug stack which - * is 8K. - */ -static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { - [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, - [DEBUG_STACK - 1] = DEBUG_STKSZ -}; - -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); - /* May not be marked __init: used by software suspend */ void syscall_init(void) { + extern char _entry_trampoline[]; + extern char entry_SYSCALL_64_trampoline[]; + + int cpu = smp_processor_id(); + unsigned long SYSCALL64_entry_trampoline = + (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + + (entry_SYSCALL_64_trampoline - _entry_trampoline); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + if (static_cpu_has(X86_FEATURE_PTI)) + wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); + else + wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); @@ -1386,7 +1378,7 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1530,7 +1522,7 @@ void cpu_init(void) if (cpu) load_ucode_ap(); - t = &per_cpu(cpu_tss, cpu); + t = &per_cpu(cpu_tss_rw, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1569,7 +1561,7 @@ void cpu_init(void) * set up and load the per-CPU TSS */ if (!oist->ist[0]) { - char *estacks = per_cpu(exception_stacks, cpu); + char *estacks = get_cpu_entry_area(cpu)->exception_stacks; for (v = 0; v < N_EXCEPTION_STACKS; v++) { estacks += exception_stack_sizes[v]; @@ -1580,7 +1572,7 @@ void cpu_init(void) } } - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; /* * <= is required because the CPU will access up to @@ -1596,11 +1588,12 @@ void cpu_init(void) enter_lazy_tlb(&init_mm, me); /* - * Initialize the TSS. Don't bother initializing sp0, as the initial - * task never enters user mode. + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); load_mm_ldt(&init_mm); @@ -1612,7 +1605,6 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } @@ -1622,7 +1614,7 @@ void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); wait_for_master_cpu(cpu); @@ -1657,12 +1649,12 @@ void cpu_init(void) * Initialize the TSS. Don't bother initializing sp0, as the initial * task never enters user mode. */ - set_tss_desc(cpu, t); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); load_mm_ldt(&init_mm); - t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap); + t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET; #ifdef CONFIG_DOUBLEFAULT /* Set up doublefault TSS pointer in the GDT */ @@ -1674,7 +1666,6 @@ void cpu_init(void) fpu__init_cpu(); - setup_fixmap_gdt(cpu); load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 7dbcb7adf797..8ccdca6d3f9e 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -565,15 +565,6 @@ static void print_ucode(struct ucode_cpu_info *uci) } #else -/* - * Flush global tlb. We only do this in x86_64 where paging has been enabled - * already and PGE should be enabled as well. - */ -static inline void flush_tlb_early(void) -{ - __native_flush_tlb_global_irq_disabled(); -} - static inline void print_ucode(struct ucode_cpu_info *uci) { struct microcode_intel *mc; @@ -602,10 +593,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) if (rev != mc->hdr.rev) return -1; -#ifdef CONFIG_X86_64 - /* Flush global tlb. This is precaution. */ - flush_tlb_early(); -#endif uci->cpu_sig.rev = rev; if (early) diff --git a/arch/x86/kernel/doublefault.c b/arch/x86/kernel/doublefault.c index 0e662c55ae90..0b8cedb20d6d 100644 --- a/arch/x86/kernel/doublefault.c +++ b/arch/x86/kernel/doublefault.c @@ -50,25 +50,23 @@ static void doublefault_fn(void) cpu_relax(); } -struct tss_struct doublefault_tss __cacheline_aligned = { - .x86_tss = { - .sp0 = STACK_START, - .ss0 = __KERNEL_DS, - .ldt = 0, - .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, - - .ip = (unsigned long) doublefault_fn, - /* 0x2 bit is always set */ - .flags = X86_EFLAGS_SF | 0x2, - .sp = STACK_START, - .es = __USER_DS, - .cs = __KERNEL_CS, - .ss = __KERNEL_DS, - .ds = __USER_DS, - .fs = __KERNEL_PERCPU, - - .__cr3 = __pa_nodebug(swapper_pg_dir), - } +struct x86_hw_tss doublefault_tss __cacheline_aligned = { + .sp0 = STACK_START, + .ss0 = __KERNEL_DS, + .ldt = 0, + .io_bitmap_base = INVALID_IO_BITMAP_OFFSET, + + .ip = (unsigned long) doublefault_fn, + /* 0x2 bit is always set */ + .flags = X86_EFLAGS_SF | 0x2, + .sp = STACK_START, + .es = __USER_DS, + .cs = __KERNEL_CS, + .ss = __KERNEL_DS, + .ds = __USER_DS, + .fs = __KERNEL_PERCPU, + + .__cr3 = __pa_nodebug(swapper_pg_dir), }; /* dummy for do_double_fault() call */ diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f13b4c00a5de..5fa110699ed2 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -18,6 +18,7 @@ #include <linux/nmi.h> #include <linux/sysfs.h> +#include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> #include <asm/unwind.h> @@ -43,6 +44,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } +bool in_entry_stack(unsigned long *stack, struct stack_info *info) +{ + struct entry_stack *ss = cpu_entry_stack(smp_processor_id()); + + void *begin = ss; + void *end = ss + 1; + + if ((void *)stack < begin || (void *)stack >= end) + return false; + + info->type = STACK_TYPE_ENTRY; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, char *log_lvl) { @@ -50,6 +69,28 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +void show_iret_regs(struct pt_regs *regs) +{ + printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip); + printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss, + regs->sp, regs->flags); +} + +static void show_regs_safe(struct stack_info *info, struct pt_regs *regs) +{ + if (on_stack(info, regs, sizeof(*regs))) + __show_regs(regs, 0); + else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET, + IRET_FRAME_SIZE)) { + /* + * When an interrupt or exception occurs in entry code, the + * full pt_regs might not have been saved yet. In that case + * just print the iret frame. + */ + show_iret_regs(regs); + } +} + void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, char *log_lvl) { @@ -71,31 +112,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - task stack * - interrupt stack * - HW exception stacks (double fault, nmi, debug, mce) + * - entry stack * - * x86-32 can have up to three stacks: + * x86-32 can have up to four stacks: * - task stack * - softirq stack * - hardirq stack + * - entry stack */ for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; - /* - * If we overflowed the task stack into a guard page, jump back - * to the bottom of the usable stack. - */ - if (task_stack_page(task) - (void *)stack < PAGE_SIZE) - stack = task_stack_page(task); - - if (get_stack_info(stack, task, &stack_info, &visit_mask)) - break; + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) + break; + } stack_name = stack_type_name(stack_info.type); if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); /* * Scan the stack, printing any text addresses we find. At the @@ -119,7 +164,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, /* * Don't print regs->ip again if it was already printed - * by __show_regs() below. + * by show_regs_safe() below. */ if (regs && stack == ®s->ip) goto next; @@ -155,8 +200,8 @@ next: /* if the frame has entry regs, print them */ regs = unwind_get_entry_regs(&state); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); } if (stack_name) @@ -252,11 +297,13 @@ int __die(const char *str, struct pt_regs *regs, long err) unsigned long sp; #endif printk(KERN_DEFAULT - "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter, + "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter, IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", - IS_ENABLED(CONFIG_KASAN) ? " KASAN" : ""); + IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", + IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? + (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index daefae83a3aa..04170f63e3a1 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_SOFTIRQ) return "SOFTIRQ"; + if (type == STACK_TYPE_ENTRY) + return "ENTRY_TRAMPOLINE"; + return NULL; } @@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (task != current) goto unknown; + if (in_entry_stack(stack, info)) + goto recursion_check; + if (in_hardirq_stack(stack, info)) goto recursion_check; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 88ce2ffdb110..563e28d14f2c 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -37,6 +37,15 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_IRQ) return "IRQ"; + if (type == STACK_TYPE_ENTRY) { + /* + * On 64-bit, we have a generic entry stack that we + * use for all the kernel entry points, including + * SYSENTER. + */ + return "ENTRY_TRAMPOLINE"; + } + if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST) return exception_stack_names[type - STACK_TYPE_EXCEPTION]; @@ -115,6 +124,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (in_irq_stack(stack, info)) goto recursion_check; + if (in_entry_stack(stack, info)) + goto recursion_check; + goto unknown; recursion_check: diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 7dca675fe78d..04a625f0fcda 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag) .balign PAGE_SIZE; \ GLOBAL(name) +#ifdef CONFIG_PAGE_TABLE_ISOLATION +/* + * Each PGD needs to be 8k long and 8k aligned. We do not + * ever go out to userspace with these, so we do not + * strictly *need* the second page, but this allows us to + * have a single set_pgd() implementation that does not + * need to worry about whether it has 4k or 8k to work + * with. + * + * This ensures PGDs are 8k long: + */ +#define PTI_USER_PGD_FILL 512 +/* This ensures they are 8k-aligned: */ +#define NEXT_PGD_PAGE(name) \ + .balign 2 * PAGE_SIZE; \ +GLOBAL(name) +#else +#define NEXT_PGD_PAGE(name) NEXT_PAGE(name) +#define PTI_USER_PGD_FILL 0 +#endif + /* Automate the creation of 1 to 1 mapping pmd entries */ #define PMDS(START, PERM, COUNT) \ i = 0 ; \ @@ -350,13 +371,14 @@ GLOBAL(name) .endr __INITDATA -NEXT_PAGE(early_top_pgt) +NEXT_PGD_PAGE(early_top_pgt) .fill 511,8,0 #ifdef CONFIG_X86_5LEVEL .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #else .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC #endif + .fill PTI_USER_PGD_FILL,8,0 NEXT_PAGE(early_dynamic_pgts) .fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0 @@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts) .data #if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH) -NEXT_PAGE(init_top_pgt) +NEXT_PGD_PAGE(init_top_pgt) .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_PAGE_OFFSET*8, 0 .quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC .org init_top_pgt + PGD_START_KERNEL*8, 0 /* (2^48-(2*1024*1024*1024))/(2^39) = 511 */ .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC + .fill PTI_USER_PGD_FILL,8,0 NEXT_PAGE(level3_ident_pgt) .quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC @@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt) */ PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD) #else -NEXT_PAGE(init_top_pgt) +NEXT_PGD_PAGE(init_top_pgt) .fill 512,8,0 + .fill PTI_USER_PGD_FILL,8,0 #endif #ifdef CONFIG_X86_5LEVEL diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 3feb648781c4..2f723301eb58 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * because the ->io_bitmap_max value must match the bitmap * contents: */ - tss = &per_cpu(cpu_tss, get_cpu()); + tss = &per_cpu(cpu_tss_rw, get_cpu()); if (turn_on) bitmap_clear(t->io_bitmap_ptr, from, num); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 49cfd9fe7589..68e1867cca80 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) /* high bit used in ret_from_ code */ unsigned vector = ~regs->orig_ax; - /* - * NB: Unlike exception entries, IRQ entries do not reliably - * handle context tracking in the low-level entry code. This is - * because syscall entries execute briefly with IRQs on before - * updating context tracking state, so we can take an IRQ from - * kernel mode with CONTEXT_USER. The low-level entry code only - * updates the context if we came from user mode, so we won't - * switch to CONTEXT_KERNEL. We'll fix that once the syscall - * code is cleaned up enough that we can cleanly defer enabling - * IRQs. - */ - entering_irq(); /* entering_irq() tells RCU that we're not quiescent. Check it. */ diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 020efbf5786b..d86e344f5b3d 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs) if (regs->sp >= estack_top && regs->sp <= estack_bottom) return; - WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n", + WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n", current->comm, curbase, regs->sp, irq_stack_top, irq_stack_bottom, - estack_top, estack_bottom); + estack_top, estack_bottom, (void *)regs->ip); if (sysctl_panic_on_stackoverflow) panic("low stack detected by irq handler - check messages\n"); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 1c1eae961340..26d713ecad34 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -5,6 +5,11 @@ * Copyright (C) 2002 Andi Kleen * * This handles calls from both 32bit and 64bit mode. + * + * Lock order: + * contex.ldt_usr_sem + * mmap_sem + * context.lock */ #include <linux/errno.h> @@ -19,6 +24,7 @@ #include <linux/uaccess.h> #include <asm/ldt.h> +#include <asm/tlb.h> #include <asm/desc.h> #include <asm/mmu_context.h> #include <asm/syscalls.h> @@ -42,17 +48,15 @@ static void refresh_ldt_segments(void) #endif } -/* context.lock is held for us, so we don't need any locking. */ +/* context.lock is held by the task which issued the smp function call */ static void flush_ldt(void *__mm) { struct mm_struct *mm = __mm; - mm_context_t *pc; if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm) return; - pc = &mm->context; - set_ldt(pc->ldt->entries, pc->ldt->nr_entries); + load_mm_ldt(mm); refresh_ldt_segments(); } @@ -89,25 +93,143 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) return NULL; } + /* The new LDT isn't aliased for PTI yet. */ + new_ldt->slot = -1; + new_ldt->nr_entries = num_entries; return new_ldt; } +/* + * If PTI is enabled, this maps the LDT into the kernelmode and + * usermode tables for the given mm. + * + * There is no corresponding unmap function. Even if the LDT is freed, we + * leave the PTEs around until the slot is reused or the mm is destroyed. + * This is harmless: the LDT is always in ordinary memory, and no one will + * access the freed slot. + * + * If we wanted to unmap freed LDTs, we'd also need to do a flush to make + * it useful, and the flush would slow down modify_ldt(). + */ +static int +map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + bool is_vmalloc, had_top_level_entry; + unsigned long va; + spinlock_t *ptl; + pgd_t *pgd; + int i; + + if (!static_cpu_has(X86_FEATURE_PTI)) + return 0; + + /* + * Any given ldt_struct should have map_ldt_struct() called at most + * once. + */ + WARN_ON(ldt->slot != -1); + + /* + * Did we already have the top level entry allocated? We can't + * use pgd_none() for this because it doens't do anything on + * 4-level page table kernels. + */ + pgd = pgd_offset(mm, LDT_BASE_ADDR); + had_top_level_entry = (pgd->pgd != 0); + + is_vmalloc = is_vmalloc_addr(ldt->entries); + + for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) { + unsigned long offset = i << PAGE_SHIFT; + const void *src = (char *)ldt->entries + offset; + unsigned long pfn; + pte_t pte, *ptep; + + va = (unsigned long)ldt_slot_va(slot) + offset; + pfn = is_vmalloc ? vmalloc_to_pfn(src) : + page_to_pfn(virt_to_page(src)); + /* + * Treat the PTI LDT range as a *userspace* range. + * get_locked_pte() will allocate all needed pagetables + * and account for them in this mm. + */ + ptep = get_locked_pte(mm, va, &ptl); + if (!ptep) + return -ENOMEM; + /* + * Map it RO so the easy to find address is not a primary + * target via some kernel interface which misses a + * permission check. + */ + pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL)); + set_pte_at(mm, va, ptep, pte); + pte_unmap_unlock(ptep, ptl); + } + + if (mm->context.ldt) { + /* + * We already had an LDT. The top-level entry should already + * have been allocated and synchronized with the usermode + * tables. + */ + WARN_ON(!had_top_level_entry); + if (static_cpu_has(X86_FEATURE_PTI)) + WARN_ON(!kernel_to_user_pgdp(pgd)->pgd); + } else { + /* + * This is the first time we're mapping an LDT for this process. + * Sync the pgd to the usermode tables. + */ + WARN_ON(had_top_level_entry); + if (static_cpu_has(X86_FEATURE_PTI)) { + WARN_ON(kernel_to_user_pgdp(pgd)->pgd); + set_pgd(kernel_to_user_pgdp(pgd), *pgd); + } + } + + va = (unsigned long)ldt_slot_va(slot); + flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0); + + ldt->slot = slot; +#endif + return 0; +} + +static void free_ldt_pgtables(struct mm_struct *mm) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + struct mmu_gather tlb; + unsigned long start = LDT_BASE_ADDR; + unsigned long end = start + (1UL << PGDIR_SHIFT); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + tlb_gather_mmu(&tlb, mm, start, end); + free_pgd_range(&tlb, start, end, start, end); + tlb_finish_mmu(&tlb, start, end); +#endif +} + /* After calling this, the LDT is immutable. */ static void finalize_ldt_struct(struct ldt_struct *ldt) { paravirt_alloc_ldt(ldt->entries, ldt->nr_entries); } -/* context.lock is held */ -static void install_ldt(struct mm_struct *current_mm, - struct ldt_struct *ldt) +static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt) { + mutex_lock(&mm->context.lock); + /* Synchronizes with READ_ONCE in load_mm_ldt. */ - smp_store_release(¤t_mm->context.ldt, ldt); + smp_store_release(&mm->context.ldt, ldt); - /* Activate the LDT for all CPUs using current_mm. */ - on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true); + /* Activate the LDT for all CPUs using currents mm. */ + on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true); + + mutex_unlock(&mm->context.lock); } static void free_ldt_struct(struct ldt_struct *ldt) @@ -124,27 +246,20 @@ static void free_ldt_struct(struct ldt_struct *ldt) } /* - * we do not have to muck with descriptors here, that is - * done in switch_mm() as needed. + * Called on fork from arch_dup_mmap(). Just copy the current LDT state, + * the new task is not running, so nothing can be installed. */ -int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) +int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm) { struct ldt_struct *new_ldt; - struct mm_struct *old_mm; int retval = 0; - mutex_init(&mm->context.lock); - old_mm = current->mm; - if (!old_mm) { - mm->context.ldt = NULL; + if (!old_mm) return 0; - } mutex_lock(&old_mm->context.lock); - if (!old_mm->context.ldt) { - mm->context.ldt = NULL; + if (!old_mm->context.ldt) goto out_unlock; - } new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries); if (!new_ldt) { @@ -156,6 +271,12 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm) new_ldt->nr_entries * LDT_ENTRY_SIZE); finalize_ldt_struct(new_ldt); + retval = map_ldt_struct(mm, new_ldt, 0); + if (retval) { + free_ldt_pgtables(mm); + free_ldt_struct(new_ldt); + goto out_unlock; + } mm->context.ldt = new_ldt; out_unlock: @@ -174,13 +295,18 @@ void destroy_context_ldt(struct mm_struct *mm) mm->context.ldt = NULL; } +void ldt_arch_exit_mmap(struct mm_struct *mm) +{ + free_ldt_pgtables(mm); +} + static int read_ldt(void __user *ptr, unsigned long bytecount) { struct mm_struct *mm = current->mm; unsigned long entries_size; int retval; - mutex_lock(&mm->context.lock); + down_read(&mm->context.ldt_usr_sem); if (!mm->context.ldt) { retval = 0; @@ -209,7 +335,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount) retval = bytecount; out_unlock: - mutex_unlock(&mm->context.lock); + up_read(&mm->context.ldt_usr_sem); return retval; } @@ -269,7 +395,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) ldt.avl = 0; } - mutex_lock(&mm->context.lock); + if (down_write_killable(&mm->context.ldt_usr_sem)) + return -EINTR; old_ldt = mm->context.ldt; old_nr_entries = old_ldt ? old_ldt->nr_entries : 0; @@ -286,12 +413,31 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) new_ldt->entries[ldt_info.entry_number] = ldt; finalize_ldt_struct(new_ldt); + /* + * If we are using PTI, map the new LDT into the userspace pagetables. + * If there is already an LDT, use the other slot so that other CPUs + * will continue to use the old LDT until install_ldt() switches + * them over to the new LDT. + */ + error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0); + if (error) { + /* + * This only can fail for the first LDT setup. If an LDT is + * already installed then the PTE page is already + * populated. Mop up a half populated page table. + */ + if (!WARN_ON_ONCE(old_ldt)) + free_ldt_pgtables(mm); + free_ldt_struct(new_ldt); + goto out_unlock; + } + install_ldt(mm, new_ldt); free_ldt_struct(old_ldt); error = 0; out_unlock: - mutex_unlock(&mm->context.lock); + up_write(&mm->context.ldt_usr_sem); out: return error; } diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 00bc751c861c..edfede768688 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -48,8 +48,6 @@ static void load_segments(void) "\tmovl $"STR(__KERNEL_DS)",%%eax\n" "\tmovl %%eax,%%ds\n" "\tmovl %%eax,%%es\n" - "\tmovl %%eax,%%fs\n" - "\tmovl %%eax,%%gs\n" "\tmovl %%eax,%%ss\n" : : : "eax", "memory"); #undef STR @@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image) * The gdt & idt are now invalid. * If you want to load them you must set up your own idt & gdt. */ - set_gdt(phys_to_virt(0), 0); idt_invalidate(phys_to_virt(0)); + set_gdt(phys_to_virt(0), 0); /* now call it */ image->start = relocate_kernel_ptr((unsigned long)image->head, diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index ac0be8283325..9edadabf04f6 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -10,7 +10,6 @@ DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); -DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); @@ -60,7 +59,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); - PATCH_SITE(pv_mmu_ops, flush_tlb_single); PATCH_SITE(pv_cpu_ops, wbinvd); #if defined(CONFIG_PARAVIRT_SPINLOCKS) case PARAVIRT_PATCH(pv_lock_ops.queued_spin_unlock): diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index bb988a24db92..aed9d94bd46f 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -47,7 +47,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss_rw) = { .x86_tss = { /* * .sp0 is only used when entering ring 0 from a lower @@ -56,6 +56,16 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { * Poison it. */ .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, + +#ifdef CONFIG_X86_64 + /* + * .sp1 is cpu_current_top_of_stack. The init task never + * runs user code, but cpu_current_top_of_stack should still + * be well defined before the first context switch. + */ + .sp1 = TOP_OF_INIT_STACK, +#endif + #ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, @@ -71,11 +81,8 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif -#ifdef CONFIG_X86_32 - .SYSENTER_stack_canary = STACK_END_MAGIC, -#endif }; -EXPORT_PER_CPU_SYMBOL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); DEFINE_PER_CPU(bool, __tss_limit_invalid); EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); @@ -104,7 +111,7 @@ void exit_thread(struct task_struct *tsk) struct fpu *fpu = &t->fpu; if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); t->io_bitmap_ptr = NULL; clear_thread_flag(TIF_IO_BITMAP); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 45bf0c5f93e1..5224c6099184 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index eeeb34f85c25..c75466232016 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -69,9 +69,8 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip); - printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss, - regs->sp, regs->flags); + show_iret_regs(regs); + if (regs->orig_ax != -1) pr_cont(" ORIG_RAX: %016lx\n", regs->orig_ax); else @@ -88,6 +87,9 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); + if (!all) + return; + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); @@ -98,9 +100,6 @@ void __show_regs(struct pt_regs *regs, int all) rdmsrl(MSR_GS_BASE, gs); rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); - if (!all) - return; - cr0 = read_cr0(); cr2 = read_cr2(); cr3 = __read_cr3(); @@ -400,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(irq_count) != -1); @@ -462,6 +461,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) * Switch the PDA and FPU contexts. */ this_cpu_write(current_task, next_p); + this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); /* Reload sp0. */ update_sp0(next_p); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 35cb20994e32..ed556d50d7ed 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -126,14 +126,10 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) spin_lock_irqsave(&rtc_lock, flags); CMOS_WRITE(0xa, 0xf); spin_unlock_irqrestore(&rtc_lock, flags); - local_flush_tlb(); - pr_debug("1.\n"); *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4; - pr_debug("2.\n"); *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf; - pr_debug("3.\n"); } static inline void smpboot_restore_warm_reset_vector(void) @@ -141,11 +137,6 @@ static inline void smpboot_restore_warm_reset_vector(void) unsigned long flags; /* - * Install writable page 0 entry to set BIOS data area. - */ - local_flush_tlb(); - - /* * Paranoid: Set warm reset code and vector here back * to default values. */ @@ -932,12 +923,8 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, initial_code = (unsigned long)start_secondary; initial_stack = idle->thread.sp; - /* - * Enable the espfix hack for this CPU - */ -#ifdef CONFIG_X86_ESPFIX64 + /* Enable the espfix hack for this CPU */ init_espfix_ap(cpu); -#endif /* So we see what's up */ announce_cpu(cpu, apicid); diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 77835bc021c7..20161ef53537 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -164,8 +164,12 @@ int save_stack_trace_tsk_reliable(struct task_struct *tsk, { int ret; + /* + * If the task doesn't have a stack (e.g., a zombie), the stack is + * "reliably" empty. + */ if (!try_get_task_stack(tsk)) - return -EINVAL; + return 0; ret = __save_stack_trace_reliable(trace, tsk); diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 9a9c9b076955..a5b802a12212 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx, cpu = get_cpu(); while (n-- > 0) { - if (LDT_empty(info) || LDT_zero(info)) { + if (LDT_empty(info) || LDT_zero(info)) memset(desc, 0, sizeof(*desc)); - } else { + else fill_ldt(desc, info); - - /* - * Always set the accessed bit so that the CPU - * doesn't try to write to the (read-only) GDT. - */ - desc->type |= 1; - } ++info; ++desc; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 989514c94a55..446c9ef8cfc3 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -51,6 +51,7 @@ #include <asm/traps.h> #include <asm/desc.h> #include <asm/fpu/internal.h> +#include <asm/cpu_entry_area.h> #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> @@ -348,23 +349,42 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) /* * 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. + * end up promoting it to a doublefault. In that case, take + * advantage of the fact that we're not using the normal (TSS.sp0) + * stack right now. We can write a fake #GP(0) frame at TSS.sp0 + * and then modify our own IRET frame so that, when we return, + * we land directly at the #GP(0) vector with the stack already + * set up according to its expectations. + * + * The net result is that our #GP handler will think that we + * entered from usermode with the bad user context. * * No need for ist_enter here because we don't use RCU. */ - if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY && + if (((long)regs->sp >> P4D_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); + struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; - /* 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->sp points to the failing IRET frame on the + * ESPFIX64 stack. Copy it to the entry stack. This fills + * in gpregs->ss through gpregs->ip. + * + */ + memmove(&gpregs->ip, (void *)regs->sp, 5*8); + gpregs->orig_ax = 0; /* Missing (lost) #GP error code */ + + /* + * Adjust our frame so that we return straight to the #GP + * vector with the expected RSP value. This is safe because + * we won't enable interupts or schedule before we invoke + * general_protection, so nothing will clobber the stack + * frame we just set up. + */ regs->ip = (unsigned long)general_protection; - regs->sp = (unsigned long)&normal_regs->orig_ax; + regs->sp = (unsigned long)&gpregs->orig_ax; return; } @@ -389,7 +409,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * * Processors update CR2 whenever a page fault is detected. If a * second page fault occurs while an earlier page fault is being - * deliv- ered, the faulting linear address of the second fault will + * delivered, the faulting linear address of the second fault will * overwrite the contents of CR2 (replacing the previous * address). These updates to CR2 occur even if the page fault * results in a double fault or occurs during the delivery of a @@ -605,14 +625,15 @@ NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* - * Help handler running on IST stack to switch off the IST stack if the - * interrupted code was in user mode. The actual stack switch is done in - * entry_64.S + * Help handler running on a per-cpu (IST or entry trampoline) stack + * to switch to the normal thread stack if the interrupted code was in + * user mode. The actual stack switch is done in entry_64.S */ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = task_pt_regs(current); - *regs = *eregs; + struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; + if (regs != eregs) + *regs = *eregs; return regs; } NOKPROBE_SYMBOL(sync_regs); @@ -628,13 +649,13 @@ 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. + * correctly, we want to move our stack frame to where it would + * be had we entered directly on the entry stack (rather than + * just below the IRET frame) 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); + (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the new stack. */ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); @@ -795,14 +816,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: -#if defined(CONFIG_X86_32) - /* - * This is the most likely code path that involves non-trivial use - * of the SYSENTER stack. Check that we haven't overrun it. - */ - WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC, - "Overran or corrupted SYSENTER stack\n"); -#endif ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -929,6 +942,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) void __init trap_init(void) { + /* Init cpu_entry_area before IST entries are set up */ + setup_cpu_entry_areas(); + idt_setup_traps(); /* @@ -936,8 +952,9 @@ void __init trap_init(void) * "sidt" instruction will not leak the location of the kernel, and * to defend the IDT against arbitrary memory write vulnerabilities. * It will be reloaded in cpu_init() */ - __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); - idt_descr.address = fix_to_virt(FIX_RO_IDT); + cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table), + PAGE_KERNEL_RO); + idt_descr.address = CPU_ENTRY_AREA_RO_IDT; /* * Should be a barrier for any external CPU state: diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index a3f973b2c97a..be86a865087a 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -253,22 +253,15 @@ unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) return NULL; } -static bool stack_access_ok(struct unwind_state *state, unsigned long addr, +static bool stack_access_ok(struct unwind_state *state, unsigned long _addr, size_t len) { struct stack_info *info = &state->stack_info; + void *addr = (void *)_addr; - /* - * If the address isn't on the current stack, switch to the next one. - * - * We may have to traverse multiple stacks to deal with the possibility - * that info->next_sp could point to an empty stack and the address - * could be on a subsequent stack. - */ - while (!on_stack(info, (void *)addr, len)) - if (get_stack_info(info->next_sp, state->task, info, - &state->stack_mask)) - return false; + if (!on_stack(info, addr, len) && + (get_stack_info(addr, state->task, info, &state->stack_mask))) + return false; return true; } @@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr, return true; } -#define REGS_SIZE (sizeof(struct pt_regs)) -#define SP_OFFSET (offsetof(struct pt_regs, sp)) -#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip)) -#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip)) - static bool deref_stack_regs(struct unwind_state *state, unsigned long addr, - unsigned long *ip, unsigned long *sp, bool full) + unsigned long *ip, unsigned long *sp) { - size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE; - size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET; - struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE); - - if (IS_ENABLED(CONFIG_X86_64)) { - if (!stack_access_ok(state, addr, regs_size)) - return false; + struct pt_regs *regs = (struct pt_regs *)addr; - *ip = regs->ip; - *sp = regs->sp; + /* x86-32 support will be more complicated due to the ®s->sp hack */ + BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32)); - return true; - } - - if (!stack_access_ok(state, addr, sp_offset)) + if (!stack_access_ok(state, addr, sizeof(struct pt_regs))) return false; *ip = regs->ip; + *sp = regs->sp; + return true; +} - if (user_mode(regs)) { - if (!stack_access_ok(state, addr + sp_offset, - REGS_SIZE - SP_OFFSET)) - return false; +static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr, + unsigned long *ip, unsigned long *sp) +{ + struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET; - *sp = regs->sp; - } else - *sp = (unsigned long)®s->sp; + if (!stack_access_ok(state, addr, IRET_FRAME_SIZE)) + return false; + *ip = regs->ip; + *sp = regs->sp; return true; } @@ -327,7 +310,6 @@ bool unwind_next_frame(struct unwind_state *state) unsigned long ip_p, sp, orig_ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; - struct pt_regs *ptregs; bool indirect = false; if (unwind_done(state)) @@ -435,7 +417,7 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_TYPE_REGS: - if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) { + if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; @@ -447,20 +429,14 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_TYPE_REGS_IRET: - if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) { + if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { orc_warn("can't dereference iret registers at %p for ip %pB\n", (void *)sp, (void *)orig_ip); goto done; } - ptregs = container_of((void *)sp, struct pt_regs, ip); - if ((unsigned long)ptregs >= prev_sp && - on_stack(&state->stack_info, ptregs, REGS_SIZE)) { - state->regs = ptregs; - state->full_regs = false; - } else - state->regs = NULL; - + state->regs = (void *)sp - IRET_FRAME_OFFSET; + state->full_regs = false; state->signal = true; break; @@ -553,8 +529,18 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, } if (get_stack_info((unsigned long *)state->sp, state->task, - &state->stack_info, &state->stack_mask)) - return; + &state->stack_info, &state->stack_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + if (get_stack_info(next_page, state->task, &state->stack_info, + &state->stack_mask)) + return; + } /* * The caller can provide the address of the first frame directly diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a4009fb9be87..1e413a9326aa 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -61,11 +61,17 @@ jiffies_64 = jiffies; . = ALIGN(HPAGE_SIZE); \ __end_rodata_hpage_align = .; +#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE); +#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE); + #else #define X64_ALIGN_RODATA_BEGIN #define X64_ALIGN_RODATA_END +#define ALIGN_ENTRY_TEXT_BEGIN +#define ALIGN_ENTRY_TEXT_END + #endif PHDRS { @@ -102,11 +108,22 @@ SECTIONS CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT + ALIGN_ENTRY_TEXT_BEGIN ENTRY_TEXT IRQENTRY_TEXT + ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_X86_64 + . = ALIGN(PAGE_SIZE); + _entry_trampoline = .; + *(.entry_trampoline) + . = ALIGN(PAGE_SIZE); + ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); +#endif + /* End of text section */ _etext = .; } :text = 0x9090 diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index abe74f779f9d..b514b2b2845a 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2390,9 +2390,21 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) } static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, - u64 cr0, u64 cr4) + u64 cr0, u64 cr3, u64 cr4) { int bad; + u64 pcid; + + /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ + pcid = 0; + if (cr4 & X86_CR4_PCIDE) { + pcid = cr3 & 0xfff; + cr3 &= ~0xfff; + } + + bad = ctxt->ops->set_cr(ctxt, 3, cr3); + if (bad) + return X86EMUL_UNHANDLEABLE; /* * First enable PAE, long mode needs it before CR0.PG = 1 is set. @@ -2411,6 +2423,12 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, bad = ctxt->ops->set_cr(ctxt, 4, cr4); if (bad) return X86EMUL_UNHANDLEABLE; + if (pcid) { + bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + } return X86EMUL_CONTINUE; @@ -2421,11 +2439,11 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) struct desc_struct desc; struct desc_ptr dt; u16 selector; - u32 val, cr0, cr4; + u32 val, cr0, cr3, cr4; int i; cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); - ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8)); + cr3 = GET_SMSTATE(u32, smbase, 0x7ff8); ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); @@ -2467,14 +2485,14 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); - return rsm_enter_protected_mode(ctxt, cr0, cr4); + return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); } static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) { struct desc_struct desc; struct desc_ptr dt; - u64 val, cr0, cr4; + u64 val, cr0, cr3, cr4; u32 base3; u16 selector; int i, r; @@ -2491,7 +2509,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); cr0 = GET_SMSTATE(u64, smbase, 0x7f58); - ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u64, smbase, 0x7f50)); + cr3 = GET_SMSTATE(u64, smbase, 0x7f50); cr4 = GET_SMSTATE(u64, smbase, 0x7f48); ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); val = GET_SMSTATE(u64, smbase, 0x7ed0); @@ -2519,7 +2537,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) dt.address = GET_SMSTATE(u64, smbase, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); - r = rsm_enter_protected_mode(ctxt, cr0, cr4); + r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); if (r != X86EMUL_CONTINUE) return r; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e5e66e5c6640..c4deb1f34faa 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3395,7 +3395,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); if(make_mmu_pages_available(vcpu) < 0) { spin_unlock(&vcpu->kvm->mmu_lock); - return 1; + return -ENOSPC; } sp = kvm_mmu_get_page(vcpu, 0, 0, vcpu->arch.mmu.shadow_root_level, 1, ACC_ALL); @@ -3410,7 +3410,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); if (make_mmu_pages_available(vcpu) < 0) { spin_unlock(&vcpu->kvm->mmu_lock); - return 1; + return -ENOSPC; } sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL); @@ -3450,7 +3450,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); if (make_mmu_pages_available(vcpu) < 0) { spin_unlock(&vcpu->kvm->mmu_lock); - return 1; + return -ENOSPC; } sp = kvm_mmu_get_page(vcpu, root_gfn, 0, vcpu->arch.mmu.shadow_root_level, 0, ACC_ALL); @@ -3487,7 +3487,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); if (make_mmu_pages_available(vcpu) < 0) { spin_unlock(&vcpu->kvm->mmu_lock); - return 1; + return -ENOSPC; } sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, 0, ACC_ALL); diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 8eba631c4dbd..023afa0c8887 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2302,7 +2302,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * processors. See 22.2.4. */ vmcs_writel(HOST_TR_BASE, - (unsigned long)this_cpu_ptr(&cpu_tss)); + (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index faf843c9b916..1cec2c62a0b0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4384,7 +4384,7 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) addr, n, v)) && kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v)) break; - trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v); + trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v); handled += n; addr += n; len -= n; @@ -4643,7 +4643,7 @@ static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes) { if (vcpu->mmio_read_completed) { trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes, - vcpu->mmio_fragments[0].gpa, *(u64 *)val); + vcpu->mmio_fragments[0].gpa, val); vcpu->mmio_read_completed = 0; return 1; } @@ -4665,14 +4665,14 @@ static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa, static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val) { - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val); return vcpu_mmio_write(vcpu, gpa, bytes, val); } static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, void *val, int bytes) { - trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0); + trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL); return X86EMUL_IO_NEEDED; } @@ -7264,13 +7264,12 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) { - struct fpu *fpu = ¤t->thread.fpu; int r; - fpu__initialize(fpu); - kvm_sigset_activate(vcpu); + kvm_load_guest_fpu(vcpu); + if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -7296,14 +7295,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } - kvm_load_guest_fpu(vcpu); - if (unlikely(vcpu->arch.complete_userspace_io)) { int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io; vcpu->arch.complete_userspace_io = NULL; r = cui(vcpu); if (r <= 0) - goto out_fpu; + goto out; } else WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed); @@ -7312,9 +7309,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) else r = vcpu_run(vcpu); -out_fpu: - kvm_put_guest_fpu(vcpu); out: + kvm_put_guest_fpu(vcpu); post_kvm_run_save(vcpu); kvm_sigset_deactivate(vcpu); @@ -7384,7 +7380,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) #endif kvm_rip_write(vcpu, regs->rip); - kvm_set_rflags(vcpu, regs->rflags); + kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED); vcpu->arch.exception.pending = false; @@ -7498,6 +7494,29 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index, } EXPORT_SYMBOL_GPL(kvm_task_switch); +int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) +{ + if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG_BIT)) { + /* + * When EFER.LME and CR0.PG are set, the processor is in + * 64-bit mode (though maybe in a 32-bit code segment). + * CR4.PAE and EFER.LMA must be set. + */ + if (!(sregs->cr4 & X86_CR4_PAE_BIT) + || !(sregs->efer & EFER_LMA)) + return -EINVAL; + } else { + /* + * Not in 64-bit mode: EFER.LMA is clear and the code + * segment cannot be 64-bit. + */ + if (sregs->efer & EFER_LMA || sregs->cs.l) + return -EINVAL; + } + + return 0; +} + int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -7510,6 +7529,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, (sregs->cr4 & X86_CR4_OSXSAVE)) return -EINVAL; + if (kvm_valid_sregs(vcpu, sregs)) + return -EINVAL; + apic_base_msr.data = sregs->apic_base; apic_base_msr.host_initiated = true; if (kvm_set_apic_base(vcpu, &apic_base_msr)) diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 553f8fd23cc4..4846eff7e4c8 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops) delay = min_t(u64, MWAITX_MAX_LOOPS, loops); /* - * Use cpu_tss as a cacheline-aligned, seldomly + * Use cpu_tss_rw as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 8e13b8cc6bed..27e9e90a8d35 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -10,7 +10,7 @@ CFLAGS_REMOVE_mem_encrypt.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o setup_nx.o tlb.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) @@ -41,9 +41,10 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_X86_INTEL_MPX) += mpx.o -obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o -obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o +obj-$(CONFIG_X86_INTEL_MPX) += mpx.o +obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o +obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o +obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c new file mode 100644 index 000000000000..b9283cc27622 --- /dev/null +++ b/arch/x86/mm/cpu_entry_area.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/spinlock.h> +#include <linux/percpu.h> + +#include <asm/cpu_entry_area.h> +#include <asm/pgtable.h> +#include <asm/fixmap.h> +#include <asm/desc.h> + +static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage); + +#ifdef CONFIG_X86_64 +static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks + [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); +#endif + +struct cpu_entry_area *get_cpu_entry_area(int cpu) +{ + unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; + BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); + + return (struct cpu_entry_area *) va; +} +EXPORT_SYMBOL(get_cpu_entry_area); + +void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags) +{ + unsigned long va = (unsigned long) cea_vaddr; + + set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags)); +} + +static void __init +cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) +{ + for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE) + cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); +} + +static void percpu_setup_debug_store(int cpu) +{ +#ifdef CONFIG_CPU_SUP_INTEL + int npages; + void *cea; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; + + cea = &get_cpu_entry_area(cpu)->cpu_debug_store; + npages = sizeof(struct debug_store) / PAGE_SIZE; + BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0); + cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages, + PAGE_KERNEL); + + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers; + /* + * Force the population of PMDs for not yet allocated per cpu + * memory like debug store buffers. + */ + npages = sizeof(struct debug_store_buffers) / PAGE_SIZE; + for (; npages; npages--, cea += PAGE_SIZE) + cea_set_pte(cea, 0, PAGE_NONE); +#endif +} + +/* Setup the fixmap mappings only once per-processor */ +static void __init setup_cpu_entry_area(int cpu) +{ +#ifdef CONFIG_X86_64 + extern char _entry_trampoline[]; + + /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ + pgprot_t gdt_prot = PAGE_KERNEL_RO; + pgprot_t tss_prot = PAGE_KERNEL_RO; +#else + /* + * On native 32-bit systems, the GDT cannot be read-only because + * our double fault handler uses a task gate, and entering through + * a task gate needs to change an available TSS to busy. If the + * GDT is read-only, that will triple fault. The TSS cannot be + * read-only because the CPU writes to it on task switches. + * + * On Xen PV, the GDT must be read-only because the hypervisor + * requires it. + */ + pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ? + PAGE_KERNEL_RO : PAGE_KERNEL; + pgprot_t tss_prot = PAGE_KERNEL; +#endif + + cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu), + gdt_prot); + + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page, + per_cpu_ptr(&entry_stack_storage, cpu), 1, + PAGE_KERNEL); + + /* + * The Intel SDM says (Volume 3, 7.2.1): + * + * Avoid placing a page boundary in the part of the TSS that the + * processor reads during a task switch (the first 104 bytes). The + * processor may not correctly perform address translations if a + * boundary occurs in this area. During a task switch, the processor + * reads and writes into the first 104 bytes of each TSS (using + * contiguous physical addresses beginning with the physical address + * of the first byte of the TSS). So, after TSS access begins, if + * part of the 104 bytes is not physically contiguous, the processor + * will access incorrect information without generating a page-fault + * exception. + * + * There are also a lot of errata involving the TSS spanning a page + * boundary. Assert that we're not doing that. + */ + BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ + offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); + BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0); + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss, + &per_cpu(cpu_tss_rw, cpu), + sizeof(struct tss_struct) / PAGE_SIZE, tss_prot); + +#ifdef CONFIG_X86_32 + per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu); +#endif + +#ifdef CONFIG_X86_64 + BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0); + BUILD_BUG_ON(sizeof(exception_stacks) != + sizeof(((struct cpu_entry_area *)0)->exception_stacks)); + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks, + &per_cpu(exception_stacks, cpu), + sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL); + + cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline, + __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); +#endif + percpu_setup_debug_store(cpu); +} + +static __init void setup_cpu_entry_area_ptes(void) +{ +#ifdef CONFIG_X86_32 + unsigned long start, end; + + BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE); + BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK); + + start = CPU_ENTRY_AREA_BASE; + end = start + CPU_ENTRY_AREA_MAP_SIZE; + + /* Careful here: start + PMD_SIZE might wrap around */ + for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE) + populate_extra_pte(start); +#endif +} + +void __init setup_cpu_entry_areas(void) +{ + unsigned int cpu; + + setup_cpu_entry_area_ptes(); + + for_each_possible_cpu(cpu) + setup_cpu_entry_area(cpu); +} diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index bfcffdf6c577..421f2664ffa0 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -5,7 +5,7 @@ static int ptdump_show(struct seq_file *m, void *v) { - ptdump_walk_pgd_level(m, NULL); + ptdump_walk_pgd_level_debugfs(m, NULL, false); return 0; } @@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = { .release = single_release, }; -static struct dentry *pe; +static int ptdump_show_curknl(struct seq_file *m, void *v) +{ + if (current->mm->pgd) { + down_read(¤t->mm->mmap_sem); + ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false); + up_read(¤t->mm->mmap_sem); + } + return 0; +} + +static int ptdump_open_curknl(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show_curknl, NULL); +} + +static const struct file_operations ptdump_curknl_fops = { + .owner = THIS_MODULE, + .open = ptdump_open_curknl, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +static struct dentry *pe_curusr; + +static int ptdump_show_curusr(struct seq_file *m, void *v) +{ + if (current->mm->pgd) { + down_read(¤t->mm->mmap_sem); + ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true); + up_read(¤t->mm->mmap_sem); + } + return 0; +} + +static int ptdump_open_curusr(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show_curusr, NULL); +} + +static const struct file_operations ptdump_curusr_fops = { + .owner = THIS_MODULE, + .open = ptdump_open_curusr, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + +static struct dentry *dir, *pe_knl, *pe_curknl; static int __init pt_dump_debug_init(void) { - pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL, - &ptdump_fops); - if (!pe) + dir = debugfs_create_dir("page_tables", NULL); + if (!dir) return -ENOMEM; + pe_knl = debugfs_create_file("kernel", 0400, dir, NULL, + &ptdump_fops); + if (!pe_knl) + goto err; + + pe_curknl = debugfs_create_file("current_kernel", 0400, + dir, NULL, &ptdump_curknl_fops); + if (!pe_curknl) + goto err; + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pe_curusr = debugfs_create_file("current_user", 0400, + dir, NULL, &ptdump_curusr_fops); + if (!pe_curusr) + goto err; +#endif return 0; +err: + debugfs_remove_recursive(dir); + return -ENOMEM; } static void __exit pt_dump_debug_exit(void) { - debugfs_remove_recursive(pe); + debugfs_remove_recursive(dir); } module_init(pt_dump_debug_init); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 5e3ac6fe6c9e..f56902c1f04b 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -44,68 +44,97 @@ struct addr_marker { unsigned long max_lines; }; -/* indices for address_markers; keep sync'd w/ address_markers below */ +/* Address space markers hints */ + +#ifdef CONFIG_X86_64 + enum address_markers_idx { USER_SPACE_NR = 0, -#ifdef CONFIG_X86_64 KERNEL_SPACE_NR, LOW_KERNEL_NR, +#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL) + LDT_NR, +#endif VMALLOC_START_NR, VMEMMAP_START_NR, #ifdef CONFIG_KASAN KASAN_SHADOW_START_NR, KASAN_SHADOW_END_NR, #endif -# ifdef CONFIG_X86_ESPFIX64 +#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL) + LDT_NR, +#endif + CPU_ENTRY_AREA_NR, +#ifdef CONFIG_X86_ESPFIX64 ESPFIX_START_NR, -# endif +#endif +#ifdef CONFIG_EFI + EFI_END_NR, +#endif HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, -#else + FIXADDR_START_NR, + END_OF_SPACE_NR, +}; + +static struct addr_marker address_markers[] = { + [USER_SPACE_NR] = { 0, "User Space" }, + [KERNEL_SPACE_NR] = { (1UL << 63), "Kernel Space" }, + [LOW_KERNEL_NR] = { 0UL, "Low Kernel Mapping" }, + [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" }, + [VMEMMAP_START_NR] = { 0UL, "Vmemmap" }, +#ifdef CONFIG_KASAN + [KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" }, + [KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" }, +#endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL + [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" }, +#endif + [CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" }, +#ifdef CONFIG_X86_ESPFIX64 + [ESPFIX_START_NR] = { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, +#endif +#ifdef CONFIG_EFI + [EFI_END_NR] = { EFI_VA_END, "EFI Runtime Services" }, +#endif + [HIGH_KERNEL_NR] = { __START_KERNEL_map, "High Kernel Mapping" }, + [MODULES_VADDR_NR] = { MODULES_VADDR, "Modules" }, + [MODULES_END_NR] = { MODULES_END, "End Modules" }, + [FIXADDR_START_NR] = { FIXADDR_START, "Fixmap Area" }, + [END_OF_SPACE_NR] = { -1, NULL } +}; + +#else /* CONFIG_X86_64 */ + +enum address_markers_idx { + USER_SPACE_NR = 0, KERNEL_SPACE_NR, VMALLOC_START_NR, VMALLOC_END_NR, -# ifdef CONFIG_HIGHMEM +#ifdef CONFIG_HIGHMEM PKMAP_BASE_NR, -# endif - FIXADDR_START_NR, #endif + CPU_ENTRY_AREA_NR, + FIXADDR_START_NR, + END_OF_SPACE_NR, }; -/* Address space markers hints */ static struct addr_marker address_markers[] = { - { 0, "User Space" }, -#ifdef CONFIG_X86_64 - { 0x8000000000000000UL, "Kernel Space" }, - { 0/* PAGE_OFFSET */, "Low Kernel Mapping" }, - { 0/* VMALLOC_START */, "vmalloc() Area" }, - { 0/* VMEMMAP_START */, "Vmemmap" }, -#ifdef CONFIG_KASAN - { KASAN_SHADOW_START, "KASAN shadow" }, - { KASAN_SHADOW_END, "KASAN shadow end" }, + [USER_SPACE_NR] = { 0, "User Space" }, + [KERNEL_SPACE_NR] = { PAGE_OFFSET, "Kernel Mapping" }, + [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" }, + [VMALLOC_END_NR] = { 0UL, "vmalloc() End" }, +#ifdef CONFIG_HIGHMEM + [PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" }, #endif -# 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" }, -#else - { PAGE_OFFSET, "Kernel Mapping" }, - { 0/* VMALLOC_START */, "vmalloc() Area" }, - { 0/*VMALLOC_END*/, "vmalloc() End" }, -# ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, -# endif - { 0/*FIXADDR_START*/, "Fixmap Area" }, -#endif - { -1, NULL } /* End of list */ + [CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" }, + [FIXADDR_START_NR] = { 0UL, "Fixmap area" }, + [END_OF_SPACE_NR] = { -1, NULL } }; +#endif /* !CONFIG_X86_64 */ + /* Multipliers for offsets within the PTEs */ #define PTE_LEVEL_MULT (PAGE_SIZE) #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT) @@ -140,7 +169,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) static const char * const level_name[] = { "cr3", "pgd", "p4d", "pud", "pmd", "pte" }; - if (!pgprot_val(prot)) { + if (!(pr & _PAGE_PRESENT)) { /* Not present */ pt_dump_cont_printf(m, dmsg, " "); } else { @@ -447,7 +476,7 @@ static inline bool is_hypervisor_range(int idx) } static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, - bool checkwx) + bool checkwx, bool dmesg) { #ifdef CONFIG_X86_64 pgd_t *start = (pgd_t *) &init_top_pgt; @@ -460,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, if (pgd) { start = pgd; - st.to_dmesg = true; + st.to_dmesg = dmesg; } st.check_wx = checkwx; @@ -498,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { - ptdump_walk_pgd_level_core(m, pgd, false); + ptdump_walk_pgd_level_core(m, pgd, false, true); +} + +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (user && static_cpu_has(X86_FEATURE_PTI)) + pgd = kernel_to_user_pgdp(pgd); +#endif + ptdump_walk_pgd_level_core(m, pgd, false, false); +} +EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); + +static void ptdump_walk_user_pgd_level_checkwx(void) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pgd_t *pgd = (pgd_t *) &init_top_pgt; + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + pr_info("x86/mm: Checking user space page tables\n"); + pgd = kernel_to_user_pgdp(pgd); + ptdump_walk_pgd_level_core(NULL, pgd, true, false); +#endif } -EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level); void ptdump_walk_pgd_level_checkwx(void) { - ptdump_walk_pgd_level_core(NULL, NULL, true); + ptdump_walk_pgd_level_core(NULL, NULL, true, false); + ptdump_walk_user_pgd_level_checkwx(); } static int __init pt_dump_init(void) @@ -525,8 +578,8 @@ static int __init pt_dump_init(void) address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE; # endif address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; + address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE; #endif - return 0; } __initcall(pt_dump_init); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index febf6980e653..06fe3d51d385 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -860,7 +860,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 6fdf91ef130a..8ca324d07282 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -20,6 +20,7 @@ #include <asm/kaslr.h> #include <asm/hypervisor.h> #include <asm/cpufeature.h> +#include <asm/pti.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -160,6 +161,12 @@ struct map_range { static int page_size_mask; +static void enable_global_pages(void) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + __supported_pte_mask |= _PAGE_GLOBAL; +} + static void __init probe_page_size_mask(void) { /* @@ -177,11 +184,11 @@ static void __init probe_page_size_mask(void) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ + __supported_pte_mask &= ~_PAGE_GLOBAL; if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); - __supported_pte_mask |= _PAGE_GLOBAL; - } else - __supported_pte_mask &= ~_PAGE_GLOBAL; + enable_global_pages(); + } /* Enable 1 GB linear kernel mappings if available: */ if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { @@ -194,34 +201,44 @@ static void __init probe_page_size_mask(void) static void setup_pcid(void) { -#ifdef CONFIG_X86_64 - if (boot_cpu_has(X86_FEATURE_PCID)) { - if (boot_cpu_has(X86_FEATURE_PGE)) { - /* - * This can't be cr4_set_bits_and_update_boot() -- - * the trampoline code can't handle CR4.PCIDE and - * it wouldn't do any good anyway. Despite the name, - * cr4_set_bits_and_update_boot() doesn't actually - * cause the bits in question to remain set all the - * way through the secondary boot asm. - * - * Instead, we brute-force it and set CR4.PCIDE - * manually in start_secondary(). - */ - cr4_set_bits(X86_CR4_PCIDE); - } else { - /* - * flush_tlb_all(), as currently implemented, won't - * work if PCID is on but PGE is not. Since that - * combination doesn't exist on real hardware, there's - * no reason to try to fully support it, but it's - * polite to avoid corrupting data if we're on - * an improperly configured VM. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); - } + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + if (!boot_cpu_has(X86_FEATURE_PCID)) + return; + + if (boot_cpu_has(X86_FEATURE_PGE)) { + /* + * This can't be cr4_set_bits_and_update_boot() -- the + * trampoline code can't handle CR4.PCIDE and it wouldn't + * do any good anyway. Despite the name, + * cr4_set_bits_and_update_boot() doesn't actually cause + * the bits in question to remain set all the way through + * the secondary boot asm. + * + * Instead, we brute-force it and set CR4.PCIDE manually in + * start_secondary(). + */ + cr4_set_bits(X86_CR4_PCIDE); + + /* + * INVPCID's single-context modes (2/3) only work if we set + * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable + * on systems that have X86_CR4_PCIDE clear, or that have + * no INVPCID support at all. + */ + if (boot_cpu_has(X86_FEATURE_INVPCID)) + setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't work if + * PCID is on but PGE is not. Since that combination + * doesn't exist on real hardware, there's no reason to try + * to fully support it, but it's polite to avoid corrupting + * data if we're on an improperly configured VM. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); } -#endif } #ifdef CONFIG_X86_32 @@ -622,6 +639,7 @@ void __init init_mem_mapping(void) { unsigned long end; + pti_check_boottime_disable(); probe_page_size_mask(); setup_pcid(); @@ -845,7 +863,7 @@ void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } -DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8a64a6f2848d..135c9a7898c7 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -50,6 +50,7 @@ #include <asm/setup.h> #include <asm/set_memory.h> #include <asm/page_types.h> +#include <asm/cpu_entry_area.h> #include <asm/init.h> #include "mm_internal.h" @@ -766,6 +767,7 @@ void __init mem_init(void) mem_init_print_info(NULL); printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" + " cpu_entry : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HIGHMEM " pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #endif @@ -777,6 +779,10 @@ void __init mem_init(void) FIXADDR_START, FIXADDR_TOP, (FIXADDR_TOP - FIXADDR_START) >> 10, + CPU_ENTRY_AREA_BASE, + CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE, + CPU_ENTRY_AREA_MAP_SIZE >> 10, + #ifdef CONFIG_HIGHMEM PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, (LAST_PKMAP*PAGE_SIZE) >> 10, diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 99dfed6dfef8..47388f0c0e59 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -15,6 +15,7 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/pgtable.h> +#include <asm/cpu_entry_area.h> extern struct range pfn_mapped[E820_MAX_ENTRIES]; @@ -277,6 +278,7 @@ void __init kasan_early_init(void) void __init kasan_init(void) { int i; + void *shadow_cpu_entry_begin, *shadow_cpu_entry_end; #ifdef CONFIG_KASAN_INLINE register_die_notifier(&kasan_die_notifier); @@ -321,16 +323,33 @@ void __init kasan_init(void) map_range(&pfn_mapped[i]); } + shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE; + shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin); + shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin, + PAGE_SIZE); + + shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE + + CPU_ENTRY_AREA_MAP_SIZE); + shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end); + shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end, + PAGE_SIZE); + kasan_populate_zero_shadow( kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), - kasan_mem_to_shadow((void *)__START_KERNEL_map)); + shadow_cpu_entry_begin); + + kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, + (unsigned long)shadow_cpu_entry_end, 0); + + kasan_populate_zero_shadow(shadow_cpu_entry_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), (unsigned long)kasan_mem_to_shadow(_end), early_pfn_to_nid(__pa(_stext))); kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), - (void *)KASAN_SHADOW_END); + (void *)KASAN_SHADOW_END); load_cr3(init_top_pgt); __flush_tlb_all(); diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index d9a9e9fc75dd..391b13402e40 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -405,13 +405,13 @@ bool sme_active(void) { return sme_me_mask && !sev_enabled; } -EXPORT_SYMBOL_GPL(sme_active); +EXPORT_SYMBOL(sme_active); bool sev_active(void) { return sme_me_mask && sev_enabled; } -EXPORT_SYMBOL_GPL(sev_active); +EXPORT_SYMBOL(sev_active); static const struct dma_map_ops sev_dma_ops = { .alloc = sev_alloc, diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 96d456a94b03..004abf9ebf12 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } #else + static inline pgd_t *_pgd_alloc(void) { - return (pgd_t *)__get_free_page(PGALLOC_GFP); + return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) { - free_page((unsigned long)pgd); + free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); } #endif /* CONFIG_X86_PAE */ diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 6b9bf023a700..c3c5274410a9 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -10,6 +10,7 @@ #include <linux/pagemap.h> #include <linux/spinlock.h> +#include <asm/cpu_entry_area.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c new file mode 100644 index 000000000000..bce8aea65606 --- /dev/null +++ b/arch/x86/mm/pti.c @@ -0,0 +1,387 @@ +/* + * Copyright(c) 2017 Intel Corporation. All rights reserved. + * + * 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. + * + * This code is based in part on work published here: + * + * https://github.com/IAIK/KAISER + * + * The original work was written by and and signed off by for the Linux + * kernel by: + * + * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at> + * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at> + * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at> + * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at> + * + * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com> + * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and + * Andy Lutomirsky <luto@amacapital.net> + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/bug.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/mm.h> +#include <linux/uaccess.h> + +#include <asm/cpufeature.h> +#include <asm/hypervisor.h> +#include <asm/vsyscall.h> +#include <asm/cmdline.h> +#include <asm/pti.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/desc.h> + +#undef pr_fmt +#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt + +/* Backporting helper */ +#ifndef __GFP_NOTRACK +#define __GFP_NOTRACK 0 +#endif + +static void __init pti_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE)) + pr_info("%s\n", reason); +} + +static void __init pti_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE)) + pr_info("%s\n", reason); +} + +void __init pti_check_boottime_disable(void) +{ + char arg[5]; + int ret; + + if (hypervisor_is_type(X86_HYPER_XEN_PV)) { + pti_print_if_insecure("disabled on XEN PV."); + return; + } + + ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg)); + if (ret > 0) { + if (ret == 3 && !strncmp(arg, "off", 3)) { + pti_print_if_insecure("disabled on command line."); + return; + } + if (ret == 2 && !strncmp(arg, "on", 2)) { + pti_print_if_secure("force enabled on command line."); + goto enable; + } + if (ret == 4 && !strncmp(arg, "auto", 4)) + goto autosel; + } + + if (cmdline_find_option_bool(boot_command_line, "nopti")) { + pti_print_if_insecure("disabled on command line."); + return; + } + +autosel: + if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE)) + return; +enable: + setup_force_cpu_cap(X86_FEATURE_PTI); +} + +pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +{ + /* + * Changes to the high (kernel) portion of the kernelmode page + * tables are not automatically propagated to the usermode tables. + * + * Users should keep in mind that, unlike the kernelmode tables, + * there is no vmalloc_fault equivalent for the usermode tables. + * Top-level entries added to init_mm's usermode pgd after boot + * will not be automatically propagated to other mms. + */ + if (!pgdp_maps_userspace(pgdp)) + return pgd; + + /* + * The user page tables get the full PGD, accessible from + * userspace: + */ + kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd; + + /* + * If this is normal user memory, make it NX in the kernel + * pagetables so that, if we somehow screw up and return to + * usermode with the kernel CR3 loaded, we'll get a page fault + * instead of allowing user code to execute with the wrong CR3. + * + * As exceptions, we don't set NX if: + * - _PAGE_USER is not set. This could be an executable + * EFI runtime mapping or something similar, and the kernel + * may execute from it + * - we don't have NX support + * - we're clearing the PGD (i.e. the new pgd is not present). + */ + if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) && + (__supported_pte_mask & _PAGE_NX)) + pgd.pgd |= _PAGE_NX; + + /* return the copy of the PGD we want the kernel to use: */ + return pgd; +} + +/* + * Walk the user copy of the page tables (optionally) trying to allocate + * page table pages on the way down. + * + * Returns a pointer to a P4D on success, or NULL on failure. + */ +static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) +{ + pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + + if (address < PAGE_OFFSET) { + WARN_ONCE(1, "attempt to walk user address\n"); + return NULL; + } + + if (pgd_none(*pgd)) { + unsigned long new_p4d_page = __get_free_page(gfp); + if (!new_p4d_page) + return NULL; + + if (pgd_none(*pgd)) { + set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); + new_p4d_page = 0; + } + if (new_p4d_page) + free_page(new_p4d_page); + } + BUILD_BUG_ON(pgd_large(*pgd) != 0); + + return p4d_offset(pgd, address); +} + +/* + * Walk the user copy of the page tables (optionally) trying to allocate + * page table pages on the way down. + * + * Returns a pointer to a PMD on success, or NULL on failure. + */ +static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) +{ + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + p4d_t *p4d = pti_user_pagetable_walk_p4d(address); + pud_t *pud; + + BUILD_BUG_ON(p4d_large(*p4d) != 0); + if (p4d_none(*p4d)) { + unsigned long new_pud_page = __get_free_page(gfp); + if (!new_pud_page) + return NULL; + + if (p4d_none(*p4d)) { + set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); + new_pud_page = 0; + } + if (new_pud_page) + free_page(new_pud_page); + } + + pud = pud_offset(p4d, address); + /* The user page tables do not use large mappings: */ + if (pud_large(*pud)) { + WARN_ON(1); + return NULL; + } + if (pud_none(*pud)) { + unsigned long new_pmd_page = __get_free_page(gfp); + if (!new_pmd_page) + return NULL; + + if (pud_none(*pud)) { + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); + new_pmd_page = 0; + } + if (new_pmd_page) + free_page(new_pmd_page); + } + + return pmd_offset(pud, address); +} + +#ifdef CONFIG_X86_VSYSCALL_EMULATION +/* + * Walk the shadow copy of the page tables (optionally) trying to allocate + * page table pages on the way down. Does not support large pages. + * + * Note: this is only used when mapping *new* kernel data into the + * user/shadow page tables. It is never used for userspace data. + * + * Returns a pointer to a PTE on success, or NULL on failure. + */ +static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) +{ + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + pmd_t *pmd = pti_user_pagetable_walk_pmd(address); + pte_t *pte; + + /* We can't do anything sensible if we hit a large mapping. */ + if (pmd_large(*pmd)) { + WARN_ON(1); + return NULL; + } + + if (pmd_none(*pmd)) { + unsigned long new_pte_page = __get_free_page(gfp); + if (!new_pte_page) + return NULL; + + if (pmd_none(*pmd)) { + set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); + new_pte_page = 0; + } + if (new_pte_page) + free_page(new_pte_page); + } + + pte = pte_offset_kernel(pmd, address); + if (pte_flags(*pte) & _PAGE_USER) { + WARN_ONCE(1, "attempt to walk to user pte\n"); + return NULL; + } + return pte; +} + +static void __init pti_setup_vsyscall(void) +{ + pte_t *pte, *target_pte; + unsigned int level; + + pte = lookup_address(VSYSCALL_ADDR, &level); + if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) + return; + + target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR); + if (WARN_ON(!target_pte)) + return; + + *target_pte = *pte; + set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir)); +} +#else +static void __init pti_setup_vsyscall(void) { } +#endif + +static void __init +pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear) +{ + unsigned long addr; + + /* + * Clone the populated PMDs which cover start to end. These PMD areas + * can have holes. + */ + for (addr = start; addr < end; addr += PMD_SIZE) { + pmd_t *pmd, *target_pmd; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + pgd = pgd_offset_k(addr); + if (WARN_ON(pgd_none(*pgd))) + return; + p4d = p4d_offset(pgd, addr); + if (WARN_ON(p4d_none(*p4d))) + return; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + continue; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + + target_pmd = pti_user_pagetable_walk_pmd(addr); + if (WARN_ON(!target_pmd)) + return; + + /* + * Copy the PMD. That is, the kernelmode and usermode + * tables will share the last-level page tables of this + * address range + */ + *target_pmd = pmd_clear_flags(*pmd, clear); + } +} + +/* + * Clone a single p4d (i.e. a top-level entry on 4-level systems and a + * next-level entry on 5-level systems. + */ +static void __init pti_clone_p4d(unsigned long addr) +{ + p4d_t *kernel_p4d, *user_p4d; + pgd_t *kernel_pgd; + + user_p4d = pti_user_pagetable_walk_p4d(addr); + kernel_pgd = pgd_offset_k(addr); + kernel_p4d = p4d_offset(kernel_pgd, addr); + *user_p4d = *kernel_p4d; +} + +/* + * Clone the CPU_ENTRY_AREA into the user space visible page table. + */ +static void __init pti_clone_user_shared(void) +{ + pti_clone_p4d(CPU_ENTRY_AREA_BASE); +} + +/* + * Clone the ESPFIX P4D into the user space visinble page table + */ +static void __init pti_setup_espfix64(void) +{ +#ifdef CONFIG_X86_ESPFIX64 + pti_clone_p4d(ESPFIX_BASE_ADDR); +#endif +} + +/* + * Clone the populated PMDs of the entry and irqentry text and force it RO. + */ +static void __init pti_clone_entry_text(void) +{ + pti_clone_pmds((unsigned long) __entry_text_start, + (unsigned long) __irqentry_text_end, _PAGE_RW); +} + +/* + * Initialize kernel page table isolation + */ +void __init pti_init(void) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + pr_info("enabled\n"); + + pti_clone_user_shared(); + pti_clone_entry_text(); + pti_setup_espfix64(); + pti_setup_vsyscall(); +} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 3118392cdf75..a1561957dccb 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -28,6 +28,38 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +/* + * We get here when we do something requiring a TLB invalidation + * but could not go invalidate all of the contexts. We do the + * necessary invalidation by clearing out the 'ctx_id' which + * forces a TLB flush when the context is loaded. + */ +void clear_asid_other(void) +{ + u16 asid; + + /* + * This is only expected to be set if we have disabled + * kernel _PAGE_GLOBAL pages. + */ + if (!static_cpu_has(X86_FEATURE_PTI)) { + WARN_ON_ONCE(1); + return; + } + + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { + /* Do not need to flush the current asid */ + if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid)) + continue; + /* + * Make sure the next time we go to switch to + * this asid, we do a flush: + */ + this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0); + } + this_cpu_write(cpu_tlbstate.invalidate_other, false); +} + atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); @@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, return; } + if (this_cpu_read(cpu_tlbstate.invalidate_other)) + clear_asid_other(); + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) != next->context.ctx_id) @@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, *need_flush = true; } +static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush) +{ + unsigned long new_mm_cr3; + + if (need_flush) { + invalidate_user_asid(new_asid); + new_mm_cr3 = build_cr3(pgdir, new_asid); + } else { + new_mm_cr3 = build_cr3_noflush(pgdir, new_asid); + } + + /* + * Caution: many callers of this function expect + * that load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask writes. + */ + write_cr3(new_mm_cr3); +} + void leave_mm(int cpu) { struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); @@ -128,7 +182,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -195,7 +249,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - write_cr3(build_cr3(next, new_asid)); + load_new_mm_cr3(next->pgd, new_asid, true); /* * NB: This gets called via leave_mm() in the idle path @@ -208,7 +262,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - write_cr3(build_cr3_noflush(next, new_asid)); + load_new_mm_cr3(next->pgd, new_asid, false); /* See above wrt _rcuidle. */ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); @@ -288,7 +342,7 @@ void initialize_tlbstate_and_flush(void) !(cr4_read_shadow() & X86_CR4_PCIDE)); /* Force ASID 0 and force a TLB flush. */ - write_cr3(build_cr3(mm, 0)); + write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); @@ -551,7 +605,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_single(addr); + __flush_tlb_one(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 6a151ce70e86..d87ac96e37ed 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -196,6 +196,9 @@ static pgd_t *efi_pgd; * because we want to avoid inserting EFI region mappings (EFI_VA_END * to EFI_VA_START) into the standard kernel page tables. Everything * else can be shared, see efi_sync_low_kernel_mappings(). + * + * We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the + * allocation. */ int __init efi_alloc_page_tables(void) { @@ -208,7 +211,7 @@ int __init efi_alloc_page_tables(void) return 0; gfp_mask = GFP_KERNEL | __GFP_ZERO; - efi_pgd = (pgd_t *)__get_free_page(gfp_mask); + efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); if (!efi_pgd) return -ENOMEM; diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index f44c0bc95aa2..8538a6723171 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -299,7 +299,7 @@ static void bau_process_message(struct msg_desc *mdp, struct bau_control *bcp, local_flush_tlb(); stat->d_alltlb++; } else { - __flush_tlb_one(msg->address); + __flush_tlb_single(msg->address); stat->d_onetlb++; } stat->d_requestee++; diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 5f6fd860820a..e4cb9f4cde8a 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -128,7 +128,7 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq, * on the specified blade to allow the sending of MSIs to the specified CPU. */ static int uv_domain_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool early) + struct irq_data *irq_data, bool reserve) { uv_program_mmr(irqd_cfg(irq_data), irq_data->chip_data); return 0; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 36a28eddb435..a7d966964c6f 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -152,17 +152,19 @@ static void do_fpu_end(void) static void fix_processor_context(void) { int cpu = smp_processor_id(); - struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif - set_tss_desc(cpu, t); /* - * This just modifies memory; should not be - * necessary. But... This is necessary, because - * 386 hardware has concept of busy TSS or some - * similar stupidity. - */ + + /* + * We need to reload TR, which requires that we change the + * GDT entry to indicate "available" first. + * + * XXX: This could probably all be replaced by a call to + * force_reload_TR(). + */ + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); #ifdef CONFIG_X86_64 memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index d669e9d89001..c9081c6671f0 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1,8 +1,12 @@ +#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +#include <linux/bootmem.h> +#endif #include <linux/cpu.h> #include <linux/kexec.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/interface/memory.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -331,3 +335,80 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif + +#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +void __init arch_xen_balloon_init(struct resource *hostmem_resource) +{ + struct xen_memory_map memmap; + int rc; + unsigned int i, last_guest_ram; + phys_addr_t max_addr = PFN_PHYS(max_pfn); + struct e820_table *xen_e820_table; + const struct e820_entry *entry; + struct resource *res; + + if (!xen_initial_domain()) + return; + + xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL); + if (!xen_e820_table) + return; + + memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries); + set_xen_guest_handle(memmap.buffer, xen_e820_table->entries); + rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap); + if (rc) { + pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc); + goto out; + } + + last_guest_ram = 0; + for (i = 0; i < memmap.nr_entries; i++) { + if (xen_e820_table->entries[i].addr >= max_addr) + break; + if (xen_e820_table->entries[i].type == E820_TYPE_RAM) + last_guest_ram = i; + } + + entry = &xen_e820_table->entries[last_guest_ram]; + if (max_addr >= entry->addr + entry->size) + goto out; /* No unallocated host RAM. */ + + hostmem_resource->start = max_addr; + hostmem_resource->end = entry->addr + entry->size; + + /* + * Mark non-RAM regions between the end of dom0 RAM and end of host RAM + * as unavailable. The rest of that region can be used for hotplug-based + * ballooning. + */ + for (; i < memmap.nr_entries; i++) { + entry = &xen_e820_table->entries[i]; + + if (entry->type == E820_TYPE_RAM) + continue; + + if (entry->addr >= hostmem_resource->end) + break; + + res = kzalloc(sizeof(*res), GFP_KERNEL); + if (!res) + goto out; + + res->name = "Unavailable host RAM"; + res->start = entry->addr; + res->end = (entry->addr + entry->size < hostmem_resource->end) ? + entry->addr + entry->size : hostmem_resource->end; + rc = insert_resource(hostmem_resource, res); + if (rc) { + pr_warn("%s: Can't insert [%llx - %llx) (%d)\n", + __func__, res->start, res->end, rc); + kfree(res); + goto out; + } + } + + out: + kfree(xen_e820_table); +} +#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index f2414c6c5e7c..c047f42552e1 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -88,6 +88,8 @@ #include "multicalls.h" #include "pmu.h" +#include "../kernel/cpu/cpu.h" /* get_cpu_cap() */ + void *xen_initial_gdt; static int xen_cpu_up_prepare_pv(unsigned int cpu); @@ -826,7 +828,7 @@ static void xen_load_sp0(unsigned long sp0) mcs = xen_mc_entry(0); MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); xen_mc_issue(PARAVIRT_LAZY_CPU); - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } void xen_set_iopl_mask(unsigned mask) @@ -1258,6 +1260,7 @@ asmlinkage __visible void __init xen_start_kernel(void) __userpte_alloc_gfp &= ~__GFP_HIGHMEM; /* Work out if we support NX */ + get_cpu_cap(&boot_cpu_data); x86_configure_nx(); /* Get mfn list */ diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index fc048ec686e7..4d62c071b166 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1902,6 +1902,18 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) /* Graft it onto L4[511][510] */ copy_page(level2_kernel_pgt, l2); + /* + * Zap execute permission from the ident map. Due to the sharing of + * L1 entries we need to do this in the L2. + */ + if (__supported_pte_mask & _PAGE_NX) { + for (i = 0; i < PTRS_PER_PMD; ++i) { + if (pmd_none(level2_ident_pgt[i])) + continue; + level2_ident_pgt[i] = pmd_set_flags(level2_ident_pgt[i], _PAGE_NX); + } + } + /* Copy the initial P->M table mappings if necessary. */ i = pgd_index(xen_start_info->mfn_list); if (i && i < pgd_index(__START_KERNEL_map)) @@ -2261,7 +2273,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: - case FIX_RO_IDT: #ifdef CONFIG_X86_32 case FIX_WP_TEST: # ifdef CONFIG_HIGHMEM @@ -2272,7 +2283,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: - case FIX_GDT_REMAP_BEGIN ... FIX_GDT_REMAP_END: /* All local page mappings */ pte = pfn_pte(phys, prot); break; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index c114ca767b3b..6e0d2086eacb 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -808,7 +808,6 @@ char * __init xen_memory_setup(void) addr = xen_e820_table.entries[0].addr; size = xen_e820_table.entries[0].size; while (i < xen_e820_table.nr_entries) { - bool discard = false; chunk_size = size; type = xen_e820_table.entries[i].type; @@ -824,11 +823,10 @@ char * __init xen_memory_setup(void) xen_add_extra_mem(pfn_s, n_pfns); xen_max_p2m_pfn = pfn_s + n_pfns; } else - discard = true; + type = E820_TYPE_UNUSABLE; } - if (!discard) - xen_align_and_add_e820_region(addr, chunk_size, type); + xen_align_and_add_e820_region(addr, chunk_size, type); addr += chunk_size; size -= chunk_size; diff --git a/block/bio.c b/block/bio.c index 8bfdea58159b..9ef6cf3addb3 100644 --- a/block/bio.c +++ b/block/bio.c @@ -599,6 +599,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_disk = bio_src->bi_disk; bio->bi_partno = bio_src->bi_partno; bio_set_flag(bio, BIO_CLONED); + if (bio_flagged(bio_src, BIO_THROTTLED)) + bio_set_flag(bio, BIO_THROTTLED); bio->bi_opf = bio_src->bi_opf; bio->bi_write_hint = bio_src->bi_write_hint; bio->bi_iter = bio_src->bi_iter; diff --git a/block/blk-map.c b/block/blk-map.c index b21f8e86f120..d3a94719f03f 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -12,22 +12,29 @@ #include "blk.h" /* - * Append a bio to a passthrough request. Only works can be merged into - * the request based on the driver constraints. + * Append a bio to a passthrough request. Only works if the bio can be merged + * into the request based on the driver constraints. */ -int blk_rq_append_bio(struct request *rq, struct bio *bio) +int blk_rq_append_bio(struct request *rq, struct bio **bio) { - blk_queue_bounce(rq->q, &bio); + struct bio *orig_bio = *bio; + + blk_queue_bounce(rq->q, bio); if (!rq->bio) { - blk_rq_bio_prep(rq->q, rq, bio); + blk_rq_bio_prep(rq->q, rq, *bio); } else { - if (!ll_back_merge_fn(rq->q, rq, bio)) + if (!ll_back_merge_fn(rq->q, rq, *bio)) { + if (orig_bio != *bio) { + bio_put(*bio); + *bio = orig_bio; + } return -EINVAL; + } - rq->biotail->bi_next = bio; - rq->biotail = bio; - rq->__data_len += bio->bi_iter.bi_size; + rq->biotail->bi_next = *bio; + rq->biotail = *bio; + rq->__data_len += (*bio)->bi_iter.bi_size; } return 0; @@ -73,14 +80,12 @@ static int __blk_rq_map_user_iov(struct request *rq, * We link the bounce buffer in and could have to traverse it * later so we have to get a ref to prevent it from being freed */ - ret = blk_rq_append_bio(rq, bio); - bio_get(bio); + ret = blk_rq_append_bio(rq, &bio); if (ret) { - bio_endio(bio); __blk_rq_unmap_user(orig_bio); - bio_put(bio); return ret; } + bio_get(bio); return 0; } @@ -213,7 +218,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, int reading = rq_data_dir(rq) == READ; unsigned long addr = (unsigned long) kbuf; int do_copy = 0; - struct bio *bio; + struct bio *bio, *orig_bio; int ret; if (len > (queue_max_hw_sectors(q) << 9)) @@ -236,10 +241,11 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, if (do_copy) rq->rq_flags |= RQF_COPY_USER; - ret = blk_rq_append_bio(rq, bio); + orig_bio = bio; + ret = blk_rq_append_bio(rq, &bio); if (unlikely(ret)) { /* request is too big */ - bio_put(bio); + bio_put(orig_bio); return ret; } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 825bc29767e6..d19f416d6101 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2226,13 +2226,7 @@ again: out_unlock: spin_unlock_irq(q->queue_lock); out: - /* - * As multiple blk-throtls may stack in the same issue path, we - * don't want bios to leave with the flag set. Clear the flag if - * being issued. - */ - if (!throttled) - bio_clear_flag(bio, BIO_THROTTLED); + bio_set_flag(bio, BIO_THROTTLED); #ifdef CONFIG_BLK_DEV_THROTTLING_LOW if (throttled || !td->track_bio_latency) diff --git a/block/bounce.c b/block/bounce.c index fceb1a96480b..1d05c422c932 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -200,6 +200,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, unsigned i = 0; bool bounce = false; int sectors = 0; + bool passthrough = bio_is_passthrough(*bio_orig); bio_for_each_segment(from, *bio_orig, iter) { if (i++ < BIO_MAX_PAGES) @@ -210,13 +211,14 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, if (!bounce) return; - if (sectors < bio_sectors(*bio_orig)) { + if (!passthrough && sectors < bio_sectors(*bio_orig)) { bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split); bio_chain(bio, *bio_orig); generic_make_request(*bio_orig); *bio_orig = bio; } - bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set); + bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL : + bounce_bio_set); bio_for_each_segment_all(to, bio, i) { struct page *page = to->bv_page; diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index b4df317c2916..f95c60774ce8 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -100,9 +100,13 @@ struct kyber_hctx_data { unsigned int cur_domain; unsigned int batching; wait_queue_entry_t domain_wait[KYBER_NUM_DOMAINS]; + struct sbq_wait_state *domain_ws[KYBER_NUM_DOMAINS]; atomic_t wait_index[KYBER_NUM_DOMAINS]; }; +static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags, + void *key); + static int rq_sched_domain(const struct request *rq) { unsigned int op = rq->cmd_flags; @@ -385,6 +389,9 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) for (i = 0; i < KYBER_NUM_DOMAINS; i++) { INIT_LIST_HEAD(&khd->rqs[i]); + init_waitqueue_func_entry(&khd->domain_wait[i], + kyber_domain_wake); + khd->domain_wait[i].private = hctx; INIT_LIST_HEAD(&khd->domain_wait[i].entry); atomic_set(&khd->wait_index[i], 0); } @@ -524,35 +531,39 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd, int nr; nr = __sbitmap_queue_get(domain_tokens); - if (nr >= 0) - return nr; /* * If we failed to get a domain token, make sure the hardware queue is * run when one becomes available. Note that this is serialized on * khd->lock, but we still need to be careful about the waker. */ - if (list_empty_careful(&wait->entry)) { - init_waitqueue_func_entry(wait, kyber_domain_wake); - wait->private = hctx; + if (nr < 0 && list_empty_careful(&wait->entry)) { ws = sbq_wait_ptr(domain_tokens, &khd->wait_index[sched_domain]); + khd->domain_ws[sched_domain] = ws; add_wait_queue(&ws->wait, wait); /* * Try again in case a token was freed before we got on the wait - * queue. The waker may have already removed the entry from the - * wait queue, but list_del_init() is okay with that. + * queue. */ nr = __sbitmap_queue_get(domain_tokens); - if (nr >= 0) { - unsigned long flags; + } - spin_lock_irqsave(&ws->wait.lock, flags); - list_del_init(&wait->entry); - spin_unlock_irqrestore(&ws->wait.lock, flags); - } + /* + * If we got a token while we were on the wait queue, remove ourselves + * from the wait queue to ensure that all wake ups make forward + * progress. It's possible that the waker already deleted the entry + * between the !list_empty_careful() check and us grabbing the lock, but + * list_del_init() is okay with that. + */ + if (nr >= 0 && !list_empty_careful(&wait->entry)) { + ws = khd->domain_ws[sched_domain]; + spin_lock_irq(&ws->wait.lock); + list_del_init(&wait->entry); + spin_unlock_irq(&ws->wait.lock); } + return nr; } diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 415a54ced4d6..444a387df219 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1138,12 +1138,6 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, if (!af_alg_readable(sk)) break; - if (!ctx->used) { - err = af_alg_wait_for_data(sk, flags); - if (err) - return err; - } - seglen = min_t(size_t, (maxsize - len), msg_data_left(msg)); diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 48b34e9c6834..ddcc45f77edd 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -111,6 +111,12 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, size_t usedpages = 0; /* [in] RX bufs to be used from user */ size_t processed = 0; /* [in] TX bufs to be consumed */ + if (!ctx->used) { + err = af_alg_wait_for_data(sk, flags); + if (err) + return err; + } + /* * Data length provided by caller via sendmsg/sendpage that has not * yet been processed. @@ -285,6 +291,10 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, /* AIO operation */ sock_hold(sk); areq->iocb = msg->msg_iocb; + + /* Remember output size that will be generated. */ + areq->outlen = outlen; + aead_request_set_callback(&areq->cra_u.aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, af_alg_async_cb, areq); @@ -292,12 +302,8 @@ static int _aead_recvmsg(struct socket *sock, struct msghdr *msg, crypto_aead_decrypt(&areq->cra_u.aead_req); /* AIO operation in progress */ - if (err == -EINPROGRESS || err == -EBUSY) { - /* Remember output size that will be generated. */ - areq->outlen = outlen; - + if (err == -EINPROGRESS || err == -EBUSY) return -EIOCBQUEUED; - } sock_put(sk); } else { diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 30cff827dd8f..baef9bfccdda 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -72,6 +72,12 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, int err = 0; size_t len = 0; + if (!ctx->used) { + err = af_alg_wait_for_data(sk, flags); + if (err) + return err; + } + /* Allocate cipher request for current operation. */ areq = af_alg_alloc_areq(sk, sizeof(struct af_alg_async_req) + crypto_skcipher_reqsize(tfm)); @@ -119,6 +125,10 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, /* AIO operation */ sock_hold(sk); areq->iocb = msg->msg_iocb; + + /* Remember output size that will be generated. */ + areq->outlen = len; + skcipher_request_set_callback(&areq->cra_u.skcipher_req, CRYPTO_TFM_REQ_MAY_SLEEP, af_alg_async_cb, areq); @@ -127,12 +137,8 @@ static int _skcipher_recvmsg(struct socket *sock, struct msghdr *msg, crypto_skcipher_decrypt(&areq->cra_u.skcipher_req); /* AIO operation in progress */ - if (err == -EINPROGRESS || err == -EBUSY) { - /* Remember output size that will be generated. */ - areq->outlen = len; - + if (err == -EINPROGRESS || err == -EBUSY) return -EIOCBQUEUED; - } sock_put(sk); } else { diff --git a/crypto/mcryptd.c b/crypto/mcryptd.c index 4e6472658852..eca04d3729b3 100644 --- a/crypto/mcryptd.c +++ b/crypto/mcryptd.c @@ -81,6 +81,7 @@ static int mcryptd_init_queue(struct mcryptd_queue *queue, pr_debug("cpu_queue #%d %p\n", cpu, queue->cpu_queue); crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); INIT_WORK(&cpu_queue->work, mcryptd_queue_worker); + spin_lock_init(&cpu_queue->q_lock); } return 0; } @@ -104,15 +105,16 @@ static int mcryptd_enqueue_request(struct mcryptd_queue *queue, int cpu, err; struct mcryptd_cpu_queue *cpu_queue; - cpu = get_cpu(); - cpu_queue = this_cpu_ptr(queue->cpu_queue); - rctx->tag.cpu = cpu; + cpu_queue = raw_cpu_ptr(queue->cpu_queue); + spin_lock(&cpu_queue->q_lock); + cpu = smp_processor_id(); + rctx->tag.cpu = smp_processor_id(); err = crypto_enqueue_request(&cpu_queue->queue, request); pr_debug("enqueue request: cpu %d cpu_queue %p request %p\n", cpu, cpu_queue, request); + spin_unlock(&cpu_queue->q_lock); queue_work_on(cpu, kcrypto_wq, &cpu_queue->work); - put_cpu(); return err; } @@ -161,16 +163,11 @@ static void mcryptd_queue_worker(struct work_struct *work) cpu_queue = container_of(work, struct mcryptd_cpu_queue, work); i = 0; while (i < MCRYPTD_BATCH || single_task_running()) { - /* - * preempt_disable/enable is used to prevent - * being preempted by mcryptd_enqueue_request() - */ - local_bh_disable(); - preempt_disable(); + + spin_lock_bh(&cpu_queue->q_lock); backlog = crypto_get_backlog(&cpu_queue->queue); req = crypto_dequeue_request(&cpu_queue->queue); - preempt_enable(); - local_bh_enable(); + spin_unlock_bh(&cpu_queue->q_lock); if (!req) { mcryptd_opportunistic_flush(); @@ -185,7 +182,7 @@ static void mcryptd_queue_worker(struct work_struct *work) ++i; } if (cpu_queue->queue.qlen) - queue_work(kcrypto_wq, &cpu_queue->work); + queue_work_on(smp_processor_id(), kcrypto_wq, &cpu_queue->work); } void mcryptd_flusher(struct work_struct *__work) diff --git a/crypto/skcipher.c b/crypto/skcipher.c index 778e0ff42bfa..11af5fd6a443 100644 --- a/crypto/skcipher.c +++ b/crypto/skcipher.c @@ -449,6 +449,8 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk, walk->total = req->cryptlen; walk->nbytes = 0; + walk->iv = req->iv; + walk->oiv = req->iv; if (unlikely(!walk->total)) return 0; @@ -456,9 +458,6 @@ static int skcipher_walk_skcipher(struct skcipher_walk *walk, scatterwalk_start(&walk->in, req->src); scatterwalk_start(&walk->out, req->dst); - walk->iv = req->iv; - walk->oiv = req->iv; - walk->flags &= ~SKCIPHER_WALK_SLEEP; walk->flags |= req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ? SKCIPHER_WALK_SLEEP : 0; @@ -510,6 +509,8 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk, int err; walk->nbytes = 0; + walk->iv = req->iv; + walk->oiv = req->iv; if (unlikely(!walk->total)) return 0; @@ -525,9 +526,6 @@ static int skcipher_walk_aead_common(struct skcipher_walk *walk, scatterwalk_done(&walk->in, 0, walk->total); scatterwalk_done(&walk->out, 0, walk->total); - walk->iv = req->iv; - walk->oiv = req->iv; - if (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) walk->flags |= SKCIPHER_WALK_SLEEP; else diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index 6742f6c68034..9bff853e85f3 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -1007,7 +1007,7 @@ skip: /* The record may be cleared by others, try read next record */ if (len == -ENOENT) goto skip; - else if (len < sizeof(*rcd)) { + else if (len < 0 || len < sizeof(*rcd)) { rc = -EIO; goto out; } diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 30e84cc600ae..06ea4749ebd9 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -1171,7 +1171,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls) struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu); struct cpc_register_resource *desired_reg; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); - struct cppc_pcc_data *pcc_ss_data = pcc_data[pcc_ss_id]; + struct cppc_pcc_data *pcc_ss_data; int ret = 0; if (!cpc_desc || pcc_ss_id < 0) { diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index ff2580e7611d..abeb4df4f22e 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1670,6 +1670,11 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc, dev_name(&adev_dimm->dev)); return -ENXIO; } + /* + * Record nfit_mem for the notification path to track back to + * the nfit sysfs attributes for this dimm device object. + */ + dev_set_drvdata(&adev_dimm->dev, nfit_mem); /* * Until standardization materializes we need to consider 4 @@ -1752,9 +1757,11 @@ static void shutdown_dimm_notify(void *data) sysfs_put(nfit_mem->flags_attr); nfit_mem->flags_attr = NULL; } - if (adev_dimm) + if (adev_dimm) { acpi_remove_notify_handler(adev_dimm->handle, ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify); + dev_set_drvdata(&adev_dimm->dev, NULL); + } } mutex_unlock(&acpi_desc->init_mutex); } diff --git a/drivers/android/binder.c b/drivers/android/binder.c index bccec9de0533..a7ecfde66b7b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -482,7 +482,8 @@ enum binder_deferred_state { * @tsk task_struct for group_leader of process * (invariant after initialized) * @files files_struct for process - * (invariant after initialized) + * (protected by @files_lock) + * @files_lock mutex to protect @files * @deferred_work_node: element for binder_deferred_list * (protected by binder_deferred_lock) * @deferred_work: bitmap of deferred work to perform @@ -530,6 +531,7 @@ struct binder_proc { int pid; struct task_struct *tsk; struct files_struct *files; + struct mutex files_lock; struct hlist_node deferred_work_node; int deferred_work; bool is_dead; @@ -877,20 +879,26 @@ static void binder_inc_node_tmpref_ilocked(struct binder_node *node); static int task_get_unused_fd_flags(struct binder_proc *proc, int flags) { - struct files_struct *files = proc->files; unsigned long rlim_cur; unsigned long irqs; + int ret; - if (files == NULL) - return -ESRCH; - - if (!lock_task_sighand(proc->tsk, &irqs)) - return -EMFILE; - + mutex_lock(&proc->files_lock); + if (proc->files == NULL) { + ret = -ESRCH; + goto err; + } + if (!lock_task_sighand(proc->tsk, &irqs)) { + ret = -EMFILE; + goto err; + } rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE); unlock_task_sighand(proc->tsk, &irqs); - return __alloc_fd(files, 0, rlim_cur, flags); + ret = __alloc_fd(proc->files, 0, rlim_cur, flags); +err: + mutex_unlock(&proc->files_lock); + return ret; } /* @@ -899,8 +907,10 @@ static int task_get_unused_fd_flags(struct binder_proc *proc, int flags) static void task_fd_install( struct binder_proc *proc, unsigned int fd, struct file *file) { + mutex_lock(&proc->files_lock); if (proc->files) __fd_install(proc->files, fd, file); + mutex_unlock(&proc->files_lock); } /* @@ -910,9 +920,11 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd) { int retval; - if (proc->files == NULL) - return -ESRCH; - + mutex_lock(&proc->files_lock); + if (proc->files == NULL) { + retval = -ESRCH; + goto err; + } retval = __close_fd(proc->files, fd); /* can't restart close syscall because file table entry was cleared */ if (unlikely(retval == -ERESTARTSYS || @@ -920,7 +932,8 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd) retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK)) retval = -EINTR; - +err: + mutex_unlock(&proc->files_lock); return retval; } @@ -4627,7 +4640,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) ret = binder_alloc_mmap_handler(&proc->alloc, vma); if (ret) return ret; + mutex_lock(&proc->files_lock); proc->files = get_files_struct(current); + mutex_unlock(&proc->files_lock); return 0; err_bad_arg: @@ -4651,6 +4666,7 @@ static int binder_open(struct inode *nodp, struct file *filp) spin_lock_init(&proc->outer_lock); get_task_struct(current->group_leader); proc->tsk = current->group_leader; + mutex_init(&proc->files_lock); INIT_LIST_HEAD(&proc->todo); proc->default_priority = task_nice(current); binder_dev = container_of(filp->private_data, struct binder_device, @@ -4903,9 +4919,11 @@ static void binder_deferred_func(struct work_struct *work) files = NULL; if (defer & BINDER_DEFERRED_PUT_FILES) { + mutex_lock(&proc->files_lock); files = proc->files; if (files) proc->files = NULL; + mutex_unlock(&proc->files_lock); } if (defer & BINDER_DEFERRED_FLUSH) diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index eb3af2739537..07532d83be0b 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -186,6 +186,11 @@ static void cache_associativity(struct cacheinfo *this_leaf) this_leaf->ways_of_associativity = (size / nr_sets) / line_size; } +static bool cache_node_is_unified(struct cacheinfo *this_leaf) +{ + return of_property_read_bool(this_leaf->of_node, "cache-unified"); +} + static void cache_of_override_properties(unsigned int cpu) { int index; @@ -194,6 +199,14 @@ static void cache_of_override_properties(unsigned int cpu) for (index = 0; index < cache_leaves(cpu); index++) { this_leaf = this_cpu_ci->info_list + index; + /* + * init_cache_level must setup the cache level correctly + * overriding the architecturally specified levels, so + * if type is NONE at this stage, it should be unified + */ + if (this_leaf->type == CACHE_TYPE_NOCACHE && + cache_node_is_unified(this_leaf)) + this_leaf->type = CACHE_TYPE_UNIFIED; cache_size(this_leaf); cache_get_line_size(this_leaf); cache_nr_sets(this_leaf); diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index ccb9975a97fa..ad0477ae820f 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -35,13 +35,13 @@ static inline u64 mb_per_tick(int mbps) struct nullb_cmd { struct list_head list; struct llist_node ll_list; - call_single_data_t csd; + struct __call_single_data csd; struct request *rq; struct bio *bio; unsigned int tag; + blk_status_t error; struct nullb_queue *nq; struct hrtimer timer; - blk_status_t error; }; struct nullb_queue { diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 647d056df88c..b56c11f51baf 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -220,7 +220,8 @@ static bool clk_core_is_enabled(struct clk_core *core) ret = core->ops->is_enabled(core->hw); done: - clk_pm_runtime_put(core); + if (core->dev) + pm_runtime_put(core->dev); return ret; } @@ -1564,6 +1565,9 @@ static void clk_change_rate(struct clk_core *core) best_parent_rate = core->parent->rate; } + if (clk_pm_runtime_get(core)) + return; + if (core->flags & CLK_SET_RATE_UNGATE) { unsigned long flags; @@ -1634,6 +1638,8 @@ static void clk_change_rate(struct clk_core *core) /* handle the new child who might not be in core->children yet */ if (core->new_child) clk_change_rate(core->new_child); + + clk_pm_runtime_put(core); } static int clk_core_set_rate_nolock(struct clk_core *core, diff --git a/drivers/clk/sunxi/clk-sun9i-mmc.c b/drivers/clk/sunxi/clk-sun9i-mmc.c index a1a634253d6f..f00d8758ba24 100644 --- a/drivers/clk/sunxi/clk-sun9i-mmc.c +++ b/drivers/clk/sunxi/clk-sun9i-mmc.c @@ -16,6 +16,7 @@ #include <linux/clk.h> #include <linux/clk-provider.h> +#include <linux/delay.h> #include <linux/init.h> #include <linux/of.h> #include <linux/of_device.h> @@ -83,9 +84,20 @@ static int sun9i_mmc_reset_deassert(struct reset_controller_dev *rcdev, return 0; } +static int sun9i_mmc_reset_reset(struct reset_controller_dev *rcdev, + unsigned long id) +{ + sun9i_mmc_reset_assert(rcdev, id); + udelay(10); + sun9i_mmc_reset_deassert(rcdev, id); + + return 0; +} + static const struct reset_control_ops sun9i_mmc_reset_ops = { .assert = sun9i_mmc_reset_assert, .deassert = sun9i_mmc_reset_deassert, + .reset = sun9i_mmc_reset_reset, }; static int sun9i_a80_mmc_config_clk_probe(struct platform_device *pdev) diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c index 58d4f4e1ad6a..ca38229b045a 100644 --- a/drivers/cpufreq/cpufreq_governor.c +++ b/drivers/cpufreq/cpufreq_governor.c @@ -22,6 +22,8 @@ #include "cpufreq_governor.h" +#define CPUFREQ_DBS_MIN_SAMPLING_INTERVAL (2 * TICK_NSEC / NSEC_PER_USEC) + static DEFINE_PER_CPU(struct cpu_dbs_info, cpu_dbs); static DEFINE_MUTEX(gov_dbs_data_mutex); @@ -47,11 +49,15 @@ ssize_t store_sampling_rate(struct gov_attr_set *attr_set, const char *buf, { struct dbs_data *dbs_data = to_dbs_data(attr_set); struct policy_dbs_info *policy_dbs; + unsigned int sampling_interval; int ret; - ret = sscanf(buf, "%u", &dbs_data->sampling_rate); - if (ret != 1) + + ret = sscanf(buf, "%u", &sampling_interval); + if (ret != 1 || sampling_interval < CPUFREQ_DBS_MIN_SAMPLING_INTERVAL) return -EINVAL; + dbs_data->sampling_rate = sampling_interval; + /* * We are operating under dbs_data->mutex and so the list and its * entries can't be freed concurrently. @@ -430,7 +436,14 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy) if (ret) goto free_policy_dbs_info; - dbs_data->sampling_rate = cpufreq_policy_transition_delay_us(policy); + /* + * The sampling interval should not be less than the transition latency + * of the CPU and it also cannot be too small for dbs_update() to work + * correctly. + */ + dbs_data->sampling_rate = max_t(unsigned int, + CPUFREQ_DBS_MIN_SAMPLING_INTERVAL, + cpufreq_policy_transition_delay_us(policy)); if (!have_governor_per_policy()) gov->gdbs_data = dbs_data; diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index 628fe899cb48..d9b2c2de49c4 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -226,17 +226,18 @@ static void imx6q_opp_check_speed_grading(struct device *dev) val >>= OCOTP_CFG3_SPEED_SHIFT; val &= 0x3; - if ((val != OCOTP_CFG3_SPEED_1P2GHZ) && - of_machine_is_compatible("fsl,imx6q")) - if (dev_pm_opp_disable(dev, 1200000000)) - dev_warn(dev, "failed to disable 1.2GHz OPP\n"); if (val < OCOTP_CFG3_SPEED_996MHZ) if (dev_pm_opp_disable(dev, 996000000)) dev_warn(dev, "failed to disable 996MHz OPP\n"); - if (of_machine_is_compatible("fsl,imx6q")) { + + if (of_machine_is_compatible("fsl,imx6q") || + of_machine_is_compatible("fsl,imx6qp")) { if (val != OCOTP_CFG3_SPEED_852MHZ) if (dev_pm_opp_disable(dev, 852000000)) dev_warn(dev, "failed to disable 852MHz OPP\n"); + if (val != OCOTP_CFG3_SPEED_1P2GHZ) + if (dev_pm_opp_disable(dev, 1200000000)) + dev_warn(dev, "failed to disable 1.2GHz OPP\n"); } iounmap(base); put_node: diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index dfcf56ee3c61..76861a00bb92 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -522,6 +522,7 @@ static struct of_device_id const bcm_kona_gpio_of_match[] = { * category than their parents, so it won't report false recursion. */ static struct lock_class_key gpio_lock_class; +static struct lock_class_key gpio_request_class; static int bcm_kona_gpio_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq) @@ -531,7 +532,7 @@ static int bcm_kona_gpio_irq_map(struct irq_domain *d, unsigned int irq, ret = irq_set_chip_data(irq, d->host_data); if (ret < 0) return ret; - irq_set_lockdep_class(irq, &gpio_lock_class); + irq_set_lockdep_class(irq, &gpio_lock_class, &gpio_request_class); irq_set_chip_and_handler(irq, &bcm_gpio_irq_chip, handle_simple_irq); irq_set_noprobe(irq); diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c index 545d43a587b7..bb4f8cf18bd9 100644 --- a/drivers/gpio/gpio-brcmstb.c +++ b/drivers/gpio/gpio-brcmstb.c @@ -327,6 +327,7 @@ static struct brcmstb_gpio_bank *brcmstb_gpio_hwirq_to_bank( * category than their parents, so it won't report false recursion. */ static struct lock_class_key brcmstb_gpio_irq_lock_class; +static struct lock_class_key brcmstb_gpio_irq_request_class; static int brcmstb_gpio_irq_map(struct irq_domain *d, unsigned int irq, @@ -346,7 +347,8 @@ static int brcmstb_gpio_irq_map(struct irq_domain *d, unsigned int irq, ret = irq_set_chip_data(irq, &bank->gc); if (ret < 0) return ret; - irq_set_lockdep_class(irq, &brcmstb_gpio_irq_lock_class); + irq_set_lockdep_class(irq, &brcmstb_gpio_irq_lock_class, + &brcmstb_gpio_irq_request_class); irq_set_chip_and_handler(irq, &priv->irq_chip, handle_level_irq); irq_set_noprobe(irq); return 0; diff --git a/drivers/gpio/gpio-reg.c b/drivers/gpio/gpio-reg.c index 23e771dba4c1..e85903eddc68 100644 --- a/drivers/gpio/gpio-reg.c +++ b/drivers/gpio/gpio-reg.c @@ -103,8 +103,8 @@ static int gpio_reg_to_irq(struct gpio_chip *gc, unsigned offset) struct gpio_reg *r = to_gpio_reg(gc); int irq = r->irqs[offset]; - if (irq >= 0 && r->irq.domain) - irq = irq_find_mapping(r->irq.domain, irq); + if (irq >= 0 && r->irqdomain) + irq = irq_find_mapping(r->irqdomain, irq); return irq; } diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index 8db47f671708..02fa8fe2292a 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -565,6 +565,7 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = { * than their parents, so it won't report false recursion. */ static struct lock_class_key gpio_lock_class; +static struct lock_class_key gpio_request_class; static int tegra_gpio_probe(struct platform_device *pdev) { @@ -670,7 +671,8 @@ static int tegra_gpio_probe(struct platform_device *pdev) bank = &tgi->bank_info[GPIO_BANK(gpio)]; - irq_set_lockdep_class(irq, &gpio_lock_class); + irq_set_lockdep_class(irq, &gpio_lock_class, + &gpio_request_class); irq_set_chip_data(irq, bank); irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq); } diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c index 2313af82fad3..acd59113e08b 100644 --- a/drivers/gpio/gpio-xgene-sb.c +++ b/drivers/gpio/gpio-xgene-sb.c @@ -139,7 +139,7 @@ static int xgene_gpio_sb_to_irq(struct gpio_chip *gc, u32 gpio) static int xgene_gpio_sb_domain_activate(struct irq_domain *d, struct irq_data *irq_data, - bool early) + bool reserve) { struct xgene_gpio_sb *priv = d->host_data; u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq); diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index eb4528c87c0b..d6f3d9ee1350 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1074,7 +1074,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip) } if (!chip->names) - devprop_gpiochip_set_names(chip); + devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent)); acpi_gpiochip_request_regions(acpi_gpio); acpi_gpiochip_scan_gpios(acpi_gpio); diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c index 27f383bda7d9..f748aa3e77f7 100644 --- a/drivers/gpio/gpiolib-devprop.c +++ b/drivers/gpio/gpiolib-devprop.c @@ -19,30 +19,27 @@ /** * devprop_gpiochip_set_names - Set GPIO line names using device properties * @chip: GPIO chip whose lines should be named, if possible + * @fwnode: Property Node containing the gpio-line-names property * * Looks for device property "gpio-line-names" and if it exists assigns * GPIO line names for the chip. The memory allocated for the assigned * names belong to the underlying firmware node and should not be released * by the caller. */ -void devprop_gpiochip_set_names(struct gpio_chip *chip) +void devprop_gpiochip_set_names(struct gpio_chip *chip, + const struct fwnode_handle *fwnode) { struct gpio_device *gdev = chip->gpiodev; const char **names; int ret, i; - if (!chip->parent) { - dev_warn(&gdev->dev, "GPIO chip parent is NULL\n"); - return; - } - - ret = device_property_read_string_array(chip->parent, "gpio-line-names", + ret = fwnode_property_read_string_array(fwnode, "gpio-line-names", NULL, 0); if (ret < 0) return; if (ret != gdev->ngpio) { - dev_warn(chip->parent, + dev_warn(&gdev->dev, "names %d do not match number of GPIOs %d\n", ret, gdev->ngpio); return; @@ -52,10 +49,10 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip) if (!names) return; - ret = device_property_read_string_array(chip->parent, "gpio-line-names", + ret = fwnode_property_read_string_array(fwnode, "gpio-line-names", names, gdev->ngpio); if (ret < 0) { - dev_warn(chip->parent, "failed to read GPIO line names\n"); + dev_warn(&gdev->dev, "failed to read GPIO line names\n"); kfree(names); return; } diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index e0d59e61b52f..72a0695d2ac3 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -493,7 +493,8 @@ int of_gpiochip_add(struct gpio_chip *chip) /* If the chip defines names itself, these take precedence */ if (!chip->names) - devprop_gpiochip_set_names(chip); + devprop_gpiochip_set_names(chip, + of_fwnode_handle(chip->of_node)); of_node_get(chip->of_node); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index aad84a6306c4..44332b793718 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -73,7 +73,8 @@ LIST_HEAD(gpio_devices); static void gpiochip_free_hogs(struct gpio_chip *chip); static int gpiochip_add_irqchip(struct gpio_chip *gpiochip, - struct lock_class_key *key); + struct lock_class_key *lock_key, + struct lock_class_key *request_key); static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip); static int gpiochip_irqchip_init_valid_mask(struct gpio_chip *gpiochip); static void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gpiochip); @@ -1100,7 +1101,8 @@ static void gpiochip_setup_devs(void) } int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, - struct lock_class_key *key) + struct lock_class_key *lock_key, + struct lock_class_key *request_key) { unsigned long flags; int status = 0; @@ -1246,7 +1248,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, if (status) goto err_remove_from_list; - status = gpiochip_add_irqchip(chip, key); + status = gpiochip_add_irqchip(chip, lock_key, request_key); if (status) goto err_remove_chip; @@ -1632,7 +1634,7 @@ int gpiochip_irq_map(struct irq_domain *d, unsigned int irq, * This lock class tells lockdep that GPIO irqs are in a different * category than their parents, so it won't report false recursion. */ - irq_set_lockdep_class(irq, chip->irq.lock_key); + irq_set_lockdep_class(irq, chip->irq.lock_key, chip->irq.request_key); irq_set_chip_and_handler(irq, chip->irq.chip, chip->irq.handler); /* Chips that use nested thread handlers have them marked */ if (chip->irq.threaded) @@ -1712,10 +1714,12 @@ static int gpiochip_to_irq(struct gpio_chip *chip, unsigned offset) /** * gpiochip_add_irqchip() - adds an IRQ chip to a GPIO chip * @gpiochip: the GPIO chip to add the IRQ chip to - * @lock_key: lockdep class + * @lock_key: lockdep class for IRQ lock + * @request_key: lockdep class for IRQ request */ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip, - struct lock_class_key *lock_key) + struct lock_class_key *lock_key, + struct lock_class_key *request_key) { struct irq_chip *irqchip = gpiochip->irq.chip; const struct irq_domain_ops *ops; @@ -1753,6 +1757,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip, gpiochip->to_irq = gpiochip_to_irq; gpiochip->irq.default_type = type; gpiochip->irq.lock_key = lock_key; + gpiochip->irq.request_key = request_key; if (gpiochip->irq.domain_ops) ops = gpiochip->irq.domain_ops; @@ -1850,7 +1855,8 @@ static void gpiochip_irqchip_remove(struct gpio_chip *gpiochip) * @type: the default type for IRQs on this irqchip, pass IRQ_TYPE_NONE * to have the core avoid setting up any default type in the hardware. * @threaded: whether this irqchip uses a nested thread handler - * @lock_key: lockdep class + * @lock_key: lockdep class for IRQ lock + * @request_key: lockdep class for IRQ request * * This function closely associates a certain irqchip with a certain * gpiochip, providing an irq domain to translate the local IRQs to @@ -1872,7 +1878,8 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, irq_flow_handler_t handler, unsigned int type, bool threaded, - struct lock_class_key *lock_key) + struct lock_class_key *lock_key, + struct lock_class_key *request_key) { struct device_node *of_node; @@ -1913,6 +1920,7 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, gpiochip->irq.default_type = type; gpiochip->to_irq = gpiochip_to_irq; gpiochip->irq.lock_key = lock_key; + gpiochip->irq.request_key = request_key; gpiochip->irq.domain = irq_domain_add_simple(of_node, gpiochip->ngpio, first_irq, &gpiochip_domain_ops, gpiochip); @@ -1940,7 +1948,8 @@ EXPORT_SYMBOL_GPL(gpiochip_irqchip_add_key); #else /* CONFIG_GPIOLIB_IRQCHIP */ static inline int gpiochip_add_irqchip(struct gpio_chip *gpiochip, - struct lock_class_key *key) + struct lock_class_key *lock_key, + struct lock_class_key *request_key) { return 0; } diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index af48322839c3..6c44d1652139 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -228,7 +228,8 @@ static inline int gpio_chip_hwgpio(const struct gpio_desc *desc) return desc - &desc->gdev->descs[0]; } -void devprop_gpiochip_set_names(struct gpio_chip *chip); +void devprop_gpiochip_set_names(struct gpio_chip *chip, + const struct fwnode_handle *fwnode); /* With descriptor prefix */ diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index da43813d67a4..5aeb5f8816f3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2467,7 +2467,7 @@ static int gfx_v9_0_kiq_kcq_enable(struct amdgpu_device *adev) PACKET3_MAP_QUEUES_PIPE(ring->pipe) | PACKET3_MAP_QUEUES_ME((ring->me == 1 ? 0 : 1)) | PACKET3_MAP_QUEUES_QUEUE_TYPE(0) | /*queue_type: normal compute queue */ - PACKET3_MAP_QUEUES_ALLOC_FORMAT(1) | /* alloc format: all_on_one_pipe */ + PACKET3_MAP_QUEUES_ALLOC_FORMAT(0) | /* alloc format: all_on_one_pipe */ PACKET3_MAP_QUEUES_ENGINE_SEL(0) | /* engine_sel: compute */ PACKET3_MAP_QUEUES_NUM_QUEUES(1)); /* num_queues: must be 1 */ amdgpu_ring_write(kiq_ring, PACKET3_MAP_QUEUES_DOORBELL_OFFSET(ring->doorbell_index)); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f71fe6d2ddda..bb5fa895fb64 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2336,7 +2336,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, const struct dm_connector_state *dm_state) { struct drm_display_mode *preferred_mode = NULL; - const struct drm_connector *drm_connector; + struct drm_connector *drm_connector; struct dc_stream_state *stream = NULL; struct drm_display_mode mode = *drm_mode; bool native_mode_found = false; @@ -2355,11 +2355,13 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, if (!aconnector->dc_sink) { /* - * Exclude MST from creating fake_sink - * TODO: need to enable MST into fake_sink feature + * Create dc_sink when necessary to MST + * Don't apply fake_sink to MST */ - if (aconnector->mst_port) - goto stream_create_fail; + if (aconnector->mst_port) { + dm_dp_mst_dc_sink_create(drm_connector); + goto mst_dc_sink_create_done; + } if (create_fake_sink(aconnector)) goto stream_create_fail; @@ -2410,6 +2412,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, stream_create_fail: dm_state_null: drm_connector_null: +mst_dc_sink_create_done: return stream; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 117521c6a6ed..0230250a1164 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -189,6 +189,8 @@ struct amdgpu_dm_connector { struct mutex hpd_lock; bool fake_enable; + + bool mst_connected; }; #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index f8efb98b1fa7..638c2c2b5cd7 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -185,6 +185,42 @@ static int dm_connector_update_modes(struct drm_connector *connector, return ret; } +void dm_dp_mst_dc_sink_create(struct drm_connector *connector) +{ + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + struct edid *edid; + struct dc_sink *dc_sink; + struct dc_sink_init_data init_params = { + .link = aconnector->dc_link, + .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; + + edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port); + + if (!edid) { + drm_mode_connector_update_edid_property( + &aconnector->base, + NULL); + return; + } + + aconnector->edid = edid; + + dc_sink = dc_link_add_remote_sink( + aconnector->dc_link, + (uint8_t *)aconnector->edid, + (aconnector->edid->extensions + 1) * EDID_LENGTH, + &init_params); + + dc_sink->priv = aconnector; + aconnector->dc_sink = dc_sink; + + amdgpu_dm_add_sink_to_freesync_module( + connector, aconnector->edid); + + drm_mode_connector_update_edid_property( + &aconnector->base, aconnector->edid); +} + static int dm_dp_mst_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); @@ -311,6 +347,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, drm_mode_connector_set_path_property(connector, pathprop); drm_connector_list_iter_end(&conn_iter); + aconnector->mst_connected = true; return &aconnector->base; } } @@ -363,6 +400,8 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, */ amdgpu_dm_connector_funcs_reset(connector); + aconnector->mst_connected = true; + DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n", aconnector, connector->base.id, aconnector->mst_port); @@ -394,6 +433,8 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, drm_mode_connector_update_edid_property( &aconnector->base, NULL); + + aconnector->mst_connected = false; } static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) @@ -404,10 +445,18 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) drm_kms_helper_hotplug_event(dev); } +static void dm_dp_mst_link_status_reset(struct drm_connector *connector) +{ + mutex_lock(&connector->dev->mode_config.mutex); + drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); + mutex_unlock(&connector->dev->mode_config.mutex); +} + static void dm_dp_mst_register_connector(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = dev->dev_private; + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); if (adev->mode_info.rfbdev) drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector); @@ -416,6 +465,8 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector) drm_connector_register(connector); + if (aconnector->mst_connected) + dm_dp_mst_link_status_reset(connector); } static const struct drm_dp_mst_topology_cbs dm_mst_cbs = { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 2da851b40042..8cf51da26657 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -31,5 +31,6 @@ struct amdgpu_dm_connector; void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector); +void dm_dp_mst_dc_sink_create(struct drm_connector *connector); #endif diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c index 3dce35e66b09..b142629a1058 100644 --- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c @@ -900,6 +900,15 @@ bool dcn_validate_bandwidth( v->override_vta_ps[input_idx] = pipe->plane_res.scl_data.taps.v_taps; v->override_hta_pschroma[input_idx] = pipe->plane_res.scl_data.taps.h_taps_c; v->override_vta_pschroma[input_idx] = pipe->plane_res.scl_data.taps.v_taps_c; + /* + * Spreadsheet doesn't handle taps_c is one properly, + * need to force Chroma to always be scaled to pass + * bandwidth validation. + */ + if (v->override_hta_pschroma[input_idx] == 1) + v->override_hta_pschroma[input_idx] = 2; + if (v->override_vta_pschroma[input_idx] == 1) + v->override_vta_pschroma[input_idx] = 2; v->source_scan[input_idx] = (pipe->plane_state->rotation % 2) ? dcn_bw_vert : dcn_bw_hor; } if (v->is_line_buffer_bpp_fixed == dcn_bw_yes) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index e27ed4a45265..42a111b9505d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1801,7 +1801,7 @@ static void disable_link(struct dc_link *link, enum signal_type signal) link->link_enc->funcs->disable_output(link->link_enc, signal, link); } -bool dp_active_dongle_validate_timing( +static bool dp_active_dongle_validate_timing( const struct dc_crtc_timing *timing, const struct dc_dongle_caps *dongle_caps) { @@ -1833,6 +1833,8 @@ bool dp_active_dongle_validate_timing( /* Check Color Depth and Pixel Clock */ if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) required_pix_clk /= 2; + else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422) + required_pix_clk = required_pix_clk * 2 / 3; switch (timing->display_color_depth) { case COLOR_DEPTH_666: diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 07ff8d2faf3f..d844fadcd56f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -2866,16 +2866,19 @@ static void dce110_apply_ctx_for_surface( int num_planes, struct dc_state *context) { - int i, be_idx; + int i; if (num_planes == 0) return; - be_idx = -1; for (i = 0; i < dc->res_pool->pipe_count; i++) { - if (stream == context->res_ctx.pipe_ctx[i].stream) { - be_idx = context->res_ctx.pipe_ctx[i].stream_res.tg->inst; - break; + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + + if (stream == pipe_ctx->stream) { + if (!pipe_ctx->top_pipe && + (pipe_ctx->plane_state || old_pipe_ctx->plane_state)) + dc->hwss.pipe_control_lock(dc, pipe_ctx, true); } } @@ -2895,9 +2898,22 @@ static void dce110_apply_ctx_for_surface( context->stream_count); dce110_program_front_end_for_pipe(dc, pipe_ctx); + + dc->hwss.update_plane_addr(dc, pipe_ctx); + program_surface_visibility(dc, pipe_ctx); } + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i]; + struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i]; + + if ((stream == pipe_ctx->stream) && + (!pipe_ctx->top_pipe) && + (pipe_ctx->plane_state || old_pipe_ctx->plane_state)) + dc->hwss.pipe_control_lock(dc, pipe_ctx, false); + } } static void dce110_power_down_fe(struct dc *dc, int fe_idx) diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c index 74e7c82bdc76..a9d55d0dd69e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c @@ -159,11 +159,10 @@ bool dpp_get_optimal_number_of_taps( scl_data->taps.h_taps = 1; if (IDENTITY_RATIO(scl_data->ratios.vert)) scl_data->taps.v_taps = 1; - /* - * Spreadsheet doesn't handle taps_c is one properly, - * need to force Chroma to always be scaled to pass - * bandwidth validation. - */ + if (IDENTITY_RATIO(scl_data->ratios.horz_c)) + scl_data->taps.h_taps_c = 1; + if (IDENTITY_RATIO(scl_data->ratios.vert_c)) + scl_data->taps.v_taps_c = 1; } return true; diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 59849f02e2ad..1402c0e71b03 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -220,17 +220,6 @@ static struct drm_master *drm_lease_create(struct drm_master *lessor, struct idr mutex_lock(&dev->mode_config.idr_mutex); - /* Insert the new lessee into the tree */ - id = idr_alloc(&(drm_lease_owner(lessor)->lessee_idr), lessee, 1, 0, GFP_KERNEL); - if (id < 0) { - error = id; - goto out_lessee; - } - - lessee->lessee_id = id; - lessee->lessor = drm_master_get(lessor); - list_add_tail(&lessee->lessee_list, &lessor->lessees); - idr_for_each_entry(leases, entry, object) { error = 0; if (!idr_find(&dev->mode_config.crtc_idr, object)) @@ -246,6 +235,17 @@ static struct drm_master *drm_lease_create(struct drm_master *lessor, struct idr } } + /* Insert the new lessee into the tree */ + id = idr_alloc(&(drm_lease_owner(lessor)->lessee_idr), lessee, 1, 0, GFP_KERNEL); + if (id < 0) { + error = id; + goto out_lessee; + } + + lessee->lessee_id = id; + lessee->lessor = drm_master_get(lessor); + list_add_tail(&lessee->lessee_list, &lessor->lessees); + /* Move the leases over */ lessee->leases = *leases; DRM_DEBUG_LEASE("new lessee %d %p, lessor %d %p\n", lessee->lessee_id, lessee, lessor->lessee_id, lessor); diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 37a93cdffb4a..2c90519576a3 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -558,11 +558,10 @@ int drm_plane_check_pixel_format(const struct drm_plane *plane, u32 format) } /* - * setplane_internal - setplane handler for internal callers + * __setplane_internal - setplane handler for internal callers * - * Note that we assume an extra reference has already been taken on fb. If the - * update fails, this reference will be dropped before return; if it succeeds, - * the previous framebuffer (if any) will be unreferenced instead. + * This function will take a reference on the new fb for the plane + * on success. * * src_{x,y,w,h} are provided in 16.16 fixed point format */ @@ -630,14 +629,12 @@ static int __setplane_internal(struct drm_plane *plane, if (!ret) { plane->crtc = crtc; plane->fb = fb; - fb = NULL; + drm_framebuffer_get(plane->fb); } else { plane->old_fb = NULL; } out: - if (fb) - drm_framebuffer_put(fb); if (plane->old_fb) drm_framebuffer_put(plane->old_fb); plane->old_fb = NULL; @@ -685,6 +682,7 @@ int drm_mode_setplane(struct drm_device *dev, void *data, struct drm_plane *plane; struct drm_crtc *crtc = NULL; struct drm_framebuffer *fb = NULL; + int ret; if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; @@ -717,15 +715,16 @@ int drm_mode_setplane(struct drm_device *dev, void *data, } } - /* - * setplane_internal will take care of deref'ing either the old or new - * framebuffer depending on success. - */ - return setplane_internal(plane, crtc, fb, - plane_req->crtc_x, plane_req->crtc_y, - plane_req->crtc_w, plane_req->crtc_h, - plane_req->src_x, plane_req->src_y, - plane_req->src_w, plane_req->src_h); + ret = setplane_internal(plane, crtc, fb, + plane_req->crtc_x, plane_req->crtc_y, + plane_req->crtc_w, plane_req->crtc_h, + plane_req->src_x, plane_req->src_y, + plane_req->src_w, plane_req->src_h); + + if (fb) + drm_framebuffer_put(fb); + + return ret; } static int drm_mode_cursor_universal(struct drm_crtc *crtc, @@ -788,13 +787,12 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc, src_h = fb->height << 16; } - /* - * setplane_internal will take care of deref'ing either the old or new - * framebuffer depending on success. - */ ret = __setplane_internal(crtc->cursor, crtc, fb, - crtc_x, crtc_y, crtc_w, crtc_h, - 0, 0, src_w, src_h, ctx); + crtc_x, crtc_y, crtc_w, crtc_h, + 0, 0, src_w, src_h, ctx); + + if (fb) + drm_framebuffer_put(fb); /* Update successful; save new cursor position, if necessary */ if (ret == 0 && req->flags & DRM_MODE_CURSOR_MOVE) { diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index f776fc1cc543..cb4d09c70fd4 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -369,40 +369,26 @@ static const struct file_operations drm_syncobj_file_fops = { .release = drm_syncobj_file_release, }; -static int drm_syncobj_alloc_file(struct drm_syncobj *syncobj) -{ - struct file *file = anon_inode_getfile("syncobj_file", - &drm_syncobj_file_fops, - syncobj, 0); - if (IS_ERR(file)) - return PTR_ERR(file); - - drm_syncobj_get(syncobj); - if (cmpxchg(&syncobj->file, NULL, file)) { - /* lost the race */ - fput(file); - } - - return 0; -} - int drm_syncobj_get_fd(struct drm_syncobj *syncobj, int *p_fd) { - int ret; + struct file *file; int fd; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; - if (!syncobj->file) { - ret = drm_syncobj_alloc_file(syncobj); - if (ret) { - put_unused_fd(fd); - return ret; - } + file = anon_inode_getfile("syncobj_file", + &drm_syncobj_file_fops, + syncobj, 0); + if (IS_ERR(file)) { + put_unused_fd(fd); + return PTR_ERR(file); } - fd_install(fd, syncobj->file); + + drm_syncobj_get(syncobj); + fd_install(fd, file); + *p_fd = fd; return 0; } @@ -422,31 +408,24 @@ static int drm_syncobj_handle_to_fd(struct drm_file *file_private, return ret; } -static struct drm_syncobj *drm_syncobj_fdget(int fd) -{ - struct file *file = fget(fd); - - if (!file) - return NULL; - if (file->f_op != &drm_syncobj_file_fops) - goto err; - - return file->private_data; -err: - fput(file); - return NULL; -}; - static int drm_syncobj_fd_to_handle(struct drm_file *file_private, int fd, u32 *handle) { - struct drm_syncobj *syncobj = drm_syncobj_fdget(fd); + struct drm_syncobj *syncobj; + struct file *file; int ret; - if (!syncobj) + file = fget(fd); + if (!file) return -EINVAL; + if (file->f_op != &drm_syncobj_file_fops) { + fput(file); + return -EINVAL; + } + /* take a reference to put in the idr */ + syncobj = file->private_data; drm_syncobj_get(syncobj); idr_preload(GFP_KERNEL); @@ -455,12 +434,14 @@ static int drm_syncobj_fd_to_handle(struct drm_file *file_private, spin_unlock(&file_private->syncobj_table_lock); idr_preload_end(); - if (ret < 0) { - fput(syncobj->file); - return ret; - } - *handle = ret; - return 0; + if (ret > 0) { + *handle = ret; + ret = 0; + } else + drm_syncobj_put(syncobj); + + fput(file); + return ret; } static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private, diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 355120865efd..309f3fa6794a 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -266,6 +266,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) /* Clear host CRT status, so guest couldn't detect this host CRT. */ if (IS_BROADWELL(dev_priv)) vgpu_vreg(vgpu, PCH_ADPA) &= ~ADPA_CRT_HOTPLUG_MONITOR_MASK; + + vgpu_vreg(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE; } static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num) @@ -282,7 +284,6 @@ static void clean_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num) static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num, int type, unsigned int resolution) { - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct intel_vgpu_port *port = intel_vgpu_port(vgpu, port_num); if (WARN_ON(resolution >= GVT_EDID_NUM)) @@ -308,7 +309,7 @@ static int setup_virtual_dp_monitor(struct intel_vgpu *vgpu, int port_num, port->type = type; emulate_monitor_status_change(vgpu); - vgpu_vreg(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE; + return 0; } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index ad4050f7ab3b..18de6569d04a 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -330,17 +330,10 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj) * must wait for all rendering to complete to the object (as unbinding * must anyway), and retire the requests. */ - ret = i915_gem_object_wait(obj, - I915_WAIT_INTERRUPTIBLE | - I915_WAIT_LOCKED | - I915_WAIT_ALL, - MAX_SCHEDULE_TIMEOUT, - NULL); + ret = i915_gem_object_set_to_cpu_domain(obj, false); if (ret) return ret; - i915_gem_retire_requests(to_i915(obj->base.dev)); - while ((vma = list_first_entry_or_null(&obj->vma_list, struct i915_vma, obj_link))) { diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index e8ca67a129d2..ac236b88c99c 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -367,6 +367,7 @@ struct i915_sw_dma_fence_cb { struct dma_fence *dma; struct timer_list timer; struct irq_work work; + struct rcu_head rcu; }; static void timer_i915_sw_fence_wake(struct timer_list *t) @@ -406,7 +407,7 @@ static void irq_i915_sw_fence_work(struct irq_work *wrk) del_timer_sync(&cb->timer); dma_fence_put(cb->dma); - kfree(cb); + kfree_rcu(cb, rcu); } int i915_sw_fence_await_dma_fence(struct i915_sw_fence *fence, diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c index 5f8b9f1f40f1..bcbc7abe6693 100644 --- a/drivers/gpu/drm/i915/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c @@ -186,7 +186,7 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine) struct intel_wait *wait, *n, *first; if (!b->irq_armed) - return; + goto wakeup_signaler; /* We only disarm the irq when we are idle (all requests completed), * so if the bottom-half remains asleep, it missed the request @@ -208,6 +208,14 @@ void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine) b->waiters = RB_ROOT; spin_unlock_irq(&b->rb_lock); + + /* + * The signaling thread may be asleep holding a reference to a request, + * that had its signaling cancelled prior to being preempted. We need + * to kick the signaler, just in case, to release any such reference. + */ +wakeup_signaler: + wake_up_process(b->signaler); } static bool use_fake_irq(const struct intel_breadcrumbs *b) @@ -651,23 +659,15 @@ static int intel_breadcrumbs_signaler(void *arg) } if (unlikely(do_schedule)) { - DEFINE_WAIT(exec); - if (kthread_should_park()) kthread_parkme(); - if (kthread_should_stop()) { - GEM_BUG_ON(request); + if (unlikely(kthread_should_stop())) { + i915_gem_request_put(request); break; } - if (request) - add_wait_queue(&request->execute, &exec); - schedule(); - - if (request) - remove_wait_queue(&request->execute, &exec); } i915_gem_request_put(request); } while (1); diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index e0843bb99169..58a3755544b2 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -2128,6 +2128,8 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder, if (WARN_ON(!pll)) return; + mutex_lock(&dev_priv->dpll_lock); + if (IS_CANNONLAKE(dev_priv)) { /* Configure DPCLKA_CFGCR0 to map the DPLL to the DDI. */ val = I915_READ(DPCLKA_CFGCR0); @@ -2157,6 +2159,8 @@ static void intel_ddi_clk_select(struct intel_encoder *encoder, } else if (INTEL_INFO(dev_priv)->gen < 9) { I915_WRITE(PORT_CLK_SEL(port), hsw_pll_to_ddi_pll_sel(pll)); } + + mutex_unlock(&dev_priv->dpll_lock); } static void intel_ddi_clk_disable(struct intel_encoder *encoder) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index e8ccf89cb17b..30cf273d57aa 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -9944,11 +9944,10 @@ found: } ret = intel_modeset_setup_plane_state(state, crtc, mode, fb, 0, 0); + drm_framebuffer_put(fb); if (ret) goto fail; - drm_framebuffer_put(fb); - ret = drm_atomic_set_mode_for_crtc(&crtc_state->base, mode); if (ret) goto fail; @@ -13195,7 +13194,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe) primary->frontbuffer_bit = INTEL_FRONTBUFFER_PRIMARY(pipe); primary->check_plane = intel_check_primary_plane; - if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) { + if (INTEL_GEN(dev_priv) >= 10) { intel_primary_formats = skl_primary_formats; num_formats = ARRAY_SIZE(skl_primary_formats); modifiers = skl_format_modifiers_ccs; diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index 3bf65288ffff..5809b29044fc 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -193,7 +193,7 @@ static bool lpe_audio_detect(struct drm_i915_private *dev_priv) }; if (!pci_dev_present(atom_hdaudio_ids)) { - DRM_INFO("%s\n", "HDaudio controller not detected, using LPE audio instead\n"); + DRM_INFO("HDaudio controller not detected, using LPE audio instead\n"); lpe_present = true; } } diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2615912430cc..435ff8662cfa 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -224,7 +224,7 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align, /* Determine if we can get a cache-coherent map, forcing * uncached mapping if we can't. */ - if (mmu->type[drm->ttm.type_host].type & NVIF_MEM_UNCACHED) + if (!nouveau_drm_use_coherent_gpu_mapping(drm)) nvbo->force_coherent = true; } @@ -262,7 +262,8 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align, if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE && (flags & TTM_PL_FLAG_VRAM) && !vmm->page[i].vram) continue; - if ((flags & TTM_PL_FLAG_TT ) && !vmm->page[i].host) + if ((flags & TTM_PL_FLAG_TT) && + (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT)) continue; /* Select this page size if it's the first that supports diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 8d4a5be3b913..56fe261b6268 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -152,9 +152,9 @@ nouveau_cli_work_queue(struct nouveau_cli *cli, struct dma_fence *fence, work->cli = cli; mutex_lock(&cli->lock); list_add_tail(&work->head, &cli->worker); - mutex_unlock(&cli->lock); if (dma_fence_add_callback(fence, &work->cb, nouveau_cli_work_fence)) nouveau_cli_work_fence(fence, &work->cb); + mutex_unlock(&cli->lock); } static void diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 3331e82ae9e7..96f6bd8aee5d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -157,8 +157,8 @@ struct nouveau_drm { struct nvif_object copy; int mtrr; int type_vram; - int type_host; - int type_ncoh; + int type_host[2]; + int type_ncoh[2]; } ttm; /* GEM interface support */ @@ -217,6 +217,13 @@ nouveau_drm(struct drm_device *dev) return dev->dev_private; } +static inline bool +nouveau_drm_use_coherent_gpu_mapping(struct nouveau_drm *drm) +{ + struct nvif_mmu *mmu = &drm->client.mmu; + return !(mmu->type[drm->ttm.type_host[0]].type & NVIF_MEM_UNCACHED); +} + int nouveau_pmops_suspend(struct device *); int nouveau_pmops_resume(struct device *); bool nouveau_pmops_runtime(void); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index c533d8e04afc..be7357bf2246 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -429,7 +429,7 @@ nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon) drm_fb_helper_unregister_fbi(&fbcon->helper); drm_fb_helper_fini(&fbcon->helper); - if (nouveau_fb->nvbo) { + if (nouveau_fb && nouveau_fb->nvbo) { nouveau_vma_del(&nouveau_fb->vma); nouveau_bo_unmap(nouveau_fb->nvbo); nouveau_bo_unpin(nouveau_fb->nvbo); diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index 589a9621db76..c002f8968507 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -103,10 +103,10 @@ nouveau_mem_host(struct ttm_mem_reg *reg, struct ttm_dma_tt *tt) u8 type; int ret; - if (mmu->type[drm->ttm.type_host].type & NVIF_MEM_UNCACHED) - type = drm->ttm.type_ncoh; + if (!nouveau_drm_use_coherent_gpu_mapping(drm)) + type = drm->ttm.type_ncoh[!!mem->kind]; else - type = drm->ttm.type_host; + type = drm->ttm.type_host[0]; if (mem->kind && !(mmu->type[type].type & NVIF_MEM_KIND)) mem->comp = mem->kind = 0; diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index 08b974b30482..dff51a0ee028 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -235,27 +235,46 @@ nouveau_ttm_global_release(struct nouveau_drm *drm) drm->ttm.mem_global_ref.release = NULL; } -int -nouveau_ttm_init(struct nouveau_drm *drm) +static int +nouveau_ttm_init_host(struct nouveau_drm *drm, u8 kind) { - struct nvkm_device *device = nvxx_device(&drm->client.device); - struct nvkm_pci *pci = device->pci; struct nvif_mmu *mmu = &drm->client.mmu; - struct drm_device *dev = drm->dev; - int typei, ret; + int typei; typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE | - NVIF_MEM_COHERENT); + kind | NVIF_MEM_COHERENT); if (typei < 0) return -ENOSYS; - drm->ttm.type_host = typei; + drm->ttm.type_host[!!kind] = typei; - typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE); + typei = nvif_mmu_type(mmu, NVIF_MEM_HOST | NVIF_MEM_MAPPABLE | kind); if (typei < 0) return -ENOSYS; - drm->ttm.type_ncoh = typei; + drm->ttm.type_ncoh[!!kind] = typei; + return 0; +} + +int +nouveau_ttm_init(struct nouveau_drm *drm) +{ + struct nvkm_device *device = nvxx_device(&drm->client.device); + struct nvkm_pci *pci = device->pci; + struct nvif_mmu *mmu = &drm->client.mmu; + struct drm_device *dev = drm->dev; + int typei, ret; + + ret = nouveau_ttm_init_host(drm, 0); + if (ret) + return ret; + + if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA && + drm->client.device.info.chipset != 0x50) { + ret = nouveau_ttm_init_host(drm, NVIF_MEM_KIND); + if (ret) + return ret; + } if (drm->client.device.info.platform != NV_DEVICE_INFO_V0_SOC && drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA) { diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index 9e2628dd8e4d..f5371d96b003 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -67,8 +67,8 @@ nouveau_vma_del(struct nouveau_vma **pvma) nvif_vmm_put(&vma->vmm->vmm, &tmp); } list_del(&vma->head); - *pvma = NULL; kfree(*pvma); + *pvma = NULL; } } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index e14643615698..00eeaaffeae5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2369,7 +2369,7 @@ nv13b_chipset = { .imem = gk20a_instmem_new, .ltc = gp100_ltc_new, .mc = gp10b_mc_new, - .mmu = gf100_mmu_new, + .mmu = gp10b_mmu_new, .secboot = gp10b_secboot_new, .pmu = gm20b_pmu_new, .timer = gk20a_timer_new, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c index 972370ed36f0..7c7efa4ea0d0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/dp.c @@ -36,6 +36,7 @@ nvbios_dp_table(struct nvkm_bios *bios, u8 *ver, u8 *hdr, u8 *cnt, u8 *len) if (data) { *ver = nvbios_rd08(bios, data + 0x00); switch (*ver) { + case 0x20: case 0x21: case 0x30: case 0x40: @@ -63,6 +64,7 @@ nvbios_dpout_entry(struct nvkm_bios *bios, u8 idx, if (data && idx < *cnt) { u16 outp = nvbios_rd16(bios, data + *hdr + idx * *len); switch (*ver * !!outp) { + case 0x20: case 0x21: case 0x30: *hdr = nvbios_rd08(bios, data + 0x04); @@ -96,12 +98,16 @@ nvbios_dpout_parse(struct nvkm_bios *bios, u8 idx, info->type = nvbios_rd16(bios, data + 0x00); info->mask = nvbios_rd16(bios, data + 0x02); switch (*ver) { + case 0x20: + info->mask |= 0x00c0; /* match any link */ + /* fall-through */ case 0x21: case 0x30: info->flags = nvbios_rd08(bios, data + 0x05); info->script[0] = nvbios_rd16(bios, data + 0x06); info->script[1] = nvbios_rd16(bios, data + 0x08); - info->lnkcmp = nvbios_rd16(bios, data + 0x0a); + if (*len >= 0x0c) + info->lnkcmp = nvbios_rd16(bios, data + 0x0a); if (*len >= 0x0f) { info->script[2] = nvbios_rd16(bios, data + 0x0c); info->script[3] = nvbios_rd16(bios, data + 0x0e); @@ -170,6 +176,7 @@ nvbios_dpcfg_parse(struct nvkm_bios *bios, u16 outp, u8 idx, memset(info, 0x00, sizeof(*info)); if (data) { switch (*ver) { + case 0x20: case 0x21: info->dc = nvbios_rd08(bios, data + 0x02); info->pe = nvbios_rd08(bios, data + 0x03); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c index 1ba7289684aa..db48a1daca0c 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv50.c @@ -249,7 +249,7 @@ nv50_instobj_acquire(struct nvkm_memory *memory) iobj->base.memory.ptrs = &nv50_instobj_fast; else iobj->base.memory.ptrs = &nv50_instobj_slow; - refcount_inc(&iobj->maps); + refcount_set(&iobj->maps, 1); } mutex_unlock(&imem->subdev.mutex); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c index b1b1f3626b96..deb96de54b00 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pci/base.c @@ -136,6 +136,13 @@ nvkm_pci_init(struct nvkm_subdev *subdev) return ret; pci->irq = pdev->irq; + + /* Ensure MSI interrupts are armed, for the case where there are + * already interrupts pending (for whatever reason) at load time. + */ + if (pci->msi) + pci->func->msi_rearm(pci); + return ret; } diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c index dda904ec0534..500b6fb3e028 100644 --- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c +++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c @@ -175,11 +175,31 @@ static void sun4i_hdmi_mode_set(struct drm_encoder *encoder, writel(val, hdmi->base + SUN4I_HDMI_VID_TIMING_POL_REG); } +static enum drm_mode_status sun4i_hdmi_mode_valid(struct drm_encoder *encoder, + const struct drm_display_mode *mode) +{ + struct sun4i_hdmi *hdmi = drm_encoder_to_sun4i_hdmi(encoder); + unsigned long rate = mode->clock * 1000; + unsigned long diff = rate / 200; /* +-0.5% allowed by HDMI spec */ + long rounded_rate; + + /* 165 MHz is the typical max pixelclock frequency for HDMI <= 1.2 */ + if (rate > 165000000) + return MODE_CLOCK_HIGH; + rounded_rate = clk_round_rate(hdmi->tmds_clk, rate); + if (rounded_rate > 0 && + max_t(unsigned long, rounded_rate, rate) - + min_t(unsigned long, rounded_rate, rate) < diff) + return MODE_OK; + return MODE_NOCLOCK; +} + static const struct drm_encoder_helper_funcs sun4i_hdmi_helper_funcs = { .atomic_check = sun4i_hdmi_atomic_check, .disable = sun4i_hdmi_disable, .enable = sun4i_hdmi_enable, .mode_set = sun4i_hdmi_mode_set, + .mode_valid = sun4i_hdmi_mode_valid, }; static const struct drm_encoder_funcs sun4i_hdmi_funcs = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index e122f5b2a395..f4284b51bdca 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -724,12 +724,12 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master, if (IS_ERR(tcon->crtc)) { dev_err(dev, "Couldn't create our CRTC\n"); ret = PTR_ERR(tcon->crtc); - goto err_free_clocks; + goto err_free_dotclock; } ret = sun4i_rgb_init(drm, tcon); if (ret < 0) - goto err_free_clocks; + goto err_free_dotclock; if (tcon->quirks->needs_de_be_mux) { /* diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index 44343a2bf55c..b5ba6441489f 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -455,6 +455,7 @@ ttm_pool_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) freed += (nr_free_pool - shrink_pages) << pool->order; if (freed >= sc->nr_to_scan) break; + shrink_pages <<= pool->order; } mutex_unlock(&lock); return freed; @@ -543,7 +544,7 @@ static int ttm_alloc_new_pages(struct list_head *pages, gfp_t gfp_flags, int r = 0; unsigned i, j, cpages; unsigned npages = 1 << order; - unsigned max_cpages = min(count, (unsigned)NUM_PAGES_TO_ALLOC); + unsigned max_cpages = min(count << order, (unsigned)NUM_PAGES_TO_ALLOC); /* allocate array for page caching change */ caching_array = kmalloc(max_cpages*sizeof(struct page *), GFP_KERNEL); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index f3fcb836a1f9..0c3f608131cf 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -551,7 +551,7 @@ static int hid_parser_main(struct hid_parser *parser, struct hid_item *item) ret = hid_add_field(parser, HID_FEATURE_REPORT, data); break; default: - hid_err(parser->device, "unknown main item tag 0x%x\n", item->tag); + hid_warn(parser->device, "unknown main item tag 0x%x\n", item->tag); ret = 0; } diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 68cdc962265b..271f31461da4 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -696,8 +696,16 @@ static int cp2112_xfer(struct i2c_adapter *adap, u16 addr, (u8 *)&word, 2); break; case I2C_SMBUS_I2C_BLOCK_DATA: - size = I2C_SMBUS_BLOCK_DATA; - /* fallthrough */ + if (read_write == I2C_SMBUS_READ) { + read_length = data->block[0]; + count = cp2112_write_read_req(buf, addr, read_length, + command, NULL, 0); + } else { + count = cp2112_write_req(buf, addr, command, + data->block + 1, + data->block[0]); + } + break; case I2C_SMBUS_BLOCK_DATA: if (I2C_SMBUS_READ == read_write) { count = cp2112_write_read_req(buf, addr, @@ -785,6 +793,9 @@ static int cp2112_xfer(struct i2c_adapter *adap, u16 addr, case I2C_SMBUS_WORD_DATA: data->word = le16_to_cpup((__le16 *)buf); break; + case I2C_SMBUS_I2C_BLOCK_DATA: + memcpy(data->block + 1, buf, read_length); + break; case I2C_SMBUS_BLOCK_DATA: if (read_length > I2C_SMBUS_BLOCK_MAX) { ret = -EPROTO; diff --git a/drivers/hid/hid-holtekff.c b/drivers/hid/hid-holtekff.c index 9325545fc3ae..edc0f64bb584 100644 --- a/drivers/hid/hid-holtekff.c +++ b/drivers/hid/hid-holtekff.c @@ -32,10 +32,6 @@ #ifdef CONFIG_HOLTEK_FF -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Anssi Hannula <anssi.hannula@iki.fi>"); -MODULE_DESCRIPTION("Force feedback support for Holtek On Line Grip based devices"); - /* * These commands and parameters are currently known: * @@ -223,3 +219,7 @@ static struct hid_driver holtek_driver = { .probe = holtek_probe, }; module_hid_driver(holtek_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Anssi Hannula <anssi.hannula@iki.fi>"); +MODULE_DESCRIPTION("Force feedback support for Holtek On Line Grip based devices"); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 76ed9a216f10..610223f0e945 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1378,6 +1378,8 @@ void vmbus_device_unregister(struct hv_device *device_obj) pr_debug("child device %s unregistered\n", dev_name(&device_obj->device)); + kset_unregister(device_obj->channels_kset); + /* * Kick off the process of unregistering the device. * This will call vmbus_remove() and eventually vmbus_device_release() diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index c9790e2c3440..af5123042990 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -143,6 +143,7 @@ static int hwmon_thermal_add_sensor(struct device *dev, struct hwmon_device *hwdev, int index) { struct hwmon_thermal_data *tdata; + struct thermal_zone_device *tzd; tdata = devm_kzalloc(dev, sizeof(*tdata), GFP_KERNEL); if (!tdata) @@ -151,8 +152,14 @@ static int hwmon_thermal_add_sensor(struct device *dev, tdata->hwdev = hwdev; tdata->index = index; - devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata, - &hwmon_thermal_ops); + tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata, + &hwmon_thermal_ops); + /* + * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, + * so ignore that error but forward any other error. + */ + if (IS_ERR(tzd) && (PTR_ERR(tzd) != -ENODEV)) + return PTR_ERR(tzd); return 0; } @@ -621,14 +628,20 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, if (!chip->ops->is_visible(drvdata, hwmon_temp, hwmon_temp_input, j)) continue; - if (info[i]->config[j] & HWMON_T_INPUT) - hwmon_thermal_add_sensor(dev, hwdev, j); + if (info[i]->config[j] & HWMON_T_INPUT) { + err = hwmon_thermal_add_sensor(dev, + hwdev, j); + if (err) + goto free_device; + } } } } return hdev; +free_device: + device_unregister(hdev); free_hwmon: kfree(hwdev); ida_remove: diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c index feafdb961c48..59b2f96d986a 100644 --- a/drivers/infiniband/core/security.c +++ b/drivers/infiniband/core/security.c @@ -386,6 +386,9 @@ int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev) if (ret) return ret; + if (!qp->qp_sec) + return 0; + mutex_lock(&real_qp->qp_sec->mutex); ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys, qp->qp_sec); diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index d0202bb176a4..840b24096690 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2074,8 +2074,8 @@ int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file, return -EOPNOTSUPP; if (ucore->inlen > sizeof(cmd)) { - if (ib_is_udata_cleared(ucore, sizeof(cmd), - ucore->inlen - sizeof(cmd))) + if (!ib_is_udata_cleared(ucore, sizeof(cmd), + ucore->inlen - sizeof(cmd))) return -EOPNOTSUPP; } diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 3fb8fb6cc824..e36d27ed4daa 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -1438,7 +1438,8 @@ int ib_close_qp(struct ib_qp *qp) spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags); atomic_dec(&real_qp->usecnt); - ib_close_shared_qp_security(qp->qp_sec); + if (qp->qp_sec) + ib_close_shared_qp_security(qp->qp_sec); kfree(qp); return 0; diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index b7bfc536e00f..6f2b26126c64 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -395,7 +395,7 @@ next_cqe: static int cqe_completes_wr(struct t4_cqe *cqe, struct t4_wq *wq) { - if (CQE_OPCODE(cqe) == C4IW_DRAIN_OPCODE) { + if (DRAIN_CQE(cqe)) { WARN_ONCE(1, "Unexpected DRAIN CQE qp id %u!\n", wq->sq.qid); return 0; } @@ -494,7 +494,7 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe, /* * Special cqe for drain WR completions... */ - if (CQE_OPCODE(hw_cqe) == C4IW_DRAIN_OPCODE) { + if (DRAIN_CQE(hw_cqe)) { *cookie = CQE_DRAIN_COOKIE(hw_cqe); *cqe = *hw_cqe; goto skip_cqe; @@ -571,10 +571,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe, ret = -EAGAIN; goto skip_cqe; } - if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) { + if (unlikely(!CQE_STATUS(hw_cqe) && + CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) { t4_set_wq_in_error(wq); - hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN)); - goto proc_cqe; + hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN)); } goto proc_cqe; } @@ -748,9 +748,6 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc) c4iw_invalidate_mr(qhp->rhp, CQE_WRID_FR_STAG(&cqe)); break; - case C4IW_DRAIN_OPCODE: - wc->opcode = IB_WC_SEND; - break; default: pr_err("Unexpected opcode %d in the CQE received for QPID=0x%0x\n", CQE_OPCODE(&cqe), CQE_QPID(&cqe)); diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h index 470f97a79ebb..65dd3726ca02 100644 --- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h +++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h @@ -693,8 +693,6 @@ static inline int to_ib_qp_state(int c4iw_qp_state) return IB_QPS_ERR; } -#define C4IW_DRAIN_OPCODE FW_RI_SGE_EC_CR_RETURN - static inline u32 c4iw_ib_to_tpt_access(int a) { return (a & IB_ACCESS_REMOTE_WRITE ? FW_RI_MEM_ACCESS_REM_WRITE : 0) | diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index 38bddd02a943..d5c92fc520d6 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -790,21 +790,57 @@ static int ring_kernel_rq_db(struct c4iw_qp *qhp, u16 inc) return 0; } -static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr) +static int ib_to_fw_opcode(int ib_opcode) +{ + int opcode; + + switch (ib_opcode) { + case IB_WR_SEND_WITH_INV: + opcode = FW_RI_SEND_WITH_INV; + break; + case IB_WR_SEND: + opcode = FW_RI_SEND; + break; + case IB_WR_RDMA_WRITE: + opcode = FW_RI_RDMA_WRITE; + break; + case IB_WR_RDMA_READ: + case IB_WR_RDMA_READ_WITH_INV: + opcode = FW_RI_READ_REQ; + break; + case IB_WR_REG_MR: + opcode = FW_RI_FAST_REGISTER; + break; + case IB_WR_LOCAL_INV: + opcode = FW_RI_LOCAL_INV; + break; + default: + opcode = -EINVAL; + } + return opcode; +} + +static int complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr) { struct t4_cqe cqe = {}; struct c4iw_cq *schp; unsigned long flag; struct t4_cq *cq; + int opcode; schp = to_c4iw_cq(qhp->ibqp.send_cq); cq = &schp->cq; + opcode = ib_to_fw_opcode(wr->opcode); + if (opcode < 0) + return opcode; + cqe.u.drain_cookie = wr->wr_id; cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) | - CQE_OPCODE_V(C4IW_DRAIN_OPCODE) | + CQE_OPCODE_V(opcode) | CQE_TYPE_V(1) | CQE_SWCQE_V(1) | + CQE_DRAIN_V(1) | CQE_QPID_V(qhp->wq.sq.qid)); spin_lock_irqsave(&schp->lock, flag); @@ -819,6 +855,23 @@ static void complete_sq_drain_wr(struct c4iw_qp *qhp, struct ib_send_wr *wr) schp->ibcq.cq_context); spin_unlock_irqrestore(&schp->comp_handler_lock, flag); } + return 0; +} + +static int complete_sq_drain_wrs(struct c4iw_qp *qhp, struct ib_send_wr *wr, + struct ib_send_wr **bad_wr) +{ + int ret = 0; + + while (wr) { + ret = complete_sq_drain_wr(qhp, wr); + if (ret) { + *bad_wr = wr; + break; + } + wr = wr->next; + } + return ret; } static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr) @@ -833,9 +886,10 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr) cqe.u.drain_cookie = wr->wr_id; cqe.header = cpu_to_be32(CQE_STATUS_V(T4_ERR_SWFLUSH) | - CQE_OPCODE_V(C4IW_DRAIN_OPCODE) | + CQE_OPCODE_V(FW_RI_SEND) | CQE_TYPE_V(0) | CQE_SWCQE_V(1) | + CQE_DRAIN_V(1) | CQE_QPID_V(qhp->wq.sq.qid)); spin_lock_irqsave(&rchp->lock, flag); @@ -852,6 +906,14 @@ static void complete_rq_drain_wr(struct c4iw_qp *qhp, struct ib_recv_wr *wr) } } +static void complete_rq_drain_wrs(struct c4iw_qp *qhp, struct ib_recv_wr *wr) +{ + while (wr) { + complete_rq_drain_wr(qhp, wr); + wr = wr->next; + } +} + int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, struct ib_send_wr **bad_wr) { @@ -875,7 +937,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr, */ if (qhp->wq.flushed) { spin_unlock_irqrestore(&qhp->lock, flag); - complete_sq_drain_wr(qhp, wr); + err = complete_sq_drain_wrs(qhp, wr, bad_wr); return err; } num_wrs = t4_sq_avail(&qhp->wq); @@ -1023,7 +1085,7 @@ int c4iw_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr, */ if (qhp->wq.flushed) { spin_unlock_irqrestore(&qhp->lock, flag); - complete_rq_drain_wr(qhp, wr); + complete_rq_drain_wrs(qhp, wr); return err; } num_wrs = t4_rq_avail(&qhp->wq); diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index e9ea94268d51..79e8ee12c391 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -197,6 +197,11 @@ struct t4_cqe { #define CQE_SWCQE_G(x) ((((x) >> CQE_SWCQE_S)) & CQE_SWCQE_M) #define CQE_SWCQE_V(x) ((x)<<CQE_SWCQE_S) +#define CQE_DRAIN_S 10 +#define CQE_DRAIN_M 0x1 +#define CQE_DRAIN_G(x) ((((x) >> CQE_DRAIN_S)) & CQE_DRAIN_M) +#define CQE_DRAIN_V(x) ((x)<<CQE_DRAIN_S) + #define CQE_STATUS_S 5 #define CQE_STATUS_M 0x1F #define CQE_STATUS_G(x) ((((x) >> CQE_STATUS_S)) & CQE_STATUS_M) @@ -213,6 +218,7 @@ struct t4_cqe { #define CQE_OPCODE_V(x) ((x)<<CQE_OPCODE_S) #define SW_CQE(x) (CQE_SWCQE_G(be32_to_cpu((x)->header))) +#define DRAIN_CQE(x) (CQE_DRAIN_G(be32_to_cpu((x)->header))) #define CQE_QPID(x) (CQE_QPID_G(be32_to_cpu((x)->header))) #define CQE_TYPE(x) (CQE_TYPE_G(be32_to_cpu((x)->header))) #define SQ_TYPE(x) (CQE_TYPE((x))) diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 4a9b4d7efe63..8ce9118d4a7f 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1131,7 +1131,6 @@ struct hfi1_devdata { u16 pcie_lnkctl; u16 pcie_devctl2; u32 pci_msix0; - u32 pci_lnkctl3; u32 pci_tph2; /* diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index 09e50fd2a08f..8c7e7a60b715 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -411,15 +411,12 @@ int restore_pci_variables(struct hfi1_devdata *dd) if (ret) goto error; - ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, - dd->pci_lnkctl3); - if (ret) - goto error; - - ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2); - if (ret) - goto error; - + if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) { + ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, + dd->pci_tph2); + if (ret) + goto error; + } return 0; error: @@ -469,15 +466,12 @@ int save_pci_variables(struct hfi1_devdata *dd) if (ret) goto error; - ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1, - &dd->pci_lnkctl3); - if (ret) - goto error; - - ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2); - if (ret) - goto error; - + if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) { + ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, + &dd->pci_tph2); + if (ret) + goto error; + } return 0; error: diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 470995fa38d2..6f6712f87a73 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -47,17 +47,6 @@ int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey) return err; } -int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev, - bool reset, void *out, int out_size) -{ - u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { }; - - MLX5_SET(query_cong_statistics_in, in, opcode, - MLX5_CMD_OP_QUERY_CONG_STATISTICS); - MLX5_SET(query_cong_statistics_in, in, clear, reset); - return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size); -} - int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point, void *out, int out_size) { diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index af4c24596274..78ffded7cc2c 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -37,8 +37,6 @@ #include <linux/mlx5/driver.h> int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey); -int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev, - bool reset, void *out, int out_size); int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point, void *out, int out_size); int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev, diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 543d0a4c8bf3..8ac50de2b242 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1463,6 +1463,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev, } INIT_LIST_HEAD(&context->vma_private_list); + mutex_init(&context->vma_private_list_mutex); INIT_LIST_HEAD(&context->db_page_list); mutex_init(&context->db_page_mutex); @@ -1624,7 +1625,9 @@ static void mlx5_ib_vma_close(struct vm_area_struct *area) * mlx5_ib_disassociate_ucontext(). */ mlx5_ib_vma_priv_data->vma = NULL; + mutex_lock(mlx5_ib_vma_priv_data->vma_private_list_mutex); list_del(&mlx5_ib_vma_priv_data->list); + mutex_unlock(mlx5_ib_vma_priv_data->vma_private_list_mutex); kfree(mlx5_ib_vma_priv_data); } @@ -1644,10 +1647,13 @@ static int mlx5_ib_set_vma_data(struct vm_area_struct *vma, return -ENOMEM; vma_prv->vma = vma; + vma_prv->vma_private_list_mutex = &ctx->vma_private_list_mutex; vma->vm_private_data = vma_prv; vma->vm_ops = &mlx5_ib_vm_ops; + mutex_lock(&ctx->vma_private_list_mutex); list_add(&vma_prv->list, vma_head); + mutex_unlock(&ctx->vma_private_list_mutex); return 0; } @@ -1690,6 +1696,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext) * mlx5_ib_vma_close. */ down_write(&owning_mm->mmap_sem); + mutex_lock(&context->vma_private_list_mutex); list_for_each_entry_safe(vma_private, n, &context->vma_private_list, list) { vma = vma_private->vma; @@ -1704,6 +1711,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext) list_del(&vma_private->list); kfree(vma_private); } + mutex_unlock(&context->vma_private_list_mutex); up_write(&owning_mm->mmap_sem); mmput(owning_mm); put_task_struct(owning_process); @@ -3737,34 +3745,6 @@ free: return ret; } -static int mlx5_ib_query_cong_counters(struct mlx5_ib_dev *dev, - struct mlx5_ib_port *port, - struct rdma_hw_stats *stats) -{ - int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out); - void *out; - int ret, i; - int offset = port->cnts.num_q_counters; - - out = kvzalloc(outlen, GFP_KERNEL); - if (!out) - return -ENOMEM; - - ret = mlx5_cmd_query_cong_counter(dev->mdev, false, out, outlen); - if (ret) - goto free; - - for (i = 0; i < port->cnts.num_cong_counters; i++) { - stats->value[i + offset] = - be64_to_cpup((__be64 *)(out + - port->cnts.offsets[i + offset])); - } - -free: - kvfree(out); - return ret; -} - static int mlx5_ib_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats, u8 port_num, int index) @@ -3782,7 +3762,12 @@ static int mlx5_ib_get_hw_stats(struct ib_device *ibdev, num_counters = port->cnts.num_q_counters; if (MLX5_CAP_GEN(dev->mdev, cc_query_allowed)) { - ret = mlx5_ib_query_cong_counters(dev, port, stats); + ret = mlx5_lag_query_cong_counters(dev->mdev, + stats->value + + port->cnts.num_q_counters, + port->cnts.num_cong_counters, + port->cnts.offsets + + port->cnts.num_q_counters); if (ret) return ret; num_counters += port->cnts.num_cong_counters; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 6dd8cac78de2..2c5f3533bbc9 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -115,6 +115,8 @@ enum { struct mlx5_ib_vma_private_data { struct list_head list; struct vm_area_struct *vma; + /* protect vma_private_list add/del */ + struct mutex *vma_private_list_mutex; }; struct mlx5_ib_ucontext { @@ -129,6 +131,8 @@ struct mlx5_ib_ucontext { /* Transport Domain number */ u32 tdn; struct list_head vma_private_list; + /* protect vma_private_list add/del */ + struct mutex vma_private_list_mutex; unsigned long upd_xlt_page; /* protect ODP/KSM */ diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index ee0ee1f9994b..d109fe8290a7 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -1637,6 +1637,7 @@ struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, MLX5_SET(mkc, mkc, access_mode, mr->access_mode); MLX5_SET(mkc, mkc, umr_en, 1); + mr->ibmr.device = pd->device; err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen); if (err) goto err_destroy_psv; diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h index 63bc2efc34eb..4f7bd3b6a315 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma.h @@ -94,7 +94,7 @@ struct pvrdma_cq { u32 cq_handle; bool is_kernel; atomic_t refcnt; - wait_queue_head_t wait; + struct completion free; }; struct pvrdma_id_table { @@ -175,7 +175,7 @@ struct pvrdma_srq { u32 srq_handle; int npages; refcount_t refcnt; - wait_queue_head_t wait; + struct completion free; }; struct pvrdma_qp { @@ -197,7 +197,7 @@ struct pvrdma_qp { bool is_kernel; struct mutex mutex; /* QP state mutex. */ atomic_t refcnt; - wait_queue_head_t wait; + struct completion free; }; struct pvrdma_dev { diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c index 3562c0c30492..e529622cefad 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c @@ -179,7 +179,7 @@ struct ib_cq *pvrdma_create_cq(struct ib_device *ibdev, pvrdma_page_dir_insert_umem(&cq->pdir, cq->umem, 0); atomic_set(&cq->refcnt, 1); - init_waitqueue_head(&cq->wait); + init_completion(&cq->free); spin_lock_init(&cq->cq_lock); memset(cmd, 0, sizeof(*cmd)); @@ -230,8 +230,9 @@ err_cq: static void pvrdma_free_cq(struct pvrdma_dev *dev, struct pvrdma_cq *cq) { - atomic_dec(&cq->refcnt); - wait_event(cq->wait, !atomic_read(&cq->refcnt)); + if (atomic_dec_and_test(&cq->refcnt)) + complete(&cq->free); + wait_for_completion(&cq->free); if (!cq->is_kernel) ib_umem_release(cq->umem); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c index 1f4e18717a00..e92681878c93 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c @@ -346,9 +346,8 @@ static void pvrdma_qp_event(struct pvrdma_dev *dev, u32 qpn, int type) ibqp->event_handler(&e, ibqp->qp_context); } if (qp) { - atomic_dec(&qp->refcnt); - if (atomic_read(&qp->refcnt) == 0) - wake_up(&qp->wait); + if (atomic_dec_and_test(&qp->refcnt)) + complete(&qp->free); } } @@ -373,9 +372,8 @@ static void pvrdma_cq_event(struct pvrdma_dev *dev, u32 cqn, int type) ibcq->event_handler(&e, ibcq->cq_context); } if (cq) { - atomic_dec(&cq->refcnt); - if (atomic_read(&cq->refcnt) == 0) - wake_up(&cq->wait); + if (atomic_dec_and_test(&cq->refcnt)) + complete(&cq->free); } } @@ -404,7 +402,7 @@ static void pvrdma_srq_event(struct pvrdma_dev *dev, u32 srqn, int type) } if (srq) { if (refcount_dec_and_test(&srq->refcnt)) - wake_up(&srq->wait); + complete(&srq->free); } } @@ -539,9 +537,8 @@ static irqreturn_t pvrdma_intrx_handler(int irq, void *dev_id) if (cq && cq->ibcq.comp_handler) cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); if (cq) { - atomic_dec(&cq->refcnt); - if (atomic_read(&cq->refcnt)) - wake_up(&cq->wait); + if (atomic_dec_and_test(&cq->refcnt)) + complete(&cq->free); } pvrdma_idx_ring_inc(&ring->cons_head, ring_slots); } diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c index 10420a18d02f..4059308e1454 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_qp.c @@ -246,7 +246,7 @@ struct ib_qp *pvrdma_create_qp(struct ib_pd *pd, spin_lock_init(&qp->rq.lock); mutex_init(&qp->mutex); atomic_set(&qp->refcnt, 1); - init_waitqueue_head(&qp->wait); + init_completion(&qp->free); qp->state = IB_QPS_RESET; @@ -428,8 +428,16 @@ static void pvrdma_free_qp(struct pvrdma_qp *qp) pvrdma_unlock_cqs(scq, rcq, &scq_flags, &rcq_flags); - atomic_dec(&qp->refcnt); - wait_event(qp->wait, !atomic_read(&qp->refcnt)); + if (atomic_dec_and_test(&qp->refcnt)) + complete(&qp->free); + wait_for_completion(&qp->free); + + if (!qp->is_kernel) { + if (qp->rumem) + ib_umem_release(qp->rumem); + if (qp->sumem) + ib_umem_release(qp->sumem); + } pvrdma_page_dir_cleanup(dev, &qp->pdir); diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c index 826ccb864596..5acebb1ef631 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_srq.c @@ -149,7 +149,7 @@ struct ib_srq *pvrdma_create_srq(struct ib_pd *pd, spin_lock_init(&srq->lock); refcount_set(&srq->refcnt, 1); - init_waitqueue_head(&srq->wait); + init_completion(&srq->free); dev_dbg(&dev->pdev->dev, "create shared receive queue from user space\n"); @@ -236,8 +236,9 @@ static void pvrdma_free_srq(struct pvrdma_dev *dev, struct pvrdma_srq *srq) dev->srq_tbl[srq->srq_handle] = NULL; spin_unlock_irqrestore(&dev->srq_tbl_lock, flags); - refcount_dec(&srq->refcnt); - wait_event(srq->wait, !refcount_read(&srq->refcnt)); + if (refcount_dec_and_test(&srq->refcnt)) + complete(&srq->free); + wait_for_completion(&srq->free); /* There is no support for kernel clients, so this is safe. */ ib_umem_release(srq->umem); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c index 3b96cdaf9a83..e6151a29c412 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c @@ -1236,13 +1236,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv, ipoib_ib_dev_down(dev); if (level == IPOIB_FLUSH_HEAVY) { - rtnl_lock(); if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) ipoib_ib_dev_stop(dev); - result = ipoib_ib_dev_open(dev); - rtnl_unlock(); - if (result) + if (ipoib_ib_dev_open(dev)) return; if (netif_queue_stopped(dev)) @@ -1282,7 +1279,9 @@ void ipoib_ib_dev_flush_heavy(struct work_struct *work) struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv, flush_heavy); + rtnl_lock(); __ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0); + rtnl_unlock(); } void ipoib_ib_dev_cleanup(struct net_device *dev) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 7d5eb004091d..97baf88d9505 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -4184,7 +4184,7 @@ static void amd_ir_update_irte(struct irq_data *irqd, struct amd_iommu *iommu, struct irq_cfg *cfg); static int irq_remapping_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool early) + struct irq_data *irq_data, bool reserve) { struct amd_ir_data *data = irq_data->chip_data; struct irq_2_irte *irte_info = &data->irq_2_irte; diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c index 76a193c7fcfc..66f69af2c219 100644 --- a/drivers/iommu/intel_irq_remapping.c +++ b/drivers/iommu/intel_irq_remapping.c @@ -1397,7 +1397,7 @@ static void intel_irq_remapping_free(struct irq_domain *domain, } static int intel_irq_remapping_activate(struct irq_domain *domain, - struct irq_data *irq_data, bool early) + struct irq_data *irq_data, bool reserve) { intel_ir_reconfigure_irte(irq_data, true); return 0; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 4039e64cd342..06f025fd5726 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2303,7 +2303,7 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, } static int its_irq_domain_activate(struct irq_domain *domain, - struct irq_data *d, bool early) + struct irq_data *d, bool reserve) { struct its_device *its_dev = irq_data_get_irq_chip_data(d); u32 event = its_get_event_id(d); @@ -2818,7 +2818,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq } static int its_vpe_irq_domain_activate(struct irq_domain *domain, - struct irq_data *d, bool early) + struct irq_data *d, bool reserve) { struct its_vpe *vpe = irq_data_get_irq_chip_data(d); struct its_node *its; diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c index 06f29cf5018a..cee59fe1321c 100644 --- a/drivers/irqchip/irq-renesas-intc-irqpin.c +++ b/drivers/irqchip/irq-renesas-intc-irqpin.c @@ -342,6 +342,9 @@ static irqreturn_t intc_irqpin_shared_irq_handler(int irq, void *dev_id) */ static struct lock_class_key intc_irqpin_irq_lock_class; +/* And this is for the request mutex */ +static struct lock_class_key intc_irqpin_irq_request_class; + static int intc_irqpin_irq_domain_map(struct irq_domain *h, unsigned int virq, irq_hw_number_t hw) { @@ -352,7 +355,8 @@ static int intc_irqpin_irq_domain_map(struct irq_domain *h, unsigned int virq, intc_irqpin_dbg(&p->irq[hw], "map"); irq_set_chip_data(virq, h->host_data); - irq_set_lockdep_class(virq, &intc_irqpin_irq_lock_class); + irq_set_lockdep_class(virq, &intc_irqpin_irq_lock_class, + &intc_irqpin_irq_request_class); irq_set_chip_and_handler(virq, &p->irq_chip, handle_level_irq); return 0; } diff --git a/drivers/leds/led-core.c b/drivers/leds/led-core.c index fd83c7f77a95..f3654fd2eaf3 100644 --- a/drivers/leds/led-core.c +++ b/drivers/leds/led-core.c @@ -186,7 +186,7 @@ void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on, unsigned long *delay_off) { - del_timer_sync(&led_cdev->blink_timer); + led_stop_software_blink(led_cdev); clear_bit(LED_BLINK_ONESHOT, &led_cdev->work_flags); clear_bit(LED_BLINK_ONESHOT_STOP, &led_cdev->work_flags); diff --git a/drivers/mfd/arizona-irq.c b/drivers/mfd/arizona-irq.c index 09cf3699e354..a307832d7e45 100644 --- a/drivers/mfd/arizona-irq.c +++ b/drivers/mfd/arizona-irq.c @@ -184,6 +184,7 @@ static struct irq_chip arizona_irq_chip = { }; static struct lock_class_key arizona_irq_lock_class; +static struct lock_class_key arizona_irq_request_class; static int arizona_irq_map(struct irq_domain *h, unsigned int virq, irq_hw_number_t hw) @@ -191,7 +192,8 @@ static int arizona_irq_map(struct irq_domain *h, unsigned int virq, struct arizona *data = h->host_data; irq_set_chip_data(virq, data); - irq_set_lockdep_class(virq, &arizona_irq_lock_class); + irq_set_lockdep_class(virq, &arizona_irq_lock_class, + &arizona_irq_request_class); irq_set_chip_and_handler(virq, &arizona_irq_chip, handle_simple_irq); irq_set_nested_thread(virq, 1); irq_set_noprobe(virq); diff --git a/drivers/mfd/cros_ec_spi.c b/drivers/mfd/cros_ec_spi.c index c9714072e224..59c82cdcf48d 100644 --- a/drivers/mfd/cros_ec_spi.c +++ b/drivers/mfd/cros_ec_spi.c @@ -377,6 +377,7 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, u8 *ptr; u8 *rx_buf; u8 sum; + u8 rx_byte; int ret = 0, final_ret; len = cros_ec_prepare_tx(ec_dev, ec_msg); @@ -421,25 +422,22 @@ static int cros_ec_pkt_xfer_spi(struct cros_ec_device *ec_dev, if (!ret) { /* Verify that EC can process command */ for (i = 0; i < len; i++) { - switch (rx_buf[i]) { - case EC_SPI_PAST_END: - case EC_SPI_RX_BAD_DATA: - case EC_SPI_NOT_READY: - ret = -EAGAIN; - ec_msg->result = EC_RES_IN_PROGRESS; - default: + rx_byte = rx_buf[i]; + if (rx_byte == EC_SPI_PAST_END || + rx_byte == EC_SPI_RX_BAD_DATA || + rx_byte == EC_SPI_NOT_READY) { + ret = -EREMOTEIO; break; } - if (ret) - break; } - if (!ret) - ret = cros_ec_spi_receive_packet(ec_dev, - ec_msg->insize + sizeof(*response)); - } else { - dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); } + if (!ret) + ret = cros_ec_spi_receive_packet(ec_dev, + ec_msg->insize + sizeof(*response)); + else + dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); + final_ret = terminate_request(ec_dev); spi_bus_unlock(ec_spi->spi->master); @@ -508,6 +506,7 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, int i, len; u8 *ptr; u8 *rx_buf; + u8 rx_byte; int sum; int ret = 0, final_ret; @@ -544,25 +543,22 @@ static int cros_ec_cmd_xfer_spi(struct cros_ec_device *ec_dev, if (!ret) { /* Verify that EC can process command */ for (i = 0; i < len; i++) { - switch (rx_buf[i]) { - case EC_SPI_PAST_END: - case EC_SPI_RX_BAD_DATA: - case EC_SPI_NOT_READY: - ret = -EAGAIN; - ec_msg->result = EC_RES_IN_PROGRESS; - default: + rx_byte = rx_buf[i]; + if (rx_byte == EC_SPI_PAST_END || + rx_byte == EC_SPI_RX_BAD_DATA || + rx_byte == EC_SPI_NOT_READY) { + ret = -EREMOTEIO; break; } - if (ret) - break; } - if (!ret) - ret = cros_ec_spi_receive_response(ec_dev, - ec_msg->insize + EC_MSG_TX_PROTO_BYTES); - } else { - dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); } + if (!ret) + ret = cros_ec_spi_receive_response(ec_dev, + ec_msg->insize + EC_MSG_TX_PROTO_BYTES); + else + dev_err(ec_dev->dev, "spi transfer failed: %d\n", ret); + final_ret = terminate_request(ec_dev); spi_bus_unlock(ec_spi->spi->master); @@ -667,6 +663,7 @@ static int cros_ec_spi_probe(struct spi_device *spi) sizeof(struct ec_response_get_protocol_info); ec_dev->dout_size = sizeof(struct ec_host_request); + ec_spi->last_transfer_ns = ktime_get_ns(); err = cros_ec_register(ec_dev); if (err) { diff --git a/drivers/mfd/twl4030-audio.c b/drivers/mfd/twl4030-audio.c index da16bf45fab4..dc94ffc6321a 100644 --- a/drivers/mfd/twl4030-audio.c +++ b/drivers/mfd/twl4030-audio.c @@ -159,13 +159,18 @@ unsigned int twl4030_audio_get_mclk(void) EXPORT_SYMBOL_GPL(twl4030_audio_get_mclk); static bool twl4030_audio_has_codec(struct twl4030_audio_data *pdata, - struct device_node *node) + struct device_node *parent) { + struct device_node *node; + if (pdata && pdata->codec) return true; - if (of_find_node_by_name(node, "codec")) + node = of_get_child_by_name(parent, "codec"); + if (node) { + of_node_put(node); return true; + } return false; } diff --git a/drivers/mfd/twl6040.c b/drivers/mfd/twl6040.c index d66502d36ba0..dd19f17a1b63 100644 --- a/drivers/mfd/twl6040.c +++ b/drivers/mfd/twl6040.c @@ -97,12 +97,16 @@ static struct reg_sequence twl6040_patch[] = { }; -static bool twl6040_has_vibra(struct device_node *node) +static bool twl6040_has_vibra(struct device_node *parent) { -#ifdef CONFIG_OF - if (of_find_node_by_name(node, "vibra")) + struct device_node *node; + + node = of_get_child_by_name(parent, "vibra"); + if (node) { + of_node_put(node); return true; -#endif + } + return false; } diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index f80e911b8843..73b605577447 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -1114,7 +1114,7 @@ static int mtd_check_oob_ops(struct mtd_info *mtd, loff_t offs, if (!ops->oobbuf) ops->ooblen = 0; - if (offs < 0 || offs + ops->len >= mtd->size) + if (offs < 0 || offs + ops->len > mtd->size) return -EINVAL; if (ops->ooblen) { diff --git a/drivers/mtd/nand/brcmnand/brcmnand.c b/drivers/mtd/nand/brcmnand/brcmnand.c index e0eb51d8c012..dd56a671ea42 100644 --- a/drivers/mtd/nand/brcmnand/brcmnand.c +++ b/drivers/mtd/nand/brcmnand/brcmnand.c @@ -1763,7 +1763,7 @@ try_dmaread: err = brcmstb_nand_verify_erased_page(mtd, chip, buf, addr); /* erased page bitflips corrected */ - if (err > 0) + if (err >= 0) return err; } diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c index 484f7fbc3f7d..a8bde6665c24 100644 --- a/drivers/mtd/nand/gpio.c +++ b/drivers/mtd/nand/gpio.c @@ -253,9 +253,9 @@ static int gpio_nand_probe(struct platform_device *pdev) goto out_ce; } - gpiomtd->nwp = devm_gpiod_get(dev, "ale", GPIOD_OUT_LOW); - if (IS_ERR(gpiomtd->nwp)) { - ret = PTR_ERR(gpiomtd->nwp); + gpiomtd->ale = devm_gpiod_get(dev, "ale", GPIOD_OUT_LOW); + if (IS_ERR(gpiomtd->ale)) { + ret = PTR_ERR(gpiomtd->ale); goto out_ce; } diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index 50f8d4a1b983..d4d824ef64e9 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -1067,9 +1067,6 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip, return ret; } - /* handle the block mark swapping */ - block_mark_swapping(this, payload_virt, auxiliary_virt); - /* Loop over status bytes, accumulating ECC status. */ status = auxiliary_virt + nfc_geo->auxiliary_status_offset; @@ -1158,6 +1155,9 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip, max_bitflips = max_t(unsigned int, max_bitflips, *status); } + /* handle the block mark swapping */ + block_mark_swapping(this, buf, auxiliary_virt); + if (oob_required) { /* * It's time to deliver the OOB bytes. See gpmi_ecc_read_oob() diff --git a/drivers/net/ethernet/arc/emac.h b/drivers/net/ethernet/arc/emac.h index 3c63b16d485f..d9efbc8d783b 100644 --- a/drivers/net/ethernet/arc/emac.h +++ b/drivers/net/ethernet/arc/emac.h @@ -159,6 +159,8 @@ struct arc_emac_priv { unsigned int link; unsigned int duplex; unsigned int speed; + + unsigned int rx_missed_errors; }; /** diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 3241af1ce718..bd277b0dc615 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -26,6 +26,8 @@ #include "emac.h" +static void arc_emac_restart(struct net_device *ndev); + /** * arc_emac_tx_avail - Return the number of available slots in the tx ring. * @priv: Pointer to ARC EMAC private data structure. @@ -210,39 +212,48 @@ static int arc_emac_rx(struct net_device *ndev, int budget) continue; } - pktlen = info & LEN_MASK; - stats->rx_packets++; - stats->rx_bytes += pktlen; - skb = rx_buff->skb; - skb_put(skb, pktlen); - skb->dev = ndev; - skb->protocol = eth_type_trans(skb, ndev); - - dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr), - dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); - - /* Prepare the BD for next cycle */ - rx_buff->skb = netdev_alloc_skb_ip_align(ndev, - EMAC_BUFFER_SIZE); - if (unlikely(!rx_buff->skb)) { + /* Prepare the BD for next cycle. netif_receive_skb() + * only if new skb was allocated and mapped to avoid holes + * in the RX fifo. + */ + skb = netdev_alloc_skb_ip_align(ndev, EMAC_BUFFER_SIZE); + if (unlikely(!skb)) { + if (net_ratelimit()) + netdev_err(ndev, "cannot allocate skb\n"); + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); stats->rx_errors++; - /* Because receive_skb is below, increment rx_dropped */ stats->rx_dropped++; continue; } - /* receive_skb only if new skb was allocated to avoid holes */ - netif_receive_skb(skb); - - addr = dma_map_single(&ndev->dev, (void *)rx_buff->skb->data, + addr = dma_map_single(&ndev->dev, (void *)skb->data, EMAC_BUFFER_SIZE, DMA_FROM_DEVICE); if (dma_mapping_error(&ndev->dev, addr)) { if (net_ratelimit()) - netdev_err(ndev, "cannot dma map\n"); - dev_kfree_skb(rx_buff->skb); + netdev_err(ndev, "cannot map dma buffer\n"); + dev_kfree_skb(skb); + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); stats->rx_errors++; + stats->rx_dropped++; continue; } + + /* unmap previosly mapped skb */ + dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr), + dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); + + pktlen = info & LEN_MASK; + stats->rx_packets++; + stats->rx_bytes += pktlen; + skb_put(rx_buff->skb, pktlen); + rx_buff->skb->dev = ndev; + rx_buff->skb->protocol = eth_type_trans(rx_buff->skb, ndev); + + netif_receive_skb(rx_buff->skb); + + rx_buff->skb = skb; dma_unmap_addr_set(rx_buff, addr, addr); dma_unmap_len_set(rx_buff, len, EMAC_BUFFER_SIZE); @@ -259,6 +270,53 @@ static int arc_emac_rx(struct net_device *ndev, int budget) } /** + * arc_emac_rx_miss_handle - handle R_MISS register + * @ndev: Pointer to the net_device structure. + */ +static void arc_emac_rx_miss_handle(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &ndev->stats; + unsigned int miss; + + miss = arc_reg_get(priv, R_MISS); + if (miss) { + stats->rx_errors += miss; + stats->rx_missed_errors += miss; + priv->rx_missed_errors += miss; + } +} + +/** + * arc_emac_rx_stall_check - check RX stall + * @ndev: Pointer to the net_device structure. + * @budget: How many BDs requested to process on 1 call. + * @work_done: How many BDs processed + * + * Under certain conditions EMAC stop reception of incoming packets and + * continuously increment R_MISS register instead of saving data into + * provided buffer. This function detect that condition and restart + * EMAC. + */ +static void arc_emac_rx_stall_check(struct net_device *ndev, + int budget, unsigned int work_done) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct arc_emac_bd *rxbd; + + if (work_done) + priv->rx_missed_errors = 0; + + if (priv->rx_missed_errors && budget) { + rxbd = &priv->rxbd[priv->last_rx_bd]; + if (le32_to_cpu(rxbd->info) & FOR_EMAC) { + arc_emac_restart(ndev); + priv->rx_missed_errors = 0; + } + } +} + +/** * arc_emac_poll - NAPI poll handler. * @napi: Pointer to napi_struct structure. * @budget: How many BDs to process on 1 call. @@ -272,6 +330,7 @@ static int arc_emac_poll(struct napi_struct *napi, int budget) unsigned int work_done; arc_emac_tx_clean(ndev); + arc_emac_rx_miss_handle(ndev); work_done = arc_emac_rx(ndev, budget); if (work_done < budget) { @@ -279,6 +338,8 @@ static int arc_emac_poll(struct napi_struct *napi, int budget) arc_reg_or(priv, R_ENABLE, RXINT_MASK | TXINT_MASK); } + arc_emac_rx_stall_check(ndev, budget, work_done); + return work_done; } @@ -320,6 +381,8 @@ static irqreturn_t arc_emac_intr(int irq, void *dev_instance) if (status & MSER_MASK) { stats->rx_missed_errors += 0x100; stats->rx_errors += 0x100; + priv->rx_missed_errors += 0x100; + napi_schedule(&priv->napi); } if (status & RXCR_MASK) { @@ -732,6 +795,63 @@ static int arc_emac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } +/** + * arc_emac_restart - Restart EMAC + * @ndev: Pointer to net_device structure. + * + * This function do hardware reset of EMAC in order to restore + * network packets reception. + */ +static void arc_emac_restart(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + struct net_device_stats *stats = &ndev->stats; + int i; + + if (net_ratelimit()) + netdev_warn(ndev, "restarting stalled EMAC\n"); + + netif_stop_queue(ndev); + + /* Disable interrupts */ + arc_reg_clr(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK); + + /* Disable EMAC */ + arc_reg_clr(priv, R_CTRL, EN_MASK); + + /* Return the sk_buff to system */ + arc_free_tx_queue(ndev); + + /* Clean Tx BD's */ + priv->txbd_curr = 0; + priv->txbd_dirty = 0; + memset(priv->txbd, 0, TX_RING_SZ); + + for (i = 0; i < RX_BD_NUM; i++) { + struct arc_emac_bd *rxbd = &priv->rxbd[i]; + unsigned int info = le32_to_cpu(rxbd->info); + + if (!(info & FOR_EMAC)) { + stats->rx_errors++; + stats->rx_dropped++; + } + /* Return ownership to EMAC */ + rxbd->info = cpu_to_le32(FOR_EMAC | EMAC_BUFFER_SIZE); + } + priv->last_rx_bd = 0; + + /* Make sure info is visible to EMAC before enable */ + wmb(); + + /* Enable interrupts */ + arc_reg_set(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK); + + /* Enable EMAC */ + arc_reg_or(priv, R_CTRL, EN_MASK); + + netif_start_queue(ndev); +} + static const struct net_device_ops arc_emac_netdev_ops = { .ndo_open = arc_emac_open, .ndo_stop = arc_emac_stop, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 4c739d5355d2..8ae269ec17a1 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3030,7 +3030,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link) del_timer_sync(&bp->timer); - if (IS_PF(bp)) { + if (IS_PF(bp) && !BP_NOMCP(bp)) { /* Set ALWAYS_ALIVE bit in shmem */ bp->fw_drv_pulse_wr_seq |= DRV_PULSE_ALWAYS_ALIVE; bnx2x_drv_pulse(bp); @@ -3116,7 +3116,7 @@ int bnx2x_nic_unload(struct bnx2x *bp, int unload_mode, bool keep_link) bp->cnic_loaded = false; /* Clear driver version indication in shmem */ - if (IS_PF(bp)) + if (IS_PF(bp) && !BP_NOMCP(bp)) bnx2x_update_mng_version(bp); /* Check if there are pending parity attentions. If there are - set diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 91e2a7560b48..ddd5d3ebd201 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9578,6 +9578,15 @@ static int bnx2x_init_shmem(struct bnx2x *bp) do { bp->common.shmem_base = REG_RD(bp, MISC_REG_SHARED_MEM_ADDR); + + /* If we read all 0xFFs, means we are in PCI error state and + * should bail out to avoid crashes on adapter's FW reads. + */ + if (bp->common.shmem_base == 0xFFFFFFFF) { + bp->flags |= NO_MCP_FLAG; + return -ENODEV; + } + if (bp->common.shmem_base) { val = SHMEM_RD(bp, validity_map[BP_PORT(bp)]); if (val & SHR_MEM_VALIDITY_MB) @@ -14320,7 +14329,10 @@ static pci_ers_result_t bnx2x_io_slot_reset(struct pci_dev *pdev) BNX2X_ERR("IO slot reset --> driver unload\n"); /* MCP should have been reset; Need to wait for validity */ - bnx2x_init_shmem(bp); + if (bnx2x_init_shmem(bp)) { + rtnl_unlock(); + return PCI_ERS_RESULT_DISCONNECT; + } if (IS_PF(bp) && SHMEM2_HAS(bp, drv_capabilities_flag)) { u32 v; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index de51c2177d03..8995cfefbfcf 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -4,11 +4,13 @@ * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com) * Copyright (C) 2001, 2002, 2003 Jeff Garzik (jgarzik@pobox.com) * Copyright (C) 2004 Sun Microsystems Inc. - * Copyright (C) 2005-2014 Broadcom Corporation. + * Copyright (C) 2005-2016 Broadcom Corporation. + * Copyright (C) 2016-2017 Broadcom Limited. * * Firmware is: * Derived from proprietary unpublished source code, - * Copyright (C) 2000-2003 Broadcom Corporation. + * Copyright (C) 2000-2016 Broadcom Corporation. + * Copyright (C) 2016-2017 Broadcom Ltd. * * Permission is hereby granted for the distribution of this firmware * data in hexadecimal or equivalent format, provided this copyright @@ -10052,6 +10054,16 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) tw32(GRC_MODE, tp->grc_mode | val); + /* On one of the AMD platform, MRRS is restricted to 4000 because of + * south bridge limitation. As a workaround, Driver is setting MRRS + * to 2048 instead of default 4096. + */ + if (tp->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL && + tp->pdev->subsystem_device == TG3PCI_SUBDEVICE_ID_DELL_5762) { + val = tr32(TG3PCI_DEV_STATUS_CTRL) & ~MAX_READ_REQ_MASK; + tw32(TG3PCI_DEV_STATUS_CTRL, val | MAX_READ_REQ_SIZE_2048); + } + /* Setup the timer prescalar register. Clock is always 66Mhz. */ val = tr32(GRC_MISC_CFG); val &= ~0xff; @@ -14225,7 +14237,10 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) /* Reset PHY, otherwise the read DMA engine will be in a mode that * breaks all requests to 256 bytes. */ - if (tg3_asic_rev(tp) == ASIC_REV_57766) + if (tg3_asic_rev(tp) == ASIC_REV_57766 || + tg3_asic_rev(tp) == ASIC_REV_5717 || + tg3_asic_rev(tp) == ASIC_REV_5719 || + tg3_asic_rev(tp) == ASIC_REV_5720) reset_phy = true; err = tg3_restart_hw(tp, reset_phy); diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index c2d02d02d1e6..1f0271fa7c74 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -5,7 +5,8 @@ * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com) * Copyright (C) 2001 Jeff Garzik (jgarzik@pobox.com) * Copyright (C) 2004 Sun Microsystems Inc. - * Copyright (C) 2007-2014 Broadcom Corporation. + * Copyright (C) 2007-2016 Broadcom Corporation. + * Copyright (C) 2016-2017 Broadcom Limited. */ #ifndef _T3_H @@ -96,6 +97,7 @@ #define TG3PCI_SUBDEVICE_ID_DELL_JAGUAR 0x0106 #define TG3PCI_SUBDEVICE_ID_DELL_MERLOT 0x0109 #define TG3PCI_SUBDEVICE_ID_DELL_SLIM_MERLOT 0x010a +#define TG3PCI_SUBDEVICE_ID_DELL_5762 0x07f0 #define TG3PCI_SUBVENDOR_ID_COMPAQ PCI_VENDOR_ID_COMPAQ #define TG3PCI_SUBDEVICE_ID_COMPAQ_BANSHEE 0x007c #define TG3PCI_SUBDEVICE_ID_COMPAQ_BANSHEE_2 0x009a @@ -281,6 +283,9 @@ #define TG3PCI_STD_RING_PROD_IDX 0x00000098 /* 64-bit */ #define TG3PCI_RCV_RET_RING_CON_IDX 0x000000a0 /* 64-bit */ /* 0xa8 --> 0xb8 unused */ +#define TG3PCI_DEV_STATUS_CTRL 0x000000b4 +#define MAX_READ_REQ_SIZE_2048 0x00004000 +#define MAX_READ_REQ_MASK 0x00007000 #define TG3PCI_DUAL_MAC_CTRL 0x000000b8 #define DUAL_MAC_CTRL_CH_MASK 0x00000003 #define DUAL_MAC_CTRL_ID 0x00000004 diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 610573855213..8184d2fca9be 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -818,6 +818,12 @@ static void fec_enet_bd_init(struct net_device *dev) for (i = 0; i < txq->bd.ring_size; i++) { /* Initialize the BD for every fragment in the page. */ bdp->cbd_sc = cpu_to_fec16(0); + if (bdp->cbd_bufaddr && + !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(bdp->cbd_bufaddr), + fec16_to_cpu(bdp->cbd_datlen), + DMA_TO_DEVICE); if (txq->tx_skbuff[i]) { dev_kfree_skb_any(txq->tx_skbuff[i]); txq->tx_skbuff[i] = NULL; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index bc93b69cfd1e..a539263cd79c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1214,6 +1214,10 @@ static void mvneta_port_disable(struct mvneta_port *pp) val &= ~MVNETA_GMAC0_PORT_ENABLE; mvreg_write(pp, MVNETA_GMAC_CTRL_0, val); + pp->link = 0; + pp->duplex = -1; + pp->speed = 0; + udelay(200); } @@ -1958,9 +1962,9 @@ static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo, if (!mvneta_rxq_desc_is_first_last(rx_status) || (rx_status & MVNETA_RXD_ERR_SUMMARY)) { + mvneta_rx_error(pp, rx_desc); err_drop_frame: dev->stats.rx_errors++; - mvneta_rx_error(pp, rx_desc); /* leave the descriptor untouched */ continue; } @@ -3011,7 +3015,7 @@ static void mvneta_cleanup_rxqs(struct mvneta_port *pp) { int queue; - for (queue = 0; queue < txq_number; queue++) + for (queue = 0; queue < rxq_number; queue++) mvneta_rxq_deinit(pp, &pp->rxqs[queue]); } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 54adfd967858..fc67e35b253e 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1961,11 +1961,12 @@ static int mtk_hw_init(struct mtk_eth *eth) /* set GE2 TUNE */ regmap_write(eth->pctl, GPIO_BIAS_CTRL, 0x0); - /* GE1, Force 1000M/FD, FC ON */ - mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(0)); - - /* GE2, Force 1000M/FD, FC ON */ - mtk_w32(eth, MAC_MCR_FIXED_LINK, MTK_MAC_MCR(1)); + /* Set linkdown as the default for each GMAC. Its own MCR would be set + * up with the more appropriate value when mtk_phy_link_adjust call is + * being invoked. + */ + for (i = 0; i < MTK_MAC_COUNT; i++) + mtk_w32(eth, 0, MTK_MAC_MCR(i)); /* Indicates CDM to parse the MTK special tag from CPU * which also is working out for untag packets. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1fffdebbc9e8..e9a1fbcc4adf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_QUERY_VPORT_COUNTER: case MLX5_CMD_OP_ALLOC_Q_COUNTER: case MLX5_CMD_OP_QUERY_Q_COUNTER: - case MLX5_CMD_OP_SET_RATE_LIMIT: + case MLX5_CMD_OP_SET_PP_RATE_LIMIT: case MLX5_CMD_OP_QUERY_RATE_LIMIT: case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT: case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT: @@ -505,7 +505,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER); MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER); - MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT); + MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT); MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT); MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT); MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index c0872b3284cb..543060c305a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -82,6 +82,9 @@ max_t(u32, MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), req) #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 6) #define MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 8) +#define MLX5E_MPWQE_STRIDE_SZ(mdev, cqe_cmprs) \ + (cqe_cmprs ? MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : \ + MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev)) #define MLX5_MPWRQ_LOG_WQE_SZ 18 #define MLX5_MPWRQ_WQE_PAGE_ORDER (MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT > 0 ? \ @@ -590,6 +593,7 @@ struct mlx5e_channel { struct mlx5_core_dev *mdev; struct hwtstamp_config *tstamp; int ix; + int cpu; }; struct mlx5e_channels { @@ -935,8 +939,9 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode); -void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, u8 rq_type); +void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, + u8 rq_type); static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index c6d90b6dd80e..9bcf38f4123b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -274,6 +274,7 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets) static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, struct ieee_ets *ets) { + bool have_ets_tc = false; int bw_sum = 0; int i; @@ -288,11 +289,14 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev, } /* Validate Bandwidth Sum */ - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_ETS) { + have_ets_tc = true; bw_sum += ets->tc_tx_bw[i]; + } + } - if (bw_sum != 0 && bw_sum != 100) { + if (have_ets_tc && bw_sum != 100) { netdev_err(netdev, "Failed to validate ETS: BW sum is illegal\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 23425f028405..8f05efa5c829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1523,8 +1523,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val new_channels.params = priv->channels.params; MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS, new_val); - mlx5e_set_rq_type_params(priv->mdev, &new_channels.params, - new_channels.params.rq_wq_type); + new_channels.params.mpwqe_log_stride_sz = + MLX5E_MPWQE_STRIDE_SZ(priv->mdev, new_val); + new_channels.params.mpwqe_log_num_strides = + MLX5_MPWRQ_LOG_WQE_SZ - new_channels.params.mpwqe_log_stride_sz; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -1536,6 +1538,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val return err; mlx5e_switch_priv_channels(priv, &new_channels, NULL); + mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n", + MLX5E_GET_PFLAG(&priv->channels.params, + MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF"); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index d2b057a3e512..d9d8227f195f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -71,11 +71,6 @@ struct mlx5e_channel_param { struct mlx5e_cq_param icosq_cq; }; -static int mlx5e_get_node(struct mlx5e_priv *priv, int ix) -{ - return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix); -} - static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { return MLX5_CAP_GEN(mdev, striding_rq) && @@ -83,8 +78,8 @@ static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) MLX5_CAP_ETH(mdev, reg_umr_sq); } -void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, - struct mlx5e_params *params, u8 rq_type) +void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params, u8 rq_type) { params->rq_wq_type = rq_type; params->lro_wqe_sz = MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ; @@ -93,10 +88,8 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, params->log_rq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW : MLX5E_PARAMS_DEFAULT_LOG_RQ_SIZE_MPW; - params->mpwqe_log_stride_sz = - MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS) ? - MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : - MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev); + params->mpwqe_log_stride_sz = MLX5E_MPWQE_STRIDE_SZ(mdev, + MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); params->mpwqe_log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - params->mpwqe_log_stride_sz; break; @@ -120,13 +113,14 @@ void mlx5e_set_rq_type_params(struct mlx5_core_dev *mdev, MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); } -static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +static void mlx5e_set_rq_params(struct mlx5_core_dev *mdev, + struct mlx5e_params *params) { u8 rq_type = mlx5e_check_fragmented_striding_rq_cap(mdev) && !params->xdp_prog && !MLX5_IPSEC_DEV(mdev) ? MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ : MLX5_WQ_TYPE_LINKED_LIST; - mlx5e_set_rq_type_params(mdev, params, rq_type); + mlx5e_init_rq_type_params(mdev, params, rq_type); } static void mlx5e_update_carrier(struct mlx5e_priv *priv) @@ -444,17 +438,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int wq_sz = mlx5_wq_ll_get_size(&rq->wq); int mtt_sz = mlx5e_get_wqe_mtt_sz(); int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1; - int node = mlx5e_get_node(c->priv, c->ix); int i; rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info), - GFP_KERNEL, node); + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->mpwqe.info) goto err_out; /* We allocate more than mtt_sz as we will align the pointer */ - rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, - GFP_KERNEL, node); + rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL, + cpu_to_node(c->cpu)); if (unlikely(!rq->mpwqe.mtt_no_align)) goto err_free_wqe_info; @@ -562,7 +555,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, int err; int i; - rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + rqp->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq, &rq->wq_ctrl); @@ -629,8 +622,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, default: /* MLX5_WQ_TYPE_LINKED_LIST */ rq->wqe.frag_info = kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info), - GFP_KERNEL, - mlx5e_get_node(c->priv, c->ix)); + GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->wqe.frag_info) { err = -ENOMEM; goto err_rq_wq_destroy; @@ -1000,13 +992,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1053,13 +1045,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1126,13 +1118,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); if (err) return err; sq->wq.db = &sq->wq.db[MLX5_SND_DBR]; - err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix)); + err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu)); if (err) goto err_sq_wq_destroy; @@ -1504,8 +1496,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->priv->mdev; int err; - param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix); - param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix); + param->wq.buf_numa_node = cpu_to_node(c->cpu); + param->wq.db_numa_node = cpu_to_node(c->cpu); param->eq_ix = c->ix; err = mlx5e_alloc_cq_common(mdev, param, cq); @@ -1604,6 +1596,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq) mlx5e_free_cq(cq); } +static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix) +{ + return cpumask_first(priv->mdev->priv.irq_info[ix].mask); +} + static int mlx5e_open_tx_cqs(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_channel_param *cparam) @@ -1752,12 +1749,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, { struct mlx5e_cq_moder icocq_moder = {0, 0}; struct net_device *netdev = priv->netdev; + int cpu = mlx5e_get_cpu(priv, ix); struct mlx5e_channel *c; unsigned int irq; int err; int eqn; - c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix)); + c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); if (!c) return -ENOMEM; @@ -1765,6 +1763,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->mdev = priv->mdev; c->tstamp = &priv->tstamp; c->ix = ix; + c->cpu = cpu; c->pdev = &priv->mdev->pdev->dev; c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); @@ -1853,8 +1852,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_rq(&c->rq); - netif_set_xps_queue(c->netdev, - mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix); + netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) @@ -3679,6 +3677,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) { + unsigned int offset = 0; struct udphdr *udph; u8 proto; u16 port; @@ -3688,7 +3687,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, proto = ip_hdr(skb)->protocol; break; case htons(ETH_P_IPV6): - proto = ipv6_hdr(skb)->nexthdr; + proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL); break; default: goto out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 60771865c99c..e7e7cef2bde4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -466,7 +466,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr) break; case MLX5_EVENT_TYPE_CQ_ERROR: cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff; - mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrom 0x%x\n", + mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n", cqn, eqe->data.cq_err.syndrome); mlx5_cq_event(dev, cqn, eqe->type); break; @@ -775,7 +775,7 @@ err1: return err; } -int mlx5_stop_eqs(struct mlx5_core_dev *dev) +void mlx5_stop_eqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = &dev->priv.eq_table; int err; @@ -784,22 +784,26 @@ int mlx5_stop_eqs(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, pg)) { err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq); if (err) - return err; + mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n", + err); } #endif err = mlx5_destroy_unmap_eq(dev, &table->pages_eq); if (err) - return err; + mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n", + err); - mlx5_destroy_unmap_eq(dev, &table->async_eq); + err = mlx5_destroy_unmap_eq(dev, &table->async_eq); + if (err) + mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n", + err); mlx5_cmd_use_polling(dev); err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq); if (err) - mlx5_cmd_use_events(dev); - - return err; + mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n", + err); } int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c index 3c11d6e2160a..14962969c5ba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c @@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size, u8 actual_size; int err; + if (!size) + return -EINVAL; + if (!fdev->mdev) return -ENOTCONN; @@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size, u8 actual_size; int err; + if (!size) + return -EINVAL; + if (!fdev->mdev) return -ENOTCONN; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index c70fd663a633..dfaad9ecb2b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -174,6 +174,8 @@ static void del_hw_fte(struct fs_node *node); static void del_sw_flow_table(struct fs_node *node); static void del_sw_flow_group(struct fs_node *node); static void del_sw_fte(struct fs_node *node); +static void del_sw_prio(struct fs_node *node); +static void del_sw_ns(struct fs_node *node); /* Delete rule (destination) is special case that * requires to lock the FTE for all the deletion process. */ @@ -408,6 +410,16 @@ static inline struct mlx5_core_dev *get_dev(struct fs_node *node) return NULL; } +static void del_sw_ns(struct fs_node *node) +{ + kfree(node); +} + +static void del_sw_prio(struct fs_node *node) +{ + kfree(node); +} + static void del_hw_flow_table(struct fs_node *node) { struct mlx5_flow_table *ft; @@ -2064,7 +2076,7 @@ static struct fs_prio *fs_create_prio(struct mlx5_flow_namespace *ns, return ERR_PTR(-ENOMEM); fs_prio->node.type = FS_TYPE_PRIO; - tree_init_node(&fs_prio->node, NULL, NULL); + tree_init_node(&fs_prio->node, NULL, del_sw_prio); tree_add_node(&fs_prio->node, &ns->node); fs_prio->num_levels = num_levels; fs_prio->prio = prio; @@ -2090,7 +2102,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); - tree_init_node(&ns->node, NULL, NULL); + tree_init_node(&ns->node, NULL, del_sw_ns); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 1a0e797ad001..21d29f7936f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -241,7 +241,7 @@ static void print_health_info(struct mlx5_core_dev *dev) u32 fw; int i; - /* If the syndrom is 0, the device is OK and no need to print buffer */ + /* If the syndrome is 0, the device is OK and no need to print buffer */ if (!ioread8(&h->synd)) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index d2a66dc4adc6..8812d7208e8f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -57,7 +57,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { /* Override RQ params as IPoIB supports only LINKED LIST RQ for now */ - mlx5e_set_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST); + mlx5e_init_rq_type_params(mdev, params, MLX5_WQ_TYPE_LINKED_LIST); /* RQ size in ipoib by default is 512 */ params->log_rq_size = is_kdump_kernel() ? diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index f26f97fe4666..582b2f18010a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -137,6 +137,17 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev) } EXPORT_SYMBOL(mlx5_cmd_destroy_vport_lag); +static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev, + bool reset, void *out, int out_size) +{ + u32 in[MLX5_ST_SZ_DW(query_cong_statistics_in)] = { }; + + MLX5_SET(query_cong_statistics_in, in, opcode, + MLX5_CMD_OP_QUERY_CONG_STATISTICS); + MLX5_SET(query_cong_statistics_in, in, clear, reset); + return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size); +} + static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev) { return dev->priv.lag; @@ -633,3 +644,48 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv) /* If bonded, we do not add an IB device for PF1. */ return false; } + +int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, + u64 *values, + int num_counters, + size_t *offsets) +{ + int outlen = MLX5_ST_SZ_BYTES(query_cong_statistics_out); + struct mlx5_core_dev *mdev[MLX5_MAX_PORTS]; + struct mlx5_lag *ldev; + int num_ports; + int ret, i, j; + void *out; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + memset(values, 0, sizeof(*values) * num_counters); + + mutex_lock(&lag_mutex); + ldev = mlx5_lag_dev_get(dev); + if (ldev && mlx5_lag_is_bonded(ldev)) { + num_ports = MLX5_MAX_PORTS; + mdev[0] = ldev->pf[0].dev; + mdev[1] = ldev->pf[1].dev; + } else { + num_ports = 1; + mdev[0] = dev; + } + + for (i = 0; i < num_ports; ++i) { + ret = mlx5_cmd_query_cong_counter(mdev[i], false, out, outlen); + if (ret) + goto unlock; + + for (j = 0; j < num_counters; ++j) + values[j] += be64_to_cpup((__be64 *)(out + offsets[j])); + } + +unlock: + mutex_unlock(&lag_mutex); + kvfree(out); + return ret; +} +EXPORT_SYMBOL(mlx5_lag_query_cong_counters); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 5f323442cc5a..8a89c7e8cd63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -317,9 +317,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; struct mlx5_eq_table *table = &priv->eq_table; - struct irq_affinity irqdesc = { - .pre_vectors = MLX5_EQ_VEC_COMP_BASE, - }; int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; @@ -333,10 +330,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) if (!priv->irq_info) goto err_free_msix; - nvec = pci_alloc_irq_vectors_affinity(dev->pdev, + nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1, nvec, - PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, - &irqdesc); + PCI_IRQ_MSIX); if (nvec < 0) return nvec; @@ -622,6 +618,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev) return (u64)timer_l | (u64)timer_h1 << 32; } +static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i); + + if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) { + mlx5_core_warn(mdev, "zalloc_cpumask_var failed"); + return -ENOMEM; + } + + cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node), + priv->irq_info[i].mask); + + if (IS_ENABLED(CONFIG_SMP) && + irq_set_affinity_hint(irq, priv->irq_info[i].mask)) + mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq); + + return 0; +} + +static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i) +{ + struct mlx5_priv *priv = &mdev->priv; + int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i); + + irq_set_affinity_hint(irq, NULL); + free_cpumask_var(priv->irq_info[i].mask); +} + +static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev) +{ + int err; + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) { + err = mlx5_irq_set_affinity_hint(mdev, i); + if (err) + goto err_out; + } + + return 0; + +err_out: + for (i--; i >= 0; i--) + mlx5_irq_clear_affinity_hint(mdev, i); + + return err; +} + +static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev) +{ + int i; + + for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) + mlx5_irq_clear_affinity_hint(mdev, i); +} + int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn) { @@ -1097,6 +1150,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_eqs; } + err = mlx5_irq_set_affinity_hints(dev); + if (err) { + dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n"); + goto err_affinity_hints; + } + err = mlx5_init_fs(dev); if (err) { dev_err(&pdev->dev, "Failed to init flow steering\n"); @@ -1154,6 +1213,9 @@ err_sriov: mlx5_cleanup_fs(dev); err_fs: + mlx5_irq_clear_affinity_hints(dev); + +err_affinity_hints: free_comp_eqs(dev); err_stop_eqs: @@ -1222,6 +1284,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); + mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); mlx5_stop_eqs(dev); mlx5_put_uars_page(dev, priv->uar); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index db9e665ab104..889130edb715 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev, err_cmd: memset(din, 0, sizeof(din)); memset(dout, 0, sizeof(dout)); - MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP); - MLX5_SET(destroy_qp_in, in, qpn, qp->qpn); + MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP); + MLX5_SET(destroy_qp_in, din, qpn, qp->qpn); mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout)); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c index e651e4c02867..d3c33e9eea72 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c @@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table, return ret_entry; } -static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev, +static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev, u32 rate, u16 index) { - u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)] = {0}; - u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0}; + u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {0}; + u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0}; - MLX5_SET(set_rate_limit_in, in, opcode, - MLX5_CMD_OP_SET_RATE_LIMIT); - MLX5_SET(set_rate_limit_in, in, rate_limit_index, index); - MLX5_SET(set_rate_limit_in, in, rate_limit, rate); + MLX5_SET(set_pp_rate_limit_in, in, opcode, + MLX5_CMD_OP_SET_PP_RATE_LIMIT); + MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index); + MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index) entry->refcount++; } else { /* new rate limit */ - err = mlx5_set_rate_limit_cmd(dev, rate, entry->index); + err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index); if (err) { mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n", rate, err); @@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate) entry->refcount--; if (!entry->refcount) { /* need to remove rate */ - mlx5_set_rate_limit_cmd(dev, 0, entry->index); + mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index); entry->rate = 0; } @@ -262,8 +262,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev) /* Clear all configured rates */ for (i = 0; i < table->max_size; i++) if (table->rl_entry[i].rate) - mlx5_set_rate_limit_cmd(dev, 0, - table->rl_entry[i].index); + mlx5_set_pp_rate_limit_cmd(dev, 0, + table->rl_entry[i].index); kfree(dev->priv.rl_table.rl_entry); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c index 07a9ba6cfc70..2f74953e4561 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c @@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port) struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; struct mlx5e_vxlan *vxlan; - spin_lock(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); vxlan = radix_tree_lookup(&vxlan_db->tree, port); - spin_unlock(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); return vxlan; } @@ -88,8 +88,12 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) struct mlx5e_vxlan *vxlan; int err; - if (mlx5e_vxlan_lookup_port(priv, port)) + mutex_lock(&priv->state_lock); + vxlan = mlx5e_vxlan_lookup_port(priv, port); + if (vxlan) { + atomic_inc(&vxlan->refcount); goto free_work; + } if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port)) goto free_work; @@ -99,10 +103,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work) goto err_delete_port; vxlan->udp_port = port; + atomic_set(&vxlan->refcount, 1); - spin_lock_irq(&vxlan_db->lock); + spin_lock_bh(&vxlan_db->lock); err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan); - spin_unlock_irq(&vxlan_db->lock); + spin_unlock_bh(&vxlan_db->lock); if (err) goto err_free; @@ -113,35 +118,39 @@ err_free: err_delete_port: mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); free_work: + mutex_unlock(&priv->state_lock); kfree(vxlan_work); } -static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port) +static void mlx5e_vxlan_del_port(struct work_struct *work) { + struct mlx5e_vxlan_work *vxlan_work = + container_of(work, struct mlx5e_vxlan_work, work); + struct mlx5e_priv *priv = vxlan_work->priv; struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan; + u16 port = vxlan_work->port; struct mlx5e_vxlan *vxlan; + bool remove = false; - spin_lock_irq(&vxlan_db->lock); - vxlan = radix_tree_delete(&vxlan_db->tree, port); - spin_unlock_irq(&vxlan_db->lock); - + mutex_lock(&priv->state_lock); + spin_lock_bh(&vxlan_db->lock); + vxlan = radix_tree_lookup(&vxlan_db->tree, port); if (!vxlan) - return; - - mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port); - - kfree(vxlan); -} + goto out_unlock; -static void mlx5e_vxlan_del_port(struct work_struct *work) -{ - struct mlx5e_vxlan_work *vxlan_work = - container_of(work, struct mlx5e_vxlan_work, work); - struct mlx5e_priv *priv = vxlan_work->priv; - u16 port = vxlan_work->port; + if (atomic_dec_and_test(&vxlan->refcount)) { + radix_tree_delete(&vxlan_db->tree, port); + remove = true; + } - __mlx5e_vxlan_core_del_port(priv, port); +out_unlock: + spin_unlock_bh(&vxlan_db->lock); + if (remove) { + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + kfree(vxlan); + } + mutex_unlock(&priv->state_lock); kfree(vxlan_work); } @@ -171,12 +180,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv) struct mlx5e_vxlan *vxlan; unsigned int port = 0; - spin_lock_irq(&vxlan_db->lock); + /* Lockless since we are the only radix-tree consumers, wq is disabled */ while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) { port = vxlan->udp_port; - spin_unlock_irq(&vxlan_db->lock); - __mlx5e_vxlan_core_del_port(priv, (u16)port); - spin_lock_irq(&vxlan_db->lock); + radix_tree_delete(&vxlan_db->tree, port); + mlx5e_vxlan_core_del_port_cmd(priv->mdev, port); + kfree(vxlan); } - spin_unlock_irq(&vxlan_db->lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h index 5def12c048e3..5ef6ae7d568a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h @@ -36,6 +36,7 @@ #include "en.h" struct mlx5e_vxlan { + atomic_t refcount; u16 udp_port; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 72ef4f8025f0..be657b8533f0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2436,25 +2436,16 @@ static void mlxsw_sp_neigh_fini(struct mlxsw_sp *mlxsw_sp) rhashtable_destroy(&mlxsw_sp->router->neigh_ht); } -static int mlxsw_sp_neigh_rif_flush(struct mlxsw_sp *mlxsw_sp, - const struct mlxsw_sp_rif *rif) -{ - char rauht_pl[MLXSW_REG_RAUHT_LEN]; - - mlxsw_reg_rauht_pack(rauht_pl, MLXSW_REG_RAUHT_OP_WRITE_DELETE_ALL, - rif->rif_index, rif->addr); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rauht), rauht_pl); -} - static void mlxsw_sp_neigh_rif_gone_sync(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_rif *rif) { struct mlxsw_sp_neigh_entry *neigh_entry, *tmp; - mlxsw_sp_neigh_rif_flush(mlxsw_sp, rif); list_for_each_entry_safe(neigh_entry, tmp, &rif->neigh_list, - rif_list_node) + rif_list_node) { + mlxsw_sp_neigh_entry_update(mlxsw_sp, neigh_entry, false); mlxsw_sp_neigh_entry_destroy(mlxsw_sp, neigh_entry); + } } enum mlxsw_sp_nexthop_type { diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index e379b78e86ef..13190aa09faf 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -82,10 +82,33 @@ static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn) return nfp_net_ebpf_capable(nn) ? "BPF" : ""; } +static int +nfp_bpf_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) +{ + int err; + + nn->app_priv = kzalloc(sizeof(struct nfp_bpf_vnic), GFP_KERNEL); + if (!nn->app_priv) + return -ENOMEM; + + err = nfp_app_nic_vnic_alloc(app, nn, id); + if (err) + goto err_free_priv; + + return 0; +err_free_priv: + kfree(nn->app_priv); + return err; +} + static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn) { + struct nfp_bpf_vnic *bv = nn->app_priv; + if (nn->dp.bpf_offload_xdp) nfp_bpf_xdp_offload(app, nn, NULL); + WARN_ON(bv->tc_prog); + kfree(bv); } static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, @@ -93,6 +116,9 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, { struct tc_cls_bpf_offload *cls_bpf = type_data; struct nfp_net *nn = cb_priv; + struct bpf_prog *oldprog; + struct nfp_bpf_vnic *bv; + int err; if (type != TC_SETUP_CLSBPF || !tc_can_offload(nn->dp.netdev) || @@ -100,8 +126,6 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, cls_bpf->common.protocol != htons(ETH_P_ALL) || cls_bpf->common.chain_index) return -EOPNOTSUPP; - if (nn->dp.bpf_offload_xdp) - return -EBUSY; /* Only support TC direct action */ if (!cls_bpf->exts_integrated || @@ -110,16 +134,25 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type, return -EOPNOTSUPP; } - switch (cls_bpf->command) { - case TC_CLSBPF_REPLACE: - return nfp_net_bpf_offload(nn, cls_bpf->prog, true); - case TC_CLSBPF_ADD: - return nfp_net_bpf_offload(nn, cls_bpf->prog, false); - case TC_CLSBPF_DESTROY: - return nfp_net_bpf_offload(nn, NULL, true); - default: + if (cls_bpf->command != TC_CLSBPF_OFFLOAD) return -EOPNOTSUPP; + + bv = nn->app_priv; + oldprog = cls_bpf->oldprog; + + /* Don't remove if oldprog doesn't match driver's state */ + if (bv->tc_prog != oldprog) { + oldprog = NULL; + if (!cls_bpf->prog) + return 0; } + + err = nfp_net_bpf_offload(nn, cls_bpf->prog, oldprog); + if (err) + return err; + + bv->tc_prog = cls_bpf->prog; + return 0; } static int nfp_bpf_setup_tc_block(struct net_device *netdev, @@ -167,7 +200,7 @@ const struct nfp_app_type app_bpf = { .extra_cap = nfp_bpf_extra_cap, - .vnic_alloc = nfp_app_nic_vnic_alloc, + .vnic_alloc = nfp_bpf_vnic_alloc, .vnic_free = nfp_bpf_vnic_free, .setup_tc = nfp_bpf_setup_tc, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 082a15f6dfb5..57b6043177a3 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -172,6 +172,14 @@ struct nfp_prog { struct list_head insns; }; +/** + * struct nfp_bpf_vnic - per-vNIC BPF priv structure + * @tc_prog: currently loaded cls_bpf program + */ +struct nfp_bpf_vnic { + struct bpf_prog *tc_prog; +}; + int nfp_bpf_jit(struct nfp_prog *prog); extern const struct bpf_ext_analyzer_ops nfp_bpf_analyzer_ops; diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 70c92b649b29..38c924bdd32e 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -253,18 +253,18 @@ static int emac_open(struct net_device *netdev) return ret; } - ret = emac_mac_up(adpt); + ret = adpt->phy.open(adpt); if (ret) { emac_mac_rx_tx_rings_free_all(adpt); free_irq(irq->irq, irq); return ret; } - ret = adpt->phy.open(adpt); + ret = emac_mac_up(adpt); if (ret) { - emac_mac_down(adpt); emac_mac_rx_tx_rings_free_all(adpt); free_irq(irq->irq, irq); + adpt->phy.close(adpt); return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index e1e5ac053760..ce2ea2d491ac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -409,7 +409,7 @@ struct stmmac_desc_ops { /* get timestamp value */ u64(*get_timestamp) (void *desc, u32 ats); /* get rx timestamp status */ - int (*get_rx_timestamp_status) (void *desc, u32 ats); + int (*get_rx_timestamp_status)(void *desc, void *next_desc, u32 ats); /* Display ring */ void (*display_ring)(void *head, unsigned int size, bool rx); /* set MSS via context descriptor */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 4b286e27c4ca..7e089bf906b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -258,7 +258,8 @@ static int dwmac4_rx_check_timestamp(void *desc) return ret; } -static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) +static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc, + u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; int ret = -EINVAL; @@ -270,7 +271,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, u32 ats) /* Check if timestamp is OK from context descriptor */ do { - ret = dwmac4_rx_check_timestamp(desc); + ret = dwmac4_rx_check_timestamp(next_desc); if (ret < 0) goto exit; i++; diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 7546b3664113..2a828a312814 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -400,7 +400,8 @@ static u64 enh_desc_get_timestamp(void *desc, u32 ats) return ns; } -static int enh_desc_get_rx_timestamp_status(void *desc, u32 ats) +static int enh_desc_get_rx_timestamp_status(void *desc, void *next_desc, + u32 ats) { if (ats) { struct dma_extended_desc *p = (struct dma_extended_desc *)desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index f817f8f36569..db4cee57bb24 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -265,7 +265,7 @@ static u64 ndesc_get_timestamp(void *desc, u32 ats) return ns; } -static int ndesc_get_rx_timestamp_status(void *desc, u32 ats) +static int ndesc_get_rx_timestamp_status(void *desc, void *next_desc, u32 ats) { struct dma_desc *p = (struct dma_desc *)desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 721b61655261..08c19ebd5306 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -34,6 +34,7 @@ static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; + u32 reg_value; /* For GMAC3.x, 4.x versions, convert the ptp_clock to nano second * formula = (1/ptp_clock) * 1000000000 @@ -50,10 +51,11 @@ static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, data &= PTP_SSIR_SSINC_MASK; + reg_value = data; if (gmac4) - data = data << GMAC4_PTP_SSIR_SSINC_SHIFT; + reg_value <<= GMAC4_PTP_SSIR_SSINC_SHIFT; - writel(data, ioaddr + PTP_SSIR); + writel(reg_value, ioaddr + PTP_SSIR); return data; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d7250539d0bd..337d53d12e94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -482,7 +482,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, desc = np; /* Check if timestamp is available */ - if (priv->hw->desc->get_rx_timestamp_status(desc, priv->adv_ts)) { + if (priv->hw->desc->get_rx_timestamp_status(p, np, priv->adv_ts)) { ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index b5a8f750e433..82104edca393 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -879,6 +879,8 @@ static int m88e1510_config_init(struct phy_device *phydev) /* SGMII-to-Copper mode initialization */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + u32 pause; + /* Select page 18 */ err = marvell_set_page(phydev, 18); if (err < 0) @@ -902,6 +904,16 @@ static int m88e1510_config_init(struct phy_device *phydev) err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) return err; + + /* There appears to be a bug in the 88e1512 when used in + * SGMII to copper mode, where the AN advertisment register + * clears the pause bits each time a negotiation occurs. + * This means we can never be truely sure what was advertised, + * so disable Pause support. + */ + pause = SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->supported &= ~pause; + phydev->advertising &= ~pause; } return m88e1121_config_init(phydev); @@ -2073,7 +2085,7 @@ static struct phy_driver marvell_drivers[] = { .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, .config_init = &m88e1145_config_init, - .config_aneg = &marvell_config_aneg, + .config_aneg = &m88e1101_config_aneg, .read_status = &genphy_read_status, .ack_interrupt = &marvell_ack_interrupt, .config_intr = &marvell_config_intr, diff --git a/drivers/net/phy/mdio-xgene.c b/drivers/net/phy/mdio-xgene.c index bfd3090fb055..07c6048200c6 100644 --- a/drivers/net/phy/mdio-xgene.c +++ b/drivers/net/phy/mdio-xgene.c @@ -194,8 +194,11 @@ static int xgene_mdio_reset(struct xgene_mdio_pdata *pdata) } ret = xgene_enet_ecc_init(pdata); - if (ret) + if (ret) { + if (pdata->dev->of_node) + clk_disable_unprepare(pdata->clk); return ret; + } xgene_gmac_reset(pdata); return 0; @@ -388,8 +391,10 @@ static int xgene_mdio_probe(struct platform_device *pdev) return ret; mdio_bus = mdiobus_alloc(); - if (!mdio_bus) - return -ENOMEM; + if (!mdio_bus) { + ret = -ENOMEM; + goto out_clk; + } mdio_bus->name = "APM X-Gene MDIO bus"; @@ -418,7 +423,7 @@ static int xgene_mdio_probe(struct platform_device *pdev) mdio_bus->phy_mask = ~0; ret = mdiobus_register(mdio_bus); if (ret) - goto out; + goto out_mdiobus; acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_HANDLE(dev), 1, acpi_register_phy, NULL, mdio_bus, NULL); @@ -426,16 +431,20 @@ static int xgene_mdio_probe(struct platform_device *pdev) } if (ret) - goto out; + goto out_mdiobus; pdata->mdio_bus = mdio_bus; xgene_mdio_status = true; return 0; -out: +out_mdiobus: mdiobus_free(mdio_bus); +out_clk: + if (dev->of_node) + clk_disable_unprepare(pdata->clk); + return ret; } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index ab4614113403..422ff6333c52 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -624,6 +624,7 @@ static int ksz9031_read_status(struct phy_device *phydev) phydev->link = 0; if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev)) phydev->drv->config_intr(phydev); + return genphy_config_aneg(phydev); } return 0; diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 5dc9668dde34..827f3f92560e 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -526,6 +526,7 @@ struct phylink *phylink_create(struct net_device *ndev, struct device_node *np, pl->link_config.pause = MLO_PAUSE_AN; pl->link_config.speed = SPEED_UNKNOWN; pl->link_config.duplex = DUPLEX_UNKNOWN; + pl->link_config.an_enabled = true; pl->ops = ops; __set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); @@ -951,6 +952,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl, mutex_lock(&pl->state_mutex); /* Configure the MAC to match the new settings */ linkmode_copy(pl->link_config.advertising, our_kset.link_modes.advertising); + pl->link_config.interface = config.interface; pl->link_config.speed = our_kset.base.speed; pl->link_config.duplex = our_kset.base.duplex; pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 19b9cc51079e..31f4b7911ef8 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2155,6 +2155,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ndst = &rt->dst; + if (skb_dst(skb)) { + int mtu = dst_mtu(ndst) - VXLAN_HEADROOM; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, + skb, mtu); + } + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr), @@ -2190,6 +2197,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto out_unlock; } + if (skb_dst(skb)) { + int mtu = dst_mtu(ndst) - VXLAN6_HEADROOM; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, + skb, mtu); + } + tos = ip_tunnel_ecn_encap(tos, old_iph, skb); ttl = ttl ? : ip6_dst_hoplimit(ndst); skb_scrub_packet(skb, xnet); @@ -3103,6 +3117,11 @@ static void vxlan_config_apply(struct net_device *dev, max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); + if (max_mtu < ETH_MIN_MTU) + max_mtu = ETH_MIN_MTU; + + if (!changelink && !conf->mtu) + dev->mtu = max_mtu; } if (dev->mtu > max_mtu) diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 10b075a46b26..e8189c07b41f 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -684,6 +684,7 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, hdr = skb_put(skb, sizeof(*hdr) - ETH_ALEN); hdr->frame_control = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | + IEEE80211_FCTL_TODS | (ps ? IEEE80211_FCTL_PM : 0)); hdr->duration_id = cpu_to_le16(0); memcpy(hdr->addr1, vp->bssid, ETH_ALEN); @@ -3215,7 +3216,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) if (!net_eq(wiphy_net(data->hw->wiphy), genl_info_net(info))) continue; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) { res = -ENOMEM; goto out_err; diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index e949e3302af4..c586bcdb5190 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -211,12 +211,12 @@ static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping, return ret; } -static int btt_log_read_pair(struct arena_info *arena, u32 lane, - struct log_entry *ent) +static int btt_log_group_read(struct arena_info *arena, u32 lane, + struct log_group *log) { return arena_read_bytes(arena, - arena->logoff + (2 * lane * LOG_ENT_SIZE), ent, - 2 * LOG_ENT_SIZE, 0); + arena->logoff + (lane * LOG_GRP_SIZE), log, + LOG_GRP_SIZE, 0); } static struct dentry *debugfs_root; @@ -256,6 +256,8 @@ static void arena_debugfs_init(struct arena_info *a, struct dentry *parent, debugfs_create_x64("logoff", S_IRUGO, d, &a->logoff); debugfs_create_x64("info2off", S_IRUGO, d, &a->info2off); debugfs_create_x32("flags", S_IRUGO, d, &a->flags); + debugfs_create_u32("log_index_0", S_IRUGO, d, &a->log_index[0]); + debugfs_create_u32("log_index_1", S_IRUGO, d, &a->log_index[1]); } static void btt_debugfs_init(struct btt *btt) @@ -274,6 +276,11 @@ static void btt_debugfs_init(struct btt *btt) } } +static u32 log_seq(struct log_group *log, int log_idx) +{ + return le32_to_cpu(log->ent[log_idx].seq); +} + /* * This function accepts two log entries, and uses the * sequence number to find the 'older' entry. @@ -283,8 +290,10 @@ static void btt_debugfs_init(struct btt *btt) * * TODO The logic feels a bit kludge-y. make it better.. */ -static int btt_log_get_old(struct log_entry *ent) +static int btt_log_get_old(struct arena_info *a, struct log_group *log) { + int idx0 = a->log_index[0]; + int idx1 = a->log_index[1]; int old; /* @@ -292,23 +301,23 @@ static int btt_log_get_old(struct log_entry *ent) * the next time, the following logic works out to put this * (next) entry into [1] */ - if (ent[0].seq == 0) { - ent[0].seq = cpu_to_le32(1); + if (log_seq(log, idx0) == 0) { + log->ent[idx0].seq = cpu_to_le32(1); return 0; } - if (ent[0].seq == ent[1].seq) + if (log_seq(log, idx0) == log_seq(log, idx1)) return -EINVAL; - if (le32_to_cpu(ent[0].seq) + le32_to_cpu(ent[1].seq) > 5) + if (log_seq(log, idx0) + log_seq(log, idx1) > 5) return -EINVAL; - if (le32_to_cpu(ent[0].seq) < le32_to_cpu(ent[1].seq)) { - if (le32_to_cpu(ent[1].seq) - le32_to_cpu(ent[0].seq) == 1) + if (log_seq(log, idx0) < log_seq(log, idx1)) { + if ((log_seq(log, idx1) - log_seq(log, idx0)) == 1) old = 0; else old = 1; } else { - if (le32_to_cpu(ent[0].seq) - le32_to_cpu(ent[1].seq) == 1) + if ((log_seq(log, idx0) - log_seq(log, idx1)) == 1) old = 1; else old = 0; @@ -328,17 +337,18 @@ static int btt_log_read(struct arena_info *arena, u32 lane, { int ret; int old_ent, ret_ent; - struct log_entry log[2]; + struct log_group log; - ret = btt_log_read_pair(arena, lane, log); + ret = btt_log_group_read(arena, lane, &log); if (ret) return -EIO; - old_ent = btt_log_get_old(log); + old_ent = btt_log_get_old(arena, &log); if (old_ent < 0 || old_ent > 1) { dev_err(to_dev(arena), "log corruption (%d): lane %d seq [%d, %d]\n", - old_ent, lane, log[0].seq, log[1].seq); + old_ent, lane, log.ent[arena->log_index[0]].seq, + log.ent[arena->log_index[1]].seq); /* TODO set error state? */ return -EIO; } @@ -346,7 +356,7 @@ static int btt_log_read(struct arena_info *arena, u32 lane, ret_ent = (old_flag ? old_ent : (1 - old_ent)); if (ent != NULL) - memcpy(ent, &log[ret_ent], LOG_ENT_SIZE); + memcpy(ent, &log.ent[arena->log_index[ret_ent]], LOG_ENT_SIZE); return ret_ent; } @@ -360,17 +370,13 @@ static int __btt_log_write(struct arena_info *arena, u32 lane, u32 sub, struct log_entry *ent, unsigned long flags) { int ret; - /* - * Ignore the padding in log_entry for calculating log_half. - * The entry is 'committed' when we write the sequence number, - * and we want to ensure that that is the last thing written. - * We don't bother writing the padding as that would be extra - * media wear and write amplification - */ - unsigned int log_half = (LOG_ENT_SIZE - 2 * sizeof(u64)) / 2; - u64 ns_off = arena->logoff + (((2 * lane) + sub) * LOG_ENT_SIZE); + u32 group_slot = arena->log_index[sub]; + unsigned int log_half = LOG_ENT_SIZE / 2; void *src = ent; + u64 ns_off; + ns_off = arena->logoff + (lane * LOG_GRP_SIZE) + + (group_slot * LOG_ENT_SIZE); /* split the 16B write into atomic, durable halves */ ret = arena_write_bytes(arena, ns_off, src, log_half, flags); if (ret) @@ -453,7 +459,7 @@ static int btt_log_init(struct arena_info *arena) { size_t logsize = arena->info2off - arena->logoff; size_t chunk_size = SZ_4K, offset = 0; - struct log_entry log; + struct log_entry ent; void *zerobuf; int ret; u32 i; @@ -485,11 +491,11 @@ static int btt_log_init(struct arena_info *arena) } for (i = 0; i < arena->nfree; i++) { - log.lba = cpu_to_le32(i); - log.old_map = cpu_to_le32(arena->external_nlba + i); - log.new_map = cpu_to_le32(arena->external_nlba + i); - log.seq = cpu_to_le32(LOG_SEQ_INIT); - ret = __btt_log_write(arena, i, 0, &log, 0); + ent.lba = cpu_to_le32(i); + ent.old_map = cpu_to_le32(arena->external_nlba + i); + ent.new_map = cpu_to_le32(arena->external_nlba + i); + ent.seq = cpu_to_le32(LOG_SEQ_INIT); + ret = __btt_log_write(arena, i, 0, &ent, 0); if (ret) goto free; } @@ -594,6 +600,123 @@ static int btt_freelist_init(struct arena_info *arena) return 0; } +static bool ent_is_padding(struct log_entry *ent) +{ + return (ent->lba == 0) && (ent->old_map == 0) && (ent->new_map == 0) + && (ent->seq == 0); +} + +/* + * Detecting valid log indices: We read a log group (see the comments in btt.h + * for a description of a 'log_group' and its 'slots'), and iterate over its + * four slots. We expect that a padding slot will be all-zeroes, and use this + * to detect a padding slot vs. an actual entry. + * + * If a log_group is in the initial state, i.e. hasn't been used since the + * creation of this BTT layout, it will have three of the four slots with + * zeroes. We skip over these log_groups for the detection of log_index. If + * all log_groups are in the initial state (i.e. the BTT has never been + * written to), it is safe to assume the 'new format' of log entries in slots + * (0, 1). + */ +static int log_set_indices(struct arena_info *arena) +{ + bool idx_set = false, initial_state = true; + int ret, log_index[2] = {-1, -1}; + u32 i, j, next_idx = 0; + struct log_group log; + u32 pad_count = 0; + + for (i = 0; i < arena->nfree; i++) { + ret = btt_log_group_read(arena, i, &log); + if (ret < 0) + return ret; + + for (j = 0; j < 4; j++) { + if (!idx_set) { + if (ent_is_padding(&log.ent[j])) { + pad_count++; + continue; + } else { + /* Skip if index has been recorded */ + if ((next_idx == 1) && + (j == log_index[0])) + continue; + /* valid entry, record index */ + log_index[next_idx] = j; + next_idx++; + } + if (next_idx == 2) { + /* two valid entries found */ + idx_set = true; + } else if (next_idx > 2) { + /* too many valid indices */ + return -ENXIO; + } + } else { + /* + * once the indices have been set, just verify + * that all subsequent log groups are either in + * their initial state or follow the same + * indices. + */ + if (j == log_index[0]) { + /* entry must be 'valid' */ + if (ent_is_padding(&log.ent[j])) + return -ENXIO; + } else if (j == log_index[1]) { + ; + /* + * log_index[1] can be padding if the + * lane never got used and it is still + * in the initial state (three 'padding' + * entries) + */ + } else { + /* entry must be invalid (padding) */ + if (!ent_is_padding(&log.ent[j])) + return -ENXIO; + } + } + } + /* + * If any of the log_groups have more than one valid, + * non-padding entry, then the we are no longer in the + * initial_state + */ + if (pad_count < 3) + initial_state = false; + pad_count = 0; + } + + if (!initial_state && !idx_set) + return -ENXIO; + + /* + * If all the entries in the log were in the initial state, + * assume new padding scheme + */ + if (initial_state) + log_index[1] = 1; + + /* + * Only allow the known permutations of log/padding indices, + * i.e. (0, 1), and (0, 2) + */ + if ((log_index[0] == 0) && ((log_index[1] == 1) || (log_index[1] == 2))) + ; /* known index possibilities */ + else { + dev_err(to_dev(arena), "Found an unknown padding scheme\n"); + return -ENXIO; + } + + arena->log_index[0] = log_index[0]; + arena->log_index[1] = log_index[1]; + dev_dbg(to_dev(arena), "log_index_0 = %d\n", log_index[0]); + dev_dbg(to_dev(arena), "log_index_1 = %d\n", log_index[1]); + return 0; +} + static int btt_rtt_init(struct arena_info *arena) { arena->rtt = kcalloc(arena->nfree, sizeof(u32), GFP_KERNEL); @@ -650,8 +773,7 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size, available -= 2 * BTT_PG_SIZE; /* The log takes a fixed amount of space based on nfree */ - logsize = roundup(2 * arena->nfree * sizeof(struct log_entry), - BTT_PG_SIZE); + logsize = roundup(arena->nfree * LOG_GRP_SIZE, BTT_PG_SIZE); available -= logsize; /* Calculate optimal split between map and data area */ @@ -668,6 +790,10 @@ static struct arena_info *alloc_arena(struct btt *btt, size_t size, arena->mapoff = arena->dataoff + datasize; arena->logoff = arena->mapoff + mapsize; arena->info2off = arena->logoff + logsize; + + /* Default log indices are (0,1) */ + arena->log_index[0] = 0; + arena->log_index[1] = 1; return arena; } @@ -758,6 +884,13 @@ static int discover_arenas(struct btt *btt) arena->external_lba_start = cur_nlba; parse_arena_meta(arena, super, cur_off); + ret = log_set_indices(arena); + if (ret) { + dev_err(to_dev(arena), + "Unable to deduce log/padding indices\n"); + goto out; + } + mutex_init(&arena->err_lock); ret = btt_freelist_init(arena); if (ret) diff --git a/drivers/nvdimm/btt.h b/drivers/nvdimm/btt.h index 578c2057524d..db3cb6d4d0d4 100644 --- a/drivers/nvdimm/btt.h +++ b/drivers/nvdimm/btt.h @@ -27,6 +27,7 @@ #define MAP_ERR_MASK (1 << MAP_ERR_SHIFT) #define MAP_LBA_MASK (~((1 << MAP_TRIM_SHIFT) | (1 << MAP_ERR_SHIFT))) #define MAP_ENT_NORMAL 0xC0000000 +#define LOG_GRP_SIZE sizeof(struct log_group) #define LOG_ENT_SIZE sizeof(struct log_entry) #define ARENA_MIN_SIZE (1UL << 24) /* 16 MB */ #define ARENA_MAX_SIZE (1ULL << 39) /* 512 GB */ @@ -50,12 +51,52 @@ enum btt_init_state { INIT_READY }; +/* + * A log group represents one log 'lane', and consists of four log entries. + * Two of the four entries are valid entries, and the remaining two are + * padding. Due to an old bug in the padding location, we need to perform a + * test to determine the padding scheme being used, and use that scheme + * thereafter. + * + * In kernels prior to 4.15, 'log group' would have actual log entries at + * indices (0, 2) and padding at indices (1, 3), where as the correct/updated + * format has log entries at indices (0, 1) and padding at indices (2, 3). + * + * Old (pre 4.15) format: + * +-----------------+-----------------+ + * | ent[0] | ent[1] | + * | 16B | 16B | + * | lba/old/new/seq | pad | + * +-----------------------------------+ + * | ent[2] | ent[3] | + * | 16B | 16B | + * | lba/old/new/seq | pad | + * +-----------------+-----------------+ + * + * New format: + * +-----------------+-----------------+ + * | ent[0] | ent[1] | + * | 16B | 16B | + * | lba/old/new/seq | lba/old/new/seq | + * +-----------------------------------+ + * | ent[2] | ent[3] | + * | 16B | 16B | + * | pad | pad | + * +-----------------+-----------------+ + * + * We detect during start-up which format is in use, and set + * arena->log_index[(0, 1)] with the detected format. + */ + struct log_entry { __le32 lba; __le32 old_map; __le32 new_map; __le32 seq; - __le64 padding[2]; +}; + +struct log_group { + struct log_entry ent[4]; }; struct btt_sb { @@ -125,6 +166,8 @@ struct aligned_lock { * @list: List head for list of arenas * @debugfs_dir: Debugfs dentry * @flags: Arena flags - may signify error states. + * @err_lock: Mutex for synchronizing error clearing. + * @log_index: Indices of the valid log entries in a log_group * * arena_info is a per-arena handle. Once an arena is narrowed down for an * IO, this struct is passed around for the duration of the IO. @@ -157,6 +200,7 @@ struct arena_info { /* Arena flags */ u32 flags; struct mutex err_lock; + int log_index[2]; }; /** @@ -176,6 +220,7 @@ struct arena_info { * @init_lock: Mutex used for the BTT initialization * @init_state: Flag describing the initialization state for the BTT * @num_arenas: Number of arenas in the BTT instance + * @phys_bb: Pointer to the namespace's badblocks structure */ struct btt { struct gendisk *btt_disk; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 65cc171c721d..2adada1a5855 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -364,9 +364,9 @@ struct device *nd_pfn_create(struct nd_region *nd_region) int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) { u64 checksum, offset; - unsigned long align; enum nd_pfn_mode mode; struct nd_namespace_io *nsio; + unsigned long align, start_pad; struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; struct nd_namespace_common *ndns = nd_pfn->ndns; const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev); @@ -410,6 +410,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) align = le32_to_cpu(pfn_sb->align); offset = le64_to_cpu(pfn_sb->dataoff); + start_pad = le32_to_cpu(pfn_sb->start_pad); if (align == 0) align = 1UL << ilog2(offset); mode = le32_to_cpu(pfn_sb->mode); @@ -468,7 +469,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) return -EBUSY; } - if ((align && !IS_ALIGNED(offset, align)) + if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align)) || !IS_ALIGNED(offset, PAGE_SIZE)) { dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled align: %#lx\n", @@ -582,6 +583,12 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn, return altmap; } +static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys) +{ + return min_t(u64, PHYS_SECTION_ALIGN_DOWN(phys), + ALIGN_DOWN(phys, nd_pfn->align)); +} + static int nd_pfn_init(struct nd_pfn *nd_pfn) { u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0; @@ -637,13 +644,16 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) start = nsio->res.start; size = PHYS_SECTION_ALIGN_UP(start + size) - start; if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM, - IORES_DESC_NONE) == REGION_MIXED) { + IORES_DESC_NONE) == REGION_MIXED + || !IS_ALIGNED(start + resource_size(&nsio->res), + nd_pfn->align)) { size = resource_size(&nsio->res); - end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size); + end_trunc = start + size - phys_pmem_align_down(nd_pfn, + start + size); } if (start_pad + end_trunc) - dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n", + dev_info(&nd_pfn->dev, "%s alignment collision, truncate %d bytes\n", dev_name(&ndns->dev), start_pad + end_trunc); /* diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f837d666cbd4..1e46e60b8f10 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1287,7 +1287,7 @@ static void nvme_config_discard(struct nvme_ctrl *ctrl, BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) < NVME_DSM_MAX_RANGES); - queue->limits.discard_alignment = size; + queue->limits.discard_alignment = 0; queue->limits.discard_granularity = size; blk_queue_max_discard_sectors(queue, UINT_MAX); @@ -1705,7 +1705,8 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, blk_queue_max_hw_sectors(q, ctrl->max_hw_sectors); blk_queue_max_segments(q, min_t(u32, max_segments, USHRT_MAX)); } - if (ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) + if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) && + is_power_of_2(ctrl->max_hw_sectors)) blk_queue_chunk_sectors(q, ctrl->max_hw_sectors); blk_queue_virt_boundary(q, ctrl->page_size - 1); if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) @@ -2869,7 +2870,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift); nvme_set_queue_limits(ctrl, ns->queue); - nvme_setup_streams_ns(ctrl, ns); id = nvme_identify_ns(ctrl, nsid); if (!id) @@ -2880,6 +2880,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (nvme_init_ns_head(ns, nsid, id, &new)) goto out_free_id; + nvme_setup_streams_ns(ctrl, ns); #ifdef CONFIG_NVME_MULTIPATH /* @@ -2965,8 +2966,6 @@ static void nvme_ns_remove(struct nvme_ns *ns) return; if (ns->disk && ns->disk->flags & GENHD_FL_UP) { - if (blk_get_integrity(ns->disk)) - blk_integrity_unregister(ns->disk); nvme_mpath_remove_disk_links(ns); sysfs_remove_group(&disk_to_dev(ns->disk)->kobj, &nvme_ns_id_attr_group); @@ -2974,6 +2973,8 @@ static void nvme_ns_remove(struct nvme_ns *ns) nvme_nvm_unregister_sysfs(ns); del_gendisk(ns->disk); blk_cleanup_queue(ns->queue); + if (blk_get_integrity(ns->disk)) + blk_integrity_unregister(ns->disk); } mutex_lock(&ns->ctrl->subsys->lock); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 0a8af4daef89..794e66e4aa20 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3221,7 +3221,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, /* initiate nvme ctrl ref counting teardown */ nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); /* Remove core ctrl ref. */ nvme_put_ctrl(&ctrl->ctrl); diff --git a/drivers/nvmem/meson-mx-efuse.c b/drivers/nvmem/meson-mx-efuse.c index a346b4923550..41d3a3c1104e 100644 --- a/drivers/nvmem/meson-mx-efuse.c +++ b/drivers/nvmem/meson-mx-efuse.c @@ -156,8 +156,8 @@ static int meson_mx_efuse_read(void *context, unsigned int offset, MESON_MX_EFUSE_CNTL1_AUTO_RD_ENABLE, MESON_MX_EFUSE_CNTL1_AUTO_RD_ENABLE); - for (i = offset; i < offset + bytes; i += efuse->config.word_size) { - addr = i / efuse->config.word_size; + for (i = 0; i < bytes; i += efuse->config.word_size) { + addr = (offset + i) / efuse->config.word_size; err = meson_mx_efuse_read_addr(efuse, addr, &tmp); if (err) diff --git a/drivers/parisc/lba_pci.c b/drivers/parisc/lba_pci.c index a25fed52f7e9..41b740aed3a3 100644 --- a/drivers/parisc/lba_pci.c +++ b/drivers/parisc/lba_pci.c @@ -1692,3 +1692,36 @@ void lba_set_iregs(struct parisc_device *lba, u32 ibase, u32 imask) iounmap(base_addr); } + +/* + * The design of the Diva management card in rp34x0 machines (rp3410, rp3440) + * seems rushed, so that many built-in components simply don't work. + * The following quirks disable the serial AUX port and the built-in ATI RV100 + * Radeon 7000 graphics card which both don't have any external connectors and + * thus are useless, and even worse, e.g. the AUX port occupies ttyS0 and as + * such makes those machines the only PARISC machines on which we can't use + * ttyS0 as boot console. + */ +static void quirk_diva_ati_card(struct pci_dev *dev) +{ + if (dev->subsystem_vendor != PCI_VENDOR_ID_HP || + dev->subsystem_device != 0x1292) + return; + + dev_info(&dev->dev, "Hiding Diva built-in ATI card"); + dev->device = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_RADEON_QY, + quirk_diva_ati_card); + +static void quirk_diva_aux_disable(struct pci_dev *dev) +{ + if (dev->subsystem_vendor != PCI_VENDOR_ID_HP || + dev->subsystem_device != 0x1291) + return; + + dev_info(&dev->dev, "Hiding Diva built-in AUX serial device"); + dev->device = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HP, PCI_DEVICE_ID_HP_DIVA_AUX, + quirk_diva_aux_disable); diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c index 04dac6a42c9f..6b8d060d07de 100644 --- a/drivers/pci/host/pci-hyperv.c +++ b/drivers/pci/host/pci-hyperv.c @@ -985,9 +985,7 @@ static u32 hv_compose_msi_req_v1( int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.vector_count = 1; - int_pkt->int_desc.delivery_mode = - (apic->irq_delivery_mode == dest_LowestPrio) ? - dest_LowestPrio : dest_Fixed; + int_pkt->int_desc.delivery_mode = dest_Fixed; /* * Create MSI w/ dummy vCPU set, overwritten by subsequent retarget in @@ -1008,9 +1006,7 @@ static u32 hv_compose_msi_req_v2( int_pkt->wslot.slot = slot; int_pkt->int_desc.vector = vector; int_pkt->int_desc.vector_count = 1; - int_pkt->int_desc.delivery_mode = - (apic->irq_delivery_mode == dest_LowestPrio) ? - dest_LowestPrio : dest_Fixed; + int_pkt->int_desc.delivery_mode = dest_Fixed; /* * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 945099d49f8f..14fd865a5120 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -1012,7 +1012,12 @@ static int pci_pm_thaw_noirq(struct device *dev) if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_resume_early(dev); - pci_update_current_state(pci_dev, PCI_D0); + /* + * pci_restore_state() requires the device to be in D0 (because of MSI + * restoration among other things), so force it into D0 in case the + * driver's "freeze" callbacks put it into a low-power state directly. + */ + pci_set_power_state(pci_dev, PCI_D0); pci_restore_state(pci_dev); if (drv && drv->pm && drv->pm->thaw_noirq) diff --git a/drivers/phy/motorola/phy-cpcap-usb.c b/drivers/phy/motorola/phy-cpcap-usb.c index accaaaccb662..6601ad0dfb3a 100644 --- a/drivers/phy/motorola/phy-cpcap-usb.c +++ b/drivers/phy/motorola/phy-cpcap-usb.c @@ -310,7 +310,7 @@ static int cpcap_usb_init_irq(struct platform_device *pdev, int irq, error; irq = platform_get_irq_byname(pdev, name); - if (!irq) + if (irq < 0) return -ENODEV; error = devm_request_threaded_irq(ddata->dev, irq, NULL, diff --git a/drivers/phy/renesas/Kconfig b/drivers/phy/renesas/Kconfig index cb09245e9b4c..c845facacb06 100644 --- a/drivers/phy/renesas/Kconfig +++ b/drivers/phy/renesas/Kconfig @@ -12,7 +12,9 @@ config PHY_RCAR_GEN3_USB2 tristate "Renesas R-Car generation 3 USB 2.0 PHY driver" depends on ARCH_RENESAS depends on EXTCON + depends on USB_SUPPORT select GENERIC_PHY + select USB_COMMON help Support for USB 2.0 PHY found on Renesas R-Car generation 3 SoCs. diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c index ee85fa0ca4b0..7492c8978217 100644 --- a/drivers/phy/rockchip/phy-rockchip-typec.c +++ b/drivers/phy/rockchip/phy-rockchip-typec.c @@ -1137,6 +1137,7 @@ static int rockchip_typec_phy_probe(struct platform_device *pdev) if (IS_ERR(phy)) { dev_err(dev, "failed to create phy: %s\n", child_np->name); + pm_runtime_disable(dev); return PTR_ERR(phy); } @@ -1146,6 +1147,7 @@ static int rockchip_typec_phy_probe(struct platform_device *pdev) phy_provider = devm_of_phy_provider_register(dev, of_phy_simple_xlate); if (IS_ERR(phy_provider)) { dev_err(dev, "Failed to register phy provider\n"); + pm_runtime_disable(dev); return PTR_ERR(phy_provider); } diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 4307bf0013e1..63e916d4d069 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -75,14 +75,14 @@ MODULE_DEVICE_TABLE(of, tegra_xusb_padctl_of_match); static struct device_node * tegra_xusb_find_pad_node(struct tegra_xusb_padctl *padctl, const char *name) { - /* - * of_find_node_by_name() drops a reference, so make sure to grab one. - */ - struct device_node *np = of_node_get(padctl->dev->of_node); + struct device_node *pads, *np; + + pads = of_get_child_by_name(padctl->dev->of_node, "pads"); + if (!pads) + return NULL; - np = of_find_node_by_name(np, "pads"); - if (np) - np = of_find_node_by_name(np, name); + np = of_get_child_by_name(pads, name); + of_node_put(pads); return np; } @@ -90,16 +90,16 @@ tegra_xusb_find_pad_node(struct tegra_xusb_padctl *padctl, const char *name) static struct device_node * tegra_xusb_pad_find_phy_node(struct tegra_xusb_pad *pad, unsigned int index) { - /* - * of_find_node_by_name() drops a reference, so make sure to grab one. - */ - struct device_node *np = of_node_get(pad->dev.of_node); + struct device_node *np, *lanes; - np = of_find_node_by_name(np, "lanes"); - if (!np) + lanes = of_get_child_by_name(pad->dev.of_node, "lanes"); + if (!lanes) return NULL; - return of_find_node_by_name(np, pad->soc->lanes[index].name); + np = of_get_child_by_name(lanes, pad->soc->lanes[index].name); + of_node_put(lanes); + + return np; } static int @@ -195,7 +195,7 @@ int tegra_xusb_pad_register(struct tegra_xusb_pad *pad, unsigned int i; int err; - children = of_find_node_by_name(pad->dev.of_node, "lanes"); + children = of_get_child_by_name(pad->dev.of_node, "lanes"); if (!children) return -ENODEV; @@ -444,21 +444,21 @@ static struct device_node * tegra_xusb_find_port_node(struct tegra_xusb_padctl *padctl, const char *type, unsigned int index) { - /* - * of_find_node_by_name() drops a reference, so make sure to grab one. - */ - struct device_node *np = of_node_get(padctl->dev->of_node); + struct device_node *ports, *np; + char *name; - np = of_find_node_by_name(np, "ports"); - if (np) { - char *name; + ports = of_get_child_by_name(padctl->dev->of_node, "ports"); + if (!ports) + return NULL; - name = kasprintf(GFP_KERNEL, "%s-%u", type, index); - if (!name) - return ERR_PTR(-ENOMEM); - np = of_find_node_by_name(np, name); - kfree(name); + name = kasprintf(GFP_KERNEL, "%s-%u", type, index); + if (!name) { + of_node_put(ports); + return ERR_PTR(-ENOMEM); } + np = of_get_child_by_name(ports, name); + kfree(name); + of_node_put(ports); return np; } @@ -847,7 +847,7 @@ static void tegra_xusb_remove_ports(struct tegra_xusb_padctl *padctl) static int tegra_xusb_padctl_probe(struct platform_device *pdev) { - struct device_node *np = of_node_get(pdev->dev.of_node); + struct device_node *np = pdev->dev.of_node; const struct tegra_xusb_padctl_soc *soc; struct tegra_xusb_padctl *padctl; const struct of_device_id *match; @@ -855,7 +855,7 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev) int err; /* for backwards compatibility with old device trees */ - np = of_find_node_by_name(np, "pads"); + np = of_get_child_by_name(np, "pads"); if (!np) { dev_warn(&pdev->dev, "deprecated DT, using legacy driver\n"); return tegra_xusb_padctl_legacy_probe(pdev); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index bdedb6325c72..4471fd94e1fe 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1620,6 +1620,22 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) clear_bit(i, chip->irq.valid_mask); } + /* + * The same set of machines in chv_no_valid_mask[] have incorrectly + * configured GPIOs that generate spurious interrupts so we use + * this same list to apply another quirk for them. + * + * See also https://bugzilla.kernel.org/show_bug.cgi?id=197953. + */ + if (!need_valid_mask) { + /* + * Mask all interrupts the community is able to generate + * but leave the ones that can only generate GPEs unmasked. + */ + chv_writel(GENMASK(31, pctrl->community->nirqs), + pctrl->regs + CHV_INTMASK); + } + /* Clear all interrupts */ chv_writel(0xffff, pctrl->regs + CHV_INTSTAT); diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c index e6cd8de793e2..3501491e5bfc 100644 --- a/drivers/pinctrl/pinctrl-single.c +++ b/drivers/pinctrl/pinctrl-single.c @@ -222,6 +222,9 @@ static enum pin_config_param pcs_bias[] = { */ static struct lock_class_key pcs_lock_class; +/* Class for the IRQ request mutex */ +static struct lock_class_key pcs_request_class; + /* * REVISIT: Reads and writes could eventually use regmap or something * generic. But at least on omaps, some mux registers are performance @@ -1486,7 +1489,7 @@ static int pcs_irqdomain_map(struct irq_domain *d, unsigned int irq, irq_set_chip_data(irq, pcs_soc); irq_set_chip_and_handler(irq, &pcs->chip, handle_level_irq); - irq_set_lockdep_class(irq, &pcs_lock_class); + irq_set_lockdep_class(irq, &pcs_lock_class, &pcs_request_class); irq_set_noprobe(irq); return 0; diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index a276c61be217..e62ab087bfd8 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -290,7 +290,7 @@ static int stm32_gpio_domain_translate(struct irq_domain *d, } static int stm32_gpio_domain_activate(struct irq_domain *d, - struct irq_data *irq_data, bool early) + struct irq_data *irq_data, bool reserve) { struct stm32_gpio_bank *bank = d->host_data; struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 6c815207f4f5..3614df68830f 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5386,6 +5386,13 @@ out: } EXPORT_SYMBOL_GPL(qeth_poll); +static int qeth_setassparms_inspect_rc(struct qeth_ipa_cmd *cmd) +{ + if (!cmd->hdr.return_code) + cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code; + return cmd->hdr.return_code; +} + int qeth_setassparms_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { @@ -6242,7 +6249,7 @@ static int qeth_ipa_checksum_run_cmd_cb(struct qeth_card *card, (struct qeth_checksum_cmd *)reply->param; QETH_CARD_TEXT(card, 4, "chkdoccb"); - if (cmd->hdr.return_code) + if (qeth_setassparms_inspect_rc(cmd)) return 0; memset(chksum_cb, 0, sizeof(*chksum_cb)); diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 6e3d81969a77..d52265416da2 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1725,6 +1725,7 @@ struct aac_dev #define FIB_CONTEXT_FLAG_NATIVE_HBA (0x00000010) #define FIB_CONTEXT_FLAG_NATIVE_HBA_TMF (0x00000020) #define FIB_CONTEXT_FLAG_SCSI_CMD (0x00000040) +#define FIB_CONTEXT_FLAG_EH_RESET (0x00000080) /* * Define the command values diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index bdf127aaab41..d55332de08f9 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -1037,7 +1037,7 @@ static int aac_eh_bus_reset(struct scsi_cmnd* cmd) info = &aac->hba_map[bus][cid]; if (bus >= AAC_MAX_BUSES || cid >= AAC_MAX_TARGETS || info->devtype != AAC_DEVTYPE_NATIVE_RAW) { - fib->flags |= FIB_CONTEXT_FLAG_TIMED_OUT; + fib->flags |= FIB_CONTEXT_FLAG_EH_RESET; cmd->SCp.phase = AAC_OWNER_ERROR_HANDLER; } } diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index a4f28b7e4c65..e18877177f1b 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -1576,7 +1576,9 @@ static struct request *_make_request(struct request_queue *q, bool has_write, return req; for_each_bio(bio) { - ret = blk_rq_append_bio(req, bio); + struct bio *bounce_bio = bio; + + ret = blk_rq_append_bio(req, &bounce_bio); if (ret) return ERR_PTR(ret); } diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 449ef5adbb2b..dfb8da83fa50 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -374,10 +374,8 @@ int scsi_dev_info_list_add_keyed(int compatible, char *vendor, char *model, model, compatible); if (strflags) - devinfo->flags = simple_strtoul(strflags, NULL, 0); - else - devinfo->flags = flags; - + flags = (__force blist_flags_t)simple_strtoul(strflags, NULL, 0); + devinfo->flags = flags; devinfo->compatible = compatible; if (compatible) diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index be5e919db0e8..0880d975eed3 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -770,7 +770,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result, * SCSI_SCAN_LUN_PRESENT: a new scsi_device was allocated and initialized **/ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result, - int *bflags, int async) + blist_flags_t *bflags, int async) { int ret; @@ -1049,14 +1049,15 @@ static unsigned char *scsi_inq_str(unsigned char *buf, unsigned char *inq, * - SCSI_SCAN_LUN_PRESENT: a new scsi_device was allocated and initialized **/ static int scsi_probe_and_add_lun(struct scsi_target *starget, - u64 lun, int *bflagsp, + u64 lun, blist_flags_t *bflagsp, struct scsi_device **sdevp, enum scsi_scan_mode rescan, void *hostdata) { struct scsi_device *sdev; unsigned char *result; - int bflags, res = SCSI_SCAN_NO_RESPONSE, result_len = 256; + blist_flags_t bflags; + int res = SCSI_SCAN_NO_RESPONSE, result_len = 256; struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); /* @@ -1201,7 +1202,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * Modifies sdevscan->lun. **/ static void scsi_sequential_lun_scan(struct scsi_target *starget, - int bflags, int scsi_level, + blist_flags_t bflags, int scsi_level, enum scsi_scan_mode rescan) { uint max_dev_lun; @@ -1292,7 +1293,7 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget, * 0: scan completed (or no memory, so further scanning is futile) * 1: could not scan with REPORT LUN **/ -static int scsi_report_lun_scan(struct scsi_target *starget, int bflags, +static int scsi_report_lun_scan(struct scsi_target *starget, blist_flags_t bflags, enum scsi_scan_mode rescan) { unsigned char scsi_cmd[MAX_COMMAND_SIZE]; @@ -1538,7 +1539,7 @@ static void __scsi_scan_target(struct device *parent, unsigned int channel, unsigned int id, u64 lun, enum scsi_scan_mode rescan) { struct Scsi_Host *shost = dev_to_shost(parent); - int bflags = 0; + blist_flags_t bflags = 0; int res; struct scsi_target *starget; diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 50e7d7e4a861..26ce17178401 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -967,7 +967,8 @@ sdev_show_wwid(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(wwid, S_IRUGO, sdev_show_wwid, NULL); -#define BLIST_FLAG_NAME(name) [ilog2(BLIST_##name)] = #name +#define BLIST_FLAG_NAME(name) \ + [ilog2((__force unsigned int)BLIST_##name)] = #name static const char *const sdev_bflags_name[] = { #include "scsi_devinfo_tbl.c" }; @@ -984,7 +985,7 @@ sdev_show_blacklist(struct device *dev, struct device_attribute *attr, for (i = 0; i < sizeof(sdev->sdev_bflags) * BITS_PER_BYTE; i++) { const char *name = NULL; - if (!(sdev->sdev_bflags & BIT(i))) + if (!(sdev->sdev_bflags & (__force blist_flags_t)BIT(i))) continue; if (i < ARRAY_SIZE(sdev_bflags_name) && sdev_bflags_name[i]) name = sdev_bflags_name[i]; @@ -1414,7 +1415,10 @@ static void __scsi_remove_target(struct scsi_target *starget) * check. */ if (sdev->channel != starget->channel || - sdev->id != starget->id || + sdev->id != starget->id) + continue; + if (sdev->sdev_state == SDEV_DEL || + sdev->sdev_state == SDEV_CANCEL || !get_device(&sdev->sdev_gendev)) continue; spin_unlock_irqrestore(shost->host_lock, flags); diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c index d0219e36080c..10ebb213ddb3 100644 --- a/drivers/scsi/scsi_transport_spi.c +++ b/drivers/scsi/scsi_transport_spi.c @@ -50,14 +50,14 @@ /* Our blacklist flags */ enum { - SPI_BLIST_NOIUS = 0x1, + SPI_BLIST_NOIUS = (__force blist_flags_t)0x1, }; /* blacklist table, modelled on scsi_devinfo.c */ static struct { char *vendor; char *model; - unsigned flags; + blist_flags_t flags; } spi_static_device_list[] __initdata = { {"HP", "Ultrium 3-SCSI", SPI_BLIST_NOIUS }, {"IBM", "ULTRIUM-TD3", SPI_BLIST_NOIUS }, @@ -221,9 +221,11 @@ static int spi_device_configure(struct transport_container *tc, { struct scsi_device *sdev = to_scsi_device(dev); struct scsi_target *starget = sdev->sdev_target; - unsigned bflags = scsi_get_device_flags_keyed(sdev, &sdev->inquiry[8], - &sdev->inquiry[16], - SCSI_DEVINFO_SPI); + blist_flags_t bflags; + + bflags = scsi_get_device_flags_keyed(sdev, &sdev->inquiry[8], + &sdev->inquiry[16], + SCSI_DEVINFO_SPI); /* Populate the target capability fields with the values * gleaned from the device inquiry */ diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 1b06cf0375dc..3b3d1d050cac 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -953,10 +953,11 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, case TEST_UNIT_READY: break; default: - set_host_byte(scmnd, DID_TARGET_FAILURE); + set_host_byte(scmnd, DID_ERROR); } break; case SRB_STATUS_INVALID_LUN: + set_host_byte(scmnd, DID_NO_CONNECT); do_work = true; process_err_fn = storvsc_remove_lun; break; diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c index 77fe55ce790c..d65345312527 100644 --- a/drivers/spi/spi-armada-3700.c +++ b/drivers/spi/spi-armada-3700.c @@ -79,6 +79,7 @@ #define A3700_SPI_BYTE_LEN BIT(5) #define A3700_SPI_CLK_PRESCALE BIT(0) #define A3700_SPI_CLK_PRESCALE_MASK (0x1f) +#define A3700_SPI_CLK_EVEN_OFFS (0x10) #define A3700_SPI_WFIFO_THRS_BIT 28 #define A3700_SPI_RFIFO_THRS_BIT 24 @@ -220,6 +221,13 @@ static void a3700_spi_clock_set(struct a3700_spi *a3700_spi, prescale = DIV_ROUND_UP(clk_get_rate(a3700_spi->clk), speed_hz); + /* For prescaler values over 15, we can only set it by steps of 2. + * Starting from A3700_SPI_CLK_EVEN_OFFS, we set values from 0 up to + * 30. We only use this range from 16 to 30. + */ + if (prescale > 15) + prescale = A3700_SPI_CLK_EVEN_OFFS + DIV_ROUND_UP(prescale, 2); + val = spireg_read(a3700_spi, A3700_SPI_IF_CFG_REG); val = val & ~A3700_SPI_CLK_PRESCALE_MASK; diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c index f95da364c283..669470971023 100644 --- a/drivers/spi/spi-atmel.c +++ b/drivers/spi/spi-atmel.c @@ -1661,12 +1661,12 @@ static int atmel_spi_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); /* reset the hardware and block queue progress */ - spin_lock_irq(&as->lock); if (as->use_dma) { atmel_spi_stop_dma(master); atmel_spi_release_dma(master); } + spin_lock_irq(&as->lock); spi_writel(as, CR, SPI_BIT(SWRST)); spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */ spi_readl(as, SR); diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c index 2ce875764ca6..0835a8d88fb8 100644 --- a/drivers/spi/spi-rspi.c +++ b/drivers/spi/spi-rspi.c @@ -377,8 +377,8 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size) /* Sets SPCMD */ rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0); - /* Enables SPI function in master mode */ - rspi_write8(rspi, SPCR_SPE | SPCR_MSTR, RSPI_SPCR); + /* Sets RSPI mode */ + rspi_write8(rspi, SPCR_MSTR, RSPI_SPCR); return 0; } diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c index c5cd635c28f3..41410031f8e9 100644 --- a/drivers/spi/spi-sun4i.c +++ b/drivers/spi/spi-sun4i.c @@ -525,7 +525,7 @@ err_free_master: static int sun4i_spi_remove(struct platform_device *pdev) { - pm_runtime_disable(&pdev->dev); + pm_runtime_force_suspend(&pdev->dev); return 0; } diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c index bc7100b93dfc..e0b9fe1d0e37 100644 --- a/drivers/spi/spi-xilinx.c +++ b/drivers/spi/spi-xilinx.c @@ -271,6 +271,7 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) while (remaining_words) { int n_words, tx_words, rx_words; u32 sr; + int stalled; n_words = min(remaining_words, xspi->buffer_size); @@ -299,7 +300,17 @@ static int xilinx_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t) /* Read out all the data from the Rx FIFO */ rx_words = n_words; + stalled = 10; while (rx_words) { + if (rx_words == n_words && !(stalled--) && + !(sr & XSPI_SR_TX_EMPTY_MASK) && + (sr & XSPI_SR_RX_EMPTY_MASK)) { + dev_err(&spi->dev, + "Detected stall. Check C_SPI_MODE and C_SPI_MEMORY\n"); + xspi_init_hw(xspi); + return -EIO; + } + if ((sr & XSPI_SR_TX_EMPTY_MASK) && (rx_words > 1)) { xilinx_spi_rx(xspi); rx_words--; diff --git a/drivers/staging/android/ion/Kconfig b/drivers/staging/android/ion/Kconfig index a517b2d29f1b..8f6494158d3d 100644 --- a/drivers/staging/android/ion/Kconfig +++ b/drivers/staging/android/ion/Kconfig @@ -37,7 +37,7 @@ config ION_CHUNK_HEAP config ION_CMA_HEAP bool "Ion CMA heap support" - depends on ION && CMA + depends on ION && DMA_CMA help Choose this option to enable CMA heaps with Ion. This heap is backed by the Contiguous Memory Allocator (CMA). If your system has these diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c index a7d9b0e98572..f480885e346b 100644 --- a/drivers/staging/android/ion/ion.c +++ b/drivers/staging/android/ion/ion.c @@ -346,7 +346,7 @@ static int ion_dma_buf_begin_cpu_access(struct dma_buf *dmabuf, mutex_lock(&buffer->lock); list_for_each_entry(a, &buffer->attachments, list) { dma_sync_sg_for_cpu(a->dev, a->table->sgl, a->table->nents, - DMA_BIDIRECTIONAL); + direction); } mutex_unlock(&buffer->lock); @@ -368,7 +368,7 @@ static int ion_dma_buf_end_cpu_access(struct dma_buf *dmabuf, mutex_lock(&buffer->lock); list_for_each_entry(a, &buffer->attachments, list) { dma_sync_sg_for_device(a->dev, a->table->sgl, a->table->nents, - DMA_BIDIRECTIONAL); + direction); } mutex_unlock(&buffer->lock); diff --git a/drivers/staging/android/ion/ion_cma_heap.c b/drivers/staging/android/ion/ion_cma_heap.c index dd5545d9990a..86196ffd2faf 100644 --- a/drivers/staging/android/ion/ion_cma_heap.c +++ b/drivers/staging/android/ion/ion_cma_heap.c @@ -39,9 +39,15 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer, struct ion_cma_heap *cma_heap = to_cma_heap(heap); struct sg_table *table; struct page *pages; + unsigned long size = PAGE_ALIGN(len); + unsigned long nr_pages = size >> PAGE_SHIFT; + unsigned long align = get_order(size); int ret; - pages = cma_alloc(cma_heap->cma, len, 0, GFP_KERNEL); + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pages = cma_alloc(cma_heap->cma, nr_pages, align, GFP_KERNEL); if (!pages) return -ENOMEM; @@ -53,7 +59,7 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer, if (ret) goto free_mem; - sg_set_page(table->sgl, pages, len, 0); + sg_set_page(table->sgl, pages, size, 0); buffer->priv_virt = pages; buffer->sg_table = table; @@ -62,7 +68,7 @@ static int ion_cma_allocate(struct ion_heap *heap, struct ion_buffer *buffer, free_mem: kfree(table); err: - cma_release(cma_heap->cma, pages, buffer->size); + cma_release(cma_heap->cma, pages, nr_pages); return -ENOMEM; } @@ -70,9 +76,10 @@ static void ion_cma_free(struct ion_buffer *buffer) { struct ion_cma_heap *cma_heap = to_cma_heap(buffer->heap); struct page *pages = buffer->priv_virt; + unsigned long nr_pages = PAGE_ALIGN(buffer->size) >> PAGE_SHIFT; /* release memory */ - cma_release(cma_heap->cma, pages, buffer->size); + cma_release(cma_heap->cma, pages, nr_pages); /* release sg table */ sg_free_table(buffer->sg_table); kfree(buffer->sg_table); diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.c b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.c index 986c2a40d978..8267119ccc8e 100644 --- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.c +++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.c @@ -487,21 +487,18 @@ ksocknal_add_peer(struct lnet_ni *ni, struct lnet_process_id id, __u32 ipaddr, ksocknal_nid2peerlist(id.nid)); } - route2 = NULL; list_for_each_entry(route2, &peer->ksnp_routes, ksnr_list) { - if (route2->ksnr_ipaddr == ipaddr) - break; - - route2 = NULL; - } - if (!route2) { - ksocknal_add_route_locked(peer, route); - route->ksnr_share_count++; - } else { - ksocknal_route_decref(route); - route2->ksnr_share_count++; + if (route2->ksnr_ipaddr == ipaddr) { + /* Route already exists, use the old one */ + ksocknal_route_decref(route); + route2->ksnr_share_count++; + goto out; + } } - + /* Route doesn't already exist, add the new one */ + ksocknal_add_route_locked(peer, route); + route->ksnr_share_count++; +out: write_unlock_bh(&ksocknal_data.ksnd_global_lock); return 0; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 7c69b4a9694d..0d99b242e82e 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -920,7 +920,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, " %d i: %d bio: %p, allocating another" " bio\n", bio->bi_vcnt, i, bio); - rc = blk_rq_append_bio(req, bio); + rc = blk_rq_append_bio(req, &bio); if (rc) { pr_err("pSCSI: failed to append bio\n"); goto fail; @@ -938,7 +938,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, } if (bio) { - rc = blk_rq_append_bio(req, bio); + rc = blk_rq_append_bio(req, &bio); if (rc) { pr_err("pSCSI: failed to append bio\n"); goto fail; diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 419a7a90bce0..f45bcbc63738 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -339,7 +339,7 @@ static void __ring_interrupt(struct tb_ring *ring) return; if (ring->start_poll) { - __ring_interrupt_mask(ring, false); + __ring_interrupt_mask(ring, true); ring->start_poll(ring->poll_data); } else { schedule_work(&ring->work); diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 427e0d5d8f13..539b49adb6af 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -1762,7 +1762,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old) { struct n_tty_data *ldata = tty->disc_data; - if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) { + if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) { bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE); ldata->line_start = ldata->read_tail; if (!L_ICANON(tty) || !read_cnt(ldata)) { @@ -2425,7 +2425,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file, return put_user(tty_chars_in_buffer(tty), (int __user *) arg); case TIOCINQ: down_write(&tty->termios_rwsem); - if (L_ICANON(tty)) + if (L_ICANON(tty) && !L_EXTPROC(tty)) retval = inq_canon(ldata); else retval = read_cnt(ldata); diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index 3593ce0ec641..880009987460 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -247,7 +247,7 @@ static int ci_hdrc_msm_probe(struct platform_device *pdev) if (ret) goto err_mux; - ulpi_node = of_find_node_by_name(of_node_get(pdev->dev.of_node), "ulpi"); + ulpi_node = of_get_child_by_name(pdev->dev.of_node, "ulpi"); if (ulpi_node) { phy_node = of_get_next_available_child(ulpi_node, NULL); ci->hsic = of_device_is_compatible(phy_node, "qcom,usb-hsic-phy"); diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 78e92d29f8d9..c821b4b9647e 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -1007,7 +1007,7 @@ int usb_get_bos_descriptor(struct usb_device *dev) case USB_SSP_CAP_TYPE: ssp_cap = (struct usb_ssp_cap_descriptor *)buffer; ssac = (le32_to_cpu(ssp_cap->bmAttributes) & - USB_SSP_SUBLINK_SPEED_ATTRIBS) + 1; + USB_SSP_SUBLINK_SPEED_ATTRIBS); if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac)) dev->bos->ssp_cap = ssp_cap; break; diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index a10b346b9777..4024926c1d68 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -52,10 +52,11 @@ static const struct usb_device_id usb_quirk_list[] = { /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME }, - /* Logitech HD Pro Webcams C920, C920-C and C930e */ + /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */ { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT }, + { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT }, /* Logitech ConferenceCam CC3000e */ { USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT }, @@ -149,6 +150,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */ { USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM }, + /* ELSA MicroLink 56K */ + { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */ { USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM }, diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c index 4f7895dbcf88..e26e685d8a57 100644 --- a/drivers/usb/host/xhci-debugfs.c +++ b/drivers/usb/host/xhci-debugfs.c @@ -162,7 +162,7 @@ static void xhci_debugfs_extcap_regset(struct xhci_hcd *xhci, int cap_id, static int xhci_ring_enqueue_show(struct seq_file *s, void *unused) { dma_addr_t dma; - struct xhci_ring *ring = s->private; + struct xhci_ring *ring = *(struct xhci_ring **)s->private; dma = xhci_trb_virt_to_dma(ring->enq_seg, ring->enqueue); seq_printf(s, "%pad\n", &dma); @@ -173,7 +173,7 @@ static int xhci_ring_enqueue_show(struct seq_file *s, void *unused) static int xhci_ring_dequeue_show(struct seq_file *s, void *unused) { dma_addr_t dma; - struct xhci_ring *ring = s->private; + struct xhci_ring *ring = *(struct xhci_ring **)s->private; dma = xhci_trb_virt_to_dma(ring->deq_seg, ring->dequeue); seq_printf(s, "%pad\n", &dma); @@ -183,7 +183,7 @@ static int xhci_ring_dequeue_show(struct seq_file *s, void *unused) static int xhci_ring_cycle_show(struct seq_file *s, void *unused) { - struct xhci_ring *ring = s->private; + struct xhci_ring *ring = *(struct xhci_ring **)s->private; seq_printf(s, "%d\n", ring->cycle_state); @@ -346,7 +346,7 @@ static void xhci_debugfs_create_files(struct xhci_hcd *xhci, } static struct dentry *xhci_debugfs_create_ring_dir(struct xhci_hcd *xhci, - struct xhci_ring *ring, + struct xhci_ring **ring, const char *name, struct dentry *parent) { @@ -387,7 +387,7 @@ void xhci_debugfs_create_endpoint(struct xhci_hcd *xhci, snprintf(epriv->name, sizeof(epriv->name), "ep%02d", ep_index); epriv->root = xhci_debugfs_create_ring_dir(xhci, - dev->eps[ep_index].new_ring, + &dev->eps[ep_index].new_ring, epriv->name, spriv->root); spriv->eps[ep_index] = epriv; @@ -423,7 +423,7 @@ void xhci_debugfs_create_slot(struct xhci_hcd *xhci, int slot_id) priv->dev = dev; dev->debugfs_private = priv; - xhci_debugfs_create_ring_dir(xhci, dev->eps[0].ring, + xhci_debugfs_create_ring_dir(xhci, &dev->eps[0].ring, "ep00", priv->root); xhci_debugfs_create_context_files(xhci, priv->root, slot_id); @@ -488,11 +488,11 @@ void xhci_debugfs_init(struct xhci_hcd *xhci) ARRAY_SIZE(xhci_extcap_dbc), "reg-ext-dbc"); - xhci_debugfs_create_ring_dir(xhci, xhci->cmd_ring, + xhci_debugfs_create_ring_dir(xhci, &xhci->cmd_ring, "command-ring", xhci->debugfs_root); - xhci_debugfs_create_ring_dir(xhci, xhci->event_ring, + xhci_debugfs_create_ring_dir(xhci, &xhci->event_ring, "event-ring", xhci->debugfs_root); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 4bcddd424a07..6c79037876db 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -178,6 +178,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_BROKEN_STREAMS; } if (pdev->vendor == PCI_VENDOR_ID_RENESAS && + pdev->device == 0x0014) + xhci->quirks |= XHCI_TRUST_TX_LENGTH; + if (pdev->vendor == PCI_VENDOR_ID_RENESAS && pdev->device == 0x0015) xhci->quirks |= XHCI_RESET_ON_RESUME; if (pdev->vendor == PCI_VENDOR_ID_VIA) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 05104bd2b611..1eeb3396300f 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3518,8 +3518,6 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) struct xhci_slot_ctx *slot_ctx; int i, ret; - xhci_debugfs_remove_slot(xhci, udev->slot_id); - #ifndef CONFIG_USB_DEFAULT_PERSIST /* * We called pm_runtime_get_noresume when the device was attached. @@ -3548,8 +3546,10 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) } ret = xhci_disable_slot(xhci, udev->slot_id); - if (ret) + if (ret) { + xhci_debugfs_remove_slot(xhci, udev->slot_id); xhci_free_virt_device(xhci, udev->slot_id); + } } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 1aba9105b369..fc68952c994a 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -1013,6 +1013,7 @@ static const struct usb_device_id id_table_combined[] = { .driver_info = (kernel_ulong_t)&ftdi_jtag_quirk }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) }, { USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) }, + { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index 4faa09fe308c..8b4ecd2bd297 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -915,6 +915,12 @@ #define ICPDAS_I7563U_PID 0x0105 /* + * Airbus Defence and Space + */ +#define AIRBUS_DS_VID 0x1e8e /* Vendor ID */ +#define AIRBUS_DS_P8GR 0x6001 /* Tetra P8GR */ + +/* * RT Systems programming cables for various ham radios */ #define RTSYSTEMS_VID 0x2100 /* Vendor ID */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 3b3513874cfd..b6320e3be429 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -233,6 +233,8 @@ static void option_instat_callback(struct urb *urb); /* These Quectel products use Qualcomm's vendor ID */ #define QUECTEL_PRODUCT_UC20 0x9003 #define QUECTEL_PRODUCT_UC15 0x9090 +/* These Yuga products use Qualcomm's vendor ID */ +#define YUGA_PRODUCT_CLM920_NC5 0x9625 #define QUECTEL_VENDOR_ID 0x2c7c /* These Quectel products use Quectel's vendor ID */ @@ -280,6 +282,7 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_LE922_USBCFG3 0x1043 #define TELIT_PRODUCT_LE922_USBCFG5 0x1045 #define TELIT_PRODUCT_ME910 0x1100 +#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101 #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 #define TELIT_PRODUCT_LE910_USBCFG4 0x1206 @@ -645,6 +648,11 @@ static const struct option_blacklist_info telit_me910_blacklist = { .reserved = BIT(1) | BIT(3), }; +static const struct option_blacklist_info telit_me910_dual_modem_blacklist = { + .sendsetup = BIT(0), + .reserved = BIT(3), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -674,6 +682,10 @@ static const struct option_blacklist_info cinterion_rmnet2_blacklist = { .reserved = BIT(4) | BIT(5), }; +static const struct option_blacklist_info yuga_clm920_nc5_blacklist = { + .reserved = BIT(1) | BIT(4), +}; + static const struct usb_device_id option_ids[] = { { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) }, { USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) }, @@ -1178,6 +1190,9 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)}, { USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, + /* Yuga products use Qualcomm vendor ID */ + { USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5), + .driver_info = (kernel_ulong_t)&yuga_clm920_nc5_blacklist }, /* Quectel products using Quectel vendor ID */ { USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21), .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, @@ -1244,6 +1259,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = (kernel_ulong_t)&telit_me910_blacklist }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), + .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910), .driver_info = (kernel_ulong_t)&telit_le910_blacklist }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4), diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index e3892541a489..613f91add03d 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -162,6 +162,8 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */ {DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */ {DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */ + {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */ + {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */ {DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */ {DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */ @@ -342,6 +344,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id) break; case 2: dev_dbg(dev, "NMEA GPS interface found\n"); + sendsetup = true; break; case 3: dev_dbg(dev, "Modem port found\n"); diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index a3df8ee82faf..e31a6f204397 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -149,8 +149,7 @@ static void stub_shutdown_connection(struct usbip_device *ud) * step 1? */ if (ud->tcp_socket) { - dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n", - ud->tcp_socket); + dev_dbg(&sdev->udev->dev, "shutdown sockfd %d\n", ud->sockfd); kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR); } diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c index 4f48b306713f..c31c8402a0c5 100644 --- a/drivers/usb/usbip/stub_main.c +++ b/drivers/usb/usbip/stub_main.c @@ -237,11 +237,12 @@ void stub_device_cleanup_urbs(struct stub_device *sdev) struct stub_priv *priv; struct urb *urb; - dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev); + dev_dbg(&sdev->udev->dev, "Stub device cleaning up urbs\n"); while ((priv = stub_priv_pop(sdev))) { urb = priv->urb; - dev_dbg(&sdev->udev->dev, "free urb %p\n", urb); + dev_dbg(&sdev->udev->dev, "free urb seqnum %lu\n", + priv->seqnum); usb_kill_urb(urb); kmem_cache_free(stub_priv_cache, priv); diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c index 894cf916db31..97b09a42a10c 100644 --- a/drivers/usb/usbip/stub_rx.c +++ b/drivers/usb/usbip/stub_rx.c @@ -211,9 +211,6 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev, if (priv->seqnum != pdu->u.cmd_unlink.seqnum) continue; - dev_info(&priv->urb->dev->dev, "unlink urb %p\n", - priv->urb); - /* * This matched urb is not completed yet (i.e., be in * flight in usb hcd hardware/driver). Now we are @@ -252,8 +249,8 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev, ret = usb_unlink_urb(priv->urb); if (ret != -EINPROGRESS) dev_err(&priv->urb->dev->dev, - "failed to unlink a urb %p, ret %d\n", - priv->urb, ret); + "failed to unlink a urb # %lu, ret %d\n", + priv->seqnum, ret); return 0; } @@ -342,14 +339,6 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu) epd = &ep->desc; - /* validate transfer_buffer_length */ - if (pdu->u.cmd_submit.transfer_buffer_length > INT_MAX) { - dev_err(&sdev->udev->dev, - "CMD_SUBMIT: -EMSGSIZE transfer_buffer_length %d\n", - pdu->u.cmd_submit.transfer_buffer_length); - return -1; - } - if (usb_endpoint_xfer_control(epd)) { if (dir == USBIP_DIR_OUT) return usb_sndctrlpipe(udev, epnum); @@ -479,8 +468,7 @@ static void stub_recv_cmd_submit(struct stub_device *sdev, } /* allocate urb transfer buffer, if needed */ - if (pdu->u.cmd_submit.transfer_buffer_length > 0 && - pdu->u.cmd_submit.transfer_buffer_length <= INT_MAX) { + if (pdu->u.cmd_submit.transfer_buffer_length > 0) { priv->urb->transfer_buffer = kzalloc(pdu->u.cmd_submit.transfer_buffer_length, GFP_KERNEL); diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c index 53172b1f6257..f0ec41a50cbc 100644 --- a/drivers/usb/usbip/stub_tx.c +++ b/drivers/usb/usbip/stub_tx.c @@ -88,7 +88,7 @@ void stub_complete(struct urb *urb) /* link a urb to the queue of tx. */ spin_lock_irqsave(&sdev->priv_lock, flags); if (sdev->ud.tcp_socket == NULL) { - usbip_dbg_stub_tx("ignore urb for closed connection %p", urb); + usbip_dbg_stub_tx("ignore urb for closed connection\n"); /* It will be freed in stub_device_cleanup_urbs(). */ } else if (priv->unlinking) { stub_enqueue_ret_unlink(sdev, priv->seqnum, urb->status); @@ -190,8 +190,8 @@ static int stub_send_ret_submit(struct stub_device *sdev) /* 1. setup usbip_header */ setup_ret_submit_pdu(&pdu_header, urb); - usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n", - pdu_header.base.seqnum, urb); + usbip_dbg_stub_tx("setup txdata seqnum: %d\n", + pdu_header.base.seqnum); usbip_header_correct_endian(&pdu_header, 1); iov[iovnum].iov_base = &pdu_header; diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index f7978933b402..7b219d9109b4 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -317,26 +317,20 @@ int usbip_recv(struct socket *sock, void *buf, int size) struct msghdr msg = {.msg_flags = MSG_NOSIGNAL}; int total = 0; + if (!sock || !buf || !size) + return -EINVAL; + iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size); usbip_dbg_xmit("enter\n"); - if (!sock || !buf || !size) { - pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf, - size); - return -EINVAL; - } - do { - int sz = msg_data_left(&msg); + msg_data_left(&msg); sock->sk->sk_allocation = GFP_NOIO; result = sock_recvmsg(sock, &msg, MSG_WAITALL); - if (result <= 0) { - pr_debug("receive sock %p buf %p size %u ret %d total %d\n", - sock, buf + total, sz, result, total); + if (result <= 0) goto err; - } total += result; } while (msg_data_left(&msg)); diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 6b3278c4b72a..c3e1008aa491 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -656,9 +656,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag struct vhci_device *vdev; unsigned long flags; - usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n", - hcd, urb, mem_flags); - if (portnum > VHCI_HC_PORTS) { pr_err("invalid port number %d\n", portnum); return -ENODEV; @@ -822,8 +819,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) struct vhci_device *vdev; unsigned long flags; - pr_info("dequeue a urb %p\n", urb); - spin_lock_irqsave(&vhci->lock, flags); priv = urb->hcpriv; @@ -851,7 +846,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) /* tcp connection is closed */ spin_lock(&vdev->priv_lock); - pr_info("device %p seems to be disconnected\n", vdev); list_del(&priv->list); kfree(priv); urb->hcpriv = NULL; @@ -863,8 +857,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) * vhci_rx will receive RET_UNLINK and give back the URB. * Otherwise, we give back it here. */ - pr_info("gives back urb %p\n", urb); - usb_hcd_unlink_urb_from_ep(hcd, urb); spin_unlock_irqrestore(&vhci->lock, flags); @@ -892,8 +884,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) unlink->unlink_seqnum = priv->seqnum; - pr_info("device %p seems to be still connected\n", vdev); - /* send cmd_unlink and try to cancel the pending URB in the * peer */ list_add_tail(&unlink->list, &vdev->unlink_tx); @@ -975,7 +965,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud) /* need this? see stub_dev.c */ if (ud->tcp_socket) { - pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket); + pr_debug("shutdown tcp_socket %d\n", ud->sockfd); kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR); } diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c index a9813f1d507d..112ebb90d8c9 100644 --- a/drivers/usb/usbip/vhci_rx.c +++ b/drivers/usb/usbip/vhci_rx.c @@ -23,24 +23,23 @@ struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum) urb = priv->urb; status = urb->status; - usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n", - urb, priv, seqnum); + usbip_dbg_vhci_rx("find urb seqnum %u\n", seqnum); switch (status) { case -ENOENT: /* fall through */ case -ECONNRESET: - dev_info(&urb->dev->dev, - "urb %p was unlinked %ssynchronously.\n", urb, - status == -ENOENT ? "" : "a"); + dev_dbg(&urb->dev->dev, + "urb seq# %u was unlinked %ssynchronuously\n", + seqnum, status == -ENOENT ? "" : "a"); break; case -EINPROGRESS: /* no info output */ break; default: - dev_info(&urb->dev->dev, - "urb %p may be in a error, status %d\n", urb, - status); + dev_dbg(&urb->dev->dev, + "urb seq# %u may be in a error, status %d\n", + seqnum, status); } list_del(&priv->list); @@ -67,8 +66,8 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, spin_unlock_irqrestore(&vdev->priv_lock, flags); if (!urb) { - pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum); - pr_info("max seqnum %d\n", + pr_err("cannot find a urb of seqnum %u max seqnum %d\n", + pdu->base.seqnum, atomic_read(&vhci_hcd->seqnum)); usbip_event_add(ud, VDEV_EVENT_ERROR_TCP); return; @@ -91,7 +90,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev, if (usbip_dbg_flag_vhci_rx) usbip_dump_urb(urb); - usbip_dbg_vhci_rx("now giveback urb %p\n", urb); + usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum); spin_lock_irqsave(&vhci->lock, flags); usb_hcd_unlink_urb_from_ep(vhci_hcd_to_hcd(vhci_hcd), urb); @@ -158,7 +157,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev, pr_info("the urb (seqnum %d) was already given back\n", pdu->base.seqnum); } else { - usbip_dbg_vhci_rx("now giveback urb %p\n", urb); + usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum); /* If unlink is successful, status is -ECONNRESET */ urb->status = pdu->u.ret_unlink.status; diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c index d625a2ff4b71..9aed15a358b7 100644 --- a/drivers/usb/usbip/vhci_tx.c +++ b/drivers/usb/usbip/vhci_tx.c @@ -69,7 +69,8 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev) memset(&msg, 0, sizeof(msg)); memset(&iov, 0, sizeof(iov)); - usbip_dbg_vhci_tx("setup txdata urb %p\n", urb); + usbip_dbg_vhci_tx("setup txdata urb seqnum %lu\n", + priv->seqnum); /* 1. setup usbip_header */ setup_cmd_submit_pdu(&pdu_header, urb); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index f77e499afddd..065f0b607373 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -257,10 +257,25 @@ static void release_memory_resource(struct resource *resource) kfree(resource); } +/* + * Host memory not allocated to dom0. We can use this range for hotplug-based + * ballooning. + * + * It's a type-less resource. Setting IORESOURCE_MEM will make resource + * management algorithms (arch_remove_reservations()) look into guest e820, + * which we don't want. + */ +static struct resource hostmem_resource = { + .name = "Host RAM", +}; + +void __attribute__((weak)) __init arch_xen_balloon_init(struct resource *res) +{} + static struct resource *additional_memory_resource(phys_addr_t size) { - struct resource *res; - int ret; + struct resource *res, *res_hostmem; + int ret = -ENOMEM; res = kzalloc(sizeof(*res), GFP_KERNEL); if (!res) @@ -269,13 +284,42 @@ static struct resource *additional_memory_resource(phys_addr_t size) res->name = "System RAM"; res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - ret = allocate_resource(&iomem_resource, res, - size, 0, -1, - PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); - if (ret < 0) { - pr_err("Cannot allocate new System RAM resource\n"); - kfree(res); - return NULL; + res_hostmem = kzalloc(sizeof(*res), GFP_KERNEL); + if (res_hostmem) { + /* Try to grab a range from hostmem */ + res_hostmem->name = "Host memory"; + ret = allocate_resource(&hostmem_resource, res_hostmem, + size, 0, -1, + PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); + } + + if (!ret) { + /* + * Insert this resource into iomem. Because hostmem_resource + * tracks portion of guest e820 marked as UNUSABLE noone else + * should try to use it. + */ + res->start = res_hostmem->start; + res->end = res_hostmem->end; + ret = insert_resource(&iomem_resource, res); + if (ret < 0) { + pr_err("Can't insert iomem_resource [%llx - %llx]\n", + res->start, res->end); + release_memory_resource(res_hostmem); + res_hostmem = NULL; + res->start = res->end = 0; + } + } + + if (ret) { + ret = allocate_resource(&iomem_resource, res, + size, 0, -1, + PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); + if (ret < 0) { + pr_err("Cannot allocate new System RAM resource\n"); + kfree(res); + return NULL; + } } #ifdef CONFIG_SPARSEMEM @@ -287,6 +331,7 @@ static struct resource *additional_memory_resource(phys_addr_t size) pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n", pfn, limit); release_memory_resource(res); + release_memory_resource(res_hostmem); return NULL; } } @@ -765,6 +810,8 @@ static int __init balloon_init(void) set_online_page_callback(&xen_online_page); register_memory_notifier(&xen_memory_nb); register_sysctl_table(xen_root); + + arch_xen_balloon_init(&hostmem_resource); #endif #ifdef CONFIG_XEN_PV diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 0da80019a917..83ed7715f856 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -702,7 +702,7 @@ xfs_alloc_ag_vextent( ASSERT(args->agbno % args->alignment == 0); /* if not file data, insert new block into the reverse map btree */ - if (args->oinfo.oi_owner != XFS_RMAP_OWN_UNKNOWN) { + if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) { error = xfs_rmap_alloc(args->tp, args->agbp, args->agno, args->agbno, args->len, &args->oinfo); if (error) @@ -1682,7 +1682,7 @@ xfs_free_ag_extent( bno_cur = cnt_cur = NULL; mp = tp->t_mountp; - if (oinfo->oi_owner != XFS_RMAP_OWN_UNKNOWN) { + if (!xfs_rmap_should_skip_owner_update(oinfo)) { error = xfs_rmap_free(tp, agbp, agno, bno, len, oinfo); if (error) goto error0; diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index 6249c92671de..a76914db72ef 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -212,6 +212,7 @@ xfs_attr_set( int flags) { struct xfs_mount *mp = dp->i_mount; + struct xfs_buf *leaf_bp = NULL; struct xfs_da_args args; struct xfs_defer_ops dfops; struct xfs_trans_res tres; @@ -327,9 +328,16 @@ xfs_attr_set( * GROT: another possible req'mt for a double-split btree op. */ xfs_defer_init(args.dfops, args.firstblock); - error = xfs_attr_shortform_to_leaf(&args); + error = xfs_attr_shortform_to_leaf(&args, &leaf_bp); if (error) goto out_defer_cancel; + /* + * Prevent the leaf buffer from being unlocked so that a + * concurrent AIL push cannot grab the half-baked leaf + * buffer and run into problems with the write verifier. + */ + xfs_trans_bhold(args.trans, leaf_bp); + xfs_defer_bjoin(args.dfops, leaf_bp); xfs_defer_ijoin(args.dfops, dp); error = xfs_defer_finish(&args.trans, args.dfops); if (error) @@ -337,13 +345,14 @@ xfs_attr_set( /* * Commit the leaf transformation. We'll need another (linked) - * transaction to add the new attribute to the leaf. + * transaction to add the new attribute to the leaf, which + * means that we have to hold & join the leaf buffer here too. */ - error = xfs_trans_roll_inode(&args.trans, dp); if (error) goto out; - + xfs_trans_bjoin(args.trans, leaf_bp); + leaf_bp = NULL; } if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) @@ -374,8 +383,9 @@ xfs_attr_set( out_defer_cancel: xfs_defer_cancel(&dfops); - args.trans = NULL; out: + if (leaf_bp) + xfs_trans_brelse(args.trans, leaf_bp); if (args.trans) xfs_trans_cancel(args.trans); xfs_iunlock(dp, XFS_ILOCK_EXCL); diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 53cc8b986eac..601eaa36f1ad 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -735,10 +735,13 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args) } /* - * Convert from using the shortform to the leaf. + * Convert from using the shortform to the leaf. On success, return the + * buffer so that we can keep it locked until we're totally done with it. */ int -xfs_attr_shortform_to_leaf(xfs_da_args_t *args) +xfs_attr_shortform_to_leaf( + struct xfs_da_args *args, + struct xfs_buf **leaf_bp) { xfs_inode_t *dp; xfs_attr_shortform_t *sf; @@ -818,7 +821,7 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args) sfe = XFS_ATTR_SF_NEXTENTRY(sfe); } error = 0; - + *leaf_bp = bp; out: kmem_free(tmpbuffer); return error; diff --git a/fs/xfs/libxfs/xfs_attr_leaf.h b/fs/xfs/libxfs/xfs_attr_leaf.h index f7dda0c237b0..894124efb421 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -48,7 +48,8 @@ void xfs_attr_shortform_create(struct xfs_da_args *args); void xfs_attr_shortform_add(struct xfs_da_args *args, int forkoff); int xfs_attr_shortform_lookup(struct xfs_da_args *args); int xfs_attr_shortform_getvalue(struct xfs_da_args *args); -int xfs_attr_shortform_to_leaf(struct xfs_da_args *args); +int xfs_attr_shortform_to_leaf(struct xfs_da_args *args, + struct xfs_buf **leaf_bp); int xfs_attr_shortform_remove(struct xfs_da_args *args); int xfs_attr_shortform_allfit(struct xfs_buf *bp, struct xfs_inode *dp); int xfs_attr_shortform_bytesfit(struct xfs_inode *dp, int bytes); diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 1210f684d3c2..1bddbba6b80c 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -5136,7 +5136,7 @@ __xfs_bunmapi( * blowing out the transaction with a mix of EFIs and reflink * adjustments. */ - if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) + if (tp && xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res)); else max_len = len; diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index 072ebfe1d6ae..087fea02c389 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -249,6 +249,10 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE); + /* Hold the (previously bjoin'd) buffer locked across the roll. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) + xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]); + trace_xfs_defer_trans_roll((*tp)->t_mountp, dop); /* Roll the transaction. */ @@ -264,6 +268,12 @@ xfs_defer_trans_roll( for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++) xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0); + /* Rejoin the buffers and dirty them so the log moves forward. */ + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) { + xfs_trans_bjoin(*tp, dop->dop_bufs[i]); + xfs_trans_bhold(*tp, dop->dop_bufs[i]); + } + return error; } @@ -295,6 +305,31 @@ xfs_defer_ijoin( } } + ASSERT(0); + return -EFSCORRUPTED; +} + +/* + * Add this buffer to the deferred op. Each joined buffer is relogged + * each time we roll the transaction. + */ +int +xfs_defer_bjoin( + struct xfs_defer_ops *dop, + struct xfs_buf *bp) +{ + int i; + + for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) { + if (dop->dop_bufs[i] == bp) + return 0; + else if (dop->dop_bufs[i] == NULL) { + dop->dop_bufs[i] = bp; + return 0; + } + } + + ASSERT(0); return -EFSCORRUPTED; } @@ -493,9 +528,7 @@ xfs_defer_init( struct xfs_defer_ops *dop, xfs_fsblock_t *fbp) { - dop->dop_committed = false; - dop->dop_low = false; - memset(&dop->dop_inodes, 0, sizeof(dop->dop_inodes)); + memset(dop, 0, sizeof(struct xfs_defer_ops)); *fbp = NULLFSBLOCK; INIT_LIST_HEAD(&dop->dop_intake); INIT_LIST_HEAD(&dop->dop_pending); diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index d4f046dd44bd..045beacdd37d 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -59,6 +59,7 @@ enum xfs_defer_ops_type { }; #define XFS_DEFER_OPS_NR_INODES 2 /* join up to two inodes */ +#define XFS_DEFER_OPS_NR_BUFS 2 /* join up to two buffers */ struct xfs_defer_ops { bool dop_committed; /* did any trans commit? */ @@ -66,8 +67,9 @@ struct xfs_defer_ops { struct list_head dop_intake; /* unlogged pending work */ struct list_head dop_pending; /* logged pending work */ - /* relog these inodes with each roll */ + /* relog these with each roll */ struct xfs_inode *dop_inodes[XFS_DEFER_OPS_NR_INODES]; + struct xfs_buf *dop_bufs[XFS_DEFER_OPS_NR_BUFS]; }; void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type, @@ -77,6 +79,7 @@ void xfs_defer_cancel(struct xfs_defer_ops *dop); void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp); bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop); int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip); +int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp); /* Description of a deferred type. */ struct xfs_defer_op_type { diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c index 89bf16b4d937..b0f31791c7e6 100644 --- a/fs/xfs/libxfs/xfs_iext_tree.c +++ b/fs/xfs/libxfs/xfs_iext_tree.c @@ -632,8 +632,6 @@ xfs_iext_insert( struct xfs_iext_leaf *new = NULL; int nr_entries, i; - trace_xfs_iext_insert(ip, cur, state, _RET_IP_); - if (ifp->if_height == 0) xfs_iext_alloc_root(ifp, cur); else if (ifp->if_height == 1) @@ -661,6 +659,8 @@ xfs_iext_insert( xfs_iext_set(cur_rec(cur), irec); ifp->if_bytes += sizeof(struct xfs_iext_rec); + trace_xfs_iext_insert(ip, cur, state, _RET_IP_); + if (new) xfs_iext_insert_node(ifp, xfs_iext_leaf_key(new, 0), new, 2); } diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 585b35d34142..c40d26763075 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1488,27 +1488,12 @@ __xfs_refcount_cow_alloc( xfs_extlen_t aglen, struct xfs_defer_ops *dfops) { - int error; - trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno, agbno, aglen); /* Add refcount btree reservation */ - error = xfs_refcount_adjust_cow(rcur, agbno, aglen, + return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_ALLOC, dfops); - if (error) - return error; - - /* Add rmap entry */ - if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) { - error = xfs_rmap_alloc_extent(rcur->bc_mp, dfops, - rcur->bc_private.a.agno, - agbno, aglen, XFS_RMAP_OWN_COW); - if (error) - return error; - } - - return error; } /* @@ -1521,27 +1506,12 @@ __xfs_refcount_cow_free( xfs_extlen_t aglen, struct xfs_defer_ops *dfops) { - int error; - trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno, agbno, aglen); /* Remove refcount btree reservation */ - error = xfs_refcount_adjust_cow(rcur, agbno, aglen, + return xfs_refcount_adjust_cow(rcur, agbno, aglen, XFS_REFCOUNT_ADJUST_COW_FREE, dfops); - if (error) - return error; - - /* Remove rmap entry */ - if (xfs_sb_version_hasrmapbt(&rcur->bc_mp->m_sb)) { - error = xfs_rmap_free_extent(rcur->bc_mp, dfops, - rcur->bc_private.a.agno, - agbno, aglen, XFS_RMAP_OWN_COW); - if (error) - return error; - } - - return error; } /* Record a CoW staging extent in the refcount btree. */ @@ -1552,11 +1522,19 @@ xfs_refcount_alloc_cow_extent( xfs_fsblock_t fsb, xfs_extlen_t len) { + int error; + if (!xfs_sb_version_hasreflink(&mp->m_sb)) return 0; - return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW, + error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW, fsb, len); + if (error) + return error; + + /* Add rmap entry */ + return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb), + XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); } /* Forget a CoW staging event in the refcount btree. */ @@ -1567,9 +1545,17 @@ xfs_refcount_free_cow_extent( xfs_fsblock_t fsb, xfs_extlen_t len) { + int error; + if (!xfs_sb_version_hasreflink(&mp->m_sb)) return 0; + /* Remove rmap entry */ + error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb), + XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW); + if (error) + return error; + return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW, fsb, len); } diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index dd019cee1b3b..50db920ceeeb 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -368,6 +368,51 @@ xfs_rmap_lookup_le_range( } /* + * Perform all the relevant owner checks for a removal op. If we're doing an + * unknown-owner removal then we have no owner information to check. + */ +static int +xfs_rmap_free_check_owner( + struct xfs_mount *mp, + uint64_t ltoff, + struct xfs_rmap_irec *rec, + xfs_fsblock_t bno, + xfs_filblks_t len, + uint64_t owner, + uint64_t offset, + unsigned int flags) +{ + int error = 0; + + if (owner == XFS_RMAP_OWN_UNKNOWN) + return 0; + + /* Make sure the unwritten flag matches. */ + XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) == + (rec->rm_flags & XFS_RMAP_UNWRITTEN), out); + + /* Make sure the owner matches what we expect to find in the tree. */ + XFS_WANT_CORRUPTED_GOTO(mp, owner == rec->rm_owner, out); + + /* Check the offset, if necessary. */ + if (XFS_RMAP_NON_INODE_OWNER(owner)) + goto out; + + if (flags & XFS_RMAP_BMBT_BLOCK) { + XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_flags & XFS_RMAP_BMBT_BLOCK, + out); + } else { + XFS_WANT_CORRUPTED_GOTO(mp, rec->rm_offset <= offset, out); + XFS_WANT_CORRUPTED_GOTO(mp, + ltoff + rec->rm_blockcount >= offset + len, + out); + } + +out: + return error; +} + +/* * Find the extent in the rmap btree and remove it. * * The record we find should always be an exact match for the extent that we're @@ -444,33 +489,40 @@ xfs_rmap_unmap( goto out_done; } - /* Make sure the unwritten flag matches. */ - XFS_WANT_CORRUPTED_GOTO(mp, (flags & XFS_RMAP_UNWRITTEN) == - (ltrec.rm_flags & XFS_RMAP_UNWRITTEN), out_error); + /* + * If we're doing an unknown-owner removal for EFI recovery, we expect + * to find the full range in the rmapbt or nothing at all. If we + * don't find any rmaps overlapping either end of the range, we're + * done. Hopefully this means that the EFI creator already queued + * (and finished) a RUI to remove the rmap. + */ + if (owner == XFS_RMAP_OWN_UNKNOWN && + ltrec.rm_startblock + ltrec.rm_blockcount <= bno) { + struct xfs_rmap_irec rtrec; + + error = xfs_btree_increment(cur, 0, &i); + if (error) + goto out_error; + if (i == 0) + goto out_done; + error = xfs_rmap_get_rec(cur, &rtrec, &i); + if (error) + goto out_error; + XFS_WANT_CORRUPTED_GOTO(mp, i == 1, out_error); + if (rtrec.rm_startblock >= bno + len) + goto out_done; + } /* Make sure the extent we found covers the entire freeing range. */ XFS_WANT_CORRUPTED_GOTO(mp, ltrec.rm_startblock <= bno && - ltrec.rm_startblock + ltrec.rm_blockcount >= - bno + len, out_error); + ltrec.rm_startblock + ltrec.rm_blockcount >= + bno + len, out_error); - /* Make sure the owner matches what we expect to find in the tree. */ - XFS_WANT_CORRUPTED_GOTO(mp, owner == ltrec.rm_owner || - XFS_RMAP_NON_INODE_OWNER(owner), out_error); - - /* Check the offset, if necessary. */ - if (!XFS_RMAP_NON_INODE_OWNER(owner)) { - if (flags & XFS_RMAP_BMBT_BLOCK) { - XFS_WANT_CORRUPTED_GOTO(mp, - ltrec.rm_flags & XFS_RMAP_BMBT_BLOCK, - out_error); - } else { - XFS_WANT_CORRUPTED_GOTO(mp, - ltrec.rm_offset <= offset, out_error); - XFS_WANT_CORRUPTED_GOTO(mp, - ltoff + ltrec.rm_blockcount >= offset + len, - out_error); - } - } + /* Check owner information. */ + error = xfs_rmap_free_check_owner(mp, ltoff, <rec, bno, len, owner, + offset, flags); + if (error) + goto out_error; if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) { /* exact match, simply remove the record from rmap tree */ @@ -664,6 +716,7 @@ xfs_rmap_map( flags |= XFS_RMAP_UNWRITTEN; trace_xfs_rmap_map(mp, cur->bc_private.a.agno, bno, len, unwritten, oinfo); + ASSERT(!xfs_rmap_should_skip_owner_update(oinfo)); /* * For the initial lookup, look for an exact match or the left-adjacent diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h index 466ede637080..0fcd5b1ba729 100644 --- a/fs/xfs/libxfs/xfs_rmap.h +++ b/fs/xfs/libxfs/xfs_rmap.h @@ -61,7 +61,21 @@ static inline void xfs_rmap_skip_owner_update( struct xfs_owner_info *oi) { - oi->oi_owner = XFS_RMAP_OWN_UNKNOWN; + xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_NULL); +} + +static inline bool +xfs_rmap_should_skip_owner_update( + struct xfs_owner_info *oi) +{ + return oi->oi_owner == XFS_RMAP_OWN_NULL; +} + +static inline void +xfs_rmap_any_owner_update( + struct xfs_owner_info *oi) +{ + xfs_rmap_ag_owner(oi, XFS_RMAP_OWN_UNKNOWN); } /* Reverse mapping functions. */ diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 44f8c5451210..64da90655e95 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -538,7 +538,7 @@ xfs_efi_recover( return error; efdp = xfs_trans_get_efd(tp, efip, efip->efi_format.efi_nextents); - xfs_rmap_skip_owner_update(&oinfo); + xfs_rmap_any_owner_update(&oinfo); for (i = 0; i < efip->efi_format.efi_nextents; i++) { extp = &efip->efi_format.efi_extents[i]; error = xfs_trans_free_extent(tp, efdp, extp->ext_start, diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 8f22fc579dbb..60a2e128cb6a 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -571,6 +571,11 @@ xfs_growfs_data_private( * this doesn't actually exist in the rmap btree. */ xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_NULL); + error = xfs_rmap_free(tp, bp, agno, + be32_to_cpu(agf->agf_length) - new, + new, &oinfo); + if (error) + goto error0; error = xfs_free_extent(tp, XFS_AGB_TO_FSB(mp, agno, be32_to_cpu(agf->agf_length) - new), diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 43005fbe8b1e..3861d61fb265 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -870,7 +870,7 @@ xfs_eofblocks_worker( * based on the 'speculative_cow_prealloc_lifetime' tunable (5m by default). * (We'll just piggyback on the post-EOF prealloc space workqueue.) */ -STATIC void +void xfs_queue_cowblocks( struct xfs_mount *mp) { @@ -1536,8 +1536,23 @@ xfs_inode_free_quota_eofblocks( return __xfs_inode_free_quota_eofblocks(ip, xfs_icache_free_eofblocks); } +static inline unsigned long +xfs_iflag_for_tag( + int tag) +{ + switch (tag) { + case XFS_ICI_EOFBLOCKS_TAG: + return XFS_IEOFBLOCKS; + case XFS_ICI_COWBLOCKS_TAG: + return XFS_ICOWBLOCKS; + default: + ASSERT(0); + return 0; + } +} + static void -__xfs_inode_set_eofblocks_tag( +__xfs_inode_set_blocks_tag( xfs_inode_t *ip, void (*execute)(struct xfs_mount *mp), void (*set_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, @@ -1552,10 +1567,10 @@ __xfs_inode_set_eofblocks_tag( * Don't bother locking the AG and looking up in the radix trees * if we already know that we have the tag set. */ - if (ip->i_flags & XFS_IEOFBLOCKS) + if (ip->i_flags & xfs_iflag_for_tag(tag)) return; spin_lock(&ip->i_flags_lock); - ip->i_flags |= XFS_IEOFBLOCKS; + ip->i_flags |= xfs_iflag_for_tag(tag); spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); @@ -1587,13 +1602,13 @@ xfs_inode_set_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_eofblocks_tag(ip); - return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_eofblocks, + return __xfs_inode_set_blocks_tag(ip, xfs_queue_eofblocks, trace_xfs_perag_set_eofblocks, XFS_ICI_EOFBLOCKS_TAG); } static void -__xfs_inode_clear_eofblocks_tag( +__xfs_inode_clear_blocks_tag( xfs_inode_t *ip, void (*clear_tp)(struct xfs_mount *mp, xfs_agnumber_t agno, int error, unsigned long caller_ip), @@ -1603,7 +1618,7 @@ __xfs_inode_clear_eofblocks_tag( struct xfs_perag *pag; spin_lock(&ip->i_flags_lock); - ip->i_flags &= ~XFS_IEOFBLOCKS; + ip->i_flags &= ~xfs_iflag_for_tag(tag); spin_unlock(&ip->i_flags_lock); pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino)); @@ -1630,7 +1645,7 @@ xfs_inode_clear_eofblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_eofblocks_tag(ip); - return __xfs_inode_clear_eofblocks_tag(ip, + return __xfs_inode_clear_blocks_tag(ip, trace_xfs_perag_clear_eofblocks, XFS_ICI_EOFBLOCKS_TAG); } @@ -1724,7 +1739,7 @@ xfs_inode_set_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_set_cowblocks_tag(ip); - return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks, + return __xfs_inode_set_blocks_tag(ip, xfs_queue_cowblocks, trace_xfs_perag_set_cowblocks, XFS_ICI_COWBLOCKS_TAG); } @@ -1734,6 +1749,6 @@ xfs_inode_clear_cowblocks_tag( xfs_inode_t *ip) { trace_xfs_inode_clear_cowblocks_tag(ip); - return __xfs_inode_clear_eofblocks_tag(ip, + return __xfs_inode_clear_blocks_tag(ip, trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG); } diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h index bff4d85e5498..d4a77588eca1 100644 --- a/fs/xfs/xfs_icache.h +++ b/fs/xfs/xfs_icache.h @@ -81,6 +81,7 @@ void xfs_inode_clear_cowblocks_tag(struct xfs_inode *ip); int xfs_icache_free_cowblocks(struct xfs_mount *, struct xfs_eofblocks *); int xfs_inode_free_quota_cowblocks(struct xfs_inode *ip); void xfs_cowblocks_worker(struct work_struct *); +void xfs_queue_cowblocks(struct xfs_mount *); int xfs_inode_ag_iterator(struct xfs_mount *mp, int (*execute)(struct xfs_inode *ip, int flags, void *args), diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index b41952a4ddd8..6f95bdb408ce 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1487,6 +1487,24 @@ xfs_link( return error; } +/* Clear the reflink flag and the cowblocks tag if possible. */ +static void +xfs_itruncate_clear_reflink_flags( + struct xfs_inode *ip) +{ + struct xfs_ifork *dfork; + struct xfs_ifork *cfork; + + if (!xfs_is_reflink_inode(ip)) + return; + dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK); + cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK); + if (dfork->if_bytes == 0 && cfork->if_bytes == 0) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; + if (cfork->if_bytes == 0) + xfs_inode_clear_cowblocks_tag(ip); +} + /* * Free up the underlying blocks past new_size. The new size must be smaller * than the current size. This routine can be used both for the attribute and @@ -1583,15 +1601,7 @@ xfs_itruncate_extents( if (error) goto out; - /* - * Clear the reflink flag if there are no data fork blocks and - * there are no extents staged in the cow fork. - */ - if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) { - if (ip->i_d.di_nblocks == 0) - ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK; - xfs_inode_clear_cowblocks_tag(ip); - } + xfs_itruncate_clear_reflink_flags(ip); /* * Always re-log the inode so that our permanent transaction can keep diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index b2136af9289f..d383e392ec9d 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -232,6 +232,7 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip) * log recovery to replay a bmap operation on the inode. */ #define XFS_IRECOVERY (1 << 11) +#define XFS_ICOWBLOCKS (1 << 12)/* has the cowblocks tag set */ /* * Per-lifetime flags need to be reset when re-using a reclaimable inode during diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index cf7c8f81bebb..47aea2e82c26 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -454,6 +454,8 @@ retry: if (error) goto out_bmap_cancel; + xfs_inode_set_cowblocks_tag(ip); + /* Finish up. */ error = xfs_defer_finish(&tp, &dfops); if (error) @@ -490,8 +492,9 @@ xfs_reflink_find_cow_mapping( struct xfs_iext_cursor icur; ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)); - ASSERT(xfs_is_reflink_inode(ip)); + if (!xfs_is_reflink_inode(ip)) + return false; offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset); if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got)) return false; @@ -610,6 +613,9 @@ xfs_reflink_cancel_cow_blocks( /* Remove the mapping from the CoW fork. */ xfs_bmap_del_extent_cow(ip, &icur, &got, &del); + } else { + /* Didn't do anything, push cursor back. */ + xfs_iext_prev(ifp, &icur); } next_extent: if (!xfs_iext_get_extent(ifp, &icur, &got)) @@ -725,7 +731,7 @@ xfs_reflink_end_cow( (unsigned int)(end_fsb - offset_fsb), XFS_DATA_FORK); error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write, - resblks, 0, 0, &tp); + resblks, 0, XFS_TRANS_RESERVE, &tp); if (error) goto out; @@ -1291,6 +1297,17 @@ xfs_reflink_remap_range( trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out); + /* + * Clear out post-eof preallocations because we don't have page cache + * backing the delayed allocations and they'll never get freed on + * their own. + */ + if (xfs_can_free_eofblocks(dest, true)) { + ret = xfs_free_eofblocks(dest); + if (ret) + goto out_unlock; + } + /* Set flags and remap blocks. */ ret = xfs_reflink_set_inode_flag(src, dest); if (ret) diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 5122d3021117..1dacccc367f8 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1360,6 +1360,7 @@ xfs_fs_remount( xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); return error; } + xfs_queue_cowblocks(mp); /* Create the per-AG metadata reservation pool .*/ error = xfs_fs_reserve_ag_blocks(mp); @@ -1369,6 +1370,14 @@ xfs_fs_remount( /* rw -> ro */ if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & SB_RDONLY)) { + /* Get rid of any leftover CoW reservations... */ + cancel_delayed_work_sync(&mp->m_cowblocks_work); + error = xfs_icache_free_cowblocks(mp, NULL); + if (error) { + xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE); + return error; + } + /* Free the per-AG metadata reservation pool. */ error = xfs_fs_unreserve_ag_blocks(mp); if (error) { diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h index ea189d88a3cc..8ac4e68a12f0 100644 --- a/include/asm-generic/mm_hooks.h +++ b/include/asm-generic/mm_hooks.h @@ -7,9 +7,10 @@ #ifndef _ASM_GENERIC_MM_HOOKS_H #define _ASM_GENERIC_MM_HOOKS_H -static inline void arch_dup_mmap(struct mm_struct *oldmm, - struct mm_struct *mm) +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) { + return 0; } static inline void arch_exit_mmap(struct mm_struct *mm) diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index b234d54f2cb6..868e68561f91 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1025,6 +1025,11 @@ static inline int pmd_clear_huge(pmd_t *pmd) struct file; int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot); + +#ifndef CONFIG_X86_ESPFIX64 +static inline void init_espfix_bsp(void) { } +#endif + #endif /* !__ASSEMBLY__ */ #ifndef io_remap_pfn_range diff --git a/include/crypto/mcryptd.h b/include/crypto/mcryptd.h index cceafa01f907..b67404fc4b34 100644 --- a/include/crypto/mcryptd.h +++ b/include/crypto/mcryptd.h @@ -27,6 +27,7 @@ static inline struct mcryptd_ahash *__mcryptd_ahash_cast( struct mcryptd_cpu_queue { struct crypto_queue queue; + spinlock_t q_lock; struct work_struct work; }; diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 6e45608b2399..9da6ce22803f 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -62,7 +62,7 @@ struct arch_timer_cpu { bool enabled; }; -int kvm_timer_hyp_init(void); +int kvm_timer_hyp_init(bool); int kvm_timer_enable(struct kvm_vcpu *vcpu); int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); diff --git a/include/linux/bio.h b/include/linux/bio.h index 82f0c8fd7be8..23d29b39f71e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -492,6 +492,8 @@ extern unsigned int bvec_nr_vecs(unsigned short idx); #define bio_set_dev(bio, bdev) \ do { \ + if ((bio)->bi_disk != (bdev)->bd_disk) \ + bio_clear_flag(bio, BIO_THROTTLED);\ (bio)->bi_disk = (bdev)->bd_disk; \ (bio)->bi_partno = (bdev)->bd_partno; \ } while (0) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index a1e628e032da..9e7d8bd776d2 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -50,8 +50,6 @@ struct blk_issue_stat { struct bio { struct bio *bi_next; /* request queue link */ struct gendisk *bi_disk; - u8 bi_partno; - blk_status_t bi_status; unsigned int bi_opf; /* bottom bits req flags, * top bits REQ_OP. Use * accessors. @@ -59,8 +57,8 @@ struct bio { unsigned short bi_flags; /* status, etc and bvec pool number */ unsigned short bi_ioprio; unsigned short bi_write_hint; - - struct bvec_iter bi_iter; + blk_status_t bi_status; + u8 bi_partno; /* Number of segments in this BIO after * physical address coalescing is performed. @@ -74,8 +72,9 @@ struct bio { unsigned int bi_seg_front_size; unsigned int bi_seg_back_size; - atomic_t __bi_remaining; + struct bvec_iter bi_iter; + atomic_t __bi_remaining; bio_end_io_t *bi_end_io; void *bi_private; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8089ca17db9a..0ce8a372d506 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -135,7 +135,7 @@ typedef __u32 __bitwise req_flags_t; struct request { struct list_head queuelist; union { - call_single_data_t csd; + struct __call_single_data csd; u64 fifo_time; }; @@ -241,14 +241,24 @@ struct request { struct request *next_rq; }; +static inline bool blk_op_is_scsi(unsigned int op) +{ + return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT; +} + +static inline bool blk_op_is_private(unsigned int op) +{ + return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; +} + static inline bool blk_rq_is_scsi(struct request *rq) { - return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT; + return blk_op_is_scsi(req_op(rq)); } static inline bool blk_rq_is_private(struct request *rq) { - return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT; + return blk_op_is_private(req_op(rq)); } static inline bool blk_rq_is_passthrough(struct request *rq) @@ -256,6 +266,13 @@ static inline bool blk_rq_is_passthrough(struct request *rq) return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); } +static inline bool bio_is_passthrough(struct bio *bio) +{ + unsigned op = bio_op(bio); + + return blk_op_is_scsi(op) || blk_op_is_private(op); +} + static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; @@ -948,7 +965,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); -extern int blk_rq_append_bio(struct request *rq, struct bio *bio); +extern int blk_rq_append_bio(struct request *rq, struct bio **bio); extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_queue_split(struct request_queue *, struct bio **); extern void blk_recount_segments(struct request_queue *, struct bio *); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c561b986bab0..1632bb13ad8a 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -15,11 +15,11 @@ * In practice this is far bigger than any realistic pointer offset; this limit * ensures that umax_value + (int)off + (int)size cannot overflow a u64. */ -#define BPF_MAX_VAR_OFF (1ULL << 31) +#define BPF_MAX_VAR_OFF (1 << 29) /* Maximum variable size permitted for ARG_CONST_SIZE[_OR_ZERO]. This ensures * that converting umax_value to int cannot overflow. */ -#define BPF_MAX_VAR_SIZ INT_MAX +#define BPF_MAX_VAR_SIZ (1 << 29) /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 201ab7267986..1a32e558eb11 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -86,7 +86,7 @@ enum cpuhp_state { CPUHP_MM_ZSWP_POOL_PREPARE, CPUHP_KVM_PPC_BOOK3S_PREPARE, CPUHP_ZCOMP_PREPARE, - CPUHP_TIMERS_DEAD, + CPUHP_TIMERS_PREPARE, CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 55e672592fa9..7258cd676df4 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -66,9 +66,10 @@ struct gpio_irq_chip { /** * @lock_key: * - * Per GPIO IRQ chip lockdep class. + * Per GPIO IRQ chip lockdep classes. */ struct lock_class_key *lock_key; + struct lock_class_key *request_key; /** * @parent_handler: @@ -323,7 +324,8 @@ extern const char *gpiochip_is_requested(struct gpio_chip *chip, /* add/remove chips */ extern int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, - struct lock_class_key *lock_key); + struct lock_class_key *lock_key, + struct lock_class_key *request_key); /** * gpiochip_add_data() - register a gpio_chip @@ -350,11 +352,13 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data, */ #ifdef CONFIG_LOCKDEP #define gpiochip_add_data(chip, data) ({ \ - static struct lock_class_key key; \ - gpiochip_add_data_with_key(chip, data, &key); \ + static struct lock_class_key lock_key; \ + static struct lock_class_key request_key; \ + gpiochip_add_data_with_key(chip, data, &lock_key, \ + &request_key); \ }) #else -#define gpiochip_add_data(chip, data) gpiochip_add_data_with_key(chip, data, NULL) +#define gpiochip_add_data(chip, data) gpiochip_add_data_with_key(chip, data, NULL, NULL) #endif static inline int gpiochip_add(struct gpio_chip *chip) @@ -429,7 +433,8 @@ int gpiochip_irqchip_add_key(struct gpio_chip *gpiochip, irq_flow_handler_t handler, unsigned int type, bool threaded, - struct lock_class_key *lock_key); + struct lock_class_key *lock_key, + struct lock_class_key *request_key); #ifdef CONFIG_LOCKDEP @@ -445,10 +450,12 @@ static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, irq_flow_handler_t handler, unsigned int type) { - static struct lock_class_key key; + static struct lock_class_key lock_key; + static struct lock_class_key request_key; return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, - handler, type, false, &key); + handler, type, false, + &lock_key, &request_key); } static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, @@ -458,10 +465,12 @@ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, unsigned int type) { - static struct lock_class_key key; + static struct lock_class_key lock_key; + static struct lock_class_key request_key; return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, - handler, type, true, &key); + handler, type, true, + &lock_key, &request_key); } #else static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, @@ -471,7 +480,7 @@ static inline int gpiochip_irqchip_add(struct gpio_chip *gpiochip, unsigned int type) { return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, - handler, type, false, NULL); + handler, type, false, NULL, NULL); } static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, @@ -481,7 +490,7 @@ static inline int gpiochip_irqchip_add_nested(struct gpio_chip *gpiochip, unsigned int type) { return gpiochip_irqchip_add_key(gpiochip, irqchip, first_irq, - handler, type, true, NULL); + handler, type, true, NULL, NULL); } #endif /* CONFIG_LOCKDEP */ diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index cb18c6290ca8..8415bf1a9776 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -273,7 +273,8 @@ struct ipv6_pinfo { * 100: prefer care-of address */ dontfrag:1, - autoflowlabel:1; + autoflowlabel:1, + autoflowlabel_set:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; diff --git a/include/linux/irq.h b/include/linux/irq.h index e140f69163b6..a0231e96a578 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -212,6 +212,7 @@ struct irq_data { * mask. Applies only to affinity managed irqs. * IRQD_SINGLE_TARGET - IRQ allows only a single affinity target * IRQD_DEFAULT_TRIGGER_SET - Expected trigger already been set + * IRQD_CAN_RESERVE - Can use reservation mode */ enum { IRQD_TRIGGER_MASK = 0xf, @@ -233,6 +234,7 @@ enum { IRQD_MANAGED_SHUTDOWN = (1 << 23), IRQD_SINGLE_TARGET = (1 << 24), IRQD_DEFAULT_TRIGGER_SET = (1 << 25), + IRQD_CAN_RESERVE = (1 << 26), }; #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors) @@ -377,6 +379,21 @@ static inline bool irqd_is_managed_and_shutdown(struct irq_data *d) return __irqd_to_state(d) & IRQD_MANAGED_SHUTDOWN; } +static inline void irqd_set_can_reserve(struct irq_data *d) +{ + __irqd_to_state(d) |= IRQD_CAN_RESERVE; +} + +static inline void irqd_clr_can_reserve(struct irq_data *d) +{ + __irqd_to_state(d) &= ~IRQD_CAN_RESERVE; +} + +static inline bool irqd_can_reserve(struct irq_data *d) +{ + return __irqd_to_state(d) & IRQD_CAN_RESERVE; +} + #undef __irqd_to_state static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 39fb3700f7a9..25b33b664537 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -255,12 +255,15 @@ static inline bool irq_is_percpu_devid(unsigned int irq) } static inline void -irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class) +irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, + struct lock_class_key *request_class) { struct irq_desc *desc = irq_to_desc(irq); - if (desc) - lockdep_set_class(&desc->lock, class); + if (desc) { + lockdep_set_class(&desc->lock, lock_class); + lockdep_set_class(&desc->request_mutex, request_class); + } } #ifdef CONFIG_IRQ_PREFLOW_FASTEOI diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index a34355d19546..48c7e86bb556 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -113,7 +113,7 @@ struct irq_domain_ops { unsigned int nr_irqs, void *arg); void (*free)(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs); - int (*activate)(struct irq_domain *d, struct irq_data *irqd, bool early); + int (*activate)(struct irq_domain *d, struct irq_data *irqd, bool reserve); void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data); int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *out_hwirq, unsigned int *out_type); diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h index a2a1318a3d0c..c3d3f04d8cc6 100644 --- a/include/linux/mfd/rtsx_pci.h +++ b/include/linux/mfd/rtsx_pci.h @@ -915,10 +915,10 @@ enum PDEV_STAT {PDEV_STAT_IDLE, PDEV_STAT_RUN}; #define LTR_L1SS_PWR_GATE_CHECK_CARD_EN BIT(6) enum dev_aspm_mode { - DEV_ASPM_DISABLE = 0, DEV_ASPM_DYNAMIC, DEV_ASPM_BACKDOOR, DEV_ASPM_STATIC, + DEV_ASPM_DISABLE, }; /* diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a886b51511ab..1f509d072026 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -556,6 +556,7 @@ struct mlx5_core_sriov { }; struct mlx5_irq_info { + cpumask_var_t mask; char name[MLX5_MAX_IRQ_NAME]; }; @@ -1048,7 +1049,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, enum mlx5_eq_type type); int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq); int mlx5_start_eqs(struct mlx5_core_dev *dev); -int mlx5_stop_eqs(struct mlx5_core_dev *dev); +void mlx5_stop_eqs(struct mlx5_core_dev *dev); int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn, unsigned int *irqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); @@ -1164,6 +1165,10 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev); int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev); bool mlx5_lag_is_active(struct mlx5_core_dev *dev); struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev); +int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev, + u64 *values, + int num_counters, + size_t *offsets); struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev); void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 38a7577a9ce7..d44ec5f41d4a 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -147,7 +147,7 @@ enum { MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771, MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772, MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773, - MLX5_CMD_OP_SET_RATE_LIMIT = 0x780, + MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780, MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781, MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782, MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783, @@ -7239,7 +7239,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits { u8 vxlan_udp_port[0x10]; }; -struct mlx5_ifc_set_rate_limit_out_bits { +struct mlx5_ifc_set_pp_rate_limit_out_bits { u8 status[0x8]; u8 reserved_at_8[0x18]; @@ -7248,7 +7248,7 @@ struct mlx5_ifc_set_rate_limit_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_set_rate_limit_in_bits { +struct mlx5_ifc_set_pp_rate_limit_in_bits { u8 opcode[0x10]; u8 reserved_at_10[0x10]; @@ -7261,6 +7261,8 @@ struct mlx5_ifc_set_rate_limit_in_bits { u8 reserved_at_60[0x20]; u8 rate_limit[0x20]; + + u8 reserved_at_a0[0x160]; }; struct mlx5_ifc_access_register_out_bits { diff --git a/include/linux/pti.h b/include/linux/pti.h new file mode 100644 index 000000000000..0174883a935a --- /dev/null +++ b/include/linux/pti.h @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef _INCLUDE_PTI_H +#define _INCLUDE_PTI_H + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +#include <asm/pti.h> +#else +static inline void pti_init(void) { } +#endif + +#endif diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 7b2170bfd6e7..bc6bb325d1bf 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -126,7 +126,7 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, * for that name. This appears in the sysfs "modalias" attribute * for driver coldplugging, and in uevents used for hotplugging * @cs_gpio: gpio number of the chipselect line (optional, -ENOENT when - * when not using a GPIO line) + * not using a GPIO line) * * @statistics: statistics for the spi_device * diff --git a/include/linux/tick.h b/include/linux/tick.h index f442d1a42025..7cc35921218e 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -119,6 +119,7 @@ extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); extern unsigned long tick_nohz_get_idle_calls(void); +extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ diff --git a/include/linux/timer.h b/include/linux/timer.h index 04af640ea95b..2448f9cc48a3 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -207,9 +207,11 @@ unsigned long round_jiffies_up(unsigned long j); unsigned long round_jiffies_up_relative(unsigned long j); #ifdef CONFIG_HOTPLUG_CPU +int timers_prepare_cpu(unsigned int cpu); int timers_dead_cpu(unsigned int cpu); #else -#define timers_dead_cpu NULL +#define timers_prepare_cpu NULL +#define timers_dead_cpu NULL #endif #endif diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 8b8118a7fadb..cb4d92b79cd9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -3226,7 +3226,6 @@ struct cfg80211_ops { * @WIPHY_FLAG_IBSS_RSN: The device supports IBSS RSN. * @WIPHY_FLAG_MESH_AUTH: The device supports mesh authentication by routing * auth frames to userspace. See @NL80211_MESH_SETUP_USERSPACE_AUTH. - * @WIPHY_FLAG_SUPPORTS_SCHED_SCAN: The device supports scheduled scans. * @WIPHY_FLAG_SUPPORTS_FW_ROAM: The device supports roaming feature in the * firmware. * @WIPHY_FLAG_AP_UAPSD: The device supports uapsd on AP. diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 0105445cab83..8e08b6da72f3 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -694,9 +694,7 @@ struct tc_cls_matchall_offload { }; enum tc_clsbpf_command { - TC_CLSBPF_ADD, - TC_CLSBPF_REPLACE, - TC_CLSBPF_DESTROY, + TC_CLSBPF_OFFLOAD, TC_CLSBPF_STATS, }; @@ -705,6 +703,7 @@ struct tc_cls_bpf_offload { enum tc_clsbpf_command command; struct tcf_exts *exts; struct bpf_prog *prog; + struct bpf_prog *oldprog; const char *name; bool exts_integrated; u32 gen_flags; diff --git a/include/net/sock.h b/include/net/sock.h index 9155da422692..7a7b14e9628a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1514,6 +1514,11 @@ static inline bool sock_owned_by_user(const struct sock *sk) return sk->sk_lock.owned; } +static inline bool sock_owned_by_user_nocheck(const struct sock *sk) +{ + return sk->sk_lock.owned; +} + /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index dc28a98ce97c..ae35991b5877 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1570,6 +1570,9 @@ int xfrm_init_state(struct xfrm_state *x); int xfrm_prepare_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)); int xfrm_output_resume(struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb); diff --git a/include/trace/events/clk.h b/include/trace/events/clk.h index 758607226bfd..2cd449328aee 100644 --- a/include/trace/events/clk.h +++ b/include/trace/events/clk.h @@ -134,12 +134,12 @@ DECLARE_EVENT_CLASS(clk_parent, TP_STRUCT__entry( __string( name, core->name ) - __string( pname, parent->name ) + __string( pname, parent ? parent->name : "none" ) ), TP_fast_assign( __assign_str(name, core->name); - __assign_str(pname, parent->name); + __assign_str(pname, parent ? parent->name : "none"); ), TP_printk("%s %s", __get_str(name), __get_str(pname)) diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index e4b0b8e09932..2c735a3e6613 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -211,7 +211,7 @@ TRACE_EVENT(kvm_ack_irq, { KVM_TRACE_MMIO_WRITE, "write" } TRACE_EVENT(kvm_mmio, - TP_PROTO(int type, int len, u64 gpa, u64 val), + TP_PROTO(int type, int len, u64 gpa, void *val), TP_ARGS(type, len, gpa, val), TP_STRUCT__entry( @@ -225,7 +225,10 @@ TRACE_EVENT(kvm_mmio, __entry->type = type; __entry->len = len; __entry->gpa = gpa; - __entry->val = val; + __entry->val = 0; + if (val) + memcpy(&__entry->val, val, + min_t(u32, sizeof(__entry->val), len)); ), TP_printk("mmio %s len %u gpa 0x%llx val 0x%llx", diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 07cccca6cbf1..ab34c561f26b 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -25,6 +25,35 @@ tcp_state_name(TCP_CLOSING), \ tcp_state_name(TCP_NEW_SYN_RECV)) +#define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ + do { \ + struct in6_addr *pin6; \ + \ + pin6 = (struct in6_addr *)__entry->saddr_v6; \ + ipv6_addr_set_v4mapped(saddr, pin6); \ + pin6 = (struct in6_addr *)__entry->daddr_v6; \ + ipv6_addr_set_v4mapped(daddr, pin6); \ + } while (0) + +#if IS_ENABLED(CONFIG_IPV6) +#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ + do { \ + if (sk->sk_family == AF_INET6) { \ + struct in6_addr *pin6; \ + \ + pin6 = (struct in6_addr *)__entry->saddr_v6; \ + *pin6 = saddr6; \ + pin6 = (struct in6_addr *)__entry->daddr_v6; \ + *pin6 = daddr6; \ + } else { \ + TP_STORE_V4MAPPED(__entry, saddr, daddr); \ + } \ + } while (0) +#else +#define TP_STORE_ADDRS(__entry, saddr, daddr, saddr6, daddr6) \ + TP_STORE_V4MAPPED(__entry, saddr, daddr) +#endif + /* * tcp event with arguments sk and skb * @@ -50,7 +79,6 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, TP_fast_assign( struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->skbaddr = skb; @@ -65,20 +93,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk_skb, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", @@ -127,7 +143,6 @@ DECLARE_EVENT_CLASS(tcp_event_sk, TP_fast_assign( struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->skaddr = sk; @@ -141,20 +156,8 @@ DECLARE_EVENT_CLASS(tcp_event_sk, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", @@ -197,7 +200,6 @@ TRACE_EVENT(tcp_set_state, TP_fast_assign( struct inet_sock *inet = inet_sk(sk); - struct in6_addr *pin6; __be32 *p32; __entry->skaddr = sk; @@ -213,20 +215,8 @@ TRACE_EVENT(tcp_set_state, p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = sk->sk_v6_rcv_saddr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = sk->sk_v6_daddr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(inet->inet_saddr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(inet->inet_daddr, pin6); - } + TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, + sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", @@ -256,7 +246,6 @@ TRACE_EVENT(tcp_retransmit_synack, TP_fast_assign( struct inet_request_sock *ireq = inet_rsk(req); - struct in6_addr *pin6; __be32 *p32; __entry->skaddr = sk; @@ -271,20 +260,8 @@ TRACE_EVENT(tcp_retransmit_synack, p32 = (__be32 *) __entry->daddr; *p32 = ireq->ir_rmt_addr; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) { - pin6 = (struct in6_addr *)__entry->saddr_v6; - *pin6 = ireq->ir_v6_loc_addr; - pin6 = (struct in6_addr *)__entry->daddr_v6; - *pin6 = ireq->ir_v6_rmt_addr; - } else -#endif - { - pin6 = (struct in6_addr *)__entry->saddr_v6; - ipv6_addr_set_v4mapped(ireq->ir_loc_addr, pin6); - pin6 = (struct in6_addr *)__entry->daddr_v6; - ipv6_addr_set_v4mapped(ireq->ir_rmt_addr, pin6); - } + TP_STORE_ADDRS(__entry, ireq->ir_loc_addr, ireq->ir_rmt_addr, + ireq->ir_v6_loc_addr, ireq->ir_v6_rmt_addr); ), TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", diff --git a/include/xen/balloon.h b/include/xen/balloon.h index 4914b93a23f2..61f410fd74e4 100644 --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -44,3 +44,8 @@ static inline void xen_balloon_init(void) { } #endif + +#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG +struct resource; +void arch_xen_balloon_init(struct resource *hostmem_resource); +#endif diff --git a/init/Kconfig b/init/Kconfig index 2934249fba46..690a381adee0 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -461,10 +461,14 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" + default y help Make sure that CPUs running critical tasks are not disturbed by any source of "noise" such as unbound workqueues, timers, kthreads... - Unbound jobs get offloaded to housekeeping CPUs. + Unbound jobs get offloaded to housekeeping CPUs. This is driven by + the "isolcpus=" boot parameter. + + Say Y if unsure. source "kernel/rcu/Kconfig" diff --git a/init/main.c b/init/main.c index e96e3a14533c..a8100b954839 100644 --- a/init/main.c +++ b/init/main.c @@ -75,6 +75,7 @@ #include <linux/slab.h> #include <linux/perf_event.h> #include <linux/ptrace.h> +#include <linux/pti.h> #include <linux/blkdev.h> #include <linux/elevator.h> #include <linux/sched_clock.h> @@ -504,6 +505,10 @@ static void __init mm_init(void) pgtable_init(); vmalloc_init(); ioremap_huge_init(); + /* Should be run before the first non-init thread is created */ + init_espfix_bsp(); + /* Should be run after espfix64 is set up. */ + pti_init(); } asmlinkage __visible void __init start_kernel(void) @@ -679,10 +684,6 @@ asmlinkage __visible void __init start_kernel(void) if (efi_enabled(EFI_RUNTIME_SERVICES)) efi_enter_virtual_mode(); #endif -#ifdef CONFIG_X86_ESPFIX64 - /* Should be run before the first non-init thread is created */ - init_espfix_bsp(); -#endif thread_stack_cache_init(); cred_init(); fork_init(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d4593571c404..04b24876cd23 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1059,6 +1059,11 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, break; case PTR_TO_STACK: pointer_desc = "stack "; + /* The stack spill tracking logic in check_stack_write() + * and check_stack_read() relies on stack accesses being + * aligned. + */ + strict = true; break; default: break; @@ -1067,6 +1072,29 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, strict); } +/* truncate register to smaller size (in bytes) + * must be called with size < BPF_REG_SIZE + */ +static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) +{ + u64 mask; + + /* clear high bits in bit representation */ + reg->var_off = tnum_cast(reg->var_off, size); + + /* fix arithmetic bounds */ + mask = ((u64)1 << (size * 8)) - 1; + if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) { + reg->umin_value &= mask; + reg->umax_value &= mask; + } else { + reg->umin_value = 0; + reg->umax_value = mask; + } + reg->smin_value = reg->umin_value; + reg->smax_value = reg->umax_value; +} + /* check whether memory at (regno + off) is accessible for t = (read | write) * if t==write, value_regno is a register which value is stored into memory * if t==read, value_regno is a register which will receive the value from memory @@ -1200,9 +1228,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ && regs[value_regno].type == SCALAR_VALUE) { /* b/h/w load zero-extends, mark upper bits as known 0 */ - regs[value_regno].var_off = - tnum_cast(regs[value_regno].var_off, size); - __update_reg_bounds(®s[value_regno]); + coerce_reg_to_size(®s[value_regno], size); } return err; } @@ -1282,6 +1308,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno, tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off); verbose(env, "invalid variable stack read R%d var_off=%s\n", regno, tn_buf); + return -EACCES; } off = regs[regno].off + regs[regno].var_off.value; if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 || @@ -1674,7 +1701,13 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return -EINVAL; } + /* With LD_ABS/IND some JITs save/restore skb from r1. */ changes_data = bpf_helper_changes_pkt_data(fn->func); + if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) { + verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n", + func_id_name(func_id), func_id); + return -EINVAL; + } memset(&meta, 0, sizeof(meta)); meta.pkt_access = fn->pkt_access; @@ -1766,14 +1799,6 @@ static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx) return 0; } -static void coerce_reg_to_32(struct bpf_reg_state *reg) -{ - /* clear high 32 bits */ - reg->var_off = tnum_cast(reg->var_off, 4); - /* Update bounds */ - __update_reg_bounds(reg); -} - static bool signed_add_overflows(s64 a, s64 b) { /* Do the add in u64, where overflow is well-defined */ @@ -1794,6 +1819,41 @@ static bool signed_sub_overflows(s64 a, s64 b) return res > a; } +static bool check_reg_sane_offset(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, + enum bpf_reg_type type) +{ + bool known = tnum_is_const(reg->var_off); + s64 val = reg->var_off.value; + s64 smin = reg->smin_value; + + if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { + verbose(env, "math between %s pointer and %lld is not allowed\n", + reg_type_str[type], val); + return false; + } + + if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { + verbose(env, "%s pointer offset %d is not allowed\n", + reg_type_str[type], reg->off); + return false; + } + + if (smin == S64_MIN) { + verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", + reg_type_str[type]); + return false; + } + + if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { + verbose(env, "value %lld makes %s pointer be out of bounds\n", + smin, reg_type_str[type]); + return false; + } + + return true; +} + /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. * If we return -EACCES, caller may want to try again treating pointer as a @@ -1830,29 +1890,25 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (BPF_CLASS(insn->code) != BPF_ALU64) { /* 32-bit ALU ops on pointers produce (meaningless) scalars */ - if (!env->allow_ptr_leaks) - verbose(env, - "R%d 32-bit pointer arithmetic prohibited\n", - dst); + verbose(env, + "R%d 32-bit pointer arithmetic prohibited\n", + dst); return -EACCES; } if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", - dst); + verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n", + dst); return -EACCES; } if (ptr_reg->type == CONST_PTR_TO_MAP) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", - dst); + verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n", + dst); return -EACCES; } if (ptr_reg->type == PTR_TO_PACKET_END) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", - dst); + verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n", + dst); return -EACCES; } @@ -1862,6 +1918,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->type = ptr_reg->type; dst_reg->id = ptr_reg->id; + if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) || + !check_reg_sane_offset(env, ptr_reg, ptr_reg->type)) + return -EINVAL; + switch (opcode) { case BPF_ADD: /* We can take a fixed offset as long as it doesn't overflow @@ -1915,9 +1975,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case BPF_SUB: if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ - if (!env->allow_ptr_leaks) - verbose(env, "R%d tried to subtract pointer from scalar\n", - dst); + verbose(env, "R%d tried to subtract pointer from scalar\n", + dst); return -EACCES; } /* We don't allow subtraction from FP, because (according to @@ -1925,9 +1984,8 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, * be able to deal with it. */ if (ptr_reg->type == PTR_TO_STACK) { - if (!env->allow_ptr_leaks) - verbose(env, "R%d subtraction from stack pointer prohibited\n", - dst); + verbose(env, "R%d subtraction from stack pointer prohibited\n", + dst); return -EACCES; } if (known && (ptr_reg->off - smin_val == @@ -1976,28 +2034,30 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case BPF_AND: case BPF_OR: case BPF_XOR: - /* bitwise ops on pointers are troublesome, prohibit for now. - * (However, in principle we could allow some cases, e.g. - * ptr &= ~3 which would reduce min_value by 3.) - */ - if (!env->allow_ptr_leaks) - verbose(env, "R%d bitwise operator %s on pointer prohibited\n", - dst, bpf_alu_string[opcode >> 4]); + /* bitwise ops on pointers are troublesome, prohibit. */ + verbose(env, "R%d bitwise operator %s on pointer prohibited\n", + dst, bpf_alu_string[opcode >> 4]); return -EACCES; default: /* other operators (e.g. MUL,LSH) produce non-pointer results */ - if (!env->allow_ptr_leaks) - verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", - dst, bpf_alu_string[opcode >> 4]); + verbose(env, "R%d pointer arithmetic with %s operator prohibited\n", + dst, bpf_alu_string[opcode >> 4]); return -EACCES; } + if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type)) + return -EINVAL; + __update_reg_bounds(dst_reg); __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; } +/* WARNING: This function does calculations on 64-bit values, but the actual + * execution may occur on 32-bit values. Therefore, things like bitshifts + * need extra checks in the 32-bit case. + */ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn, struct bpf_reg_state *dst_reg, @@ -2008,12 +2068,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, bool src_known, dst_known; s64 smin_val, smax_val; u64 umin_val, umax_val; + u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; - if (BPF_CLASS(insn->code) != BPF_ALU64) { - /* 32-bit ALU ops are (32,32)->64 */ - coerce_reg_to_32(dst_reg); - coerce_reg_to_32(&src_reg); - } smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; umin_val = src_reg.umin_value; @@ -2021,6 +2077,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, src_known = tnum_is_const(src_reg.var_off); dst_known = tnum_is_const(dst_reg->var_off); + if (!src_known && + opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) { + __mark_reg_unknown(dst_reg); + return 0; + } + switch (opcode) { case BPF_ADD: if (signed_add_overflows(dst_reg->smin_value, smin_val) || @@ -2149,9 +2211,9 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); break; case BPF_LSH: - if (umax_val > 63) { - /* Shifts greater than 63 are undefined. This includes - * shifts by a negative number. + if (umax_val >= insn_bitness) { + /* Shifts greater than 31 or 63 are undefined. + * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; @@ -2177,27 +2239,29 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, __update_reg_bounds(dst_reg); break; case BPF_RSH: - if (umax_val > 63) { - /* Shifts greater than 63 are undefined. This includes - * shifts by a negative number. + if (umax_val >= insn_bitness) { + /* Shifts greater than 31 or 63 are undefined. + * This includes shifts by a negative number. */ mark_reg_unknown(env, regs, insn->dst_reg); break; } - /* BPF_RSH is an unsigned shift, so make the appropriate casts */ - if (dst_reg->smin_value < 0) { - if (umin_val) { - /* Sign bit will be cleared */ - dst_reg->smin_value = 0; - } else { - /* Lost sign bit information */ - dst_reg->smin_value = S64_MIN; - dst_reg->smax_value = S64_MAX; - } - } else { - dst_reg->smin_value = - (u64)(dst_reg->smin_value) >> umax_val; - } + /* BPF_RSH is an unsigned shift. If the value in dst_reg might + * be negative, then either: + * 1) src_reg might be zero, so the sign bit of the result is + * unknown, so we lose our signed bounds + * 2) it's known negative, thus the unsigned bounds capture the + * signed bounds + * 3) the signed bounds cross zero, so they tell us nothing + * about the result + * If the value in dst_reg is known nonnegative, then again the + * unsigned bounts capture the signed bounds. + * Thus, in all cases it suffices to blow away our signed bounds + * and rely on inferring new ones from the unsigned bounds and + * var_off of the result. + */ + dst_reg->smin_value = S64_MIN; + dst_reg->smax_value = S64_MAX; if (src_known) dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); @@ -2213,6 +2277,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, break; } + if (BPF_CLASS(insn->code) != BPF_ALU64) { + /* 32-bit ALU ops are (32,32)->32 */ + coerce_reg_to_size(dst_reg, 4); + coerce_reg_to_size(&src_reg, 4); + } + __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); return 0; @@ -2227,7 +2297,6 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg; struct bpf_reg_state *ptr_reg = NULL, off_reg = {0}; u8 opcode = BPF_OP(insn->code); - int rc; dst_reg = ®s[insn->dst_reg]; src_reg = NULL; @@ -2238,43 +2307,29 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, if (src_reg->type != SCALAR_VALUE) { if (dst_reg->type != SCALAR_VALUE) { /* Combining two pointers by any ALU op yields - * an arbitrary scalar. + * an arbitrary scalar. Disallow all math except + * pointer subtraction */ - if (!env->allow_ptr_leaks) { - verbose(env, "R%d pointer %s pointer prohibited\n", - insn->dst_reg, - bpf_alu_string[opcode >> 4]); - return -EACCES; + if (opcode == BPF_SUB){ + mark_reg_unknown(env, regs, insn->dst_reg); + return 0; } - mark_reg_unknown(env, regs, insn->dst_reg); - return 0; + verbose(env, "R%d pointer %s pointer prohibited\n", + insn->dst_reg, + bpf_alu_string[opcode >> 4]); + return -EACCES; } else { /* scalar += pointer * This is legal, but we have to reverse our * src/dest handling in computing the range */ - rc = adjust_ptr_min_max_vals(env, insn, - src_reg, dst_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* scalar += unknown scalar */ - __mark_reg_unknown(&off_reg); - return adjust_scalar_min_max_vals( - env, insn, - dst_reg, off_reg); - } - return rc; + return adjust_ptr_min_max_vals(env, insn, + src_reg, dst_reg); } } else if (ptr_reg) { /* pointer += scalar */ - rc = adjust_ptr_min_max_vals(env, insn, - dst_reg, src_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* unknown scalar += scalar */ - __mark_reg_unknown(dst_reg); - return adjust_scalar_min_max_vals( - env, insn, dst_reg, *src_reg); - } - return rc; + return adjust_ptr_min_max_vals(env, insn, + dst_reg, src_reg); } } else { /* Pretend the src is a reg with a known value, since we only @@ -2283,17 +2338,9 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, off_reg.type = SCALAR_VALUE; __mark_reg_known(&off_reg, insn->imm); src_reg = &off_reg; - if (ptr_reg) { /* pointer += K */ - rc = adjust_ptr_min_max_vals(env, insn, - ptr_reg, src_reg); - if (rc == -EACCES && env->allow_ptr_leaks) { - /* unknown scalar += K */ - __mark_reg_unknown(dst_reg); - return adjust_scalar_min_max_vals( - env, insn, dst_reg, off_reg); - } - return rc; - } + if (ptr_reg) /* pointer += K */ + return adjust_ptr_min_max_vals(env, insn, + ptr_reg, src_reg); } /* Got here implies adding two SCALAR_VALUEs */ @@ -2390,17 +2437,20 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EACCES; } mark_reg_unknown(env, regs, insn->dst_reg); - /* high 32 bits are known zero. */ - regs[insn->dst_reg].var_off = tnum_cast( - regs[insn->dst_reg].var_off, 4); - __update_reg_bounds(®s[insn->dst_reg]); + coerce_reg_to_size(®s[insn->dst_reg], 4); } } else { /* case: R = imm * remember the value we stored into this reg */ regs[insn->dst_reg].type = SCALAR_VALUE; - __mark_reg_known(regs + insn->dst_reg, insn->imm); + if (BPF_CLASS(insn->code) == BPF_ALU64) { + __mark_reg_known(regs + insn->dst_reg, + insn->imm); + } else { + __mark_reg_known(regs + insn->dst_reg, + (u32)insn->imm); + } } } else if (opcode > BPF_END) { @@ -3431,15 +3481,14 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, return range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); } else { - /* if we knew anything about the old value, we're not - * equal, because we can't know anything about the - * scalar value of the pointer in the new value. + /* We're trying to use a pointer in place of a scalar. + * Even if the scalar was unbounded, this could lead to + * pointer leaks because scalars are allowed to leak + * while pointers are not. We could make this safe in + * special cases if root is calling us, but it's + * probably not worth the hassle. */ - return rold->umin_value == 0 && - rold->umax_value == U64_MAX && - rold->smin_value == S64_MIN && - rold->smax_value == S64_MAX && - tnum_is_unknown(rold->var_off); + return false; } case PTR_TO_MAP_VALUE: /* If the new min/max/var_off satisfy the old ones and diff --git a/kernel/cpu.c b/kernel/cpu.c index 41376c3ac93b..53f7dc65f9a3 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -80,19 +80,19 @@ static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); -static void inline cpuhp_lock_acquire(bool bringup) +static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } -static void inline cpuhp_lock_release(bool bringup) +static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else -static void inline cpuhp_lock_acquire(bool bringup) { } -static void inline cpuhp_lock_release(bool bringup) { } +static inline void cpuhp_lock_acquire(bool bringup) { } +static inline void cpuhp_lock_release(bool bringup) { } #endif @@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = { * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ - [CPUHP_TIMERS_DEAD] = { + [CPUHP_TIMERS_PREPARE] = { .name = "timers:dead", - .startup.single = NULL, + .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, /* Kicks the plugged cpu into life */ diff --git a/kernel/fork.c b/kernel/fork.c index 432eadf6b58c..2295fc69717f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -721,8 +721,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; } /* a new mm has just been created */ - arch_dup_mmap(oldmm, mm); - retval = 0; + retval = arch_dup_mmap(oldmm, mm); out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); diff --git a/kernel/irq/debug.h b/kernel/irq/debug.h index 17f05ef8f575..e4d3819a91cc 100644 --- a/kernel/irq/debug.h +++ b/kernel/irq/debug.h @@ -12,6 +12,11 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc) { + static DEFINE_RATELIMIT_STATE(ratelimit, 5 * HZ, 5); + + if (!__ratelimit(&ratelimit)) + return; + printk("irq %d, desc: %p, depth: %d, count: %d, unhandled: %d\n", irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled); printk("->handle_irq(): %p, ", desc->handle_irq); diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c index 7f608ac39653..acfaaef8672a 100644 --- a/kernel/irq/debugfs.c +++ b/kernel/irq/debugfs.c @@ -113,6 +113,7 @@ static const struct irq_bit_descr irqdata_states[] = { BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING), BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED), BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN), + BIT_MASK_DESCR(IRQD_CAN_RESERVE), BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU), diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index c26c5bb6b491..508c03dfef25 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -364,10 +364,11 @@ irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq) EXPORT_SYMBOL_GPL(irq_get_domain_generic_chip); /* - * Separate lockdep class for interrupt chip which can nest irq_desc - * lock. + * Separate lockdep classes for interrupt chip which can nest irq_desc + * lock and request mutex. */ static struct lock_class_key irq_nested_lock_class; +static struct lock_class_key irq_nested_request_class; /* * irq_map_generic_chip - Map a generic chip for an irq domain @@ -409,7 +410,8 @@ int irq_map_generic_chip(struct irq_domain *d, unsigned int virq, set_bit(idx, &gc->installed); if (dgc->gc_flags & IRQ_GC_INIT_NESTED_LOCK) - irq_set_lockdep_class(virq, &irq_nested_lock_class); + irq_set_lockdep_class(virq, &irq_nested_lock_class, + &irq_nested_request_class); if (chip->irq_calc_mask) chip->irq_calc_mask(data); @@ -479,7 +481,8 @@ void irq_setup_generic_chip(struct irq_chip_generic *gc, u32 msk, continue; if (flags & IRQ_GC_INIT_NESTED_LOCK) - irq_set_lockdep_class(i, &irq_nested_lock_class); + irq_set_lockdep_class(i, &irq_nested_lock_class, + &irq_nested_request_class); if (!(flags & IRQ_GC_NO_MASK)) { struct irq_data *d = irq_get_irq_data(i); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 07d08ca701ec..ab19371eab9b 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -440,7 +440,7 @@ static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear) #endif /* !CONFIG_GENERIC_PENDING_IRQ */ #if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY) -static inline int irq_domain_activate_irq(struct irq_data *data, bool early) +static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve) { irqd_set_activated(data); return 0; diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 4f4f60015e8a..62068ad46930 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -1693,7 +1693,7 @@ static void __irq_domain_deactivate_irq(struct irq_data *irq_data) } } -static int __irq_domain_activate_irq(struct irq_data *irqd, bool early) +static int __irq_domain_activate_irq(struct irq_data *irqd, bool reserve) { int ret = 0; @@ -1702,9 +1702,9 @@ static int __irq_domain_activate_irq(struct irq_data *irqd, bool early) if (irqd->parent_data) ret = __irq_domain_activate_irq(irqd->parent_data, - early); + reserve); if (!ret && domain->ops->activate) { - ret = domain->ops->activate(domain, irqd, early); + ret = domain->ops->activate(domain, irqd, reserve); /* Rollback in case of error */ if (ret && irqd->parent_data) __irq_domain_deactivate_irq(irqd->parent_data); @@ -1716,17 +1716,18 @@ static int __irq_domain_activate_irq(struct irq_data *irqd, bool early) /** * irq_domain_activate_irq - Call domain_ops->activate recursively to activate * interrupt - * @irq_data: outermost irq_data associated with interrupt + * @irq_data: Outermost irq_data associated with interrupt + * @reserve: If set only reserve an interrupt vector instead of assigning one * * This is the second step to call domain_ops->activate to program interrupt * controllers, so the interrupt could actually get delivered. */ -int irq_domain_activate_irq(struct irq_data *irq_data, bool early) +int irq_domain_activate_irq(struct irq_data *irq_data, bool reserve) { int ret = 0; if (!irqd_is_activated(irq_data)) - ret = __irq_domain_activate_irq(irq_data, early); + ret = __irq_domain_activate_irq(irq_data, reserve); if (!ret) irqd_set_activated(irq_data); return ret; diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index edb987b2c58d..2f3c4f5382cc 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -339,6 +339,40 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, return ret; } +/* + * Carefully check whether the device can use reservation mode. If + * reservation mode is enabled then the early activation will assign a + * dummy vector to the device. If the PCI/MSI device does not support + * masking of the entry then this can result in spurious interrupts when + * the device driver is not absolutely careful. But even then a malfunction + * of the hardware could result in a spurious interrupt on the dummy vector + * and render the device unusable. If the entry can be masked then the core + * logic will prevent the spurious interrupt and reservation mode can be + * used. For now reservation mode is restricted to PCI/MSI. + */ +static bool msi_check_reservation_mode(struct irq_domain *domain, + struct msi_domain_info *info, + struct device *dev) +{ + struct msi_desc *desc; + + if (domain->bus_token != DOMAIN_BUS_PCI_MSI) + return false; + + if (!(info->flags & MSI_FLAG_MUST_REACTIVATE)) + return false; + + if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_ignore_mask) + return false; + + /* + * Checking the first MSI descriptor is sufficient. MSIX supports + * masking and MSI does so when the maskbit is set. + */ + desc = first_msi_entry(dev); + return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit; +} + /** * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain * @domain: The domain to allocate from @@ -353,9 +387,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; - msi_alloc_info_t arg; + struct irq_data *irq_data; struct msi_desc *desc; + msi_alloc_info_t arg; int i, ret, virq; + bool can_reserve; ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg); if (ret) @@ -385,6 +421,8 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, if (ops->msi_finish) ops->msi_finish(&arg, 0); + can_reserve = msi_check_reservation_mode(domain, info, dev); + for_each_msi_entry(desc, dev) { virq = desc->irq; if (desc->nvec_used == 1) @@ -397,15 +435,25 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, * the MSI entries before the PCI layer enables MSI in the * card. Otherwise the card latches a random msi message. */ - if (info->flags & MSI_FLAG_ACTIVATE_EARLY) { - struct irq_data *irq_data; + if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) + continue; + irq_data = irq_domain_get_irq_data(domain, desc->irq); + if (!can_reserve) + irqd_clr_can_reserve(irq_data); + ret = irq_domain_activate_irq(irq_data, can_reserve); + if (ret) + goto cleanup; + } + + /* + * If these interrupts use reservation mode, clear the activated bit + * so request_irq() will assign the final vector. + */ + if (can_reserve) { + for_each_msi_entry(desc, dev) { irq_data = irq_domain_get_irq_data(domain, desc->irq); - ret = irq_domain_activate_irq(irq_data, true); - if (ret) - goto cleanup; - if (info->flags & MSI_FLAG_MUST_REACTIVATE) - irqd_clr_activated(irq_data); + irqd_clr_activated(irq_data); } } return 0; diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 2f52ec0f1539..d6717a3331a1 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -244,7 +244,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util, #ifdef CONFIG_NO_HZ_COMMON static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { - unsigned long idle_calls = tick_nohz_get_idle_calls(); + unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu); bool ret = idle_calls == sg_cpu->saved_idle_calls; sg_cpu->saved_idle_calls = idle_calls; diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index e776fc8cc1df..f6b5f19223d6 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -95,6 +95,7 @@ config NO_HZ_FULL select RCU_NOCB_CPU select VIRT_CPU_ACCOUNTING_GEN select IRQ_WORK + select CPU_ISOLATION help Adaptively try to shutdown the tick whenever possible, even when the CPU is running tasks. Typically this requires running a single diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 99578f06c8d4..f7cc7abfcf25 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -650,6 +650,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) ts->next_tick = 0; } +static inline bool local_timer_softirq_pending(void) +{ + return local_softirq_pending() & TIMER_SOFTIRQ; +} + static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ktime_t now, int cpu) { @@ -666,8 +671,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, } while (read_seqretry(&jiffies_lock, seq)); ts->last_jiffies = basejiff; - if (rcu_needs_cpu(basemono, &next_rcu) || - arch_needs_cpu() || irq_work_needs_cpu()) { + /* + * Keep the periodic tick, when RCU, architecture or irq_work + * requests it. + * Aside of that check whether the local timer softirq is + * pending. If so its a bad idea to call get_next_timer_interrupt() + * because there is an already expired timer, so it will request + * immeditate expiry, which rearms the hardware timer with a + * minimal delta which brings us back to this place + * immediately. Lather, rinse and repeat... + */ + if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() || + irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /* @@ -986,6 +1001,19 @@ ktime_t tick_nohz_get_sleep_length(void) } /** + * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value + * for a particular CPU. + * + * Called from the schedutil frequency scaling governor in scheduler context. + */ +unsigned long tick_nohz_get_idle_calls_cpu(int cpu) +{ + struct tick_sched *ts = tick_get_tick_sched(cpu); + + return ts->idle_calls; +} + +/** * tick_nohz_get_idle_calls - return the current idle calls counter value * * Called from the schedutil frequency scaling governor in scheduler context. diff --git a/kernel/time/timer.c b/kernel/time/timer.c index ffebcf878fba..89a9e1b4264a 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -823,11 +823,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); /* - * If the timer is deferrable and nohz is active then we need to use - * the deferrable base. + * If the timer is deferrable and NO_HZ_COMMON is set then we need + * to use the deferrable base. */ - if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active && - (tflags & TIMER_DEFERRABLE)) + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu); return base; } @@ -837,11 +836,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); /* - * If the timer is deferrable and nohz is active then we need to use - * the deferrable base. + * If the timer is deferrable and NO_HZ_COMMON is set then we need + * to use the deferrable base. */ - if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active && - (tflags & TIMER_DEFERRABLE)) + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE)) base = this_cpu_ptr(&timer_bases[BASE_DEF]); return base; } @@ -1009,8 +1007,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; - debug_activate(timer, expires); - new_base = get_target_base(base, timer->flags); if (base != new_base) { @@ -1034,6 +1030,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option } } + debug_activate(timer, expires); + timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance @@ -1684,7 +1682,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) base->must_forward_clk = false; __run_timers(base); - if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) + if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); } @@ -1855,6 +1853,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h } } +int timers_prepare_cpu(unsigned int cpu) +{ + struct timer_base *base; + int b; + + for (b = 0; b < NR_BASES; b++) { + base = per_cpu_ptr(&timer_bases[b], cpu); + base->clk = jiffies; + base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA; + base->is_idle = false; + base->must_forward_clk = true; + } + return 0; +} + int timers_dead_cpu(unsigned int cpu) { struct timer_base *old_base; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c87766c1c204..9ab18995ff1e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -280,6 +280,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data); /* Missed count stored at end */ #define RB_MISSED_STORED (1 << 30) +#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED) + struct buffer_data_page { u64 time_stamp; /* page time stamp */ local_t commit; /* write committed index */ @@ -331,7 +333,9 @@ static void rb_init_page(struct buffer_data_page *bpage) */ size_t ring_buffer_page_len(void *page) { - return local_read(&((struct buffer_data_page *)page)->commit) + struct buffer_data_page *bpage = page; + + return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS) + BUF_PAGE_HDR_SIZE; } @@ -4400,8 +4404,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) { struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; struct buffer_data_page *bpage = data; + struct page *page = virt_to_page(bpage); unsigned long flags; + /* If the page is still in use someplace else, we can't reuse it */ + if (page_ref_count(page) > 1) + goto out; + local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); @@ -4413,6 +4422,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data) arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags); + out: free_page((unsigned long)bpage); } EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 59518b8126d0..2a8d8a294345 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6769,7 +6769,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; - int entries, size, i; + int entries, i; ssize_t ret = 0; #ifdef CONFIG_TRACER_MAX_TRACE @@ -6823,14 +6823,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - /* - * zero out any left over data, this is going to - * user land. - */ - size = ring_buffer_page_len(ref->page); - if (size < PAGE_SIZE) - memset(ref->page + size, 0, PAGE_SIZE - size); - page = virt_to_page(ref->page); spd.pages[i] = page; @@ -7588,6 +7580,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size buf->data = alloc_percpu(struct trace_array_cpu); if (!buf->data) { ring_buffer_free(buf->buffer); + buf->buffer = NULL; return -ENOMEM; } @@ -7611,7 +7604,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) allocate_snapshot ? size : 1); if (WARN_ON(ret)) { ring_buffer_free(tr->trace_buffer.buffer); + tr->trace_buffer.buffer = NULL; free_percpu(tr->trace_buffer.data); + tr->trace_buffer.data = NULL; return -ENOMEM; } tr->allocated_snapshot = allocate_snapshot; diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index c3e84edc47c9..2615074d3de5 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -346,7 +346,8 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj, static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; - int i; + size_t len; + int i, j; for (i = 0; i < env->envp_idx;) { if (strncmp(env->envp[i], modalias_prefix, @@ -355,11 +356,18 @@ static void zap_modalias_env(struct kobj_uevent_env *env) continue; } - if (i != env->envp_idx - 1) - memmove(&env->envp[i], &env->envp[i + 1], - sizeof(env->envp[i]) * env->envp_idx - 1); + len = strlen(env->envp[i]) + 1; + + if (i != env->envp_idx - 1) { + memmove(env->envp[i], env->envp[i + 1], + env->buflen - len); + + for (j = i; j < env->envp_idx - 1; j++) + env->envp[j] = env->envp[j + 1] - len; + } env->envp_idx--; + env->buflen -= len; } } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index aa8812ae6776..9e9748089270 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -435,6 +435,41 @@ loop: return 0; } +static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self) +{ + struct bpf_insn *insn; + + insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL); + if (!insn) + return -ENOMEM; + + /* Due to func address being non-const, we need to + * assemble this here. + */ + insn[0] = BPF_MOV64_REG(R6, R1); + insn[1] = BPF_LD_ABS(BPF_B, 0); + insn[2] = BPF_LD_ABS(BPF_H, 0); + insn[3] = BPF_LD_ABS(BPF_W, 0); + insn[4] = BPF_MOV64_REG(R7, R6); + insn[5] = BPF_MOV64_IMM(R6, 0); + insn[6] = BPF_MOV64_REG(R1, R7); + insn[7] = BPF_MOV64_IMM(R2, 1); + insn[8] = BPF_MOV64_IMM(R3, 2); + insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + bpf_skb_vlan_push_proto.func - __bpf_call_base); + insn[10] = BPF_MOV64_REG(R6, R7); + insn[11] = BPF_LD_ABS(BPF_B, 0); + insn[12] = BPF_LD_ABS(BPF_H, 0); + insn[13] = BPF_LD_ABS(BPF_W, 0); + insn[14] = BPF_MOV64_IMM(R0, 42); + insn[15] = BPF_EXIT_INSN(); + + self->u.ptr.insns = insn; + self->u.ptr.len = 16; + + return 0; +} + static int bpf_fill_jump_around_ld_abs(struct bpf_test *self) { unsigned int len = BPF_MAXINSNS; @@ -6066,6 +6101,14 @@ static struct bpf_test tests[] = { {}, { {0x1, 0x42 } }, }, + { + "LD_ABS with helper changing skb data", + { }, + INTERNAL, + { 0x34 }, + { { ETH_HLEN, 42 } }, + .fill_helper = bpf_fill_ld_abs_vlan_push_pop2, + }, }; static struct net_device dev; diff --git a/lib/timerqueue.c b/lib/timerqueue.c index 4a720ed4fdaf..0d54bcbc8170 100644 --- a/lib/timerqueue.c +++ b/lib/timerqueue.c @@ -33,8 +33,9 @@ * @head: head of timerqueue * @node: timer node to be added * - * Adds the timer node to the timerqueue, sorted by the - * node's expires value. + * Adds the timer node to the timerqueue, sorted by the node's expires + * value. Returns true if the newly added timer is the first expiring timer in + * the queue. */ bool timerqueue_add(struct timerqueue_head *head, struct timerqueue_node *node) { @@ -70,7 +71,8 @@ EXPORT_SYMBOL_GPL(timerqueue_add); * @head: head of timerqueue * @node: timer node to be removed * - * Removes the timer node from the timerqueue. + * Removes the timer node from the timerqueue. Returns true if the queue is + * not empty after the remove. */ bool timerqueue_del(struct timerqueue_head *head, struct timerqueue_node *node) { diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 84b2dc76f140..b5f940ce0143 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -882,13 +882,10 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (IS_ERR(dev)) return PTR_ERR(dev); - if (bdi_debug_register(bdi, dev_name(dev))) { - device_destroy(bdi_class, dev->devt); - return -ENOMEM; - } cgwb_bdi_register(bdi); bdi->dev = dev; + bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d0ef0a8e8831..015f465c514b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1262,19 +1262,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev, struct net_bridge *br = netdev_priv(dev); int err; + err = register_netdevice(dev); + if (err) + return err; + if (tb[IFLA_ADDRESS]) { spin_lock_bh(&br->lock); br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS])); spin_unlock_bh(&br->lock); } - err = register_netdevice(dev); - if (err) - return err; - err = br_changelink(dev, tb, data, extack); if (err) - unregister_netdevice(dev); + br_dev_delete(dev, NULL); + return err; } diff --git a/net/core/dev.c b/net/core/dev.c index f47e96b62308..01ee854454a8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3904,7 +3904,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC)) goto do_drop; - if (troom > 0 && __skb_linearize(skb)) + if (skb_linearize(skb)) goto do_drop; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b797832565d3..60a71be75aea 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -267,7 +267,7 @@ struct net *get_net_ns_by_id(struct net *net, int id) spin_lock_bh(&net->nsid_lock); peer = idr_find(&net->netns_ids, id); if (peer) - get_net(peer); + peer = maybe_get_net(peer); spin_unlock_bh(&net->nsid_lock); rcu_read_unlock(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a592ca025fc4..08f574081315 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1177,12 +1177,12 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) int i, new_frags; u32 d_off; - if (!num_frags) - return 0; - if (skb_shared(skb) || skb_unclone(skb, gfp_mask)) return -EINVAL; + if (!num_frags) + goto release; + new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < new_frags; i++) { page = alloc_page(gfp_mask); @@ -1238,6 +1238,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) __skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off); skb_shinfo(skb)->nr_frags = new_frags; +release: skb_zcopy_clear(skb, false); return 0; } @@ -3654,8 +3655,6 @@ normal: skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags & SKBTX_SHARED_FRAG; - if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC)) - goto err; while (pos < offset + len) { if (i >= nfrags) { @@ -3681,6 +3680,8 @@ normal: if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC))) goto err; + if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) + goto err; *nskb_frag = *frag; __skb_frag_ref(nskb_frag); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index f52d27a422c3..08259d078b1c 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1298,14 +1298,19 @@ err_table_hash_alloc: static void ip_fib_net_exit(struct net *net) { - unsigned int i; + int i; rtnl_lock(); #ifdef CONFIG_IP_MULTIPLE_TABLES RCU_INIT_POINTER(net->ipv4.fib_main, NULL); RCU_INIT_POINTER(net->ipv4.fib_default, NULL); #endif - for (i = 0; i < FIB_TABLE_HASHSZ; i++) { + /* Destroy the tables in reverse order to guarantee that the + * local table, ID 255, is destroyed before the main table, ID + * 254. This is necessary as the local table may contain + * references to data contained in the main table. + */ + for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) { struct hlist_head *head = &net->ipv4.fib_table_hash[i]; struct hlist_node *tmp; struct fib_table *tb; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f04d944f8abe..c586597da20d 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -698,7 +698,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { int type = nla_type(nla); - u32 val; + u32 fi_val, val; if (!type) continue; @@ -715,7 +715,11 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) val = nla_get_u32(nla); } - if (fi->fib_metrics->metrics[type - 1] != val) + fi_val = fi->fib_metrics->metrics[type - 1]; + if (type == RTAX_FEATURES) + fi_val &= ~DST_FEATURE_ECN_CA; + + if (fi_val != val) return false; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9c1735632c8c..45ffd3d045d2 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1310,6 +1310,7 @@ static const struct net_device_ops erspan_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index e50b7fea57ee..bcfc00e88756 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -23,6 +23,12 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) return xfrm4_extract_header(skb); } +static int xfrm4_rcv_encap_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return dst_input(skb); +} + static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { @@ -33,7 +39,11 @@ static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, iph->tos, skb->dev)) goto drop; } - return dst_input(skb); + + if (xfrm_trans_queue(skb, xfrm4_rcv_encap_finish2)) + goto drop; + + return 0; drop: kfree_skb(skb); return NET_RX_DROP; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c26f71234b9c..c9441ca45399 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -210,7 +210,6 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->autoflowlabel = ip6_default_np_autolabel(net); np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4cfd8e0696fe..772695960890 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1014,6 +1014,36 @@ static void ip6gre_tunnel_setup(struct net_device *dev) eth_random_addr(dev->perm_addr); } +#define GRE6_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_HW_CSUM) + +static void ip6gre_tnl_init_features(struct net_device *dev) +{ + struct ip6_tnl *nt = netdev_priv(dev); + + dev->features |= GRE6_FEATURES; + dev->hw_features |= GRE6_FEATURES; + + if (!(nt->parms.o_flags & TUNNEL_SEQ)) { + /* TCP offload with GRE SEQ is not supported, nor + * can we support 2 levels of outer headers requiring + * an update. + */ + if (!(nt->parms.o_flags & TUNNEL_CSUM) || + nt->encap.type == TUNNEL_ENCAP_NONE) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } + + /* Can use a lockless transmit, unless we generate + * output sequences + */ + dev->features |= NETIF_F_LLTX; + } +} + static int ip6gre_tunnel_init_common(struct net_device *dev) { struct ip6_tnl *tunnel; @@ -1048,6 +1078,8 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; + ip6gre_tnl_init_features(dev); + return 0; } @@ -1298,16 +1330,12 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = { .ndo_get_iflink = ip6_tnl_get_iflink, }; -#define GRE6_FEATURES (NETIF_F_SG | \ - NETIF_F_FRAGLIST | \ - NETIF_F_HIGHDMA | \ - NETIF_F_HW_CSUM) - static void ip6gre_tap_setup(struct net_device *dev) { ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &ip6gre_tap_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; @@ -1382,26 +1410,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev, nt->net = dev_net(dev); ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]); - dev->features |= GRE6_FEATURES; - dev->hw_features |= GRE6_FEATURES; - - if (!(nt->parms.o_flags & TUNNEL_SEQ)) { - /* TCP offload with GRE SEQ is not supported, nor - * can we support 2 levels of outer headers requiring - * an update. - */ - if (!(nt->parms.o_flags & TUNNEL_CSUM) || - (nt->encap.type == TUNNEL_ENCAP_NONE)) { - dev->features |= NETIF_F_GSO_SOFTWARE; - dev->hw_features |= NETIF_F_GSO_SOFTWARE; - } - - /* Can use a lockless transmit, unless we generate - * output sequences - */ - dev->features |= NETIF_F_LLTX; - } - err = register_netdevice(dev); if (err) goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5110a418cc4d..f7dd51c42314 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } +static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +{ + if (!np->autoflowlabel_set) + return ip6_default_np_autolabel(net); + else + return np->autoflowlabel; +} + /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified @@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index db84f523656d..931c38f6ff4a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1123,8 +1123,13 @@ route_lookup: max_headroom += 8; mtu -= 8; } - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + } else if (mtu < 576) { + mtu = 576; + } + if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index b9404feabd78..2d4680e0376f 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -886,6 +886,7 @@ pref_skip_coa: break; case IPV6_AUTOFLOWLABEL: np->autoflowlabel = valbool; + np->autoflowlabel_set = 1; retv = 0; break; case IPV6_RECVFRAGSIZE: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7a8d1500d374..0458b761f3c5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2336,6 +2336,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, } rt->dst.flags |= DST_HOST; + rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; @@ -4297,19 +4298,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - if (!fibmatch) - dst = ip6_route_input_lookup(net, dev, &fl6, flags); - else - dst = ip6_route_lookup(net, &fl6, 0); + dst = ip6_route_input_lookup(net, dev, &fl6, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; - if (!fibmatch) - dst = ip6_route_output(net, NULL, &fl6); - else - dst = ip6_route_lookup(net, &fl6, 0); + dst = ip6_route_output(net, NULL, &fl6); } @@ -4326,6 +4321,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout; } + if (fibmatch && rt->dst.from) { + struct rt6_info *ort = container_of(rt->dst.from, + struct rt6_info, dst); + + dst_hold(&ort->dst); + ip6_rt_put(rt); + rt = ort; + } + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index fe04e23af986..841f4a07438e 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -32,6 +32,14 @@ int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, } EXPORT_SYMBOL(xfrm6_rcv_spi); +static int xfrm6_transport_finish2(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + if (xfrm_trans_queue(skb, ip6_rcv_finish)) + __kfree_skb(skb); + return -1; +} + int xfrm6_transport_finish(struct sk_buff *skb, int async) { struct xfrm_offload *xo = xfrm_offload(skb); @@ -56,7 +64,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, dev_net(skb->dev), NULL, skb, skb->dev, NULL, - ip6_rcv_finish); + xfrm6_transport_finish2); return -1; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index dbe2379329c5..f039064ce922 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -579,6 +579,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) return -EINVAL; skb_reset_network_header(skb); + key->eth.type = skb->protocol; } else { eth = eth_hdr(skb); ether_addr_copy(key->eth.src, eth->h_source); @@ -592,15 +593,23 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key) if (unlikely(parse_vlan(skb, key))) return -ENOMEM; - skb->protocol = parse_ethertype(skb); - if (unlikely(skb->protocol == htons(0))) + key->eth.type = parse_ethertype(skb); + if (unlikely(key->eth.type == htons(0))) return -ENOMEM; + /* Multiple tagged packets need to retain TPID to satisfy + * skb_vlan_pop(), which will later shift the ethertype into + * skb->protocol. + */ + if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT)) + skb->protocol = key->eth.cvlan.tpid; + else + skb->protocol = key->eth.type; + skb_reset_network_header(skb); __skb_push(skb, skb->data - skb_mac_header(skb)); } skb_reset_mac_len(skb); - key->eth.type = skb->protocol; /* Network layer. */ if (key->eth.type == htons(ETH_P_IP)) { diff --git a/net/rds/send.c b/net/rds/send.c index b52cdc8ae428..f72466c63f0c 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1009,6 +1009,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes) continue; if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) { + if (cmsg->cmsg_len < + CMSG_LEN(sizeof(struct rds_rdma_args))) + return -EINVAL; args = CMSG_DATA(cmsg); *rdma_bytes += args->remote_vec.bytes; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b91ea03e3afa..b9d63d2246e6 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -379,6 +379,8 @@ void tcf_block_put(struct tcf_block *block) { struct tcf_block_ext_info ei = {0, }; + if (!block) + return; tcf_block_put_ext(block, block->q, &ei); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 6fe798c2df1a..8d78e7f4ecc3 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -42,7 +42,6 @@ struct cls_bpf_prog { struct list_head link; struct tcf_result res; bool exts_integrated; - bool offloaded; u32 gen_flags; struct tcf_exts exts; u32 handle; @@ -148,33 +147,37 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog) } static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, - enum tc_clsbpf_command cmd) + struct cls_bpf_prog *oldprog) { - bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE; struct tcf_block *block = tp->chain->block; - bool skip_sw = tc_skip_sw(prog->gen_flags); struct tc_cls_bpf_offload cls_bpf = {}; + struct cls_bpf_prog *obj; + bool skip_sw; int err; + skip_sw = prog && tc_skip_sw(prog->gen_flags); + obj = prog ?: oldprog; + tc_cls_common_offload_init(&cls_bpf.common, tp); - cls_bpf.command = cmd; - cls_bpf.exts = &prog->exts; - cls_bpf.prog = prog->filter; - cls_bpf.name = prog->bpf_name; - cls_bpf.exts_integrated = prog->exts_integrated; - cls_bpf.gen_flags = prog->gen_flags; + cls_bpf.command = TC_CLSBPF_OFFLOAD; + cls_bpf.exts = &obj->exts; + cls_bpf.prog = prog ? prog->filter : NULL; + cls_bpf.oldprog = oldprog ? oldprog->filter : NULL; + cls_bpf.name = obj->bpf_name; + cls_bpf.exts_integrated = obj->exts_integrated; + cls_bpf.gen_flags = obj->gen_flags; err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw); - if (addorrep) { + if (prog) { if (err < 0) { - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); + cls_bpf_offload_cmd(tp, oldprog, prog); return err; } else if (err > 0) { prog->gen_flags |= TCA_CLS_FLAGS_IN_HW; } } - if (addorrep && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) + if (prog && skip_sw && !(prog->gen_flags & TCA_CLS_FLAGS_IN_HW)) return -EINVAL; return 0; @@ -183,38 +186,17 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog, static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog, struct cls_bpf_prog *oldprog) { - struct cls_bpf_prog *obj = prog; - enum tc_clsbpf_command cmd; - bool skip_sw; - int ret; - - skip_sw = tc_skip_sw(prog->gen_flags) || - (oldprog && tc_skip_sw(oldprog->gen_flags)); - - if (oldprog && oldprog->offloaded) { - if (!tc_skip_hw(prog->gen_flags)) { - cmd = TC_CLSBPF_REPLACE; - } else if (!tc_skip_sw(prog->gen_flags)) { - obj = oldprog; - cmd = TC_CLSBPF_DESTROY; - } else { - return -EINVAL; - } - } else { - if (tc_skip_hw(prog->gen_flags)) - return skip_sw ? -EINVAL : 0; - cmd = TC_CLSBPF_ADD; - } - - ret = cls_bpf_offload_cmd(tp, obj, cmd); - if (ret) - return ret; + if (prog && oldprog && prog->gen_flags != oldprog->gen_flags) + return -EINVAL; - obj->offloaded = true; - if (oldprog) - oldprog->offloaded = false; + if (prog && tc_skip_hw(prog->gen_flags)) + prog = NULL; + if (oldprog && tc_skip_hw(oldprog->gen_flags)) + oldprog = NULL; + if (!prog && !oldprog) + return 0; - return 0; + return cls_bpf_offload_cmd(tp, prog, oldprog); } static void cls_bpf_stop_offload(struct tcf_proto *tp, @@ -222,25 +204,26 @@ static void cls_bpf_stop_offload(struct tcf_proto *tp, { int err; - if (!prog->offloaded) - return; - - err = cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY); - if (err) { + err = cls_bpf_offload_cmd(tp, NULL, prog); + if (err) pr_err("Stopping hardware offload failed: %d\n", err); - return; - } - - prog->offloaded = false; } static void cls_bpf_offload_update_stats(struct tcf_proto *tp, struct cls_bpf_prog *prog) { - if (!prog->offloaded) - return; + struct tcf_block *block = tp->chain->block; + struct tc_cls_bpf_offload cls_bpf = {}; + + tc_cls_common_offload_init(&cls_bpf.common, tp); + cls_bpf.command = TC_CLSBPF_STATS; + cls_bpf.exts = &prog->exts; + cls_bpf.prog = prog->filter; + cls_bpf.name = prog->bpf_name; + cls_bpf.exts_integrated = prog->exts_integrated; + cls_bpf.gen_flags = prog->gen_flags; - cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_STATS); + tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, false); } static int cls_bpf_init(struct tcf_proto *tp) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index cd1b200acae7..661c7144b53a 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1040,6 +1040,8 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, if (!tp_head) { RCU_INIT_POINTER(*miniqp->p_miniq, NULL); + /* Wait for flying RCU callback before it is freed. */ + rcu_barrier_bh(); return; } @@ -1055,7 +1057,7 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, rcu_assign_pointer(*miniqp->p_miniq, miniq); if (miniq_old) - /* This is counterpart of the rcu barrier above. We need to + /* This is counterpart of the rcu barriers above. We need to * block potential new user of miniq_old until all readers * are not seeing it. */ diff --git a/net/sctp/debug.c b/net/sctp/debug.c index 3f619fdcbf0a..291c97b07058 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -78,6 +78,9 @@ const char *sctp_cname(const union sctp_subtype cid) case SCTP_CID_AUTH: return "AUTH"; + case SCTP_CID_RECONF: + return "RECONF"; + default: break; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 3253f724a995..b4fb6e4886d2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4498,7 +4498,7 @@ static int sctp_init_sock(struct sock *sk) SCTP_DBG_OBJCNT_INC(sock); local_bh_disable(); - percpu_counter_inc(&sctp_sockets_allocated); + sk_sockets_allocated_inc(sk); sock_prot_inuse_add(net, sk->sk_prot, 1); /* Nothing can fail after this block, otherwise @@ -4542,7 +4542,7 @@ static void sctp_destroy_sock(struct sock *sk) } sctp_endpoint_free(sp->ep); local_bh_disable(); - percpu_counter_dec(&sctp_sockets_allocated); + sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); } diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index a71be33f3afe..e36ec5dd64c6 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -1084,29 +1084,21 @@ void sctp_ulpq_partial_delivery(struct sctp_ulpq *ulpq, void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, gfp_t gfp) { - struct sctp_association *asoc; - __u16 needed, freed; - - asoc = ulpq->asoc; + struct sctp_association *asoc = ulpq->asoc; + __u32 freed = 0; + __u16 needed; - if (chunk) { - needed = ntohs(chunk->chunk_hdr->length); - needed -= sizeof(struct sctp_data_chunk); - } else - needed = SCTP_DEFAULT_MAXWINDOW; - - freed = 0; + needed = ntohs(chunk->chunk_hdr->length) - + sizeof(struct sctp_data_chunk); if (skb_queue_empty(&asoc->base.sk->sk_receive_queue)) { freed = sctp_ulpq_renege_order(ulpq, needed); - if (freed < needed) { + if (freed < needed) freed += sctp_ulpq_renege_frags(ulpq, needed - freed); - } } /* If able to free enough room, accept this chunk. */ - if (chunk && (freed >= needed)) { - int retval; - retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); + if (freed >= needed) { + int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp); /* * Enter partial delivery if chunk has not been * delivered; otherwise, drain the reassembly queue. diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index c5fda15ba319..1fdab5c4eda8 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -401,7 +401,7 @@ void strp_data_ready(struct strparser *strp) * allows a thread in BH context to safely check if the process * lock is held. In this case, if the lock is held, queue work. */ - if (sock_owned_by_user(strp->sk)) { + if (sock_owned_by_user_nocheck(strp->sk)) { queue_work(strp_wq, &strp->work); return; } diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 47ec121574ce..c8001471da6c 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -324,6 +324,7 @@ restart: if (res) { pr_warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); + kfree(b); return -EINVAL; } @@ -347,8 +348,10 @@ restart: if (skb) tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); - if (tipc_mon_create(net, bearer_id)) + if (tipc_mon_create(net, bearer_id)) { + bearer_disable(net, b); return -ENOMEM; + } pr_info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name, diff --git a/net/tipc/group.c b/net/tipc/group.c index 95fec2c057d6..8e12ab55346b 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -351,8 +351,7 @@ void tipc_group_update_member(struct tipc_member *m, int len) if (m->window >= ADV_IDLE) return; - if (!list_empty(&m->congested)) - return; + list_del_init(&m->congested); /* Sort member into congested members' list */ list_for_each_entry_safe(_m, tmp, &grp->congested, congested) { @@ -369,18 +368,20 @@ void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) u16 prev = grp->bc_snd_nxt - 1; struct tipc_member *m; struct rb_node *n; + u16 ackers = 0; for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); if (tipc_group_is_enabled(m)) { tipc_group_update_member(m, len); m->bc_acked = prev; + ackers++; } } /* Mark number of acknowledges to expect, if any */ if (ack) - grp->bc_ackers = grp->member_cnt; + grp->bc_ackers = ackers; grp->bc_snd_nxt++; } @@ -648,6 +649,7 @@ static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, } else if (mtyp == GRP_REMIT_MSG) { msg_set_grp_remitted(hdr, m->window); } + msg_set_dest_droppable(hdr, true); __skb_queue_tail(xmitq, skb); } @@ -689,15 +691,16 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); } - if (m->window < ADV_IDLE) - tipc_group_update_member(m, 0); - else - list_del_init(&m->congested); + list_del_init(&m->congested); + tipc_group_update_member(m, 0); return; case GRP_LEAVE_MSG: if (!m) return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); + list_del_init(&m->list); + list_del_init(&m->congested); + *usr_wakeup = true; /* Wait until WITHDRAW event is received */ if (m->state != MBR_LEAVING) { @@ -709,8 +712,6 @@ void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, ehdr = buf_msg(m->event_msg); msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); - *usr_wakeup = true; - list_del_init(&m->congested); return; case GRP_ADV_MSG: if (!m) @@ -849,19 +850,29 @@ void tipc_group_member_evt(struct tipc_group *grp, *usr_wakeup = true; m->usr_pending = false; node_up = tipc_node_is_up(net, node); - - /* Hold back event if more messages might be expected */ - if (m->state != MBR_LEAVING && node_up) { - m->event_msg = skb; - tipc_group_decr_active(grp, m); - m->state = MBR_LEAVING; - } else { - if (node_up) + m->event_msg = NULL; + + if (node_up) { + /* Hold back event if a LEAVE msg should be expected */ + if (m->state != MBR_LEAVING) { + m->event_msg = skb; + tipc_group_decr_active(grp, m); + m->state = MBR_LEAVING; + } else { msg_set_grp_bc_seqno(hdr, m->bc_syncpt); - else + __skb_queue_tail(inputq, skb); + } + } else { + if (m->state != MBR_LEAVING) { + tipc_group_decr_active(grp, m); + m->state = MBR_LEAVING; msg_set_grp_bc_seqno(hdr, m->bc_rcv_nxt); + } else { + msg_set_grp_bc_seqno(hdr, m->bc_syncpt); + } __skb_queue_tail(inputq, skb); } + list_del_init(&m->list); list_del_init(&m->congested); } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 8e884ed06d4b..32dc33a94bc7 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -642,9 +642,13 @@ void tipc_mon_delete(struct net *net, int bearer_id) { struct tipc_net *tn = tipc_net(net); struct tipc_monitor *mon = tipc_monitor(net, bearer_id); - struct tipc_peer *self = get_self(net, bearer_id); + struct tipc_peer *self; struct tipc_peer *peer, *tmp; + if (!mon) + return; + + self = get_self(net, bearer_id); write_lock_bh(&mon->lock); tn->monitors[bearer_id] = NULL; list_for_each_entry_safe(peer, tmp, &self->list, list) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 41127d0b925e..3b4084480377 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -727,11 +727,11 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock, switch (sk->sk_state) { case TIPC_ESTABLISHED: + case TIPC_CONNECTING: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) revents |= POLLOUT; /* fall thru' */ case TIPC_LISTEN: - case TIPC_CONNECTING: if (!skb_queue_empty(&sk->sk_receive_queue)) revents |= POLLIN | POLLRDNORM; break; diff --git a/net/wireless/Makefile b/net/wireless/Makefile index d7d6cb00c47b..1d84f91bbfb0 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -23,27 +23,14 @@ ifneq ($(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR),) cfg80211-y += extra-certs.o endif -$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.x509) +$(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" - @(set -e; \ - allf=""; \ - for f in $^ ; do \ - # similar to hexdump -v -e '1/1 "0x%.2x," "\n"' \ - thisf=$$(od -An -v -tx1 < $$f | \ - sed -e 's/ /\n/g' | \ - sed -e 's/^[0-9a-f]\+$$/\0/;t;d' | \ - sed -e 's/^/0x/;s/$$/,/'); \ - # file should not be empty - maybe command substitution failed? \ - test ! -z "$$thisf";\ - allf=$$allf$$thisf;\ - done; \ - ( \ - echo '#include "reg.h"'; \ - echo 'const u8 shipped_regdb_certs[] = {'; \ - echo "$$allf"; \ - echo '};'; \ - echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ - ) >> $@) + @(echo '#include "reg.h"'; \ + echo 'const u8 shipped_regdb_certs[] = {'; \ + cat $^ ; \ + echo '};'; \ + echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ + ) > $@ $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%)/*.x509) @@ -66,4 +53,6 @@ $(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR:"%"=%) \ echo "$$allf"; \ echo '};'; \ echo 'unsigned int extra_regdb_certs_len = sizeof(extra_regdb_certs);'; \ - ) >> $@) + ) > $@) + +clean-files += shipped-certs.c extra-certs.c diff --git a/net/wireless/certs/sforshee.hex b/net/wireless/certs/sforshee.hex new file mode 100644 index 000000000000..14ea66643ffa --- /dev/null +++ b/net/wireless/certs/sforshee.hex @@ -0,0 +1,86 @@ +/* Seth Forshee's regdb certificate */ +0x30, 0x82, 0x02, 0xa4, 0x30, 0x82, 0x01, 0x8c, +0x02, 0x09, 0x00, 0xb2, 0x8d, 0xdf, 0x47, 0xae, +0xf9, 0xce, 0xa7, 0x30, 0x0d, 0x06, 0x09, 0x2a, +0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, 0x01, 0x0b, +0x05, 0x00, 0x30, 0x13, 0x31, 0x11, 0x30, 0x0f, +0x06, 0x03, 0x55, 0x04, 0x03, 0x0c, 0x08, 0x73, +0x66, 0x6f, 0x72, 0x73, 0x68, 0x65, 0x65, 0x30, +0x20, 0x17, 0x0d, 0x31, 0x37, 0x31, 0x30, 0x30, +0x36, 0x31, 0x39, 0x34, 0x30, 0x33, 0x35, 0x5a, +0x18, 0x0f, 0x32, 0x31, 0x31, 0x37, 0x30, 0x39, +0x31, 0x32, 0x31, 0x39, 0x34, 0x30, 0x33, 0x35, +0x5a, 0x30, 0x13, 0x31, 0x11, 0x30, 0x0f, 0x06, +0x03, 0x55, 0x04, 0x03, 0x0c, 0x08, 0x73, 0x66, +0x6f, 0x72, 0x73, 0x68, 0x65, 0x65, 0x30, 0x82, +0x01, 0x22, 0x30, 0x0d, 0x06, 0x09, 0x2a, 0x86, +0x48, 0x86, 0xf7, 0x0d, 0x01, 0x01, 0x01, 0x05, +0x00, 0x03, 0x82, 0x01, 0x0f, 0x00, 0x30, 0x82, +0x01, 0x0a, 0x02, 0x82, 0x01, 0x01, 0x00, 0xb5, +0x40, 0xe3, 0x9c, 0x28, 0x84, 0x39, 0x03, 0xf2, +0x39, 0xd7, 0x66, 0x2c, 0x41, 0x38, 0x15, 0xac, +0x7e, 0xa5, 0x83, 0x71, 0x25, 0x7e, 0x90, 0x7c, +0x68, 0xdd, 0x6f, 0x3f, 0xd9, 0xd7, 0x59, 0x38, +0x9f, 0x7c, 0x6a, 0x52, 0xc2, 0x03, 0x2a, 0x2d, +0x7e, 0x66, 0xf4, 0x1e, 0xb3, 0x12, 0x70, 0x20, +0x5b, 0xd4, 0x97, 0x32, 0x3d, 0x71, 0x8b, 0x3b, +0x1b, 0x08, 0x17, 0x14, 0x6b, 0x61, 0xc4, 0x57, +0x8b, 0x96, 0x16, 0x1c, 0xfd, 0x24, 0xd5, 0x0b, +0x09, 0xf9, 0x68, 0x11, 0x84, 0xfb, 0xca, 0x51, +0x0c, 0xd1, 0x45, 0x19, 0xda, 0x10, 0x44, 0x8a, +0xd9, 0xfe, 0x76, 0xa9, 0xfd, 0x60, 0x2d, 0x18, +0x0b, 0x28, 0x95, 0xb2, 0x2d, 0xea, 0x88, 0x98, +0xb8, 0xd1, 0x56, 0x21, 0xf0, 0x53, 0x1f, 0xf1, +0x02, 0x6f, 0xe9, 0x46, 0x9b, 0x93, 0x5f, 0x28, +0x90, 0x0f, 0xac, 0x36, 0xfa, 0x68, 0x23, 0x71, +0x57, 0x56, 0xf6, 0xcc, 0xd3, 0xdf, 0x7d, 0x2a, +0xd9, 0x1b, 0x73, 0x45, 0xeb, 0xba, 0x27, 0x85, +0xef, 0x7a, 0x7f, 0xa5, 0xcb, 0x80, 0xc7, 0x30, +0x36, 0xd2, 0x53, 0xee, 0xec, 0xac, 0x1e, 0xe7, +0x31, 0xf1, 0x36, 0xa2, 0x9c, 0x63, 0xc6, 0x65, +0x5b, 0x7f, 0x25, 0x75, 0x68, 0xa1, 0xea, 0xd3, +0x7e, 0x00, 0x5c, 0x9a, 0x5e, 0xd8, 0x20, 0x18, +0x32, 0x77, 0x07, 0x29, 0x12, 0x66, 0x1e, 0x36, +0x73, 0xe7, 0x97, 0x04, 0x41, 0x37, 0xb1, 0xb1, +0x72, 0x2b, 0xf4, 0xa1, 0x29, 0x20, 0x7c, 0x96, +0x79, 0x0b, 0x2b, 0xd0, 0xd8, 0xde, 0xc8, 0x6c, +0x3f, 0x93, 0xfb, 0xc5, 0xee, 0x78, 0x52, 0x11, +0x15, 0x1b, 0x7a, 0xf6, 0xe2, 0x68, 0x99, 0xe7, +0xfb, 0x46, 0x16, 0x84, 0xe3, 0xc7, 0xa1, 0xe6, +0xe0, 0xd2, 0x46, 0xd5, 0xe1, 0xc4, 0x5f, 0xa0, +0x66, 0xf4, 0xda, 0xc4, 0xff, 0x95, 0x1d, 0x02, +0x03, 0x01, 0x00, 0x01, 0x30, 0x0d, 0x06, 0x09, +0x2a, 0x86, 0x48, 0x86, 0xf7, 0x0d, 0x01, 0x01, +0x0b, 0x05, 0x00, 0x03, 0x82, 0x01, 0x01, 0x00, +0x87, 0x03, 0xda, 0xf2, 0x82, 0xc2, 0xdd, 0xaf, +0x7c, 0x44, 0x2f, 0x86, 0xd3, 0x5f, 0x4c, 0x93, +0x48, 0xb9, 0xfe, 0x07, 0x17, 0xbb, 0x21, 0xf7, +0x25, 0x23, 0x4e, 0xaa, 0x22, 0x0c, 0x16, 0xb9, +0x73, 0xae, 0x9d, 0x46, 0x7c, 0x75, 0xd9, 0xc3, +0x49, 0x57, 0x47, 0xbf, 0x33, 0xb7, 0x97, 0xec, +0xf5, 0x40, 0x75, 0xc0, 0x46, 0x22, 0xf0, 0xa0, +0x5d, 0x9c, 0x79, 0x13, 0xa1, 0xff, 0xb8, 0xa3, +0x2f, 0x7b, 0x8e, 0x06, 0x3f, 0xc8, 0xb6, 0xe4, +0x6a, 0x28, 0xf2, 0x34, 0x5c, 0x23, 0x3f, 0x32, +0xc0, 0xe6, 0xad, 0x0f, 0xac, 0xcf, 0x55, 0x74, +0x47, 0x73, 0xd3, 0x01, 0x85, 0xb7, 0x0b, 0x22, +0x56, 0x24, 0x7d, 0x9f, 0x09, 0xa9, 0x0e, 0x86, +0x9e, 0x37, 0x5b, 0x9c, 0x6d, 0x02, 0xd9, 0x8c, +0xc8, 0x50, 0x6a, 0xe2, 0x59, 0xf3, 0x16, 0x06, +0xea, 0xb2, 0x42, 0xb5, 0x58, 0xfe, 0xba, 0xd1, +0x81, 0x57, 0x1a, 0xef, 0xb2, 0x38, 0x88, 0x58, +0xf6, 0xaa, 0xc4, 0x2e, 0x8b, 0x5a, 0x27, 0xe4, +0xa5, 0xe8, 0xa4, 0xca, 0x67, 0x5c, 0xac, 0x72, +0x67, 0xc3, 0x6f, 0x13, 0xc3, 0x2d, 0x35, 0x79, +0xd7, 0x8a, 0xe7, 0xf5, 0xd4, 0x21, 0x30, 0x4a, +0xd5, 0xf6, 0xa3, 0xd9, 0x79, 0x56, 0xf2, 0x0f, +0x10, 0xf7, 0x7d, 0xd0, 0x51, 0x93, 0x2f, 0x47, +0xf8, 0x7d, 0x4b, 0x0a, 0x84, 0x55, 0x12, 0x0a, +0x7d, 0x4e, 0x3b, 0x1f, 0x2b, 0x2f, 0xfc, 0x28, +0xb3, 0x69, 0x34, 0xe1, 0x80, 0x80, 0xbb, 0xe2, +0xaf, 0xb9, 0xd6, 0x30, 0xf1, 0x1d, 0x54, 0x87, +0x23, 0x99, 0x9f, 0x51, 0x03, 0x4c, 0x45, 0x7d, +0x02, 0x65, 0x73, 0xab, 0xfd, 0xcf, 0x94, 0xcc, +0x0d, 0x3a, 0x60, 0xfd, 0x3c, 0x14, 0x2f, 0x16, +0x33, 0xa9, 0x21, 0x1f, 0xcb, 0x50, 0xb1, 0x8f, +0x03, 0xee, 0xa0, 0x66, 0xa9, 0x16, 0x79, 0x14, diff --git a/net/wireless/certs/sforshee.x509 b/net/wireless/certs/sforshee.x509 Binary files differdeleted file mode 100644 index c6f8f9d6b988..000000000000 --- a/net/wireless/certs/sforshee.x509 +++ /dev/null diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index b1ac23ca20c8..213d0c498c97 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2610,7 +2610,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag case NL80211_IFTYPE_AP: if (wdev->ssid_len && nla_put(msg, NL80211_ATTR_SSID, wdev->ssid_len, wdev->ssid)) - goto nla_put_failure; + goto nla_put_failure_locked; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: @@ -2623,7 +2623,7 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag if (!ssid_ie) break; if (nla_put(msg, NL80211_ATTR_SSID, ssid_ie[1], ssid_ie + 2)) - goto nla_put_failure; + goto nla_put_failure_locked; break; } default: @@ -2635,6 +2635,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag genlmsg_end(msg, hdr); return 0; + nla_put_failure_locked: + wdev_unlock(wdev); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 347ab31574d5..3f6f6f8c9fa5 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -8,15 +8,29 @@ * */ +#include <linux/bottom_half.h> +#include <linux/interrupt.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/percpu.h> #include <net/dst.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ip_tunnels.h> #include <net/ip6_tunnel.h> +struct xfrm_trans_tasklet { + struct tasklet_struct tasklet; + struct sk_buff_head queue; +}; + +struct xfrm_trans_cb { + int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); +}; + +#define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) + static struct kmem_cache *secpath_cachep __read_mostly; static DEFINE_SPINLOCK(xfrm_input_afinfo_lock); @@ -25,6 +39,8 @@ static struct xfrm_input_afinfo const __rcu *xfrm_input_afinfo[AF_INET6 + 1]; static struct gro_cells gro_cells; static struct net_device xfrm_napi_dev; +static DEFINE_PER_CPU(struct xfrm_trans_tasklet, xfrm_trans_tasklet); + int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo) { int err = 0; @@ -207,7 +223,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) xfrm_address_t *daddr; struct xfrm_mode *inner_mode; u32 mark = skb->mark; - unsigned int family; + unsigned int family = AF_UNSPEC; int decaps = 0; int async = 0; bool xfrm_gro = false; @@ -216,6 +232,16 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) if (encap_type < 0) { x = xfrm_input_state(skb); + + if (unlikely(x->km.state != XFRM_STATE_VALID)) { + if (x->km.state == XFRM_STATE_ACQ) + XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR); + else + XFRM_INC_STATS(net, + LINUX_MIB_XFRMINSTATEINVALID); + goto drop; + } + family = x->outer_mode->afinfo->family; /* An encap_type of -1 indicates async resumption. */ @@ -467,9 +493,41 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr) } EXPORT_SYMBOL(xfrm_input_resume); +static void xfrm_trans_reinject(unsigned long data) +{ + struct xfrm_trans_tasklet *trans = (void *)data; + struct sk_buff_head queue; + struct sk_buff *skb; + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&trans->queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb); +} + +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) +{ + struct xfrm_trans_tasklet *trans; + + trans = this_cpu_ptr(&xfrm_trans_tasklet); + + if (skb_queue_len(&trans->queue) >= netdev_max_backlog) + return -ENOBUFS; + + XFRM_TRANS_SKB_CB(skb)->finish = finish; + skb_queue_tail(&trans->queue, skb); + tasklet_schedule(&trans->tasklet); + return 0; +} +EXPORT_SYMBOL(xfrm_trans_queue); + void __init xfrm_input_init(void) { int err; + int i; init_dummy_netdev(&xfrm_napi_dev); err = gro_cells_init(&gro_cells, &xfrm_napi_dev); @@ -480,4 +538,13 @@ void __init xfrm_input_init(void) sizeof(struct sec_path), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + + for_each_possible_cpu(i) { + struct xfrm_trans_tasklet *trans; + + trans = &per_cpu(xfrm_trans_tasklet, i); + __skb_queue_head_init(&trans->queue); + tasklet_init(&trans->tasklet, xfrm_trans_reinject, + (unsigned long)trans); + } } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9542975eb2f9..70aa5cb0c659 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1168,9 +1168,15 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { - bool match = xfrm_selector_match(&pol->selector, fl, family); + bool match; int err = 0; + if (pol->family != family) { + pol = NULL; + goto out; + } + + match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((sk->sk_mark & pol->mark.m) != pol->mark.v) { pol = NULL; @@ -1833,6 +1839,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, sizeof(struct xfrm_policy *) * num_pols) == 0 && xfrm_xdst_can_reuse(xdst, xfrm, err)) { dst_hold(&xdst->u.dst); + xfrm_pols_put(pols, num_pols); while (err > 0) xfrm_state_put(xfrm[--err]); return xdst; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 065d89606888..500b3391f474 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1343,6 +1343,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); + x->geniv = orig->geniv; if (!x->aead) goto error; } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 983b0233767b..bdb48e5dba04 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1419,11 +1419,14 @@ static void copy_templates(struct xfrm_policy *xp, struct xfrm_user_tmpl *ut, static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) { + u16 prev_family; int i; if (nr > XFRM_MAX_DEPTH) return -EINVAL; + prev_family = family; + for (i = 0; i < nr; i++) { /* We never validated the ut->family value, so many * applications simply leave it at zero. The check was @@ -1435,6 +1438,12 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) if (!ut[i].family) ut[i].family = family; + if ((ut[i].mode == XFRM_MODE_TRANSPORT) && + (ut[i].family != prev_family)) + return -EINVAL; + + prev_family = ut[i].family; + switch (ut[i].family) { case AF_INET: break; @@ -1445,6 +1454,21 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) default: return -EINVAL; } + + switch (ut[i].id.proto) { + case IPPROTO_AH: + case IPPROTO_ESP: + case IPPROTO_COMP: +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ROUTING: + case IPPROTO_DSTOPTS: +#endif + case IPSEC_PROTO_ANY: + break; + default: + return -EINVAL; + } + } return 0; @@ -2470,7 +2494,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = { [XFRMA_PROTO] = { .type = NLA_U8 }, [XFRMA_ADDRESS_FILTER] = { .len = sizeof(struct xfrm_address_filter) }, [XFRMA_OFFLOAD_DEV] = { .len = sizeof(struct xfrm_user_offload) }, - [XFRMA_OUTPUT_MARK] = { .len = NLA_U32 }, + [XFRMA_OUTPUT_MARK] = { .type = NLA_U32 }, }; static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = { diff --git a/security/Kconfig b/security/Kconfig index e8e449444e65..a623d13bf288 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -54,6 +54,16 @@ config SECURITY_NETWORK implement socket and networking access controls. If you are unsure how to answer this question, answer N. +config PAGE_TABLE_ISOLATION + bool "Remove the kernel mapping in user mode" + depends on X86_64 && !UML + help + This feature reduces the number of hardware side channels by + ensuring that the majority of kernel addresses are not mapped + into userspace. + + See Documentation/x86/pagetable-isolation.txt for more details. + config SECURITY_INFINIBAND bool "Infiniband Security Hooks" depends on SECURITY && INFINIBAND diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index b3b353d72527..f055ca10bbc1 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -579,15 +579,14 @@ static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream, return 0; } -int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info) +static int __snd_rawmidi_info_select(struct snd_card *card, + struct snd_rawmidi_info *info) { struct snd_rawmidi *rmidi; struct snd_rawmidi_str *pstr; struct snd_rawmidi_substream *substream; - mutex_lock(®ister_mutex); rmidi = snd_rawmidi_search(card, info->device); - mutex_unlock(®ister_mutex); if (!rmidi) return -ENXIO; if (info->stream < 0 || info->stream > 1) @@ -603,6 +602,16 @@ int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info } return -ENXIO; } + +int snd_rawmidi_info_select(struct snd_card *card, struct snd_rawmidi_info *info) +{ + int ret; + + mutex_lock(®ister_mutex); + ret = __snd_rawmidi_info_select(card, info); + mutex_unlock(®ister_mutex); + return ret; +} EXPORT_SYMBOL(snd_rawmidi_info_select); static int snd_rawmidi_info_select_user(struct snd_card *card, diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c index 038a180d3f81..cbe818eda336 100644 --- a/sound/hda/hdac_i915.c +++ b/sound/hda/hdac_i915.c @@ -325,7 +325,7 @@ static int hdac_component_master_match(struct device *dev, void *data) */ int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops) { - if (WARN_ON(!hdac_acomp)) + if (!hdac_acomp) return -ENODEV; hdac_acomp->audio_ops = aops; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index a81aacf684b2..37e1cf8218ff 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -271,6 +271,8 @@ enum { CXT_FIXUP_HP_SPECTRE, CXT_FIXUP_HP_GATE_MIC, CXT_FIXUP_MUTE_LED_GPIO, + CXT_FIXUP_HEADSET_MIC, + CXT_FIXUP_HP_MIC_NO_PRESENCE, }; /* for hda_fixup_thinkpad_acpi() */ @@ -350,6 +352,18 @@ static void cxt_fixup_headphone_mic(struct hda_codec *codec, } } +static void cxt_fixup_headset_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct conexant_spec *spec = codec->spec; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + spec->parse_flags |= HDA_PINCFG_HEADSET_MIC; + break; + } +} + /* OPLC XO 1.5 fixup */ /* OLPC XO-1.5 supports DC input mode (e.g. for use with analog sensors) @@ -880,6 +894,19 @@ static const struct hda_fixup cxt_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = cxt_fixup_mute_led_gpio, }, + [CXT_FIXUP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = cxt_fixup_headset_mic, + }, + [CXT_FIXUP_HP_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x02a1113c }, + { } + }, + .chained = true, + .chain_id = CXT_FIXUP_HEADSET_MIC, + }, }; static const struct snd_pci_quirk cxt5045_fixups[] = { @@ -934,6 +961,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC), SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO), + SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN), SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO), SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410), diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index c19c81d230bd..b4f1b6e88305 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -55,10 +55,11 @@ MODULE_PARM_DESC(static_hdmi_pcm, "Don't restrict PCM parameters per ELD info"); #define is_kabylake(codec) ((codec)->core.vendor_id == 0x8086280b) #define is_geminilake(codec) (((codec)->core.vendor_id == 0x8086280d) || \ ((codec)->core.vendor_id == 0x80862800)) +#define is_cannonlake(codec) ((codec)->core.vendor_id == 0x8086280c) #define is_haswell_plus(codec) (is_haswell(codec) || is_broadwell(codec) \ || is_skylake(codec) || is_broxton(codec) \ - || is_kabylake(codec)) || is_geminilake(codec) - + || is_kabylake(codec)) || is_geminilake(codec) \ + || is_cannonlake(codec) #define is_valleyview(codec) ((codec)->core.vendor_id == 0x80862882) #define is_cherryview(codec) ((codec)->core.vendor_id == 0x80862883) #define is_valleyview_plus(codec) (is_valleyview(codec) || is_cherryview(codec)) @@ -3841,6 +3842,7 @@ HDA_CODEC_ENTRY(0x80862808, "Broadwell HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x80862809, "Skylake HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280a, "Broxton HDMI", patch_i915_hsw_hdmi), HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI", patch_i915_hsw_hdmi), +HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862800, "Geminilake HDMI", patch_i915_glk_hdmi), HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4b21f71d685c..8fd2d9c62c96 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -324,8 +324,12 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0292: alc_update_coef_idx(codec, 0x4, 1<<15, 0); break; - case 0x10ec0215: case 0x10ec0225: + case 0x10ec0295: + case 0x10ec0299: + alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000); + /* fallthrough */ + case 0x10ec0215: case 0x10ec0233: case 0x10ec0236: case 0x10ec0255: @@ -336,10 +340,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0286: case 0x10ec0288: case 0x10ec0285: - case 0x10ec0295: case 0x10ec0298: case 0x10ec0289: - case 0x10ec0299: alc_update_coef_idx(codec, 0x10, 1<<9, 0); break; case 0x10ec0275: @@ -5185,6 +5187,22 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, } } +/* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */ +static void alc274_fixup_bind_dacs(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + static hda_nid_t preferred_pairs[] = { + 0x21, 0x03, 0x1b, 0x03, 0x16, 0x02, + 0 + }; + + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + spec->gen.preferred_dacs = preferred_pairs; +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -5302,6 +5320,8 @@ enum { ALC233_FIXUP_LENOVO_MULTI_CODECS, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC700_FIXUP_INTEL_REFERENCE, + ALC274_FIXUP_DELL_BIND_DACS, + ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, }; static const struct hda_fixup alc269_fixups[] = { @@ -6112,6 +6132,21 @@ static const struct hda_fixup alc269_fixups[] = { {} } }, + [ALC274_FIXUP_DELL_BIND_DACS] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc274_fixup_bind_dacs, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, + [ALC274_FIXUP_DELL_AIO_LINEOUT_VERB] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1b, 0x0401102f }, + { } + }, + .chained = true, + .chain_id = ALC274_FIXUP_DELL_BIND_DACS + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6295,6 +6330,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), + SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION), SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY), SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI), SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC), @@ -6553,6 +6589,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x1b, 0x01011020}, {0x21, 0x02211010}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x1b, 0x01011020}, + {0x21, 0x0221101f}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60160}, {0x14, 0x90170120}, {0x21, 0x02211030}), @@ -6578,7 +6619,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x14, 0x90170110}, {0x1b, 0x90a70130}, {0x21, 0x03211020}), - SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, {0x12, 0xb7a60130}, {0x13, 0xb8a61140}, {0x16, 0x90170110}, diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c index 9f521a55d610..b5e41df6bb3a 100644 --- a/sound/soc/amd/acp-pcm-dma.c +++ b/sound/soc/amd/acp-pcm-dma.c @@ -1051,6 +1051,11 @@ static int acp_audio_probe(struct platform_device *pdev) struct resource *res; const u32 *pdata = pdev->dev.platform_data; + if (!pdata) { + dev_err(&pdev->dev, "Missing platform data\n"); + return -ENODEV; + } + audio_drv_data = devm_kzalloc(&pdev->dev, sizeof(struct audio_drv_data), GFP_KERNEL); if (audio_drv_data == NULL) @@ -1058,6 +1063,8 @@ static int acp_audio_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); audio_drv_data->acp_mmio = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(audio_drv_data->acp_mmio)) + return PTR_ERR(audio_drv_data->acp_mmio); /* The following members gets populated in device 'open' * function. Till then interrupts are disabled in 'acp_init' diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig index 4a56f3dfba51..dcee145dd179 100644 --- a/sound/soc/atmel/Kconfig +++ b/sound/soc/atmel/Kconfig @@ -64,7 +64,7 @@ config SND_AT91_SOC_SAM9X5_WM8731 config SND_ATMEL_SOC_CLASSD tristate "Atmel ASoC driver for boards using CLASSD" depends on ARCH_AT91 || COMPILE_TEST - select SND_ATMEL_SOC_DMA + select SND_SOC_GENERIC_DMAENGINE_PCM select REGMAP_MMIO help Say Y if you want to add support for Atmel ASoC driver for boards using diff --git a/sound/soc/codecs/da7218.c b/sound/soc/codecs/da7218.c index b2d42ec1dcd9..56564ce90cb6 100644 --- a/sound/soc/codecs/da7218.c +++ b/sound/soc/codecs/da7218.c @@ -2520,7 +2520,7 @@ static struct da7218_pdata *da7218_of_to_pdata(struct snd_soc_codec *codec) } if (da7218->dev_id == DA7218_DEV_ID) { - hpldet_np = of_find_node_by_name(np, "da7218_hpldet"); + hpldet_np = of_get_child_by_name(np, "da7218_hpldet"); if (!hpldet_np) return pdata; diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c index 5f3c42c4f74a..066ea2f4ce7b 100644 --- a/sound/soc/codecs/msm8916-wcd-analog.c +++ b/sound/soc/codecs/msm8916-wcd-analog.c @@ -267,7 +267,7 @@ #define MSM8916_WCD_ANALOG_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\ SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000) #define MSM8916_WCD_ANALOG_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\ - SNDRV_PCM_FMTBIT_S24_LE) + SNDRV_PCM_FMTBIT_S32_LE) static int btn_mask = SND_JACK_BTN_0 | SND_JACK_BTN_1 | SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_BTN_4; diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c index a10a724eb448..13354d6304a8 100644 --- a/sound/soc/codecs/msm8916-wcd-digital.c +++ b/sound/soc/codecs/msm8916-wcd-digital.c @@ -194,7 +194,7 @@ SNDRV_PCM_RATE_32000 | \ SNDRV_PCM_RATE_48000) #define MSM8916_WCD_DIGITAL_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\ - SNDRV_PCM_FMTBIT_S24_LE) + SNDRV_PCM_FMTBIT_S32_LE) struct msm8916_wcd_digital_priv { struct clk *ahbclk, *mclk; @@ -645,7 +645,7 @@ static int msm8916_wcd_digital_hw_params(struct snd_pcm_substream *substream, RX_I2S_CTL_RX_I2S_MODE_MASK, RX_I2S_CTL_RX_I2S_MODE_16); break; - case SNDRV_PCM_FORMAT_S24_LE: + case SNDRV_PCM_FORMAT_S32_LE: snd_soc_update_bits(dai->codec, LPASS_CDC_CLK_TX_I2S_CTL, TX_I2S_CTL_TX_I2S_MODE_MASK, TX_I2S_CTL_TX_I2S_MODE_32); diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 714ce17da717..e853a6dfd33b 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -905,6 +905,7 @@ static int nau8825_adc_event(struct snd_soc_dapm_widget *w, switch (event) { case SND_SOC_DAPM_POST_PMU: + msleep(125); regmap_update_bits(nau8825->regmap, NAU8825_REG_ENA_CTRL, NAU8825_ENABLE_ADC, NAU8825_ENABLE_ADC); break; diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c index 2df91db765ac..64bf26cec20d 100644 --- a/sound/soc/codecs/rt5514-spi.c +++ b/sound/soc/codecs/rt5514-spi.c @@ -289,6 +289,8 @@ static int rt5514_spi_pcm_probe(struct snd_soc_platform *platform) dev_err(&rt5514_spi->dev, "%s Failed to reguest IRQ: %d\n", __func__, ret); + else + device_init_wakeup(rt5514_dsp->dev, true); } return 0; @@ -456,8 +458,6 @@ static int rt5514_spi_probe(struct spi_device *spi) return ret; } - device_init_wakeup(&spi->dev, true); - return 0; } @@ -482,10 +482,13 @@ static int __maybe_unused rt5514_resume(struct device *dev) if (device_may_wakeup(dev)) disable_irq_wake(irq); - if (rt5514_dsp->substream) { - rt5514_spi_burst_read(RT5514_IRQ_CTRL, (u8 *)&buf, sizeof(buf)); - if (buf[0] & RT5514_IRQ_STATUS_BIT) - rt5514_schedule_copy(rt5514_dsp); + if (rt5514_dsp) { + if (rt5514_dsp->substream) { + rt5514_spi_burst_read(RT5514_IRQ_CTRL, (u8 *)&buf, + sizeof(buf)); + if (buf[0] & RT5514_IRQ_STATUS_BIT) + rt5514_schedule_copy(rt5514_dsp); + } } return 0; diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c index 2a5b5d74e697..2dd6e9f990a4 100644 --- a/sound/soc/codecs/rt5514.c +++ b/sound/soc/codecs/rt5514.c @@ -496,7 +496,7 @@ static const struct snd_soc_dapm_widget rt5514_dapm_widgets[] = { SND_SOC_DAPM_PGA("DMIC1", SND_SOC_NOPM, 0, 0, NULL, 0), SND_SOC_DAPM_PGA("DMIC2", SND_SOC_NOPM, 0, 0, NULL, 0), - SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0, + SND_SOC_DAPM_SUPPLY_S("DMIC CLK", 1, SND_SOC_NOPM, 0, 0, rt5514_set_dmic_clk, SND_SOC_DAPM_PRE_PMU), SND_SOC_DAPM_SUPPLY("ADC CLK", RT5514_CLK_CTRL1, diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index f020d2d1eef4..edc152c8a1fe 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3823,6 +3823,8 @@ static int rt5645_i2c_probe(struct i2c_client *i2c, regmap_read(regmap, RT5645_VENDOR_ID, &val); rt5645->v_id = val & 0xff; + regmap_write(rt5645->regmap, RT5645_AD_DA_MIXER, 0x8080); + ret = regmap_register_patch(rt5645->regmap, init_list, ARRAY_SIZE(init_list)); if (ret != 0) diff --git a/sound/soc/codecs/rt5663.c b/sound/soc/codecs/rt5663.c index b036c9dc0c8c..d329bf719d80 100644 --- a/sound/soc/codecs/rt5663.c +++ b/sound/soc/codecs/rt5663.c @@ -1560,6 +1560,10 @@ static int rt5663_jack_detect(struct snd_soc_codec *codec, int jack_insert) RT5663_IRQ_POW_SAV_MASK, RT5663_IRQ_POW_SAV_EN); snd_soc_update_bits(codec, RT5663_IRQ_1, RT5663_EN_IRQ_JD1_MASK, RT5663_EN_IRQ_JD1_EN); + snd_soc_update_bits(codec, RT5663_EM_JACK_TYPE_1, + RT5663_EM_JD_MASK, RT5663_EM_JD_RST); + snd_soc_update_bits(codec, RT5663_EM_JACK_TYPE_1, + RT5663_EM_JD_MASK, RT5663_EM_JD_NOR); while (true) { regmap_read(rt5663->regmap, RT5663_INT_ST_2, &val); diff --git a/sound/soc/codecs/rt5663.h b/sound/soc/codecs/rt5663.h index c5a9b69579ad..03adc8004ba9 100644 --- a/sound/soc/codecs/rt5663.h +++ b/sound/soc/codecs/rt5663.h @@ -1029,6 +1029,10 @@ #define RT5663_POL_EXT_JD_SHIFT 10 #define RT5663_POL_EXT_JD_EN (0x1 << 10) #define RT5663_POL_EXT_JD_DIS (0x0 << 10) +#define RT5663_EM_JD_MASK (0x1 << 7) +#define RT5663_EM_JD_SHIFT 7 +#define RT5663_EM_JD_NOR (0x1 << 7) +#define RT5663_EM_JD_RST (0x0 << 7) /* DACREF LDO Control (0x0112)*/ #define RT5663_PWR_LDO_DACREFL_MASK (0x1 << 9) diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h index 730fb2058869..1ff3edb7bbb6 100644 --- a/sound/soc/codecs/tlv320aic31xx.h +++ b/sound/soc/codecs/tlv320aic31xx.h @@ -116,7 +116,7 @@ struct aic31xx_pdata { /* INT2 interrupt control */ #define AIC31XX_INT2CTRL AIC31XX_REG(0, 49) /* GPIO1 control */ -#define AIC31XX_GPIO1 AIC31XX_REG(0, 50) +#define AIC31XX_GPIO1 AIC31XX_REG(0, 51) #define AIC31XX_DACPRB AIC31XX_REG(0, 60) /* ADC Instruction Set Register */ diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c index c482b2e7a7d2..cfe72b9d4356 100644 --- a/sound/soc/codecs/twl4030.c +++ b/sound/soc/codecs/twl4030.c @@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec) struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev); struct device_node *twl4030_codec_node = NULL; - twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node, + twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node, "codec"); if (!pdata && twl4030_codec_node) { @@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec) GFP_KERNEL); if (!pdata) { dev_err(codec->dev, "Can not allocate memory\n"); + of_node_put(twl4030_codec_node); return NULL; } twl4030_setup_pdata_of(pdata, twl4030_codec_node); + of_node_put(twl4030_codec_node); } return pdata; diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 65c059b5ffd7..66e32f5d2917 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -1733,7 +1733,7 @@ static int wm_adsp_load(struct wm_adsp *dsp) le64_to_cpu(footer->timestamp)); while (pos < firmware->size && - pos - firmware->size > sizeof(*region)) { + sizeof(*region) < firmware->size - pos) { region = (void *)&(firmware->data[pos]); region_name = "Unknown"; reg = 0; @@ -1782,8 +1782,8 @@ static int wm_adsp_load(struct wm_adsp *dsp) regions, le32_to_cpu(region->len), offset, region_name); - if ((pos + le32_to_cpu(region->len) + sizeof(*region)) > - firmware->size) { + if (le32_to_cpu(region->len) > + firmware->size - pos - sizeof(*region)) { adsp_err(dsp, "%s.%d: %s region len %d bytes exceeds file length %zu\n", file, regions, region_name, @@ -2253,7 +2253,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) blocks = 0; while (pos < firmware->size && - pos - firmware->size > sizeof(*blk)) { + sizeof(*blk) < firmware->size - pos) { blk = (void *)(&firmware->data[pos]); type = le16_to_cpu(blk->type); @@ -2327,8 +2327,8 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp) } if (reg) { - if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) > - firmware->size) { + if (le32_to_cpu(blk->len) > + firmware->size - pos - sizeof(*blk)) { adsp_err(dsp, "%s.%d: %s region len %d bytes exceeds file length %zu\n", file, blocks, region_name, diff --git a/sound/soc/fsl/fsl_asrc.h b/sound/soc/fsl/fsl_asrc.h index 0f163abe4ba3..52c27a358933 100644 --- a/sound/soc/fsl/fsl_asrc.h +++ b/sound/soc/fsl/fsl_asrc.h @@ -260,8 +260,8 @@ #define ASRFSTi_OUTPUT_FIFO_SHIFT 12 #define ASRFSTi_OUTPUT_FIFO_MASK (((1 << ASRFSTi_OUTPUT_FIFO_WIDTH) - 1) << ASRFSTi_OUTPUT_FIFO_SHIFT) #define ASRFSTi_IAEi_SHIFT 11 -#define ASRFSTi_IAEi_MASK (1 << ASRFSTi_OAFi_SHIFT) -#define ASRFSTi_IAEi (1 << ASRFSTi_OAFi_SHIFT) +#define ASRFSTi_IAEi_MASK (1 << ASRFSTi_IAEi_SHIFT) +#define ASRFSTi_IAEi (1 << ASRFSTi_IAEi_SHIFT) #define ASRFSTi_INPUT_FIFO_WIDTH 7 #define ASRFSTi_INPUT_FIFO_SHIFT 0 #define ASRFSTi_INPUT_FIFO_MASK ((1 << ASRFSTi_INPUT_FIFO_WIDTH) - 1) diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index f2f51e06e22c..424bafaf51ef 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -38,6 +38,7 @@ #include <linux/ctype.h> #include <linux/device.h> #include <linux/delay.h> +#include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/of.h> @@ -265,6 +266,8 @@ struct fsl_ssi_private { u32 fifo_watermark; u32 dma_maxburst; + + struct mutex ac97_reg_lock; }; /* @@ -1260,11 +1263,13 @@ static void fsl_ssi_ac97_write(struct snd_ac97 *ac97, unsigned short reg, if (reg > 0x7f) return; + mutex_lock(&fsl_ac97_data->ac97_reg_lock); + ret = clk_prepare_enable(fsl_ac97_data->clk); if (ret) { pr_err("ac97 write clk_prepare_enable failed: %d\n", ret); - return; + goto ret_unlock; } lreg = reg << 12; @@ -1278,6 +1283,9 @@ static void fsl_ssi_ac97_write(struct snd_ac97 *ac97, unsigned short reg, udelay(100); clk_disable_unprepare(fsl_ac97_data->clk); + +ret_unlock: + mutex_unlock(&fsl_ac97_data->ac97_reg_lock); } static unsigned short fsl_ssi_ac97_read(struct snd_ac97 *ac97, @@ -1285,16 +1293,18 @@ static unsigned short fsl_ssi_ac97_read(struct snd_ac97 *ac97, { struct regmap *regs = fsl_ac97_data->regs; - unsigned short val = -1; + unsigned short val = 0; u32 reg_val; unsigned int lreg; int ret; + mutex_lock(&fsl_ac97_data->ac97_reg_lock); + ret = clk_prepare_enable(fsl_ac97_data->clk); if (ret) { pr_err("ac97 read clk_prepare_enable failed: %d\n", ret); - return -1; + goto ret_unlock; } lreg = (reg & 0x7f) << 12; @@ -1309,6 +1319,8 @@ static unsigned short fsl_ssi_ac97_read(struct snd_ac97 *ac97, clk_disable_unprepare(fsl_ac97_data->clk); +ret_unlock: + mutex_unlock(&fsl_ac97_data->ac97_reg_lock); return val; } @@ -1458,12 +1470,6 @@ static int fsl_ssi_probe(struct platform_device *pdev) sizeof(fsl_ssi_ac97_dai)); fsl_ac97_data = ssi_private; - - ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev); - if (ret) { - dev_err(&pdev->dev, "could not set AC'97 ops\n"); - return ret; - } } else { /* Initialize this copy of the CPU DAI driver structure */ memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template, @@ -1574,6 +1580,15 @@ static int fsl_ssi_probe(struct platform_device *pdev) return ret; } + if (fsl_ssi_is_ac97(ssi_private)) { + mutex_init(&ssi_private->ac97_reg_lock); + ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev); + if (ret) { + dev_err(&pdev->dev, "could not set AC'97 ops\n"); + goto error_ac97_ops; + } + } + ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component, &ssi_private->cpu_dai_drv, 1); if (ret) { @@ -1657,6 +1672,13 @@ error_sound_card: fsl_ssi_debugfs_remove(&ssi_private->dbg_stats); error_asoc_register: + if (fsl_ssi_is_ac97(ssi_private)) + snd_soc_set_ac97_ops(NULL); + +error_ac97_ops: + if (fsl_ssi_is_ac97(ssi_private)) + mutex_destroy(&ssi_private->ac97_reg_lock); + if (ssi_private->soc->imx) fsl_ssi_imx_clean(pdev, ssi_private); @@ -1675,8 +1697,10 @@ static int fsl_ssi_remove(struct platform_device *pdev) if (ssi_private->soc->imx) fsl_ssi_imx_clean(pdev, ssi_private); - if (fsl_ssi_is_ac97(ssi_private)) + if (fsl_ssi_is_ac97(ssi_private)) { snd_soc_set_ac97_ops(NULL); + mutex_destroy(&ssi_private->ac97_reg_lock); + } return 0; } diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c index 6f9a8bcf20f3..6dcad0a8a0d0 100644 --- a/sound/soc/intel/boards/kbl_rt5663_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c @@ -101,7 +101,7 @@ static const struct snd_soc_dapm_route kabylake_map[] = { { "ssp0 Tx", NULL, "spk_out" }, { "AIF Playback", NULL, "ssp1 Tx" }, - { "ssp1 Tx", NULL, "hs_out" }, + { "ssp1 Tx", NULL, "codec1_out" }, { "hs_in", NULL, "ssp1 Rx" }, { "ssp1 Rx", NULL, "AIF Capture" }, diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c index 6072164f2d43..271ae3c2c535 100644 --- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c +++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c @@ -109,7 +109,7 @@ static const struct snd_soc_dapm_route kabylake_map[] = { { "ssp0 Tx", NULL, "spk_out" }, { "AIF Playback", NULL, "ssp1 Tx" }, - { "ssp1 Tx", NULL, "hs_out" }, + { "ssp1 Tx", NULL, "codec1_out" }, { "hs_in", NULL, "ssp1 Rx" }, { "ssp1 Rx", NULL, "AIF Capture" }, diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c index d14c50a60289..3eaac41090ca 100644 --- a/sound/soc/intel/skylake/skl-nhlt.c +++ b/sound/soc/intel/skylake/skl-nhlt.c @@ -119,11 +119,16 @@ static bool skl_check_ep_match(struct device *dev, struct nhlt_endpoint *epnt, if ((epnt->virtual_bus_id == instance_id) && (epnt->linktype == link_type) && - (epnt->direction == dirn) && - (epnt->device_type == dev_type)) - return true; - else - return false; + (epnt->direction == dirn)) { + /* do not check dev_type for DMIC link type */ + if (epnt->linktype == NHLT_LINK_DMIC) + return true; + + if (epnt->device_type == dev_type) + return true; + } + + return false; } struct nhlt_specific_cfg diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c index a072bcf209d2..81923da18ac2 100644 --- a/sound/soc/intel/skylake/skl-topology.c +++ b/sound/soc/intel/skylake/skl-topology.c @@ -2908,7 +2908,7 @@ static int skl_tplg_control_load(struct snd_soc_component *cmpnt, break; default: - dev_warn(bus->dev, "Control load not supported %d:%d:%d\n", + dev_dbg(bus->dev, "Control load not supported %d:%d:%d\n", hdr->ops.get, hdr->ops.put, hdr->ops.info); break; } diff --git a/sound/soc/rockchip/rockchip_spdif.c b/sound/soc/rockchip/rockchip_spdif.c index ee5055d47d13..a89fe9b6463b 100644 --- a/sound/soc/rockchip/rockchip_spdif.c +++ b/sound/soc/rockchip/rockchip_spdif.c @@ -322,26 +322,30 @@ static int rk_spdif_probe(struct platform_device *pdev) spdif->mclk = devm_clk_get(&pdev->dev, "mclk"); if (IS_ERR(spdif->mclk)) { dev_err(&pdev->dev, "Can't retrieve rk_spdif master clock\n"); - return PTR_ERR(spdif->mclk); + ret = PTR_ERR(spdif->mclk); + goto err_disable_hclk; } ret = clk_prepare_enable(spdif->mclk); if (ret) { dev_err(spdif->dev, "clock enable failed %d\n", ret); - return ret; + goto err_disable_clocks; } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); regs = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(regs)) - return PTR_ERR(regs); + if (IS_ERR(regs)) { + ret = PTR_ERR(regs); + goto err_disable_clocks; + } spdif->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "hclk", regs, &rk_spdif_regmap_config); if (IS_ERR(spdif->regmap)) { dev_err(&pdev->dev, "Failed to initialise managed register map\n"); - return PTR_ERR(spdif->regmap); + ret = PTR_ERR(spdif->regmap); + goto err_disable_clocks; } spdif->playback_dma_data.addr = res->start + SPDIF_SMPDR; @@ -373,6 +377,10 @@ static int rk_spdif_probe(struct platform_device *pdev) err_pm_runtime: pm_runtime_disable(&pdev->dev); +err_disable_clocks: + clk_disable_unprepare(spdif->mclk); +err_disable_hclk: + clk_disable_unprepare(spdif->hclk); return ret; } diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c index 8ddb08714faa..4672688cac32 100644 --- a/sound/soc/sh/rcar/adg.c +++ b/sound/soc/sh/rcar/adg.c @@ -222,7 +222,7 @@ int rsnd_adg_set_cmd_timsel_gen2(struct rsnd_mod *cmd_mod, NULL, &val, NULL); val = val << shift; - mask = 0xffff << shift; + mask = 0x0f1f << shift; rsnd_mod_bset(adg_mod, CMDOUT_TIMSEL, mask, val); @@ -250,7 +250,7 @@ int rsnd_adg_set_src_timesel_gen2(struct rsnd_mod *src_mod, in = in << shift; out = out << shift; - mask = 0xffff << shift; + mask = 0x0f1f << shift; switch (id / 2) { case 0: @@ -380,7 +380,7 @@ int rsnd_adg_ssi_clk_try_start(struct rsnd_mod *ssi_mod, unsigned int rate) ckr = 0x80000000; } - rsnd_mod_bset(adg_mod, BRGCKR, 0x80FF0000, adg->ckr | ckr); + rsnd_mod_bset(adg_mod, BRGCKR, 0x80770000, adg->ckr | ckr); rsnd_mod_write(adg_mod, BRRA, adg->rbga); rsnd_mod_write(adg_mod, BRRB, adg->rbgb); diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index c70eb2097816..f12a88a21dfa 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1332,8 +1332,8 @@ static int rsnd_pcm_new(struct snd_soc_pcm_runtime *rtd) return snd_pcm_lib_preallocate_pages_for_all( rtd->pcm, - SNDRV_DMA_TYPE_CONTINUOUS, - snd_dma_continuous_data(GFP_KERNEL), + SNDRV_DMA_TYPE_DEV, + rtd->card->snd_card->dev, PREALLOC_BUFFER, PREALLOC_BUFFER_MAX); } diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c index fd557abfe390..4d750bdf8e24 100644 --- a/sound/soc/sh/rcar/dma.c +++ b/sound/soc/sh/rcar/dma.c @@ -26,10 +26,7 @@ struct rsnd_dmaen { struct dma_chan *chan; dma_cookie_t cookie; - dma_addr_t dma_buf; unsigned int dma_len; - unsigned int dma_period; - unsigned int dma_cnt; }; struct rsnd_dmapp { @@ -71,38 +68,10 @@ static struct rsnd_mod mem = { /* * Audio DMAC */ -#define rsnd_dmaen_sync(dmaen, io, i) __rsnd_dmaen_sync(dmaen, io, i, 1) -#define rsnd_dmaen_unsync(dmaen, io, i) __rsnd_dmaen_sync(dmaen, io, i, 0) -static void __rsnd_dmaen_sync(struct rsnd_dmaen *dmaen, struct rsnd_dai_stream *io, - int i, int sync) -{ - struct device *dev = dmaen->chan->device->dev; - enum dma_data_direction dir; - int is_play = rsnd_io_is_play(io); - dma_addr_t buf; - int len, max; - size_t period; - - len = dmaen->dma_len; - period = dmaen->dma_period; - max = len / period; - i = i % max; - buf = dmaen->dma_buf + (period * i); - - dir = is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE; - - if (sync) - dma_sync_single_for_device(dev, buf, period, dir); - else - dma_sync_single_for_cpu(dev, buf, period, dir); -} - static void __rsnd_dmaen_complete(struct rsnd_mod *mod, struct rsnd_dai_stream *io) { struct rsnd_priv *priv = rsnd_mod_to_priv(mod); - struct rsnd_dma *dma = rsnd_mod_to_dma(mod); - struct rsnd_dmaen *dmaen = rsnd_dma_to_dmaen(dma); bool elapsed = false; unsigned long flags; @@ -115,22 +84,9 @@ static void __rsnd_dmaen_complete(struct rsnd_mod *mod, */ spin_lock_irqsave(&priv->lock, flags); - if (rsnd_io_is_working(io)) { - rsnd_dmaen_unsync(dmaen, io, dmaen->dma_cnt); - - /* - * Next period is already started. - * Let's sync Next Next period - * see - * rsnd_dmaen_start() - */ - rsnd_dmaen_sync(dmaen, io, dmaen->dma_cnt + 2); - + if (rsnd_io_is_working(io)) elapsed = true; - dmaen->dma_cnt++; - } - spin_unlock_irqrestore(&priv->lock, flags); if (elapsed) @@ -165,14 +121,8 @@ static int rsnd_dmaen_stop(struct rsnd_mod *mod, struct rsnd_dma *dma = rsnd_mod_to_dma(mod); struct rsnd_dmaen *dmaen = rsnd_dma_to_dmaen(dma); - if (dmaen->chan) { - int is_play = rsnd_io_is_play(io); - + if (dmaen->chan) dmaengine_terminate_all(dmaen->chan); - dma_unmap_single(dmaen->chan->device->dev, - dmaen->dma_buf, dmaen->dma_len, - is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - } return 0; } @@ -237,11 +187,7 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod, struct device *dev = rsnd_priv_to_dev(priv); struct dma_async_tx_descriptor *desc; struct dma_slave_config cfg = {}; - dma_addr_t buf; - size_t len; - size_t period; int is_play = rsnd_io_is_play(io); - int i; int ret; cfg.direction = is_play ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM; @@ -258,19 +204,10 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod, if (ret < 0) return ret; - len = snd_pcm_lib_buffer_bytes(substream); - period = snd_pcm_lib_period_bytes(substream); - buf = dma_map_single(dmaen->chan->device->dev, - substream->runtime->dma_area, - len, - is_play ? DMA_TO_DEVICE : DMA_FROM_DEVICE); - if (dma_mapping_error(dmaen->chan->device->dev, buf)) { - dev_err(dev, "dma map failed\n"); - return -EIO; - } - desc = dmaengine_prep_dma_cyclic(dmaen->chan, - buf, len, period, + substream->runtime->dma_addr, + snd_pcm_lib_buffer_bytes(substream), + snd_pcm_lib_period_bytes(substream), is_play ? DMA_MEM_TO_DEV : DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT | DMA_CTRL_ACK); @@ -282,18 +219,7 @@ static int rsnd_dmaen_start(struct rsnd_mod *mod, desc->callback = rsnd_dmaen_complete; desc->callback_param = rsnd_mod_get(dma); - dmaen->dma_buf = buf; - dmaen->dma_len = len; - dmaen->dma_period = period; - dmaen->dma_cnt = 0; - - /* - * synchronize this and next period - * see - * __rsnd_dmaen_complete() - */ - for (i = 0; i < 2; i++) - rsnd_dmaen_sync(dmaen, io, i); + dmaen->dma_len = snd_pcm_lib_buffer_bytes(substream); dmaen->cookie = dmaengine_submit(desc); if (dmaen->cookie < 0) { diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index fece1e5f582f..cbf3bf312d23 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -446,25 +446,29 @@ static bool rsnd_ssi_pointer_update(struct rsnd_mod *mod, int byte) { struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); + bool ret = false; + int byte_pos; - ssi->byte_pos += byte; + byte_pos = ssi->byte_pos + byte; - if (ssi->byte_pos >= ssi->next_period_byte) { + if (byte_pos >= ssi->next_period_byte) { struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); ssi->period_pos++; ssi->next_period_byte += ssi->byte_per_period; if (ssi->period_pos >= runtime->periods) { - ssi->byte_pos = 0; + byte_pos = 0; ssi->period_pos = 0; ssi->next_period_byte = ssi->byte_per_period; } - return true; + ret = true; } - return false; + WRITE_ONCE(ssi->byte_pos, byte_pos); + + return ret; } /* @@ -838,7 +842,7 @@ static int rsnd_ssi_pointer(struct rsnd_mod *mod, struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod); struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); - *pointer = bytes_to_frames(runtime, ssi->byte_pos); + *pointer = bytes_to_frames(runtime, READ_ONCE(ssi->byte_pos)); return 0; } diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c index 4d948757d300..6ff8a36c2c82 100644 --- a/sound/soc/sh/rcar/ssiu.c +++ b/sound/soc/sh/rcar/ssiu.c @@ -125,6 +125,7 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod, { int hdmi = rsnd_ssi_hdmi_port(io); int ret; + u32 mode = 0; ret = rsnd_ssiu_init(mod, io, priv); if (ret < 0) @@ -136,9 +137,11 @@ static int rsnd_ssiu_init_gen2(struct rsnd_mod *mod, * see * rsnd_ssi_config_init() */ - rsnd_mod_write(mod, SSI_MODE, 0x1); + mode = 0x1; } + rsnd_mod_write(mod, SSI_MODE, mode); + if (rsnd_ssi_use_busif(io)) { rsnd_mod_write(mod, SSI_BUSIF_ADINR, rsnd_get_adinr_bit(mod, io) | diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 7c9e361b2200..2b4ceda36291 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2173,20 +2173,25 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid, kctl->private_value = (unsigned long)namelist; kctl->private_free = usb_mixer_selector_elem_free; - nameid = uac_selector_unit_iSelector(desc); + /* check the static mapping table at first */ len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name)); - if (len) - ; - else if (nameid) - len = snd_usb_copy_string_desc(state, nameid, kctl->id.name, - sizeof(kctl->id.name)); - else - len = get_term_name(state, &state->oterm, - kctl->id.name, sizeof(kctl->id.name), 0); - if (!len) { - strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name)); + /* no mapping ? */ + /* if iSelector is given, use it */ + nameid = uac_selector_unit_iSelector(desc); + if (nameid) + len = snd_usb_copy_string_desc(state, nameid, + kctl->id.name, + sizeof(kctl->id.name)); + /* ... or pick up the terminal name at next */ + if (!len) + len = get_term_name(state, &state->oterm, + kctl->id.name, sizeof(kctl->id.name), 0); + /* ... or use the fixed string "USB" as the last resort */ + if (!len) + strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name)); + /* and add the proper suffix */ if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR) append_ctl_name(kctl, " Clock Source"); else if ((state->oterm.type & 0xff00) == 0x0100) diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 77eecaa4db1f..a66ef5777887 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1166,10 +1166,11 @@ static bool is_marantz_denon_dac(unsigned int id) /* TEAC UD-501/UD-503/NT-503 USB DACs need a vendor cmd to switch * between PCM/DOP and native DSD mode */ -static bool is_teac_50X_dac(unsigned int id) +static bool is_teac_dsd_dac(unsigned int id) { switch (id) { case USB_ID(0x0644, 0x8043): /* TEAC UD-501/UD-503/NT-503 */ + case USB_ID(0x0644, 0x8044): /* Esoteric D-05X */ return true; } return false; @@ -1202,7 +1203,7 @@ int snd_usb_select_mode_quirk(struct snd_usb_substream *subs, break; } mdelay(20); - } else if (is_teac_50X_dac(subs->stream->chip->usb_id)) { + } else if (is_teac_dsd_dac(subs->stream->chip->usb_id)) { /* Vendor mode switch cmd is required. */ switch (fmt->altsetting) { case 3: /* DSD mode (DSD_U32) requested */ @@ -1392,7 +1393,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, } /* TEAC devices with USB DAC functionality */ - if (is_teac_50X_dac(chip->usb_id)) { + if (is_teac_dsd_dac(chip->usb_id)) { if (fp->altsetting == 3) return SNDRV_PCM_FMTBIT_DSD_U32_BE; } diff --git a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h index cefe7c7cd4f6..0a8e37a519f2 100644 --- a/tools/arch/s390/include/uapi/asm/bpf_perf_event.h +++ b/tools/arch/s390/include/uapi/asm/bpf_perf_event.h @@ -2,7 +2,7 @@ #ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ #define _UAPI__ASM_BPF_PERF_EVENT_H__ -#include <asm/ptrace.h> +#include "ptrace.h" typedef user_pt_regs bpf_user_pt_regs_t; diff --git a/tools/arch/s390/include/uapi/asm/perf_regs.h b/tools/arch/s390/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000000..d17dd9e5d516 --- /dev/null +++ b/tools/arch/s390/include/uapi/asm/perf_regs.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_S390_PERF_REGS_H +#define _ASM_S390_PERF_REGS_H + +enum perf_event_s390_regs { + PERF_REG_S390_R0, + PERF_REG_S390_R1, + PERF_REG_S390_R2, + PERF_REG_S390_R3, + PERF_REG_S390_R4, + PERF_REG_S390_R5, + PERF_REG_S390_R6, + PERF_REG_S390_R7, + PERF_REG_S390_R8, + PERF_REG_S390_R9, + PERF_REG_S390_R10, + PERF_REG_S390_R11, + PERF_REG_S390_R12, + PERF_REG_S390_R13, + PERF_REG_S390_R14, + PERF_REG_S390_R15, + PERF_REG_S390_FP0, + PERF_REG_S390_FP1, + PERF_REG_S390_FP2, + PERF_REG_S390_FP3, + PERF_REG_S390_FP4, + PERF_REG_S390_FP5, + PERF_REG_S390_FP6, + PERF_REG_S390_FP7, + PERF_REG_S390_FP8, + PERF_REG_S390_FP9, + PERF_REG_S390_FP10, + PERF_REG_S390_FP11, + PERF_REG_S390_FP12, + PERF_REG_S390_FP13, + PERF_REG_S390_FP14, + PERF_REG_S390_FP15, + PERF_REG_S390_MASK, + PERF_REG_S390_PC, + + PERF_REG_S390_MAX +}; + +#endif /* _ASM_S390_PERF_REGS_H */ diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index e2450c8e88e6..a8c3a33dd185 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -523,21 +523,23 @@ static int do_show(int argc, char **argv) break; p_err("can't get next map: %s%s", strerror(errno), errno == EINVAL ? " -- kernel too old?" : ""); - return -1; + break; } fd = bpf_map_get_fd_by_id(id); if (fd < 0) { + if (errno == ENOENT) + continue; p_err("can't get map by id (%u): %s", id, strerror(errno)); - return -1; + break; } err = bpf_obj_get_info_by_fd(fd, &info, &len); if (err) { p_err("can't get map info: %s", strerror(errno)); close(fd); - return -1; + break; } if (json_output) diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index ad619b96c276..dded77345bfb 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -382,6 +382,8 @@ static int do_show(int argc, char **argv) fd = bpf_prog_get_fd_by_id(id); if (fd < 0) { + if (errno == ENOENT) + continue; p_err("can't get prog by id (%u): %s", id, strerror(errno)); err = -1; diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 217cf6f95c36..a5684d0968b4 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -478,7 +478,7 @@ class Provider(object): @staticmethod def is_field_wanted(fields_filter, field): """Indicate whether field is valid according to fields_filter.""" - if not fields_filter or fields_filter == "help": + if not fields_filter: return True return re.match(fields_filter, field) is not None @@ -549,8 +549,8 @@ class TracepointProvider(Provider): def update_fields(self, fields_filter): """Refresh fields, applying fields_filter""" - self._fields = [field for field in self.get_available_fields() - if self.is_field_wanted(fields_filter, field)] + self.fields = [field for field in self.get_available_fields() + if self.is_field_wanted(fields_filter, field)] @staticmethod def get_online_cpus(): @@ -950,7 +950,8 @@ class Tui(object): curses.nocbreak() curses.endwin() - def get_all_gnames(self): + @staticmethod + def get_all_gnames(): """Returns a list of (pid, gname) tuples of all running guests""" res = [] try: @@ -963,7 +964,7 @@ class Tui(object): # perform a sanity check before calling the more expensive # function to possibly extract the guest name if ' -name ' in line[1]: - res.append((line[0], self.get_gname_from_pid(line[0]))) + res.append((line[0], Tui.get_gname_from_pid(line[0]))) child.stdout.close() return res @@ -984,7 +985,8 @@ class Tui(object): except Exception: self.screen.addstr(row + 1, 2, 'Not available') - def get_pid_from_gname(self, gname): + @staticmethod + def get_pid_from_gname(gname): """Fuzzy function to convert guest name to QEMU process pid. Returns a list of potential pids, can be empty if no match found. @@ -992,7 +994,7 @@ class Tui(object): """ pids = [] - for line in self.get_all_gnames(): + for line in Tui.get_all_gnames(): if gname == line[1]: pids.append(int(line[0])) @@ -1090,15 +1092,16 @@ class Tui(object): # sort by totals return (0, -stats[x][0]) total = 0. - for val in stats.values(): - total += val[0] + for key in stats.keys(): + if key.find('(') is -1: + total += stats[key][0] if self._sorting == SORT_DEFAULT: sortkey = sortCurAvg else: sortkey = sortTotal + tavg = 0 for key in sorted(stats.keys(), key=sortkey): - - if row >= self.screen.getmaxyx()[0]: + if row >= self.screen.getmaxyx()[0] - 1: break values = stats[key] if not values[0] and not values[1]: @@ -1110,9 +1113,15 @@ class Tui(object): self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key, values[0], values[0] * 100 / total, cur)) + if cur is not '' and key.find('(') is -1: + tavg += cur row += 1 if row == 3: self.screen.addstr(4, 1, 'No matching events reported yet') + else: + self.screen.addstr(row, 1, '%-40s %10d %8s' % + ('Total', total, tavg if tavg else ''), + curses.A_BOLD) self.screen.refresh() def show_msg(self, text): @@ -1358,7 +1367,7 @@ class Tui(object): if char == 'x': self.update_drilldown() # prevents display of current values on next refresh - self.stats.get() + self.stats.get(self._display_guests) except KeyboardInterrupt: break except curses.error: @@ -1451,16 +1460,13 @@ Press any other key to refresh statistics immediately. try: pids = Tui.get_pid_from_gname(val) except: - raise optparse.OptionValueError('Error while searching for guest ' - '"{}", use "-p" to specify a pid ' - 'instead'.format(val)) + sys.exit('Error while searching for guest "{}". Use "-p" to ' + 'specify a pid instead?'.format(val)) if len(pids) == 0: - raise optparse.OptionValueError('No guest by the name "{}" ' - 'found'.format(val)) + sys.exit('Error: No guest by the name "{}" found'.format(val)) if len(pids) > 1: - raise optparse.OptionValueError('Multiple processes found (pids: ' - '{}) - use "-p" to specify a pid ' - 'instead'.format(" ".join(pids))) + sys.exit('Error: Multiple processes found (pids: {}). Use "-p" ' + 'to specify the desired pid'.format(" ".join(pids))) parser.values.pid = pids[0] optparser = optparse.OptionParser(description=description_text, @@ -1518,7 +1524,16 @@ Press any other key to refresh statistics immediately. help='restrict statistics to guest by name', callback=cb_guest_to_pid, ) - (options, _) = optparser.parse_args(sys.argv) + options, unkn = optparser.parse_args(sys.argv) + if len(unkn) != 1: + sys.exit('Error: Extra argument(s): ' + ' '.join(unkn[1:])) + try: + # verify that we were passed a valid regex up front + re.compile(options.fields) + except re.error: + sys.exit('Error: "' + options.fields + '" is not a valid regular ' + 'expression') + return options @@ -1564,16 +1579,13 @@ def main(): stats = Stats(options) - if options.fields == "help": - event_list = "\n" - s = stats.get() - for key in s.keys(): - if key.find('(') != -1: - key = key[0:key.find('(')] - if event_list.find('\n' + key + '\n') == -1: - event_list += key + '\n' - sys.stdout.write(event_list) - return "" + if options.fields == 'help': + stats.fields_filter = None + event_list = [] + for key in stats.get().keys(): + event_list.append(key.split('(', 1)[0]) + sys.stdout.write(' ' + '\n '.join(sorted(set(event_list))) + '\n') + sys.exit(0) if options.log: log(stats) diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt index e5cf836be8a1..b5b3810c9e94 100644 --- a/tools/kvm/kvm_stat/kvm_stat.txt +++ b/tools/kvm/kvm_stat/kvm_stat.txt @@ -50,6 +50,8 @@ INTERACTIVE COMMANDS *s*:: set update interval *x*:: toggle reporting of stats for child trace events + :: *Note*: The stats for the parents summarize the respective child trace + events Press any other key to refresh statistics immediately. @@ -86,7 +88,7 @@ OPTIONS -f<fields>:: --fields=<fields>:: - fields to display (regex) + fields to display (regex), "-f help" for a list of available events -h:: --help:: diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 8acfc47af70e..540a209b78ab 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -138,7 +138,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, *type = INSN_STACK; op->src.type = OP_SRC_ADD; op->src.reg = op_to_cfi_reg[modrm_reg][rex_r]; - op->dest.type = OP_SRC_REG; + op->dest.type = OP_DEST_REG; op->dest.reg = CFI_SP; } break; diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c index 4c6b5c9ef073..91e8e19ff5e0 100644 --- a/tools/objtool/builtin-orc.c +++ b/tools/objtool/builtin-orc.c @@ -44,6 +44,9 @@ int cmd_orc(int argc, const char **argv) const char *objname; argc--; argv++; + if (argc <= 0) + usage_with_options(orc_usage, check_options); + if (!strncmp(argv[0], "gen", 3)) { argc = parse_options(argc, argv, check_options, orc_usage, 0); if (argc != 1) @@ -52,7 +55,6 @@ int cmd_orc(int argc, const char **argv) objname = argv[0]; return check(objname, no_fp, no_unreachable, true); - } if (!strcmp(argv[0], "dump")) { diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c index e5ca31429c9b..e61fe703197b 100644 --- a/tools/objtool/orc_gen.c +++ b/tools/objtool/orc_gen.c @@ -165,6 +165,8 @@ int create_orc_sections(struct objtool_file *file) /* create .orc_unwind_ip and .rela.orc_unwind_ip sections */ sec = elf_create_section(file->elf, ".orc_unwind_ip", sizeof(int), idx); + if (!sec) + return -1; ip_relasec = elf_create_rela_section(file->elf, sec); if (!ip_relasec) diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index ed65e82f034e..0294bfb6c5f8 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -188,9 +188,7 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS)) PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null) - ifeq ($(CC_NO_CLANG), 1) - PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) - endif + PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS)) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) endif @@ -576,14 +574,15 @@ ifndef NO_GTK2 endif endif - ifdef NO_LIBPERL CFLAGS += -DNO_LIBPERL else PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null) PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS)) PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS)) - PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null` + PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null) + PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS)) + PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS)) FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS) ifneq ($(feature-libperl), 1) diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h index d2df54a6bc5a..bcfbaed78cc2 100644 --- a/tools/perf/arch/s390/include/perf_regs.h +++ b/tools/perf/arch/s390/include/perf_regs.h @@ -3,7 +3,7 @@ #include <stdlib.h> #include <linux/types.h> -#include <../../../../arch/s390/include/uapi/asm/perf_regs.h> +#include <asm/perf_regs.h> void perf_regs_load(u64 *regs); diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index 6db9d809fe97..3e64f10b6d66 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -21,6 +21,7 @@ arch/x86/include/asm/cpufeatures.h arch/arm/include/uapi/asm/perf_regs.h arch/arm64/include/uapi/asm/perf_regs.h arch/powerpc/include/uapi/asm/perf_regs.h +arch/s390/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/perf_regs.h arch/x86/include/uapi/asm/kvm.h arch/x86/include/uapi/asm/kvm_perf.h diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index cf36de7ea255..0c6d1002b524 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -384,13 +384,13 @@ jvmti_write_code(void *agent, char const *sym, } int -jvmti_write_debug_info(void *agent, uint64_t code, const char *file, - jvmti_line_info_t *li, int nr_lines) +jvmti_write_debug_info(void *agent, uint64_t code, + int nr_lines, jvmti_line_info_t *li, + const char * const * file_names) { struct jr_code_debug_info rec; - size_t sret, len, size, flen; + size_t sret, len, size, flen = 0; uint64_t addr; - const char *fn = file; FILE *fp = agent; int i; @@ -405,7 +405,9 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file, return -1; } - flen = strlen(file) + 1; + for (i = 0; i < nr_lines; ++i) { + flen += strlen(file_names[i]) + 1; + } rec.p.id = JIT_CODE_DEBUG_INFO; size = sizeof(rec); @@ -421,7 +423,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file, * file[] : source file name */ size += nr_lines * sizeof(struct debug_entry); - size += flen * nr_lines; + size += flen; rec.p.total_size = size; /* @@ -452,7 +454,7 @@ jvmti_write_debug_info(void *agent, uint64_t code, const char *file, if (sret != 1) goto error; - sret = fwrite_unlocked(fn, flen, 1, fp); + sret = fwrite_unlocked(file_names[i], strlen(file_names[i]) + 1, 1, fp); if (sret != 1) goto error; } diff --git a/tools/perf/jvmti/jvmti_agent.h b/tools/perf/jvmti/jvmti_agent.h index fe32d8344a82..6ed82f6c06dd 100644 --- a/tools/perf/jvmti/jvmti_agent.h +++ b/tools/perf/jvmti/jvmti_agent.h @@ -14,6 +14,7 @@ typedef struct { unsigned long pc; int line_number; int discrim; /* discriminator -- 0 for now */ + jmethodID methodID; } jvmti_line_info_t; void *jvmti_open(void); @@ -22,11 +23,9 @@ int jvmti_write_code(void *agent, char const *symbol_name, uint64_t vma, void const *code, const unsigned int code_size); -int jvmti_write_debug_info(void *agent, - uint64_t code, - const char *file, +int jvmti_write_debug_info(void *agent, uint64_t code, int nr_lines, jvmti_line_info_t *li, - int nr_lines); + const char * const * file_names); #if defined(__cplusplus) } diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c index c62c9fc9a525..6add3e982614 100644 --- a/tools/perf/jvmti/libjvmti.c +++ b/tools/perf/jvmti/libjvmti.c @@ -47,6 +47,7 @@ do_get_line_numbers(jvmtiEnv *jvmti, void *pc, jmethodID m, jint bci, tab[lines].pc = (unsigned long)pc; tab[lines].line_number = loc_tab[i].line_number; tab[lines].discrim = 0; /* not yet used */ + tab[lines].methodID = m; lines++; } else { break; @@ -125,6 +126,99 @@ get_line_numbers(jvmtiEnv *jvmti, const void *compile_info, jvmti_line_info_t ** return JVMTI_ERROR_NONE; } +static void +copy_class_filename(const char * class_sign, const char * file_name, char * result, size_t max_length) +{ + /* + * Assume path name is class hierarchy, this is a common practice with Java programs + */ + if (*class_sign == 'L') { + int j, i = 0; + char *p = strrchr(class_sign, '/'); + if (p) { + /* drop the 'L' prefix and copy up to the final '/' */ + for (i = 0; i < (p - class_sign); i++) + result[i] = class_sign[i+1]; + } + /* + * append file name, we use loops and not string ops to avoid modifying + * class_sign which is used later for the symbol name + */ + for (j = 0; i < (max_length - 1) && file_name && j < strlen(file_name); j++, i++) + result[i] = file_name[j]; + + result[i] = '\0'; + } else { + /* fallback case */ + size_t file_name_len = strlen(file_name); + strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length); + } +} + +static jvmtiError +get_source_filename(jvmtiEnv *jvmti, jmethodID methodID, char ** buffer) +{ + jvmtiError ret; + jclass decl_class; + char *file_name = NULL; + char *class_sign = NULL; + char fn[PATH_MAX]; + size_t len; + + ret = (*jvmti)->GetMethodDeclaringClass(jvmti, methodID, &decl_class); + if (ret != JVMTI_ERROR_NONE) { + print_error(jvmti, "GetMethodDeclaringClass", ret); + return ret; + } + + ret = (*jvmti)->GetSourceFileName(jvmti, decl_class, &file_name); + if (ret != JVMTI_ERROR_NONE) { + print_error(jvmti, "GetSourceFileName", ret); + return ret; + } + + ret = (*jvmti)->GetClassSignature(jvmti, decl_class, &class_sign, NULL); + if (ret != JVMTI_ERROR_NONE) { + print_error(jvmti, "GetClassSignature", ret); + goto free_file_name_error; + } + + copy_class_filename(class_sign, file_name, fn, PATH_MAX); + len = strlen(fn); + *buffer = malloc((len + 1) * sizeof(char)); + if (!*buffer) { + print_error(jvmti, "GetClassSignature", ret); + ret = JVMTI_ERROR_OUT_OF_MEMORY; + goto free_class_sign_error; + } + strcpy(*buffer, fn); + ret = JVMTI_ERROR_NONE; + +free_class_sign_error: + (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign); +free_file_name_error: + (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name); + + return ret; +} + +static jvmtiError +fill_source_filenames(jvmtiEnv *jvmti, int nr_lines, + const jvmti_line_info_t * line_tab, + char ** file_names) +{ + int index; + jvmtiError ret; + + for (index = 0; index < nr_lines; ++index) { + ret = get_source_filename(jvmti, line_tab[index].methodID, &(file_names[index])); + if (ret != JVMTI_ERROR_NONE) + return ret; + } + + return JVMTI_ERROR_NONE; +} + static void JNICALL compiled_method_load_cb(jvmtiEnv *jvmti, jmethodID method, @@ -135,16 +229,18 @@ compiled_method_load_cb(jvmtiEnv *jvmti, const void *compile_info) { jvmti_line_info_t *line_tab = NULL; + char ** line_file_names = NULL; jclass decl_class; char *class_sign = NULL; char *func_name = NULL; char *func_sign = NULL; - char *file_name= NULL; + char *file_name = NULL; char fn[PATH_MAX]; uint64_t addr = (uint64_t)(uintptr_t)code_addr; jvmtiError ret; int nr_lines = 0; /* in line_tab[] */ size_t len; + int output_debug_info = 0; ret = (*jvmti)->GetMethodDeclaringClass(jvmti, method, &decl_class); @@ -158,6 +254,19 @@ compiled_method_load_cb(jvmtiEnv *jvmti, if (ret != JVMTI_ERROR_NONE) { warnx("jvmti: cannot get line table for method"); nr_lines = 0; + } else if (nr_lines > 0) { + line_file_names = malloc(sizeof(char*) * nr_lines); + if (!line_file_names) { + warnx("jvmti: cannot allocate space for line table method names"); + } else { + memset(line_file_names, 0, sizeof(char*) * nr_lines); + ret = fill_source_filenames(jvmti, nr_lines, line_tab, line_file_names); + if (ret != JVMTI_ERROR_NONE) { + warnx("jvmti: fill_source_filenames failed"); + } else { + output_debug_info = 1; + } + } } } @@ -181,33 +290,14 @@ compiled_method_load_cb(jvmtiEnv *jvmti, goto error; } - /* - * Assume path name is class hierarchy, this is a common practice with Java programs - */ - if (*class_sign == 'L') { - int j, i = 0; - char *p = strrchr(class_sign, '/'); - if (p) { - /* drop the 'L' prefix and copy up to the final '/' */ - for (i = 0; i < (p - class_sign); i++) - fn[i] = class_sign[i+1]; - } - /* - * append file name, we use loops and not string ops to avoid modifying - * class_sign which is used later for the symbol name - */ - for (j = 0; i < (PATH_MAX - 1) && file_name && j < strlen(file_name); j++, i++) - fn[i] = file_name[j]; - fn[i] = '\0'; - } else { - /* fallback case */ - strcpy(fn, file_name); - } + copy_class_filename(class_sign, file_name, fn, PATH_MAX); + /* * write source line info record if we have it */ - if (jvmti_write_debug_info(jvmti_agent, addr, fn, line_tab, nr_lines)) - warnx("jvmti: write_debug_info() failed"); + if (output_debug_info) + if (jvmti_write_debug_info(jvmti_agent, addr, nr_lines, line_tab, (const char * const *) line_file_names)) + warnx("jvmti: write_debug_info() failed"); len = strlen(func_name) + strlen(class_sign) + strlen(func_sign) + 2; { @@ -223,6 +313,13 @@ error: (*jvmti)->Deallocate(jvmti, (unsigned char *)class_sign); (*jvmti)->Deallocate(jvmti, (unsigned char *)file_name); free(line_tab); + while (line_file_names && (nr_lines > 0)) { + if (line_file_names[nr_lines - 1]) { + free(line_file_names[nr_lines - 1]); + } + nr_lines -= 1; + } + free(line_file_names); } static void JNICALL diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 792af7c3b74f..9316e648a880 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -11,7 +11,7 @@ ifneq ($(wildcard $(GENHDR)),) endif CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include -LDLIBS += -lcap -lelf +LDLIBS += -lcap -lelf -lrt TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup @@ -39,7 +39,7 @@ $(BPFOBJ): force CLANG ?= clang LLC ?= llc -PROBE := $(shell llc -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) +PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) # Let newer LLVM versions transparently probe the kernel for availability # of full BPF instruction set. diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 69427531408d..6761be18a91f 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -351,7 +351,7 @@ static void test_bpf_obj_id(void) info_len != sizeof(struct bpf_map_info) || strcmp((char *)map_infos[i].name, expected_map_name), "get-map-info(fd)", - "err %d errno %d type %d(%d) info_len %u(%lu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", + "err %d errno %d type %d(%d) info_len %u(%Zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n", err, errno, map_infos[i].type, BPF_MAP_TYPE_ARRAY, info_len, sizeof(struct bpf_map_info), @@ -395,7 +395,7 @@ static void test_bpf_obj_id(void) *(int *)prog_infos[i].map_ids != map_infos[i].id || strcmp((char *)prog_infos[i].name, expected_prog_name), "get-prog-info(fd)", - "err %d errno %d i %d type %d(%d) info_len %u(%lu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", + "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n", err, errno, i, prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER, info_len, sizeof(struct bpf_prog_info), @@ -463,7 +463,7 @@ static void test_bpf_obj_id(void) memcmp(&prog_info, &prog_infos[i], info_len) || *(int *)prog_info.map_ids != saved_map_id, "get-prog-info(next_id->fd)", - "err %d errno %d info_len %u(%lu) memcmp %d map_id %u(%u)\n", + "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n", err, errno, info_len, sizeof(struct bpf_prog_info), memcmp(&prog_info, &prog_infos[i], info_len), *(int *)prog_info.map_ids, saved_map_id); @@ -509,7 +509,7 @@ static void test_bpf_obj_id(void) memcmp(&map_info, &map_infos[i], info_len) || array_value != array_magic_value, "check get-map-info(next_id->fd)", - "err %d errno %d info_len %u(%lu) memcmp %d array_value %llu(%llu)\n", + "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n", err, errno, info_len, sizeof(struct bpf_map_info), memcmp(&map_info, &map_infos[i], info_len), array_value, array_magic_value); diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3c64f30cf63c..b51017404c62 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -422,9 +422,7 @@ static struct bpf_test tests[] = { BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr_unpriv = "R1 subtraction from stack pointer", - .result_unpriv = REJECT, - .errstr = "R1 invalid mem access", + .errstr = "R1 subtraction from stack pointer", .result = REJECT, }, { @@ -606,7 +604,6 @@ static struct bpf_test tests[] = { }, .errstr = "misaligned stack access", .result = REJECT, - .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "invalid map_fd for function call", @@ -1797,7 +1794,6 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "misaligned stack access off (0x0; 0x0)+-8+2 size 8", - .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - bad alignment on reg", @@ -1810,7 +1806,6 @@ static struct bpf_test tests[] = { }, .result = REJECT, .errstr = "misaligned stack access off (0x0; 0x0)+-10+8 size 8", - .flags = F_LOAD_WITH_STRICT_ALIGNMENT, }, { "PTR_TO_STACK store/load - out of bounds low", @@ -1862,9 +1857,8 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R1 pointer += pointer", + .result = REJECT, + .errstr = "R1 pointer += pointer", }, { "unpriv: neg pointer", @@ -2592,7 +2586,8 @@ static struct bpf_test tests[] = { BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct __sk_buff, data)), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_4), - BPF_MOV64_REG(BPF_REG_2, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, len)), BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 49), BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 49), BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_2), @@ -2899,7 +2894,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "invalid access to packet", + .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, @@ -3885,9 +3880,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3, 11 }, - .errstr_unpriv = "R0 pointer += pointer", - .errstr = "R0 invalid mem access 'inv'", - .result_unpriv = REJECT, + .errstr = "R0 pointer += pointer", .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, @@ -3928,7 +3921,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 invalid mem access", + .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -3949,7 +3942,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 invalid mem access", + .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -3970,7 +3963,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 4 }, - .errstr = "R4 invalid mem access", + .errstr = "R4 pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL", .result = REJECT, .prog_type = BPF_PROG_TYPE_SCHED_CLS }, @@ -5195,10 +5188,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 bitwise operator &= on pointer", - .errstr = "invalid mem access 'inv'", + .errstr = "R0 bitwise operator &= on pointer", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value illegal alu op, 2", @@ -5214,10 +5205,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 32-bit pointer arithmetic prohibited", - .errstr = "invalid mem access 'inv'", + .errstr = "R0 32-bit pointer arithmetic prohibited", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value illegal alu op, 3", @@ -5233,10 +5222,8 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map2 = { 3 }, - .errstr_unpriv = "R0 pointer arithmetic with /= operator", - .errstr = "invalid mem access 'inv'", + .errstr = "R0 pointer arithmetic with /= operator", .result = REJECT, - .result_unpriv = REJECT, }, { "map element value illegal alu op, 4", @@ -6019,8 +6006,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map_in_map = { 3 }, - .errstr = "R1 type=inv expected=map_ptr", - .errstr_unpriv = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", + .errstr = "R1 pointer arithmetic on CONST_PTR_TO_MAP prohibited", .result = REJECT, }, { @@ -6117,6 +6103,30 @@ static struct bpf_test tests[] = { .result = ACCEPT, }, { + "ld_abs: tests on r6 and skb data reload helper", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + }, + { "ld_ind: check calling conv, r1", .insns = { BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), @@ -6300,7 +6310,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6324,7 +6334,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6350,7 +6360,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R8 invalid mem access 'inv'", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6375,7 +6385,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R8 invalid mem access 'inv'", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6423,7 +6433,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6494,7 +6504,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6545,7 +6555,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6572,7 +6582,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6598,7 +6608,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6627,7 +6637,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6657,7 +6667,7 @@ static struct bpf_test tests[] = { BPF_JMP_IMM(BPF_JA, 0, 0, -7), }, .fixup_map1 = { 4 }, - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, }, { @@ -6685,8 +6695,7 @@ static struct bpf_test tests[] = { BPF_EXIT_INSN(), }, .fixup_map1 = { 3 }, - .errstr_unpriv = "R0 pointer comparison prohibited", - .errstr = "R0 min value is negative", + .errstr = "unbounded min value", .result = REJECT, .result_unpriv = REJECT, }, @@ -6742,6 +6751,462 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "bounds check based on zero-extended MOV", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* r2 = 0x0000'0000'ffff'ffff */ + BPF_MOV32_IMM(BPF_REG_2, 0xffffffff), + /* r2 = 0 */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32), + /* no-op */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + /* access at offset 0 */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT + }, + { + "bounds check based on sign-extended MOV. test1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* r2 = 0xffff'ffff'ffff'ffff */ + BPF_MOV64_IMM(BPF_REG_2, 0xffffffff), + /* r2 = 0xffff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 32), + /* r0 = <oob pointer> */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + /* access to OOB pointer */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "map_value pointer and 4294967295", + .result = REJECT + }, + { + "bounds check based on sign-extended MOV. test2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + /* r2 = 0xffff'ffff'ffff'ffff */ + BPF_MOV64_IMM(BPF_REG_2, 0xffffffff), + /* r2 = 0xfff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_2, 36), + /* r0 = <oob pointer> */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2), + /* access to OOB pointer */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 min value is outside of the array range", + .result = REJECT + }, + { + "bounds check based on reg_off + var_off + insn_off. test1", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 29) - 1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr = "value_size=8 off=1073741825", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "bounds check based on reg_off + var_off + insn_off. test2", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct __sk_buff, mark)), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_ALU64_IMM(BPF_AND, BPF_REG_6, 1), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, (1 << 30) - 1), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, (1 << 29) - 1), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 3), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 4 }, + .errstr = "value 1073741823", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { + "bounds check after truncation of non-boundary-crossing range", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_MOV64_IMM(BPF_REG_2, 1), + /* r2 = 0x10'0000'0000 */ + BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 36), + /* r1 = [0x10'0000'0000, 0x10'0000'00ff] */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2), + /* r1 = [0x10'7fff'ffff, 0x10'8000'00fe] */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + /* r1 = [0x00, 0xff] */ + BPF_ALU32_IMM(BPF_SUB, BPF_REG_1, 0x7fffffff), + /* r1 = 0 */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* no-op */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* access at offset 0 */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT + }, + { + "bounds check after truncation of boundary-crossing range (1)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0x1'0000'007f] */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0xffff'ffff] or + * [0x0000'0000, 0x0000'007f] + */ + BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0x00, 0xff] or + * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = 0 or + * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* no-op or OOB pointer computation */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + /* not actually fully unbounded, but the bound is very high */ + .errstr = "R0 unbounded memory access", + .result = REJECT + }, + { + "bounds check after truncation of boundary-crossing range (2)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0x1'0000'007f] */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0xffff'ff80, 0xffff'ffff] or + * [0x0000'0000, 0x0000'007f] + * difference to previous test: truncation via MOV32 + * instead of ALU32. + */ + BPF_MOV32_REG(BPF_REG_1, BPF_REG_1), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = [0x00, 0xff] or + * [0xffff'ffff'0000'0080, 0xffff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 0xffffff80 >> 1), + /* r1 = 0 or + * [0x00ff'ffff'ff00'0000, 0x00ff'ffff'ffff'ffff] + */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* no-op or OOB pointer computation */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + /* not actually fully unbounded, but the bound is very high */ + .errstr = "R0 unbounded memory access", + .result = REJECT + }, + { + "bounds check after wrapping 32-bit addition", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + /* r1 = 0x7fff'ffff */ + BPF_MOV64_IMM(BPF_REG_1, 0x7fffffff), + /* r1 = 0xffff'fffe */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + /* r1 = 0 */ + BPF_ALU32_IMM(BPF_ADD, BPF_REG_1, 2), + /* no-op */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* access at offset 0 */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT + }, + { + "bounds check after shift with oversized count operand", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_2, 32), + BPF_MOV64_IMM(BPF_REG_1, 1), + /* r1 = (u32)1 << (u32)32 = ? */ + BPF_ALU32_REG(BPF_LSH, BPF_REG_1, BPF_REG_2), + /* r1 = [0x0000, 0xffff] */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xffff), + /* computes unknown pointer, potentially OOB */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 max value is outside of the array range", + .result = REJECT + }, + { + "bounds check after right shift of maybe-negative number", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + /* r1 = [0x00, 0xff] */ + BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + /* r1 = [-0x01, 0xfe] */ + BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1), + /* r1 = 0 or 0xff'ffff'ffff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* r1 = 0 or 0xffff'ffff'ffff */ + BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 8), + /* computes unknown pointer, potentially OOB */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + /* potentially OOB access */ + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, 0), + /* exit */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "R0 unbounded memory access", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test1", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x7ffffffe), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "map_value pointer and 2147483646", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test2", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 0x1fffffff), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "pointer offset 1073741822", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test3", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 0x1fffffff), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "pointer offset -1073741822", + .result = REJECT + }, + { + "bounds check map access with off+size signed 32bit overflow. test4", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_IMM(BPF_REG_1, 1000000), + BPF_ALU64_IMM(BPF_MUL, BPF_REG_1, 1000000), + BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 2), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .errstr = "map_value pointer and 1000000000000", + .result = REJECT + }, + { + "pointer/scalar confusion in state equality check (way 1)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_JMP_A(1), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + BPF_JMP_A(0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr as return value" + }, + { + "pointer/scalar confusion in state equality check (way 2)", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_REG(BPF_REG_0, BPF_REG_10), + BPF_JMP_A(1), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 leaks addr as return value" + }, + { "variable-offset ctx access", .insns = { /* Get an unknown value */ @@ -6783,6 +7248,71 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_LWT_IN, }, { + "indirect variable-offset stack access", + .insns = { + /* Fill the top 8 bytes of the stack */ + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + /* Get an unknown value */ + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0), + /* Make it small and 4-byte aligned */ + BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4), + BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 8), + /* add it to fp. We now have either fp-4 or fp-8, but + * we don't know which + */ + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10), + /* dereference it indirectly */ + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 5 }, + .errstr = "variable stack read R2", + .result = REJECT, + .prog_type = BPF_PROG_TYPE_LWT_IN, + }, + { + "direct stack access with 32-bit wraparound. test1", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x7fffffff), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN() + }, + .errstr = "fp pointer and 2147483647", + .result = REJECT + }, + { + "direct stack access with 32-bit wraparound. test2", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x3fffffff), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN() + }, + .errstr = "fp pointer and 1073741823", + .result = REJECT + }, + { + "direct stack access with 32-bit wraparound. test3", + .insns = { + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0x1fffffff), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_B, BPF_REG_1, BPF_REG_0, 0), + BPF_EXIT_INSN() + }, + .errstr = "fp pointer offset 1073741822", + .result = REJECT + }, + { "liveness pruning and write screening", .insns = { /* Get an unknown value */ @@ -7104,6 +7634,19 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { + "pkt_end - pkt_start is allowed", + .insns = { + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, + offsetof(struct __sk_buff, data_end)), + BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, + offsetof(struct __sk_buff, data)), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_2), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + }, + { "XDP pkt read, pkt_end mangling, bad access 1", .insns = { BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, @@ -7118,7 +7661,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R1 offset is outside of the packet", + .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", .result = REJECT, .prog_type = BPF_PROG_TYPE_XDP, }, @@ -7137,7 +7680,7 @@ static struct bpf_test tests[] = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_EXIT_INSN(), }, - .errstr = "R1 offset is outside of the packet", + .errstr = "R3 pointer arithmetic on PTR_TO_PACKET_END", .result = REJECT, .prog_type = BPF_PROG_TYPE_XDP, }, diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index e57b4ac40e72..7177bea1fdfa 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -1,3 +1,4 @@ CONFIG_USER_NS=y CONFIG_BPF_SYSCALL=y CONFIG_TEST_BPF=m +CONFIG_NUMA=y diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c index 66e5ce5b91f0..1aef72df20a1 100644 --- a/tools/testing/selftests/x86/ldt_gdt.c +++ b/tools/testing/selftests/x86/ldt_gdt.c @@ -122,8 +122,7 @@ static void check_valid_segment(uint16_t index, int ldt, * NB: Different Linux versions do different things with the * accessed bit in set_thread_area(). */ - if (ar != expected_ar && - (ldt || ar != (expected_ar | AR_ACCESSED))) { + if (ar != expected_ar && ar != (expected_ar | AR_ACCESSED)) { printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n", (ldt ? "LDT" : "GDT"), index, ar, expected_ar); nerrs++; @@ -627,13 +626,10 @@ static void do_multicpu_tests(void) static int finish_exec_test(void) { /* - * In a sensible world, this would be check_invalid_segment(0, 1); - * For better or for worse, though, the LDT is inherited across exec. - * We can probably change this safely, but for now we test it. + * Older kernel versions did inherit the LDT on exec() which is + * wrong because exec() starts from a clean state. */ - check_valid_segment(0, 1, - AR_DPL3 | AR_TYPE_XRCODE | AR_S | AR_P | AR_DB, - 42, true); + check_invalid_segment(0, 1); return nerrs ? 1 : 0; } diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c index 2b3d6d235015..3d7b42e77299 100644 --- a/tools/usb/usbip/src/utils.c +++ b/tools/usb/usbip/src/utils.c @@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add) char command[SYSFS_BUS_ID_SIZE + 4]; char match_busid_attr_path[SYSFS_PATH_MAX]; int rc; + int cmd_size; snprintf(match_busid_attr_path, sizeof(match_busid_attr_path), "%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME, @@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add) attr_name); if (add) - snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid); + cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", + busid); else - snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid); + cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", + busid); rc = write_sysfs_attribute(match_busid_attr_path, command, - sizeof(command)); + cmd_size); if (rc < 0) { dbg("failed to write match_busid: %s", strerror(errno)); return -1; diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index f9555b1e7f15..cc29a8148328 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -92,16 +92,23 @@ static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id) { struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id; struct arch_timer_context *vtimer; + u32 cnt_ctl; - if (!vcpu) { - pr_warn_once("Spurious arch timer IRQ on non-VCPU thread\n"); - return IRQ_NONE; - } - vtimer = vcpu_vtimer(vcpu); + /* + * We may see a timer interrupt after vcpu_put() has been called which + * sets the CPU's vcpu pointer to NULL, because even though the timer + * has been disabled in vtimer_save_state(), the hardware interrupt + * signal may not have been retired from the interrupt controller yet. + */ + if (!vcpu) + return IRQ_HANDLED; + vtimer = vcpu_vtimer(vcpu); if (!vtimer->irq.level) { - vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl); - if (kvm_timer_irq_can_fire(vtimer)) + cnt_ctl = read_sysreg_el0(cntv_ctl); + cnt_ctl &= ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT | + ARCH_TIMER_CTRL_IT_MASK; + if (cnt_ctl == (ARCH_TIMER_CTRL_ENABLE | ARCH_TIMER_CTRL_IT_STAT)) kvm_timer_update_irq(vcpu, true, vtimer); } @@ -355,6 +362,7 @@ static void vtimer_save_state(struct kvm_vcpu *vcpu) /* Disable the virtual timer */ write_sysreg_el0(0, cntv_ctl); + isb(); vtimer->loaded = false; out: @@ -720,7 +728,7 @@ static int kvm_timer_dying_cpu(unsigned int cpu) return 0; } -int kvm_timer_hyp_init(void) +int kvm_timer_hyp_init(bool has_gic) { struct arch_timer_kvm_info *info; int err; @@ -756,10 +764,13 @@ int kvm_timer_hyp_init(void) return err; } - err = irq_set_vcpu_affinity(host_vtimer_irq, kvm_get_running_vcpus()); - if (err) { - kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); - goto out_free_irq; + if (has_gic) { + err = irq_set_vcpu_affinity(host_vtimer_irq, + kvm_get_running_vcpus()); + if (err) { + kvm_err("kvm_arch_timer: error setting vcpu affinity\n"); + goto out_free_irq; + } } kvm_info("virtual timer IRQ%d\n", host_vtimer_irq); @@ -835,10 +846,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) no_vgic: preempt_disable(); timer->enabled = 1; - if (!irqchip_in_kernel(vcpu->kvm)) - kvm_timer_vcpu_load_user(vcpu); - else - kvm_timer_vcpu_load_vgic(vcpu); + kvm_timer_vcpu_load(vcpu); preempt_enable(); return 0; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 6b60c98a6e22..2e43f9d42bd5 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -1326,7 +1326,7 @@ static int init_subsystems(void) /* * Init HYP architected timer support */ - err = kvm_timer_hyp_init(); + err = kvm_timer_hyp_init(vgic_present); if (err) goto out; diff --git a/virt/kvm/arm/mmio.c b/virt/kvm/arm/mmio.c index b6e715fd3c90..dac7ceb1a677 100644 --- a/virt/kvm/arm/mmio.c +++ b/virt/kvm/arm/mmio.c @@ -112,7 +112,7 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) } trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - data); + &data); data = vcpu_data_host_to_guest(vcpu, data, len); vcpu_set_reg(vcpu, vcpu->arch.mmio_decode.rt, data); } @@ -182,14 +182,14 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, data = vcpu_data_guest_to_host(vcpu, vcpu_get_reg(vcpu, rt), len); - trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, data); + trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, len, fault_ipa, &data); kvm_mmio_write_buf(data_buf, len, data); ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); } else { trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, len, - fault_ipa, 0); + fault_ipa, NULL); ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_ipa, len, data_buf); diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index b36945d49986..b4b69c2d1012 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -509,8 +509,6 @@ static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size) */ void free_hyp_pgds(void) { - unsigned long addr; - mutex_lock(&kvm_hyp_pgd_mutex); if (boot_hyp_pgd) { @@ -521,10 +519,10 @@ void free_hyp_pgds(void) if (hyp_pgd) { unmap_hyp_range(hyp_pgd, hyp_idmap_start, PAGE_SIZE); - for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE) - unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE); - for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE) - unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE); + unmap_hyp_range(hyp_pgd, kern_hyp_va(PAGE_OFFSET), + (uintptr_t)high_memory - PAGE_OFFSET); + unmap_hyp_range(hyp_pgd, kern_hyp_va(VMALLOC_START), + VMALLOC_END - VMALLOC_START); free_pages((unsigned long)hyp_pgd, hyp_pgd_order); hyp_pgd = NULL; |