diff options
196 files changed, 2886 insertions, 641 deletions
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index d6d862db3b5d..bfd29bc8d37a 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -375,3 +375,19 @@ Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: information about CPUs heterogeneity. cpu_capacity: capacity of cpu#. + +What: /sys/devices/system/cpu/vulnerabilities + /sys/devices/system/cpu/vulnerabilities/meltdown + /sys/devices/system/cpu/vulnerabilities/spectre_v1 + /sys/devices/system/cpu/vulnerabilities/spectre_v2 +Date: January 2018 +Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> +Description: Information about CPU vulnerabilities + + The files are named after the code names of CPU + vulnerabilities. The output of those files reflects the + state of the CPUs in the system. Possible output values: + + "Not affected" CPU is not affected by the vulnerability + "Vulnerable" CPU is affected and no mitigation in effect + "Mitigation: $M" CPU is affected and mitigation $M is in effect diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index af7104aaffd9..46b26bfee27b 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -713,9 +713,6 @@ It will be ignored when crashkernel=X,high is not used or memory reserved is below 4G. - crossrelease_fullstack - [KNL] Allow to record full stack trace in cross-release - cryptomgr.notests [KNL] Disable crypto self-tests @@ -2626,6 +2623,11 @@ nosmt [KNL,S390] Disable symmetric multithreading (SMT). Equivalent to smt=1. + nospectre_v2 [X86] Disable all mitigations for the Spectre variant 2 + (indirect branch prediction) vulnerability. System may + allow data leaks with this option, which is equivalent + to spectre_v2=off. + noxsave [BUGS=X86] Disables x86 extended register state save and restore using xsave. The kernel will fallback to enabling legacy floating-point and sse state. @@ -2712,8 +2714,6 @@ 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. @@ -3100,6 +3100,12 @@ pcie_scan_all Scan all possible PCIe devices. Otherwise we only look for one device below a PCIe downstream port. + big_root_window Try to add a big 64bit memory window to the PCIe + root complex on AMD CPUs. Some GFX hardware + can resize a BAR to allow access to all VRAM. + Adding the window is slightly risky (it may + conflict with unreported devices), so this + taints the kernel. pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power Management. @@ -3288,11 +3294,20 @@ pt. [PARIDE] See Documentation/blockdev/paride.txt. - pti= [X86_64] - Control user/kernel address space isolation: - on - enable - off - disable - auto - default setting + pti= [X86_64] Control Page Table Isolation of user and + kernel address spaces. Disabling this feature + removes hardening, but improves performance of + system calls and interrupts. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable to issues that PTI mitigates + + Not specifying this option is equivalent to pti=auto. + + nopti [X86_64] + Equivalent to pti=off pty.legacy_count= [KNL] Number of legacy pty's. Overwrites compiled-in @@ -3943,6 +3958,29 @@ sonypi.*= [HW] Sony Programmable I/O Control Device driver See Documentation/laptops/sonypi.txt + spectre_v2= [X86] Control mitigation of Spectre variant 2 + (indirect branch speculation) vulnerability. + + on - unconditionally enable + off - unconditionally disable + auto - kernel detects whether your CPU model is + vulnerable + + Selecting 'on' will, and 'auto' may, choose a + mitigation method at run time according to the + CPU, the available microcode, the setting of the + CONFIG_RETPOLINE configuration option, and the + compiler with which the kernel was built. + + Specific mitigations can also be selected manually: + + retpoline - replace indirect branches + retpoline,generic - google's original retpoline + retpoline,amd - AMD-specific minimal thunk + + Not specifying this option is equivalent to + spectre_v2=auto. + spia_io_base= [HW,MTD] spia_fio_base= spia_pedr= diff --git a/Documentation/filesystems/nilfs2.txt b/Documentation/filesystems/nilfs2.txt index c0727dc36271..f2f3f8592a6f 100644 --- a/Documentation/filesystems/nilfs2.txt +++ b/Documentation/filesystems/nilfs2.txt @@ -25,8 +25,8 @@ available from the following download page. At least "mkfs.nilfs2", cleaner or garbage collector) are required. Details on the tools are described in the man pages included in the package. -Project web page: http://nilfs.sourceforge.net/ -Download page: http://nilfs.sourceforge.net/en/download.html +Project web page: https://nilfs.sourceforge.io/ +Download page: https://nilfs.sourceforge.io/en/download.html List info: http://vger.kernel.org/vger-lists.html#linux-nilfs Caveats diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt index 262722d8867b..c4a293a03c33 100644 --- a/Documentation/kbuild/kconfig-language.txt +++ b/Documentation/kbuild/kconfig-language.txt @@ -200,10 +200,14 @@ module state. Dependency expressions have the following syntax: <expr> ::= <symbol> (1) <symbol> '=' <symbol> (2) <symbol> '!=' <symbol> (3) - '(' <expr> ')' (4) - '!' <expr> (5) - <expr> '&&' <expr> (6) - <expr> '||' <expr> (7) + <symbol1> '<' <symbol2> (4) + <symbol1> '>' <symbol2> (4) + <symbol1> '<=' <symbol2> (4) + <symbol1> '>=' <symbol2> (4) + '(' <expr> ')' (5) + '!' <expr> (6) + <expr> '&&' <expr> (7) + <expr> '||' <expr> (8) Expressions are listed in decreasing order of precedence. @@ -214,10 +218,13 @@ Expressions are listed in decreasing order of precedence. otherwise 'n'. (3) If the values of both symbols are equal, it returns 'n', otherwise 'y'. -(4) Returns the value of the expression. Used to override precedence. -(5) Returns the result of (2-/expr/). -(6) Returns the result of min(/expr/, /expr/). -(7) Returns the result of max(/expr/, /expr/). +(4) If value of <symbol1> is respectively lower, greater, lower-or-equal, + or greater-or-equal than value of <symbol2>, it returns 'y', + otherwise 'n'. +(5) Returns the value of the expression. Used to override precedence. +(6) Returns the result of (2-/expr/). +(7) Returns the result of min(/expr/, /expr/). +(8) Returns the result of max(/expr/, /expr/). An expression can have a value of 'n', 'm' or 'y' (or 0, 1, 2 respectively for calculations). A menu entry becomes visible when its diff --git a/Documentation/usb/gadget-testing.txt b/Documentation/usb/gadget-testing.txt index 441a4b9b666f..5908a21fddb6 100644 --- a/Documentation/usb/gadget-testing.txt +++ b/Documentation/usb/gadget-testing.txt @@ -693,7 +693,7 @@ such specification consists of a number of lines with an inverval value in each line. The rules stated above are best illustrated with an example: # mkdir functions/uvc.usb0/control/header/h -# cd functions/uvc.usb0/control/header/h +# cd functions/uvc.usb0/control/ # ln -s header/h class/fs # ln -s header/h class/ss # mkdir -p functions/uvc.usb0/streaming/uncompressed/u/360p diff --git a/Documentation/x86/pti.txt b/Documentation/x86/pti.txt new file mode 100644 index 000000000000..d11eff61fc9a --- /dev/null +++ b/Documentation/x86/pti.txt @@ -0,0 +1,186 @@ +Overview +======== + +Page Table Isolation (pti, previously known as KAISER[1]) is a +countermeasure against attacks on the shared user/kernel address +space such as the "Meltdown" approach[2]. + +To mitigate this class of attacks, we create an independent set of +page tables for use only when running userspace applications. When +the kernel is entered via syscalls, interrupts or exceptions, the +page tables are switched to the full "kernel" copy. When the system +switches back to user mode, the user copy is used again. + +The userspace page tables contain only a minimal amount of kernel +data: only what is needed to enter/exit the kernel such as the +entry/exit functions themselves and the interrupt descriptor table +(IDT). There are a few strictly unnecessary things that get mapped +such as the first C function when entering an interrupt (see +comments in pti.c). + +This approach helps to ensure that side-channel attacks leveraging +the paging structures do not function when PTI is enabled. It can be +enabled by setting CONFIG_PAGE_TABLE_ISOLATION=y at compile time. +Once enabled at compile-time, it can be disabled at boot with the +'nopti' or 'pti=' kernel parameters (see kernel-parameters.txt). + +Page Table Management +===================== + +When PTI is enabled, the kernel manages two sets of page tables. +The first set is very similar to the single set which is present in +kernels without PTI. This includes a complete mapping of userspace +that the kernel can use for things like copy_to_user(). + +Although _complete_, the user portion of the kernel page tables is +crippled by setting the NX bit in the top level. This ensures +that any missed kernel->user CR3 switch will immediately crash +userspace upon executing its first instruction. + +The userspace page tables map only the kernel data needed to enter +and exit the kernel. This data is entirely contained in the 'struct +cpu_entry_area' structure which is placed in the fixmap which gives +each CPU's copy of the area a compile-time-fixed virtual address. + +For new userspace mappings, the kernel makes the entries in its +page tables like normal. The only difference is when the kernel +makes entries in the top (PGD) level. In addition to setting the +entry in the main kernel PGD, a copy of the entry is made in the +userspace page tables' PGD. + +This sharing at the PGD level also inherently shares all the lower +layers of the page tables. This leaves a single, shared set of +userspace page tables to manage. One PTE to lock, one set of +accessed bits, dirty bits, etc... + +Overhead +======== + +Protection against side-channel attacks is important. But, +this protection comes at a cost: + +1. Increased Memory Use + a. Each process now needs an order-1 PGD instead of order-0. + (Consumes an additional 4k per process). + b. The 'cpu_entry_area' structure must be 2MB in size and 2MB + aligned so that it can be mapped by setting a single PMD + entry. This consumes nearly 2MB of RAM once the kernel + is decompressed, but no space in the kernel image itself. + +2. Runtime Cost + a. CR3 manipulation to switch between the page table copies + must be done at interrupt, syscall, and exception entry + and exit (it can be skipped when the kernel is interrupted, + though.) Moves to CR3 are on the order of a hundred + cycles, and are required at every entry and exit. + b. A "trampoline" must be used for SYSCALL entry. This + trampoline depends on a smaller set of resources than the + non-PTI SYSCALL entry code, so requires mapping fewer + things into the userspace page tables. The downside is + that stacks must be switched at entry time. + d. Global pages are disabled for all kernel structures not + mapped into both kernel and userspace page tables. This + feature of the MMU allows different processes to share TLB + entries mapping the kernel. Losing the feature means more + TLB misses after a context switch. The actual loss of + performance is very small, however, never exceeding 1%. + d. Process Context IDentifiers (PCID) is a CPU feature that + allows us to skip flushing the entire TLB when switching page + tables by setting a special bit in CR3 when the page tables + are changed. This makes switching the page tables (at context + switch, or kernel entry/exit) cheaper. But, on systems with + PCID support, the context switch code must flush both the user + and kernel entries out of the TLB. The user PCID TLB flush is + deferred until the exit to userspace, minimizing the cost. + See intel.com/sdm for the gory PCID/INVPCID details. + e. The userspace page tables must be populated for each new + process. Even without PTI, the shared kernel mappings + are created by copying top-level (PGD) entries into each + new process. But, with PTI, there are now *two* kernel + mappings: one in the kernel page tables that maps everything + and one for the entry/exit structures. At fork(), we need to + copy both. + f. In addition to the fork()-time copying, there must also + be an update to the userspace PGD any time a set_pgd() is done + on a PGD used to map userspace. This ensures that the kernel + and userspace copies always map the same userspace + memory. + g. On systems without PCID support, each CR3 write flushes + the entire TLB. That means that each syscall, interrupt + or exception flushes the TLB. + h. INVPCID is a TLB-flushing instruction which allows flushing + of TLB entries for non-current PCIDs. Some systems support + PCIDs, but do not support INVPCID. On these systems, addresses + can only be flushed from the TLB for the current PCID. When + flushing a kernel address, we need to flush all PCIDs, so a + single kernel address flush will require a TLB-flushing CR3 + write upon the next use of every PCID. + +Possible Future Work +==================== +1. We can be more careful about not actually writing to CR3 + unless its value is actually changed. +2. Allow PTI to be enabled/disabled at runtime in addition to the + boot-time switching. + +Testing +======== + +To test stability of PTI, the following test procedure is recommended, +ideally doing all of these in parallel: + +1. Set CONFIG_DEBUG_ENTRY=y +2. Run several copies of all of the tools/testing/selftests/x86/ tests + (excluding MPX and protection_keys) in a loop on multiple CPUs for + several minutes. These tests frequently uncover corner cases in the + kernel entry code. In general, old kernels might cause these tests + themselves to crash, but they should never crash the kernel. +3. Run the 'perf' tool in a mode (top or record) that generates many + frequent performance monitoring non-maskable interrupts (see "NMI" + in /proc/interrupts). This exercises the NMI entry/exit code which + is known to trigger bugs in code paths that did not expect to be + interrupted, including nested NMIs. Using "-c" boosts the rate of + NMIs, and using two -c with separate counters encourages nested NMIs + and less deterministic behavior. + + while true; do perf record -c 10000 -e instructions,cycles -a sleep 10; done + +4. Launch a KVM virtual machine. +5. Run 32-bit binaries on systems supporting the SYSCALL instruction. + This has been a lightly-tested code path and needs extra scrutiny. + +Debugging +========= + +Bugs in PTI cause a few different signatures of crashes +that are worth noting here. + + * Failures of the selftests/x86 code. Usually a bug in one of the + more obscure corners of entry_64.S + * Crashes in early boot, especially around CPU bringup. Bugs + in the trampoline code or mappings cause these. + * Crashes at the first interrupt. Caused by bugs in entry_64.S, + like screwing up a page table switch. Also caused by + incorrectly mapping the IRQ handler entry code. + * Crashes at the first NMI. The NMI code is separate from main + interrupt handlers and can have bugs that do not affect + normal interrupts. Also caused by incorrectly mapping NMI + code. NMIs that interrupt the entry code must be very + careful and can be the cause of crashes that show up when + running perf. + * Kernel crashes at the first exit to userspace. entry_64.S + bugs, or failing to map some of the exit code. + * Crashes at first interrupt that interrupts userspace. The paths + in entry_64.S that return to userspace are sometimes separate + from the ones that return to the kernel. + * Double faults: overflowing the kernel stack because of page + faults upon page faults. Caused by touching non-pti-mapped + data in the entry code, or forgetting to switch to kernel + CR3 before calling into C functions which are not pti-mapped. + * Userspace segfaults early in boot, sometimes manifesting + as mount(8) failing to mount the rootfs. These have + tended to be TLB invalidation issues. Usually invalidating + the wrong PCID, or otherwise missing an invalidation. + +1. https://gruss.cc/files/kaiser.pdf +2. https://meltdownattack.com/meltdown.pdf diff --git a/MAINTAINERS b/MAINTAINERS index c7f40d3bb12b..3a28cee4f0ce 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9660,8 +9660,8 @@ F: include/uapi/linux/sunrpc/ NILFS2 FILESYSTEM M: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp> L: linux-nilfs@vger.kernel.org -W: http://nilfs.sourceforge.net/ -W: http://nilfs.osdn.jp/ +W: https://nilfs.sourceforge.io/ +W: https://nilfs.osdn.jp/ T: git git://github.com/konis/nilfs2.git S: Supported F: Documentation/filesystems/nilfs2.txt @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = -rc8 NAME = Fearless Coyote # *DOCUMENTATION* @@ -484,26 +484,6 @@ CLANG_GCC_TC := --gcc-toolchain=$(GCC_TOOLCHAIN) endif KBUILD_CFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC) -KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier) -KBUILD_CFLAGS += $(call cc-disable-warning, gnu) -KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) -# Quiet clang warning: comparison of unsigned expression < 0 is always false -KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare) -# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the -# source of a reference will be _MergedGlobals and not on of the whitelisted names. -# See modpost pattern 2 -KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,) -KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior) -KBUILD_CFLAGS += $(call cc-option, -no-integrated-as) -KBUILD_AFLAGS += $(call cc-option, -no-integrated-as) -else - -# These warnings generated too much noise in a regular build. -# Use make W=1 to enable them (see scripts/Makefile.extrawarn) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) -KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) endif ifeq ($(config-targets),1) @@ -716,6 +696,29 @@ ifdef CONFIG_CC_STACKPROTECTOR endif KBUILD_CFLAGS += $(stackp-flag) +ifeq ($(cc-name),clang) +KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,) +KBUILD_CFLAGS += $(call cc-disable-warning, unused-variable) +KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier) +KBUILD_CFLAGS += $(call cc-disable-warning, gnu) +KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) +# Quiet clang warning: comparison of unsigned expression < 0 is always false +KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare) +# CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the +# source of a reference will be _MergedGlobals and not on of the whitelisted names. +# See modpost pattern 2 +KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,) +KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior) +KBUILD_CFLAGS += $(call cc-option, -no-integrated-as) +KBUILD_AFLAGS += $(call cc-option, -no-integrated-as) +else + +# These warnings generated too much noise in a regular build. +# Use make W=1 to enable them (see scripts/Makefile.extrawarn) +KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) +KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) +endif + ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls else diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index c6ecb97151a2..9025699049ca 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -88,7 +88,7 @@ void vtime_flush(struct task_struct *tsk) } if (ti->softirq_time) { - delta = cycle_to_nsec(ti->softirq_time)); + delta = cycle_to_nsec(ti->softirq_time); account_system_index_time(tsk, delta, CPUTIME_SOFTIRQ); } diff --git a/arch/powerpc/include/asm/exception-64e.h b/arch/powerpc/include/asm/exception-64e.h index a703452d67b6..555e22d5e07f 100644 --- a/arch/powerpc/include/asm/exception-64e.h +++ b/arch/powerpc/include/asm/exception-64e.h @@ -209,5 +209,11 @@ exc_##label##_book3e: ori r3,r3,vector_offset@l; \ mtspr SPRN_IVOR##vector_number,r3; +#define RFI_TO_KERNEL \ + rfi + +#define RFI_TO_USER \ + rfi + #endif /* _ASM_POWERPC_EXCEPTION_64E_H */ diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index b27205297e1d..7197b179c1b1 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -74,6 +74,59 @@ */ #define EX_R3 EX_DAR +/* + * Macros for annotating the expected destination of (h)rfid + * + * The nop instructions allow us to insert one or more instructions to flush the + * L1-D cache when returning to userspace or a guest. + */ +#define RFI_FLUSH_SLOT \ + RFI_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop + +#define RFI_TO_KERNEL \ + rfid + +#define RFI_TO_USER \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define RFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + rfid; \ + b rfi_flush_fallback + +#define HRFI_TO_KERNEL \ + hrfid + +#define HRFI_TO_USER \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_USER_OR_KERNEL \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_GUEST \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + +#define HRFI_TO_UNKNOWN \ + RFI_FLUSH_SLOT; \ + hrfid; \ + b hrfi_flush_fallback + #ifdef CONFIG_RELOCATABLE #define __EXCEPTION_RELON_PROLOG_PSERIES_1(label, h) \ mfspr r11,SPRN_##h##SRR0; /* save SRR0 */ \ @@ -218,7 +271,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtspr SPRN_##h##SRR0,r12; \ mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ mtspr SPRN_##h##SRR1,r10; \ - h##rfid; \ + h##RFI_TO_KERNEL; \ b . /* prevent speculative execution */ #define EXCEPTION_PROLOG_PSERIES_1(label, h) \ __EXCEPTION_PROLOG_PSERIES_1(label, h) @@ -232,7 +285,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943) mtspr SPRN_##h##SRR0,r12; \ mfspr r12,SPRN_##h##SRR1; /* and SRR1 */ \ mtspr SPRN_##h##SRR1,r10; \ - h##rfid; \ + h##RFI_TO_KERNEL; \ b . /* prevent speculative execution */ #define EXCEPTION_PROLOG_PSERIES_1_NORI(label, h) \ diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 8f88f771cc55..1e82eb3caabd 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -187,7 +187,20 @@ label##3: \ FTR_ENTRY_OFFSET label##1b-label##3b; \ .popsection; +#define RFI_FLUSH_FIXUP_SECTION \ +951: \ + .pushsection __rfi_flush_fixup,"a"; \ + .align 2; \ +952: \ + FTR_ENTRY_OFFSET 951b-952b; \ + .popsection; + + #ifndef __ASSEMBLY__ +#include <linux/types.h> + +extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; + void apply_feature_fixups(void); void setup_feature_keys(void); #endif diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index a409177be8bd..f0461618bf7b 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -241,6 +241,7 @@ #define H_GET_HCA_INFO 0x1B8 #define H_GET_PERF_COUNT 0x1BC #define H_MANAGE_TRACE 0x1C0 +#define H_GET_CPU_CHARACTERISTICS 0x1C8 #define H_FREE_LOGICAL_LAN_BUFFER 0x1D4 #define H_QUERY_INT_STATE 0x1E4 #define H_POLL_PENDING 0x1D8 @@ -330,6 +331,17 @@ #define H_SIGNAL_SYS_RESET_ALL_OTHERS -2 /* >= 0 values are CPU number */ +/* H_GET_CPU_CHARACTERISTICS return values */ +#define H_CPU_CHAR_SPEC_BAR_ORI31 (1ull << 63) // IBM bit 0 +#define H_CPU_CHAR_BCCTRL_SERIALISED (1ull << 62) // IBM bit 1 +#define H_CPU_CHAR_L1D_FLUSH_ORI30 (1ull << 61) // IBM bit 2 +#define H_CPU_CHAR_L1D_FLUSH_TRIG2 (1ull << 60) // IBM bit 3 +#define H_CPU_CHAR_L1D_THREAD_PRIV (1ull << 59) // IBM bit 4 + +#define H_CPU_BEHAV_FAVOUR_SECURITY (1ull << 63) // IBM bit 0 +#define H_CPU_BEHAV_L1D_FLUSH_PR (1ull << 62) // IBM bit 1 +#define H_CPU_BEHAV_BNDS_CHK_SPEC_BAR (1ull << 61) // IBM bit 2 + /* Flag values used in H_REGISTER_PROC_TBL hcall */ #define PROC_TABLE_OP_MASK 0x18 #define PROC_TABLE_DEREG 0x10 @@ -436,6 +448,11 @@ static inline unsigned int get_longbusy_msecs(int longbusy_rc) } } +struct h_cpu_char_result { + u64 character; + u64 behaviour; +}; + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_HVCALL_H */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 3892db93b837..23ac7fc0af23 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -232,6 +232,16 @@ struct paca_struct { struct sibling_subcore_state *sibling_subcore_state; #endif #endif +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * rfi fallback flush must be in its own cacheline to prevent + * other paca data leaking into the L1d + */ + u64 exrfi[EX_SIZE] __aligned(0x80); + void *rfi_flush_fallback_area; + u64 l1d_flush_congruence; + u64 l1d_flush_sets; +#endif }; extern void copy_mm_to_paca(struct mm_struct *mm); diff --git a/arch/powerpc/include/asm/plpar_wrappers.h b/arch/powerpc/include/asm/plpar_wrappers.h index 7f01b22fa6cb..55eddf50d149 100644 --- a/arch/powerpc/include/asm/plpar_wrappers.h +++ b/arch/powerpc/include/asm/plpar_wrappers.h @@ -326,4 +326,18 @@ static inline long plapr_signal_sys_reset(long cpu) return plpar_hcall_norets(H_SIGNAL_SYS_RESET, cpu); } +static inline long plpar_get_cpu_characteristics(struct h_cpu_char_result *p) +{ + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + long rc; + + rc = plpar_hcall(H_GET_CPU_CHARACTERISTICS, retbuf); + if (rc == H_SUCCESS) { + p->character = retbuf[0]; + p->behaviour = retbuf[1]; + } + + return rc; +} + #endif /* _ASM_POWERPC_PLPAR_WRAPPERS_H */ diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h index cf00ec26303a..469b7fdc9be4 100644 --- a/arch/powerpc/include/asm/setup.h +++ b/arch/powerpc/include/asm/setup.h @@ -39,6 +39,19 @@ static inline void pseries_big_endian_exceptions(void) {} static inline void pseries_little_endian_exceptions(void) {} #endif /* CONFIG_PPC_PSERIES */ +void rfi_flush_enable(bool enable); + +/* These are bit flags */ +enum l1d_flush_type { + L1D_FLUSH_NONE = 0x1, + L1D_FLUSH_FALLBACK = 0x2, + L1D_FLUSH_ORI = 0x4, + L1D_FLUSH_MTTRIG = 0x8, +}; + +void __init setup_rfi_flush(enum l1d_flush_type, bool enable); +void do_rfi_flush_fixups(enum l1d_flush_type types); + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_POWERPC_SETUP_H */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 6b958414b4e0..f390d57cf2e1 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -237,6 +237,11 @@ int main(void) OFFSET(PACA_NMI_EMERG_SP, paca_struct, nmi_emergency_sp); OFFSET(PACA_IN_MCE, paca_struct, in_mce); OFFSET(PACA_IN_NMI, paca_struct, in_nmi); + OFFSET(PACA_RFI_FLUSH_FALLBACK_AREA, paca_struct, rfi_flush_fallback_area); + OFFSET(PACA_EXRFI, paca_struct, exrfi); + OFFSET(PACA_L1D_FLUSH_CONGRUENCE, paca_struct, l1d_flush_congruence); + OFFSET(PACA_L1D_FLUSH_SETS, paca_struct, l1d_flush_sets); + #endif OFFSET(PACAHWCPUID, paca_struct, hw_cpu_id); OFFSET(PACAKEXECSTATE, paca_struct, kexec_state); diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 3320bcac7192..2748584b767d 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -37,6 +37,11 @@ #include <asm/tm.h> #include <asm/ppc-opcode.h> #include <asm/export.h> +#ifdef CONFIG_PPC_BOOK3S +#include <asm/exception-64s.h> +#else +#include <asm/exception-64e.h> +#endif /* * System calls. @@ -262,13 +267,23 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r13,GPR13(r1) /* only restore r13 if returning to usermode */ + ld r2,GPR2(r1) + ld r1,GPR1(r1) + mtlr r4 + mtcr r5 + mtspr SPRN_SRR0,r7 + mtspr SPRN_SRR1,r8 + RFI_TO_USER + b . /* prevent speculative execution */ + + /* exit to kernel */ 1: ld r2,GPR2(r1) ld r1,GPR1(r1) mtlr r4 mtcr r5 mtspr SPRN_SRR0,r7 mtspr SPRN_SRR1,r8 - RFI + RFI_TO_KERNEL b . /* prevent speculative execution */ .Lsyscall_error: @@ -397,8 +412,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) mtmsrd r10, 1 mtspr SPRN_SRR0, r11 mtspr SPRN_SRR1, r12 - - rfid + RFI_TO_USER b . /* prevent speculative execution */ #endif _ASM_NOKPROBE_SYMBOL(system_call_common); @@ -878,7 +892,7 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ACCOUNT_CPU_USER_EXIT(r13, r2, r4) REST_GPR(13, r1) -1: + mtspr SPRN_SRR1,r3 ld r2,_CCR(r1) @@ -891,8 +905,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) ld r3,GPR3(r1) ld r4,GPR4(r1) ld r1,GPR1(r1) + RFI_TO_USER + b . /* prevent speculative execution */ - rfid +1: mtspr SPRN_SRR1,r3 + + ld r2,_CCR(r1) + mtcrf 0xFF,r2 + ld r2,_NIP(r1) + mtspr SPRN_SRR0,r2 + + ld r0,GPR0(r1) + ld r2,GPR2(r1) + ld r3,GPR3(r1) + ld r4,GPR4(r1) + ld r1,GPR1(r1) + RFI_TO_KERNEL b . /* prevent speculative execution */ #endif /* CONFIG_PPC_BOOK3E */ @@ -1073,7 +1101,7 @@ __enter_rtas: mtspr SPRN_SRR0,r5 mtspr SPRN_SRR1,r6 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ rtas_return_loc: @@ -1098,7 +1126,7 @@ rtas_return_loc: mtspr SPRN_SRR0,r3 mtspr SPRN_SRR1,r4 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ _ASM_NOKPROBE_SYMBOL(__enter_rtas) _ASM_NOKPROBE_SYMBOL(rtas_return_loc) @@ -1171,7 +1199,7 @@ _GLOBAL(enter_prom) LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE) andc r11,r11,r12 mtsrr1 r11 - rfid + RFI_TO_KERNEL #endif /* CONFIG_PPC_BOOK3E */ 1: /* Return from OF */ diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e441b469dc8f..2dc10bf646b8 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -256,7 +256,7 @@ BEGIN_FTR_SECTION LOAD_HANDLER(r12, machine_check_handle_early) 1: mtspr SPRN_SRR0,r12 mtspr SPRN_SRR1,r11 - rfid + RFI_TO_KERNEL b . /* prevent speculative execution */ 2: /* Stack overflow. Stay on emergency stack and panic. @@ -445,7 +445,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) li r3,MSR_ME andc r10,r10,r3 /* Turn off MSR_ME */ mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . 2: /* @@ -463,7 +463,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) */ bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP - rfid + RFI_TO_USER_OR_KERNEL 9: /* Deliver the machine check to host kernel in V mode. */ MACHINE_CHECK_HANDLER_WINDUP @@ -598,6 +598,9 @@ EXC_COMMON_BEGIN(slb_miss_common) stw r9,PACA_EXSLB+EX_CCR(r13) /* save CR in exc. frame */ std r10,PACA_EXSLB+EX_LR(r13) /* save LR */ + andi. r9,r11,MSR_PR // Check for exception from userspace + cmpdi cr4,r9,MSR_PR // And save the result in CR4 for later + /* * Test MSR_RI before calling slb_allocate_realmode, because the * MSR in r11 gets clobbered. However we still want to allocate @@ -624,9 +627,12 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) /* All done -- return from exception. */ + bne cr4,1f /* returning to kernel */ + .machine push .machine "power4" mtcrf 0x80,r9 + mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */ mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */ mtcrf 0x02,r9 /* I/D indication is in cr6 */ mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ @@ -640,9 +646,30 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) ld r11,PACA_EXSLB+EX_R11(r13) ld r12,PACA_EXSLB+EX_R12(r13) ld r13,PACA_EXSLB+EX_R13(r13) - rfid + RFI_TO_USER + b . /* prevent speculative execution */ +1: +.machine push +.machine "power4" + mtcrf 0x80,r9 + mtcrf 0x08,r9 /* MSR[PR] indication is in cr4 */ + mtcrf 0x04,r9 /* MSR[RI] indication is in cr5 */ + mtcrf 0x02,r9 /* I/D indication is in cr6 */ + mtcrf 0x01,r9 /* slb_allocate uses cr0 and cr7 */ +.machine pop + + RESTORE_CTR(r9, PACA_EXSLB) + RESTORE_PPR_PACA(PACA_EXSLB, r9) + mr r3,r12 + ld r9,PACA_EXSLB+EX_R9(r13) + ld r10,PACA_EXSLB+EX_R10(r13) + ld r11,PACA_EXSLB+EX_R11(r13) + ld r12,PACA_EXSLB+EX_R12(r13) + ld r13,PACA_EXSLB+EX_R13(r13) + RFI_TO_KERNEL b . /* prevent speculative execution */ + 2: std r3,PACA_EXSLB+EX_DAR(r13) mr r3,r12 mfspr r11,SPRN_SRR0 @@ -651,7 +678,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . 8: std r3,PACA_EXSLB+EX_DAR(r13) @@ -662,7 +689,7 @@ END_MMU_FTR_SECTION_IFCLR(MMU_FTR_TYPE_RADIX) mtspr SPRN_SRR0,r10 ld r10,PACAKMSR(r13) mtspr SPRN_SRR1,r10 - rfid + RFI_TO_KERNEL b . EXC_COMMON_BEGIN(unrecov_slb) @@ -901,7 +928,7 @@ EXC_COMMON(trap_0b_common, 0xb00, unknown_exception) mtspr SPRN_SRR0,r10 ; \ ld r10,PACAKMSR(r13) ; \ mtspr SPRN_SRR1,r10 ; \ - rfid ; \ + RFI_TO_KERNEL ; \ b . ; /* prevent speculative execution */ #ifdef CONFIG_PPC_FAST_ENDIAN_SWITCH @@ -917,7 +944,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE) \ xori r12,r12,MSR_LE ; \ mtspr SPRN_SRR1,r12 ; \ mr r13,r9 ; \ - rfid ; /* return to userspace */ \ + RFI_TO_USER ; /* return to userspace */ \ b . ; /* prevent speculative execution */ #else #define SYSCALL_FASTENDIAN_TEST @@ -1063,7 +1090,7 @@ TRAMP_REAL_BEGIN(hmi_exception_early) mtcr r11 REST_GPR(11, r1) ld r1,GPR1(r1) - hrfid + HRFI_TO_USER_OR_KERNEL 1: mtcr r11 REST_GPR(11, r1) @@ -1314,7 +1341,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR) ld r11,PACA_EXGEN+EX_R11(r13) ld r12,PACA_EXGEN+EX_R12(r13) ld r13,PACA_EXGEN+EX_R13(r13) - HRFID + HRFI_TO_UNKNOWN b . #endif @@ -1418,10 +1445,94 @@ masked_##_H##interrupt: \ ld r10,PACA_EXGEN+EX_R10(r13); \ ld r11,PACA_EXGEN+EX_R11(r13); \ /* returns to kernel where r13 must be set up, so don't restore it */ \ - ##_H##rfid; \ + ##_H##RFI_TO_KERNEL; \ b .; \ MASKED_DEC_HANDLER(_H) +TRAMP_REAL_BEGIN(rfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + std r12,PACA_EXRFI+EX_R12(r13) + std r8,PACA_EXRFI+EX_R13(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SETS(r13) + ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ + addi r12,r12,8 + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync +1: li r8,0 + .rept 8 /* 8-way set associative */ + ldx r11,r10,r8 + add r8,r8,r12 + xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not + add r8,r8,r11 // Add 0, this creates a dependency on the ldx + .endr + addi r10,r10,128 /* 128 byte cache line */ + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + ld r12,PACA_EXRFI+EX_R12(r13) + ld r8,PACA_EXRFI+EX_R13(r13) + GET_SCRATCH0(r13); + rfid + +TRAMP_REAL_BEGIN(hrfi_flush_fallback) + SET_SCRATCH0(r13); + GET_PACA(r13); + std r9,PACA_EXRFI+EX_R9(r13) + std r10,PACA_EXRFI+EX_R10(r13) + std r11,PACA_EXRFI+EX_R11(r13) + std r12,PACA_EXRFI+EX_R12(r13) + std r8,PACA_EXRFI+EX_R13(r13) + mfctr r9 + ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13) + ld r11,PACA_L1D_FLUSH_SETS(r13) + ld r12,PACA_L1D_FLUSH_CONGRUENCE(r13) + /* + * The load adresses are at staggered offsets within cachelines, + * which suits some pipelines better (on others it should not + * hurt). + */ + addi r12,r12,8 + mtctr r11 + DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */ + + /* order ld/st prior to dcbt stop all streams with flushing */ + sync +1: li r8,0 + .rept 8 /* 8-way set associative */ + ldx r11,r10,r8 + add r8,r8,r12 + xor r11,r11,r11 // Ensure r11 is 0 even if fallback area is not + add r8,r8,r11 // Add 0, this creates a dependency on the ldx + .endr + addi r10,r10,128 /* 128 byte cache line */ + bdnz 1b + + mtctr r9 + ld r9,PACA_EXRFI+EX_R9(r13) + ld r10,PACA_EXRFI+EX_R10(r13) + ld r11,PACA_EXRFI+EX_R11(r13) + ld r12,PACA_EXRFI+EX_R12(r13) + ld r8,PACA_EXRFI+EX_R13(r13) + GET_SCRATCH0(r13); + hrfid + /* * Real mode exceptions actually use this too, but alternate * instruction code patches (which end up in the common .text area) @@ -1441,7 +1552,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_interrupt) addi r13, r13, 4 mtspr SPRN_SRR0, r13 GET_SCRATCH0(r13) - rfid + RFI_TO_KERNEL b . TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt) @@ -1453,7 +1564,7 @@ TRAMP_REAL_BEGIN(kvmppc_skip_Hinterrupt) addi r13, r13, 4 mtspr SPRN_HSRR0, r13 GET_SCRATCH0(r13) - hrfid + HRFI_TO_KERNEL b . #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 8956a9856604..491be4179ddd 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -801,3 +801,104 @@ static int __init disable_hardlockup_detector(void) return 0; } early_initcall(disable_hardlockup_detector); + +#ifdef CONFIG_PPC_BOOK3S_64 +static enum l1d_flush_type enabled_flush_types; +static void *l1d_flush_fallback_area; +static bool no_rfi_flush; +bool rfi_flush; + +static int __init handle_no_rfi_flush(char *p) +{ + pr_info("rfi-flush: disabled on command line."); + no_rfi_flush = true; + return 0; +} +early_param("no_rfi_flush", handle_no_rfi_flush); + +/* + * The RFI flush is not KPTI, but because users will see doco that says to use + * nopti we hijack that option here to also disable the RFI flush. + */ +static int __init handle_no_pti(char *p) +{ + pr_info("rfi-flush: disabling due to 'nopti' on command line.\n"); + handle_no_rfi_flush(NULL); + return 0; +} +early_param("nopti", handle_no_pti); + +static void do_nothing(void *unused) +{ + /* + * We don't need to do the flush explicitly, just enter+exit kernel is + * sufficient, the RFI exit handlers will do the right thing. + */ +} + +void rfi_flush_enable(bool enable) +{ + if (rfi_flush == enable) + return; + + if (enable) { + do_rfi_flush_fixups(enabled_flush_types); + on_each_cpu(do_nothing, NULL, 1); + } else + do_rfi_flush_fixups(L1D_FLUSH_NONE); + + rfi_flush = enable; +} + +static void init_fallback_flush(void) +{ + u64 l1d_size, limit; + int cpu; + + l1d_size = ppc64_caches.l1d.size; + limit = min(safe_stack_limit(), ppc64_rma_size); + + /* + * Align to L1d size, and size it at 2x L1d size, to catch possible + * hardware prefetch runoff. We don't have a recipe for load patterns to + * reliably avoid the prefetcher. + */ + l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit)); + memset(l1d_flush_fallback_area, 0, l1d_size * 2); + + for_each_possible_cpu(cpu) { + /* + * The fallback flush is currently coded for 8-way + * associativity. Different associativity is possible, but it + * will be treated as 8-way and may not evict the lines as + * effectively. + * + * 128 byte lines are mandatory. + */ + u64 c = l1d_size / 8; + + paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area; + paca[cpu].l1d_flush_congruence = c; + paca[cpu].l1d_flush_sets = c / 128; + } +} + +void __init setup_rfi_flush(enum l1d_flush_type types, bool enable) +{ + if (types & L1D_FLUSH_FALLBACK) { + pr_info("rfi-flush: Using fallback displacement flush\n"); + init_fallback_flush(); + } + + if (types & L1D_FLUSH_ORI) + pr_info("rfi-flush: Using ori type flush\n"); + + if (types & L1D_FLUSH_MTTRIG) + pr_info("rfi-flush: Using mttrig type flush\n"); + + enabled_flush_types = types; + + if (!no_rfi_flush) + rfi_flush_enable(enable); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 0494e1566ee2..307843d23682 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -132,6 +132,15 @@ SECTIONS /* Read-only data */ RO_DATA(PAGE_SIZE) +#ifdef CONFIG_PPC64 + . = ALIGN(8); + __rfi_flush_fixup : AT(ADDR(__rfi_flush_fixup) - LOAD_OFFSET) { + __start___rfi_flush_fixup = .; + *(__rfi_flush_fixup) + __stop___rfi_flush_fixup = .; + } +#endif + EXCEPTION_TABLE(0) NOTES :kernel :notes diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 29ebe2fd5867..a93d719edc90 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -235,6 +235,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, gpte->may_read = true; gpte->may_write = true; gpte->page_size = MMU_PAGE_4K; + gpte->wimg = HPTE_R_M; return 0; } diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 966097232d21..b73dbc9e797d 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -65,11 +65,17 @@ struct kvm_resize_hpt { u32 order; /* These fields protected by kvm->lock */ + + /* Possible values and their usage: + * <0 an error occurred during allocation, + * -EBUSY allocation is in the progress, + * 0 allocation made successfuly. + */ int error; - bool prepare_done; - /* Private to the work thread, until prepare_done is true, - * then protected by kvm->resize_hpt_sem */ + /* Private to the work thread, until error != -EBUSY, + * then protected by kvm->lock. + */ struct kvm_hpt_info hpt; }; @@ -159,8 +165,6 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) * Reset all the reverse-mapping chains for all memslots */ kvmppc_rmap_reset(kvm); - /* Ensure that each vcpu will flush its TLB on next entry. */ - cpumask_setall(&kvm->arch.need_tlb_flush); err = 0; goto out; } @@ -176,6 +180,10 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) kvmppc_set_hpt(kvm, &info); out: + if (err == 0) + /* Ensure that each vcpu will flush its TLB on next entry. */ + cpumask_setall(&kvm->arch.need_tlb_flush); + mutex_unlock(&kvm->lock); return err; } @@ -1413,16 +1421,20 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize) static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize) { - BUG_ON(kvm->arch.resize_hpt != resize); + if (WARN_ON(!mutex_is_locked(&kvm->lock))) + return; if (!resize) return; - if (resize->hpt.virt) - kvmppc_free_hpt(&resize->hpt); + if (resize->error != -EBUSY) { + if (resize->hpt.virt) + kvmppc_free_hpt(&resize->hpt); + kfree(resize); + } - kvm->arch.resize_hpt = NULL; - kfree(resize); + if (kvm->arch.resize_hpt == resize) + kvm->arch.resize_hpt = NULL; } static void resize_hpt_prepare_work(struct work_struct *work) @@ -1431,17 +1443,41 @@ static void resize_hpt_prepare_work(struct work_struct *work) struct kvm_resize_hpt, work); struct kvm *kvm = resize->kvm; - int err; + int err = 0; - resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n", - resize->order); - - err = resize_hpt_allocate(resize); + if (WARN_ON(resize->error != -EBUSY)) + return; mutex_lock(&kvm->lock); + /* Request is still current? */ + if (kvm->arch.resize_hpt == resize) { + /* We may request large allocations here: + * do not sleep with kvm->lock held for a while. + */ + mutex_unlock(&kvm->lock); + + resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n", + resize->order); + + err = resize_hpt_allocate(resize); + + /* We have strict assumption about -EBUSY + * when preparing for HPT resize. + */ + if (WARN_ON(err == -EBUSY)) + err = -EINPROGRESS; + + mutex_lock(&kvm->lock); + /* It is possible that kvm->arch.resize_hpt != resize + * after we grab kvm->lock again. + */ + } + resize->error = err; - resize->prepare_done = true; + + if (kvm->arch.resize_hpt != resize) + resize_hpt_release(kvm, resize); mutex_unlock(&kvm->lock); } @@ -1466,14 +1502,12 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, if (resize) { if (resize->order == shift) { - /* Suitable resize in progress */ - if (resize->prepare_done) { - ret = resize->error; - if (ret != 0) - resize_hpt_release(kvm, resize); - } else { + /* Suitable resize in progress? */ + ret = resize->error; + if (ret == -EBUSY) ret = 100; /* estimated time in ms */ - } + else if (ret) + resize_hpt_release(kvm, resize); goto out; } @@ -1493,6 +1527,8 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, ret = -ENOMEM; goto out; } + + resize->error = -EBUSY; resize->order = shift; resize->kvm = kvm; INIT_WORK(&resize->work, resize_hpt_prepare_work); @@ -1547,16 +1583,12 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, if (!resize || (resize->order != shift)) goto out; - ret = -EBUSY; - if (!resize->prepare_done) - goto out; - ret = resize->error; - if (ret != 0) + if (ret) goto out; ret = resize_hpt_rehash(resize); - if (ret != 0) + if (ret) goto out; resize_hpt_pivot(resize); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 2659844784b8..9c61f736c75b 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -79,7 +79,7 @@ _GLOBAL_TOC(kvmppc_hv_entry_trampoline) mtmsrd r0,1 /* clear RI in MSR */ mtsrr0 r5 mtsrr1 r6 - RFI + RFI_TO_KERNEL kvmppc_call_hv_entry: BEGIN_FTR_SECTION @@ -199,7 +199,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) mtmsrd r6, 1 /* Clear RI in MSR */ mtsrr0 r8 mtsrr1 r7 - RFI + RFI_TO_KERNEL /* Virtual-mode return */ .Lvirt_return: @@ -1167,8 +1167,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) ld r0, VCPU_GPR(R0)(r4) ld r4, VCPU_GPR(R4)(r4) - - hrfid + HRFI_TO_GUEST b . secondary_too_late: @@ -3320,7 +3319,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) ld r4, PACAKMSR(r13) mtspr SPRN_SRR0, r3 mtspr SPRN_SRR1, r4 - rfid + RFI_TO_KERNEL 9: addi r3, r1, STACK_FRAME_OVERHEAD bl kvmppc_bad_interrupt b 9b diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index d0dc8624198f..7deaeeb14b93 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -60,6 +60,7 @@ static void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac); #define MSR_USER32 MSR_USER #define MSR_USER64 MSR_USER #define HW_PAGE_SIZE PAGE_SIZE +#define HPTE_R_M _PAGE_COHERENT #endif static bool kvmppc_is_split_real(struct kvm_vcpu *vcpu) @@ -557,6 +558,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu, pte.eaddr = eaddr; pte.vpage = eaddr >> 12; pte.page_size = MMU_PAGE_64K; + pte.wimg = HPTE_R_M; } switch (kvmppc_get_msr(vcpu) & (MSR_DR|MSR_IR)) { diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S index 42a4b237df5f..34a5adeff084 100644 --- a/arch/powerpc/kvm/book3s_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_rmhandlers.S @@ -46,6 +46,9 @@ #define FUNC(name) name +#define RFI_TO_KERNEL RFI +#define RFI_TO_GUEST RFI + .macro INTERRUPT_TRAMPOLINE intno .global kvmppc_trampoline_\intno @@ -141,7 +144,7 @@ kvmppc_handler_skip_ins: GET_SCRATCH0(r13) /* And get back into the code */ - RFI + RFI_TO_KERNEL #endif /* @@ -164,6 +167,6 @@ _GLOBAL_TOC(kvmppc_entry_trampoline) ori r5, r5, MSR_EE mtsrr0 r7 mtsrr1 r6 - RFI + RFI_TO_KERNEL #include "book3s_segment.S" diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S index 2a2b96d53999..93a180ceefad 100644 --- a/arch/powerpc/kvm/book3s_segment.S +++ b/arch/powerpc/kvm/book3s_segment.S @@ -156,7 +156,7 @@ no_dcbz32_on: PPC_LL r9, SVCPU_R9(r3) PPC_LL r3, (SVCPU_R3)(r3) - RFI + RFI_TO_GUEST kvmppc_handler_trampoline_enter_end: @@ -407,5 +407,5 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) cmpwi r12, BOOK3S_INTERRUPT_DOORBELL beqa BOOK3S_INTERRUPT_DOORBELL - RFI + RFI_TO_KERNEL kvmppc_handler_trampoline_exit_end: diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 41cf5ae273cf..a95ea007d654 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -116,6 +116,47 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } } +#ifdef CONFIG_PPC_BOOK3S_64 +void do_rfi_flush_fixups(enum l1d_flush_type types) +{ + unsigned int instrs[3], *dest; + long *start, *end; + int i; + + start = PTRRELOC(&__start___rfi_flush_fixup), + end = PTRRELOC(&__stop___rfi_flush_fixup); + + instrs[0] = 0x60000000; /* nop */ + instrs[1] = 0x60000000; /* nop */ + instrs[2] = 0x60000000; /* nop */ + + if (types & L1D_FLUSH_FALLBACK) + /* b .+16 to fallback flush */ + instrs[0] = 0x48000010; + + i = 0; + if (types & L1D_FLUSH_ORI) { + instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */ + instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/ + } + + if (types & L1D_FLUSH_MTTRIG) + instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + + for (i = 0; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction(dest, instrs[0]); + patch_instruction(dest + 1, instrs[1]); + patch_instruction(dest + 2, instrs[2]); + } + + printk(KERN_DEBUG "rfi-flush: patched %d locations\n", i); +} +#endif /* CONFIG_PPC_BOOK3S_64 */ + void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end) { long *start, *end; diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index 1edfbc1e40f4..4fb21e17504a 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -37,13 +37,62 @@ #include <asm/kexec.h> #include <asm/smp.h> #include <asm/tm.h> +#include <asm/setup.h> #include "powernv.h" +static void pnv_setup_rfi_flush(void) +{ + struct device_node *np, *fw_features; + enum l1d_flush_type type; + int enable; + + /* Default to fallback in case fw-features are not available */ + type = L1D_FLUSH_FALLBACK; + enable = 1; + + np = of_find_node_by_name(NULL, "ibm,opal"); + fw_features = of_get_child_by_name(np, "fw-features"); + of_node_put(np); + + if (fw_features) { + np = of_get_child_by_name(fw_features, "inst-l1d-flush-trig2"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_MTTRIG; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "inst-l1d-flush-ori30,30,0"); + if (np && of_property_read_bool(np, "enabled")) + type = L1D_FLUSH_ORI; + + of_node_put(np); + + /* Enable unless firmware says NOT to */ + enable = 2; + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-hv-1-to-0"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + + np = of_get_child_by_name(fw_features, "needs-l1d-flush-msr-pr-0-to-1"); + if (np && of_property_read_bool(np, "disabled")) + enable--; + + of_node_put(np); + of_node_put(fw_features); + } + + setup_rfi_flush(type, enable > 0); +} + static void __init pnv_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); + pnv_setup_rfi_flush(); + /* Initialize SMP */ pnv_smp_init(); diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 6e35780c5962..a0b20c03f078 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -574,11 +574,26 @@ static ssize_t dlpar_show(struct class *class, struct class_attribute *attr, static CLASS_ATTR_RW(dlpar); -static int __init pseries_dlpar_init(void) +int __init dlpar_workqueue_init(void) { + if (pseries_hp_wq) + return 0; + pseries_hp_wq = alloc_workqueue("pseries hotplug workqueue", - WQ_UNBOUND, 1); + WQ_UNBOUND, 1); + + return pseries_hp_wq ? 0 : -ENOMEM; +} + +static int __init dlpar_sysfs_init(void) +{ + int rc; + + rc = dlpar_workqueue_init(); + if (rc) + return rc; + return sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr); } -machine_device_initcall(pseries, pseries_dlpar_init); +machine_device_initcall(pseries, dlpar_sysfs_init); diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h index 4470a3194311..1ae1d9f4dbe9 100644 --- a/arch/powerpc/platforms/pseries/pseries.h +++ b/arch/powerpc/platforms/pseries/pseries.h @@ -98,4 +98,6 @@ static inline unsigned long cmo_get_page_size(void) return CMO_PageSize; } +int dlpar_workqueue_init(void); + #endif /* _PSERIES_PSERIES_H */ diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 4923ffe230cf..81d8614e7379 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -69,7 +69,8 @@ static int __init init_ras_IRQ(void) /* Hotplug Events */ np = of_find_node_by_path("/event-sources/hot-plug-events"); if (np != NULL) { - request_event_sources_irqs(np, ras_hotplug_interrupt, + if (dlpar_workqueue_init() == 0) + request_event_sources_irqs(np, ras_hotplug_interrupt, "RAS_HOTPLUG"); of_node_put(np); } diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index a8531e012658..ae4f596273b5 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -459,6 +459,39 @@ static void __init find_and_init_phbs(void) of_pci_check_probe_only(); } +static void pseries_setup_rfi_flush(void) +{ + struct h_cpu_char_result result; + enum l1d_flush_type types; + bool enable; + long rc; + + /* Enable by default */ + enable = true; + + rc = plpar_get_cpu_characteristics(&result); + if (rc == H_SUCCESS) { + types = L1D_FLUSH_NONE; + + if (result.character & H_CPU_CHAR_L1D_FLUSH_TRIG2) + types |= L1D_FLUSH_MTTRIG; + if (result.character & H_CPU_CHAR_L1D_FLUSH_ORI30) + types |= L1D_FLUSH_ORI; + + /* Use fallback if nothing set in hcall */ + if (types == L1D_FLUSH_NONE) + types = L1D_FLUSH_FALLBACK; + + if (!(result.behaviour & H_CPU_BEHAV_L1D_FLUSH_PR)) + enable = false; + } else { + /* Default to fallback if case hcall is not available */ + types = L1D_FLUSH_FALLBACK; + } + + setup_rfi_flush(types, enable); +} + static void __init pSeries_setup_arch(void) { set_arch_panic_timeout(10, ARCH_PANIC_TIMEOUT); @@ -476,6 +509,8 @@ static void __init pSeries_setup_arch(void) fwnmi_init(); + pseries_setup_rfi_flush(); + /* By default, only probe PCI (can be overridden by rtas_pci) */ pci_add_flags(PCI_PROBE_ONLY); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 366b19cb79b7..bc2204f829d3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -55,7 +55,6 @@ config X86 select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_PMEM_API if X86_64 - # Causing hangs/crashes, see the commit that added this change for details. select ARCH_HAS_REFCOUNT select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_SET_MEMORY @@ -89,6 +88,7 @@ config X86 select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP @@ -430,6 +430,19 @@ config GOLDFISH def_bool y depends on X86_GOLDFISH +config RETPOLINE + bool "Avoid speculative indirect branches in kernel" + default y + help + Compile kernel with the retpoline compiler options to guard against + kernel-to-user data leaks by avoiding speculative indirect + branches. Requires a compiler with -mindirect-branch=thunk-extern + support for full protection. The kernel may run slower. + + Without compiler support, at least indirect branches in assembler + code are eliminated. Since this includes the syscall entry path, + it is not entirely pointless. + config INTEL_RDT bool "Intel Resource Director Technology support" default n diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 3e73bc255e4e..fad55160dcb9 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -230,6 +230,14 @@ KBUILD_CFLAGS += -Wno-sign-compare # KBUILD_CFLAGS += -fno-asynchronous-unwind-tables +# Avoid indirect branches in kernel to deal with Spectre +ifdef CONFIG_RETPOLINE + RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) + ifneq ($(RETPOLINE_CFLAGS),) + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE + endif +endif + archscripts: scripts_basic $(Q)$(MAKE) $(build)=arch/x86/tools relocs diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 16627fec80b2..3d09e3aca18d 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -32,6 +32,7 @@ #include <linux/linkage.h> #include <asm/inst.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> /* * The following macros are used to move an (un)aligned 16 byte value to/from @@ -2884,7 +2885,7 @@ ENTRY(aesni_xts_crypt8) pxor INC, STATE4 movdqu IV, 0x30(OUTP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x00(OUTP), INC pxor INC, STATE1 @@ -2929,7 +2930,7 @@ ENTRY(aesni_xts_crypt8) _aesni_gf128mul_x_ble() movups IV, (IVP) - call *%r11 + CALL_NOSPEC %r11 movdqu 0x40(OUTP), INC pxor INC, STATE1 diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index f7c495e2863c..a14af6eb09cb 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -17,6 +17,7 @@ #include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1227,7 +1228,7 @@ camellia_xts_crypt_16way: vpxor 14 * 16(%rax), %xmm15, %xmm14; vpxor 15 * 16(%rax), %xmm15, %xmm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 16), %rsp; diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index eee5b3982cfd..b66bbfa62f50 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -12,6 +12,7 @@ #include <linux/linkage.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #define CAMELLIA_TABLE_BYTE_LEN 272 @@ -1343,7 +1344,7 @@ camellia_xts_crypt_32way: vpxor 14 * 32(%rax), %ymm15, %ymm14; vpxor 15 * 32(%rax), %ymm15, %ymm15; - call *%r9; + CALL_NOSPEC %r9; addq $(16 * 32), %rsp; diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 7a7de27c6f41..d9b734d0c8cc 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -45,6 +45,7 @@ #include <asm/inst.h> #include <linux/linkage.h> +#include <asm/nospec-branch.h> ## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction @@ -172,7 +173,7 @@ continue_block: movzxw (bufp, %rax, 2), len lea crc_array(%rip), bufp lea (bufp, len, 1), bufp - jmp *bufp + JMP_NOSPEC bufp ################################################################ ## 2a) PROCESS FULL BLOCKS: diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 45a63e00a6af..3f48f695d5e6 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -198,8 +198,11 @@ For 32-bit we have the following conventions - kernel is built with * 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)) +#define PTI_USER_PGTABLE_BIT PAGE_SHIFT +#define PTI_USER_PGTABLE_MASK (1 << PTI_USER_PGTABLE_BIT) +#define PTI_USER_PCID_BIT X86_CR3_PTI_PCID_USER_BIT +#define PTI_USER_PCID_MASK (1 << PTI_USER_PCID_BIT) +#define PTI_USER_PGTABLE_AND_PCID_MASK (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK) .macro SET_NOFLUSH_BIT reg:req bts $X86_CR3_PCID_NOFLUSH_BIT, \reg @@ -208,7 +211,7 @@ For 32-bit we have the following conventions - kernel is built with .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 + andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg .endm .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req @@ -239,15 +242,19 @@ For 32-bit we have the following conventions - kernel is built with /* Flush needed, clear the bit */ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask movq \scratch_reg2, \scratch_reg - jmp .Lwrcr3_\@ + jmp .Lwrcr3_pcid_\@ .Lnoflush_\@: movq \scratch_reg2, \scratch_reg SET_NOFLUSH_BIT \scratch_reg +.Lwrcr3_pcid_\@: + /* Flip the ASID to the user version */ + orq $(PTI_USER_PCID_MASK), \scratch_reg + .Lwrcr3_\@: - /* Flip the PGD and ASID to the user version */ - orq $(PTI_SWITCH_MASK), \scratch_reg + /* Flip the PGD to the user version */ + orq $(PTI_USER_PGTABLE_MASK), \scratch_reg mov \scratch_reg, %cr3 .Lend_\@: .endm @@ -263,17 +270,12 @@ For 32-bit we have the following conventions - kernel is built with 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. + * Test the user pagetable bit. If set, then the user page tables + * are active. If clear CR3 already has the kernel page table + * active. */ - testq $(PTI_SWITCH_MASK), \scratch_reg - jz .Ldone_\@ + bt $PTI_USER_PGTABLE_BIT, \scratch_reg + jnc .Ldone_\@ ADJUST_KERNEL_CR3 \scratch_reg movq \scratch_reg, %cr3 @@ -290,7 +292,7 @@ For 32-bit we have the following conventions - kernel is built with * KERNEL pages can always resume with NOFLUSH as we do * explicit flushes. */ - bt $X86_CR3_PTI_SWITCH_BIT, \save_reg + bt $PTI_USER_PGTABLE_BIT, \save_reg jnc .Lnoflush_\@ /* diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ace8f321a5a1..a1f28a54f23a 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -44,6 +44,7 @@ #include <asm/asm.h> #include <asm/smap.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> .section .entry.text, "ax" @@ -290,7 +291,7 @@ ENTRY(ret_from_fork) /* kernel thread */ 1: movl %edi, %eax - call *%ebx + CALL_NOSPEC %ebx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() @@ -919,7 +920,7 @@ common_exception: movl %ecx, %es TRACE_IRQS_OFF movl %esp, %eax # pt_regs pointer - call *%edi + CALL_NOSPEC %edi jmp ret_from_exception END(common_exception) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f048e384ff54..4f8e1d35a97c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -37,6 +37,7 @@ #include <asm/pgtable_types.h> #include <asm/export.h> #include <asm/frame.h> +#include <asm/nospec-branch.h> #include <linux/err.h> #include "calling.h" @@ -191,7 +192,7 @@ ENTRY(entry_SYSCALL_64_trampoline) */ pushq %rdi movq $entry_SYSCALL_64_stage2, %rdi - jmp *%rdi + JMP_NOSPEC %rdi END(entry_SYSCALL_64_trampoline) .popsection @@ -270,7 +271,12 @@ entry_SYSCALL_64_fastpath: * It might end up jumping to the slow path. If it jumps, RAX * and all argument registers are clobbered. */ +#ifdef CONFIG_RETPOLINE + movq sys_call_table(, %rax, 8), %rax + call __x86_indirect_thunk_rax +#else call *sys_call_table(, %rax, 8) +#endif .Lentry_SYSCALL_64_after_fastpath_call: movq %rax, RAX(%rsp) @@ -442,7 +448,7 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path 1: - jmp *%rax /* Called from C */ + JMP_NOSPEC %rax /* Called from C */ END(stub_ptregs_64) .macro ptregs_stub func @@ -521,7 +527,7 @@ ENTRY(ret_from_fork) 1: /* kernel thread */ movq %r12, %rdi - call *%rbx + CALL_NOSPEC %rbx /* * A kernel thread is allowed to return here after successfully * calling do_execve(). Exit to userspace to complete the execve() diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 141e07b06216..24ffa1e88cf9 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -582,6 +582,24 @@ static __init int bts_init(void) if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts) return -ENODEV; + if (boot_cpu_has(X86_FEATURE_PTI)) { + /* + * BTS hardware writes through a virtual memory map we must + * either use the kernel physical map, or the user mapping of + * the AUX buffer. + * + * However, since this driver supports per-CPU and per-task inherit + * we cannot use the user mapping since it will not be availble + * if we're not running the owning process. + * + * With PTI we can't use the kernal map either, because its not + * there when we run userspace. + * + * For now, disable this driver when using PTI. + */ + return -ENODEV; + } + bts_pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE | PERF_PMU_CAP_EXCLUSIVE; bts_pmu.task_ctx_nr = perf_sw_context; diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index ff700d81e91e..0927cdc4f946 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -11,7 +11,32 @@ #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> +#include <asm/asm.h> #ifndef CONFIG_X86_CMPXCHG64 extern void cmpxchg8b_emu(void); #endif + +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_32 +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_e ## reg(void); +#else +#define INDIRECT_THUNK(reg) extern asmlinkage void __x86_indirect_thunk_r ## reg(void); +INDIRECT_THUNK(8) +INDIRECT_THUNK(9) +INDIRECT_THUNK(10) +INDIRECT_THUNK(11) +INDIRECT_THUNK(12) +INDIRECT_THUNK(13) +INDIRECT_THUNK(14) +INDIRECT_THUNK(15) +#endif +INDIRECT_THUNK(ax) +INDIRECT_THUNK(bx) +INDIRECT_THUNK(cx) +INDIRECT_THUNK(dx) +INDIRECT_THUNK(si) +INDIRECT_THUNK(di) +INDIRECT_THUNK(bp) +INDIRECT_THUNK(sp) +#endif /* CONFIG_RETPOLINE */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 21ac898df2d8..f275447862f4 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,6 +203,8 @@ #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_RETPOLINE ( 7*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* AMD Retpoline mitigation for Spectre variant 2 */ #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 */ @@ -342,5 +344,7 @@ #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_MELTDOWN X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 5400add2885b..8bf450b13d9f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -7,6 +7,7 @@ #include <linux/nmi.h> #include <asm/io.h> #include <asm/hyperv.h> +#include <asm/nospec-branch.h> /* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent @@ -186,10 +187,11 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) return U64_MAX; __asm__ __volatile__("mov %4, %%r8\n" - "call *%5" + CALL_NOSPEC : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input_address) - : "r" (output_address), "m" (hv_hypercall_pg) + : "r" (output_address), + THUNK_TARGET(hv_hypercall_pg) : "cc", "memory", "r8", "r9", "r10", "r11"); #else u32 input_address_hi = upper_32_bits(input_address); @@ -200,13 +202,13 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output) if (!hv_hypercall_pg) return U64_MAX; - __asm__ __volatile__("call *%7" + __asm__ __volatile__(CALL_NOSPEC : "=A" (hv_status), "+c" (input_address_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input_address_hi), "D"(output_address_hi), "S"(output_address_lo), - "m" (hv_hypercall_pg) + THUNK_TARGET(hv_hypercall_pg) : "cc", "memory"); #endif /* !x86_64 */ return hv_status; @@ -227,10 +229,10 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) #ifdef CONFIG_X86_64 { - __asm__ __volatile__("call *%4" + __asm__ __volatile__(CALL_NOSPEC : "=a" (hv_status), ASM_CALL_CONSTRAINT, "+c" (control), "+d" (input1) - : "m" (hv_hypercall_pg) + : THUNK_TARGET(hv_hypercall_pg) : "cc", "r8", "r9", "r10", "r11"); } #else @@ -238,13 +240,13 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) u32 input1_hi = upper_32_bits(input1); u32 input1_lo = lower_32_bits(input1); - __asm__ __volatile__ ("call *%5" + __asm__ __volatile__ (CALL_NOSPEC : "=A"(hv_status), "+c"(input1_lo), ASM_CALL_CONSTRAINT : "A" (control), "b" (input1_hi), - "m" (hv_hypercall_pg) + THUNK_TARGET(hv_hypercall_pg) : "cc", "edi", "esi"); } #endif diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 34c4922bbc3f..e7b983a35506 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -355,6 +355,9 @@ #define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL #define FAM10H_MMIO_CONF_BASE_SHIFT 20 #define MSR_FAM10H_NODE_ID 0xc001100c +#define MSR_F10H_DECFG 0xc0011029 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT) /* K8 MSRs */ #define MSR_K8_TOP_MEM1 0xc001001a diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000000..402a11c803c3 --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,214 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __NOSPEC_BRANCH_H__ +#define __NOSPEC_BRANCH_H__ + +#include <asm/alternative.h> +#include <asm/alternative-asm.h> +#include <asm/cpufeatures.h> + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. + */ + +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ +#define RSB_FILL_LOOPS 16 /* To avoid underflow */ + +/* + * Google experimented with loop-unrolling and this turned out to be + * the optimal version — two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr, sp) \ + mov $(nr/2), reg; \ +771: \ + call 772f; \ +773: /* speculation trap */ \ + pause; \ + jmp 773b; \ +772: \ + call 774f; \ +775: /* speculation trap */ \ + pause; \ + jmp 775b; \ +774: \ + dec reg; \ + jnz 771b; \ + add $(BITS_PER_LONG/8) * nr, sp; + +#ifdef __ASSEMBLY__ + +/* + * This should be used immediately before a retpoline alternative. It tells + * objtool where the retpolines are so that it can make sense of the control + * flow by just reading the original instruction(s) and ignoring the + * alternatives. + */ +.macro ANNOTATE_NOSPEC_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.nospec + .long .Lannotate_\@ - . + .popsection +.endm + +/* + * These are the bare retpoline primitives for indirect jmp and call. + * Do not use these directly; they only exist to make the ALTERNATIVE + * invocation below less ugly. + */ +.macro RETPOLINE_JMP reg:req + call .Ldo_rop_\@ +.Lspec_trap_\@: + pause + jmp .Lspec_trap_\@ +.Ldo_rop_\@: + mov \reg, (%_ASM_SP) + ret +.endm + +/* + * This is a wrapper around RETPOLINE_JMP so the called function in reg + * returns to the instruction after the macro. + */ +.macro RETPOLINE_CALL reg:req + jmp .Ldo_call_\@ +.Ldo_retpoline_jmp_\@: + RETPOLINE_JMP \reg +.Ldo_call_\@: + call .Ldo_retpoline_jmp_\@ +.endm + +/* + * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple + * indirect jmp/call which may be susceptible to the Spectre variant 2 + * attack. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(jmp *\reg), \ + __stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \ + __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD +#else + jmp *\reg +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE_2 __stringify(call *\reg), \ + __stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\ + __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD +#else + call *\reg +#endif +.endm + + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req +#ifdef CONFIG_RETPOLINE + ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ + \ftr +.Lskip_rsb_\@: +#endif +.endm + +#else /* __ASSEMBLY__ */ + +#define ANNOTATE_NOSPEC_ALTERNATIVE \ + "999:\n\t" \ + ".pushsection .discard.nospec\n\t" \ + ".long 999b - .\n\t" \ + ".popsection\n\t" + +#if defined(CONFIG_X86_64) && defined(RETPOLINE) + +/* + * Since the inline asm uses the %V modifier which is only in newer GCC, + * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + */ +# define CALL_NOSPEC \ + ANNOTATE_NOSPEC_ALTERNATIVE \ + ALTERNATIVE( \ + "call *%[thunk_target]\n", \ + "call __x86_indirect_thunk_%V[thunk_target]\n", \ + X86_FEATURE_RETPOLINE) +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC ALTERNATIVE("call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: addl $4, %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#else /* No retpoline for C / inline asm */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +/* The Spectre V2 mitigation variants */ +enum spectre_v2_mitigation { + SPECTRE_V2_NONE, + SPECTRE_V2_RETPOLINE_MINIMAL, + SPECTRE_V2_RETPOLINE_MINIMAL_AMD, + SPECTRE_V2_RETPOLINE_GENERIC, + SPECTRE_V2_RETPOLINE_AMD, + SPECTRE_V2_IBRS, +}; + +/* + * On VMEXIT we must ensure that no RSB predictions learned in the guest + * can be followed in the host, by overwriting the RSB completely. Both + * retpoline and IBRS mitigations for Spectre v2 need this; only on future + * CPUs with IBRS_ATT *might* it be avoided. + */ +static inline void vmexit_fill_RSB(void) +{ +#ifdef CONFIG_RETPOLINE + unsigned long loops = RSB_CLEAR_LOOPS / 2; + + asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE + ALTERNATIVE("jmp 910f", + __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)), + X86_FEATURE_RETPOLINE) + "910:" + : "=&r" (loops), ASM_CALL_CONSTRAINT + : "r" (loops) : "memory" ); +#endif +} +#endif /* __ASSEMBLY__ */ +#endif /* __NOSPEC_BRANCH_H__ */ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 7a5d6695abd3..eb66fa9cd0fc 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -38,6 +38,7 @@ do { \ #define PCI_NOASSIGN_ROMS 0x80000 #define PCI_ROOT_NO_CRS 0x100000 #define PCI_NOASSIGN_BARS 0x200000 +#define PCI_BIG_ROOT_WINDOW 0x400000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 6a60fea90b9d..625a52a5594f 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -40,7 +40,7 @@ #define CR3_NOFLUSH BIT_ULL(63) #ifdef CONFIG_PAGE_TABLE_ISOLATION -# define X86_CR3_PTI_SWITCH_BIT 11 +# define X86_CR3_PTI_PCID_USER_BIT 11 #endif #else diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4a08dd2ab32a..d33e4a26dc7e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -81,13 +81,13 @@ static inline u16 kern_pcid(u16 asid) * 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)); + BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_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)); + VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_PCID_USER_BIT)); #endif /* * The dynamically-assigned ASIDs that get passed in are small @@ -112,7 +112,7 @@ static inline u16 user_pcid(u16 asid) { u16 ret = kern_pcid(asid); #ifdef CONFIG_PAGE_TABLE_ISOLATION - ret |= 1 << X86_CR3_PTI_SWITCH_BIT; + ret |= 1 << X86_CR3_PTI_PCID_USER_BIT; #endif return ret; } diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 7cb282e9e587..bfd882617613 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -44,6 +44,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/smap.h> +#include <asm/nospec-branch.h> #include <xen/interface/xen.h> #include <xen/interface/sched.h> @@ -217,9 +218,9 @@ privcmd_call(unsigned call, __HYPERCALL_5ARG(a1, a2, a3, a4, a5); stac(); - asm volatile("call *%[call]" + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM - : [call] "a" (&hypercall_page[call]) + : [thunk_target] "a" (&hypercall_page[call]) : __HYPERCALL_CLOBBER5); clac(); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index dbaf14d69ebd..4817d743c263 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -344,9 +344,12 @@ done: static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr) { unsigned long flags; + int i; - if (instr[0] != 0x90) - return; + for (i = 0; i < a->padlen; i++) { + if (instr[i] != 0x90) + return; + } local_irq_save(flags); add_nops(instr + (a->instrlen - a->padlen), a->padlen); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bcb75dc97d44..ea831c858195 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -829,8 +829,32 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_K8); if (cpu_has(c, X86_FEATURE_XMM2)) { - /* MFENCE stops RDTSC speculation */ - set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + unsigned long long val; + int ret; + + /* + * A serializing LFENCE has less overhead than MFENCE, so + * use it for execution serialization. On families which + * don't have that MSR, LFENCE is already serializing. + * msr_set_bit() uses the safe accessors, too, even if the MSR + * is not present. + */ + msr_set_bit(MSR_F10H_DECFG, + MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT); + + /* + * Verify that the MSR write was successful (could be running + * under a hypervisor) and only then assume that LFENCE is + * serializing. + */ + ret = rdmsrl_safe(MSR_F10H_DECFG, &val); + if (!ret && (val & MSR_F10H_DECFG_LFENCE_SERIALIZE)) { + /* A serializing LFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); + } else { + /* MFENCE stops RDTSC speculation */ + set_cpu_cap(c, X86_FEATURE_MFENCE_RDTSC); + } } /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index ba0b2424c9b0..e4dc26185aa7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -10,6 +10,10 @@ */ #include <linux/init.h> #include <linux/utsname.h> +#include <linux/cpu.h> + +#include <asm/nospec-branch.h> +#include <asm/cmdline.h> #include <asm/bugs.h> #include <asm/processor.h> #include <asm/processor-flags.h> @@ -20,6 +24,8 @@ #include <asm/pgtable.h> #include <asm/set_memory.h> +static void __init spectre_v2_select_mitigation(void); + void __init check_bugs(void) { identify_boot_cpu(); @@ -29,6 +35,9 @@ void __init check_bugs(void) print_cpu_info(&boot_cpu_data); } + /* Select the proper spectre mitigation before patching alternatives */ + spectre_v2_select_mitigation(); + #ifdef CONFIG_X86_32 /* * Check whether we are able to run this kernel safely on SMP. @@ -60,3 +69,179 @@ void __init check_bugs(void) set_memory_4k((unsigned long)__va(0), 1); #endif } + +/* The kernel command line selection */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +static const char *spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", + [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", +}; + +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 mitigation: " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled = SPECTRE_V2_NONE; + +static void __init spec2_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static void __init spec2_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + pr_info("%s\n", reason); +} + +static inline bool retp_compiler(void) +{ + return __is_defined(RETPOLINE); +} + +static inline bool match_option(const char *arg, int arglen, const char *opt) +{ + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); +} + +static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) +{ + char arg[20]; + int ret; + + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, + sizeof(arg)); + if (ret > 0) { + if (match_option(arg, ret, "off")) { + goto disable; + } else if (match_option(arg, ret, "on")) { + spec2_print_if_secure("force enabled on command line."); + return SPECTRE_V2_CMD_FORCE; + } else if (match_option(arg, ret, "retpoline")) { + spec2_print_if_insecure("retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE; + } else if (match_option(arg, ret, "retpoline,amd")) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) { + pr_err("retpoline,amd selected but CPU is not AMD. Switching to AUTO select\n"); + return SPECTRE_V2_CMD_AUTO; + } + spec2_print_if_insecure("AMD retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_AMD; + } else if (match_option(arg, ret, "retpoline,generic")) { + spec2_print_if_insecure("generic retpoline selected on command line."); + return SPECTRE_V2_CMD_RETPOLINE_GENERIC; + } else if (match_option(arg, ret, "auto")) { + return SPECTRE_V2_CMD_AUTO; + } + } + + if (!cmdline_find_option_bool(boot_command_line, "nospectre_v2")) + return SPECTRE_V2_CMD_AUTO; +disable: + spec2_print_if_insecure("disabled on command line."); + return SPECTRE_V2_CMD_NONE; +} + +static void __init spectre_v2_select_mitigation(void) +{ + enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); + enum spectre_v2_mitigation mode = SPECTRE_V2_NONE; + + /* + * If the CPU is not affected and the command line mode is NONE or AUTO + * then nothing to do. + */ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) && + (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO)) + return; + + switch (cmd) { + case SPECTRE_V2_CMD_NONE: + return; + + case SPECTRE_V2_CMD_FORCE: + /* FALLTRHU */ + case SPECTRE_V2_CMD_AUTO: + goto retpoline_auto; + + case SPECTRE_V2_CMD_RETPOLINE_AMD: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_amd; + break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_generic; + break; + case SPECTRE_V2_CMD_RETPOLINE: + if (IS_ENABLED(CONFIG_RETPOLINE)) + goto retpoline_auto; + break; + } + pr_err("kernel not compiled with retpoline; no mitigation available!"); + return; + +retpoline_auto: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + retpoline_amd: + if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("LFENCE not serializing. Switching to generic retpoline\n"); + goto retpoline_generic; + } + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : + SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } else { + retpoline_generic: + mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : + SPECTRE_V2_RETPOLINE_MINIMAL; + setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + } + + spectre_v2_enabled = mode; + pr_info("%s\n", spectre_v2_strings[mode]); +} + +#undef pr_fmt + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return sprintf(buf, "Not affected\n"); + if (boot_cpu_has(X86_FEATURE_PTI)) + return sprintf(buf, "Mitigation: PTI\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1)) + return sprintf(buf, "Not affected\n"); + return sprintf(buf, "Vulnerable\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return sprintf(buf, "Not affected\n"); + + return sprintf(buf, "%s\n", spectre_v2_strings[spectre_v2_enabled]); +} +#endif diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 39d7ea865207..ef29ad001991 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -926,6 +926,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (c->x86_vendor != X86_VENDOR_AMD) setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); + setup_force_cpu_bug(X86_BUG_SPECTRE_V1); + setup_force_cpu_bug(X86_BUG_SPECTRE_V2); + fpu__init_system(c); #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 8ccdca6d3f9e..d9e460fc7a3b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -910,8 +910,17 @@ static bool is_blacklisted(unsigned int cpu) { struct cpuinfo_x86 *c = &cpu_data(cpu); - if (c->x86 == 6 && c->x86_model == INTEL_FAM6_BROADWELL_X) { - pr_err_once("late loading on model 79 is disabled.\n"); + /* + * Late loading on model 79 with microcode revision less than 0x0b000021 + * may result in a system hang. This behavior is documented in item + * BDF90, #334165 (Intel Xeon Processor E7-8800/4800 v4 Product Family). + */ + if (c->x86 == 6 && + c->x86_model == INTEL_FAM6_BROADWELL_X && + c->x86_mask == 0x01 && + c->microcode < 0x0b000021) { + pr_err_once("Erratum BDF90: late loading with revision < 0x0b000021 (0x%x) disabled.\n", c->microcode); + pr_err_once("Please consider either early loading through initrd/built-in or a potential BIOS update.\n"); return true; } diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index b6c6468e10bc..4c8440de3355 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -8,6 +8,7 @@ #include <asm/segment.h> #include <asm/export.h> #include <asm/ftrace.h> +#include <asm/nospec-branch.h> #ifdef CC_USING_FENTRY # define function_hook __fentry__ @@ -197,7 +198,8 @@ ftrace_stub: movl 0x4(%ebp), %edx subl $MCOUNT_INSN_SIZE, %eax - call *ftrace_trace_function + movl ftrace_trace_function, %ecx + CALL_NOSPEC %ecx popl %edx popl %ecx @@ -241,5 +243,5 @@ return_to_handler: movl %eax, %ecx popl %edx popl %eax - jmp *%ecx + JMP_NOSPEC %ecx #endif diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index c832291d948a..7cb8ba08beb9 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -7,7 +7,7 @@ #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> .code64 .section .entry.text, "ax" @@ -286,8 +286,8 @@ trace: * ip and parent ip are used and the list function is called when * function tracing is enabled. */ - call *ftrace_trace_function - + movq ftrace_trace_function, %r8 + CALL_NOSPEC %r8 restore_mcount_regs jmp fgraph_trace @@ -329,5 +329,5 @@ GLOBAL(return_to_handler) movq 8(%rsp), %rdx movq (%rsp), %rax addq $24, %rsp - jmp *%rdi + JMP_NOSPEC %rdi #endif diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index a83b3346a0e1..c1bdbd3d3232 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <asm/apic.h> +#include <asm/nospec-branch.h> #ifdef CONFIG_DEBUG_STACKOVERFLOW @@ -55,11 +56,11 @@ DEFINE_PER_CPU(struct irq_stack *, softirq_stack); static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=b" (stack) : "0" (stack), - "D"(func) + [thunk_target] "D"(func) : "memory", "cc", "edx", "ecx", "eax"); } @@ -95,11 +96,11 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) call_on_stack(print_stack_overflow, isp); asm volatile("xchgl %%ebx,%%esp \n" - "call *%%edi \n" + CALL_NOSPEC "movl %%ebx,%%esp \n" : "=a" (arg1), "=b" (isp) : "0" (desc), "1" (isp), - "D" (desc->handle_irq) + [thunk_target] "D" (desc->handle_irq) : "memory", "cc", "ecx"); return 1; } diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index a4eb27918ceb..a2486f444073 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -138,6 +138,17 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn, return -1; set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); pte_unmap(pte); + + /* + * PTI poisons low addresses in the kernel page tables in the + * name of making them unusable for userspace. To execute + * code at such a low address, the poison must be cleared. + * + * Note: 'pgd' actually gets set in p4d_alloc() _or_ + * pud_alloc() depending on 4/5-level paging. + */ + pgd->pgd &= ~_PAGE_NX; + return 0; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index c4deb1f34faa..2b8eb4da4d08 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3781,7 +3781,8 @@ static int kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn) bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu) { if (unlikely(!lapic_in_kernel(vcpu) || - kvm_event_needs_reinjection(vcpu))) + kvm_event_needs_reinjection(vcpu) || + vcpu->arch.exception.pending)) return false; if (!vcpu->arch.apf.delivery_as_pf_vmexit && is_guest_mode(vcpu)) @@ -5465,30 +5466,34 @@ static void mmu_destroy_caches(void) int kvm_mmu_module_init(void) { + int ret = -ENOMEM; + kvm_mmu_clear_all_pte_masks(); pte_list_desc_cache = kmem_cache_create("pte_list_desc", sizeof(struct pte_list_desc), 0, SLAB_ACCOUNT, NULL); if (!pte_list_desc_cache) - goto nomem; + goto out; mmu_page_header_cache = kmem_cache_create("kvm_mmu_page_header", sizeof(struct kvm_mmu_page), 0, SLAB_ACCOUNT, NULL); if (!mmu_page_header_cache) - goto nomem; + goto out; if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) - goto nomem; + goto out; - register_shrinker(&mmu_shrinker); + ret = register_shrinker(&mmu_shrinker); + if (ret) + goto out; return 0; -nomem: +out: mmu_destroy_caches(); - return -ENOMEM; + return ret; } /* diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index bb31c801f1fc..f40d0da1f1d3 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -45,6 +45,7 @@ #include <asm/debugreg.h> #include <asm/kvm_para.h> #include <asm/irq_remapping.h> +#include <asm/nospec-branch.h> #include <asm/virtext.h> #include "trace.h" @@ -361,7 +362,6 @@ static void recalc_intercepts(struct vcpu_svm *svm) { struct vmcb_control_area *c, *h; struct nested_state *g; - u32 h_intercept_exceptions; mark_dirty(svm->vmcb, VMCB_INTERCEPTS); @@ -372,14 +372,9 @@ static void recalc_intercepts(struct vcpu_svm *svm) h = &svm->nested.hsave->control; g = &svm->nested; - /* No need to intercept #UD if L1 doesn't intercept it */ - h_intercept_exceptions = - h->intercept_exceptions & ~(1U << UD_VECTOR); - c->intercept_cr = h->intercept_cr | g->intercept_cr; c->intercept_dr = h->intercept_dr | g->intercept_dr; - c->intercept_exceptions = - h_intercept_exceptions | g->intercept_exceptions; + c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions; c->intercept = h->intercept | g->intercept; } @@ -2202,7 +2197,6 @@ static int ud_interception(struct vcpu_svm *svm) { int er; - WARN_ON_ONCE(is_guest_mode(&svm->vcpu)); er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD); if (er == EMULATE_USER_EXIT) return 0; @@ -5034,6 +5028,9 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + #ifdef CONFIG_X86_64 wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5c14d65f676a..c829d89e2e63 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -50,6 +50,7 @@ #include <asm/apic.h> #include <asm/irq_remapping.h> #include <asm/mmu_context.h> +#include <asm/nospec-branch.h> #include "trace.h" #include "pmu.h" @@ -899,8 +900,16 @@ static inline short vmcs_field_to_offset(unsigned long field) { BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX); - if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) || - vmcs_field_to_offset_table[field] == 0) + if (field >= ARRAY_SIZE(vmcs_field_to_offset_table)) + return -ENOENT; + + /* + * FIXME: Mitigation for CVE-2017-5753. To be replaced with a + * generic mechanism. + */ + asm("lfence"); + + if (vmcs_field_to_offset_table[field] == 0) return -ENOENT; return vmcs_field_to_offset_table[field]; @@ -1887,7 +1896,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) { u32 eb; - eb = (1u << PF_VECTOR) | (1u << MC_VECTOR) | + eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) | (1u << DB_VECTOR) | (1u << AC_VECTOR); if ((vcpu->guest_debug & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) == @@ -1905,8 +1914,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; - else - eb |= 1u << UD_VECTOR; vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -5917,7 +5924,6 @@ static int handle_exception(struct kvm_vcpu *vcpu) return 1; /* already handled by vmx_vcpu_run() */ if (is_invalid_opcode(intr_info)) { - WARN_ON_ONCE(is_guest_mode(vcpu)); er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD); if (er == EMULATE_USER_EXIT) return 0; @@ -9485,6 +9491,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) #endif ); + /* Eliminate branch target predictions from guest mode */ + vmexit_fill_RSB(); + /* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */ if (debugctlmsr) update_debugctlmsr(debugctlmsr); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 171377b83be1..25a972c61b0a 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -27,6 +27,7 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +lib-$(CONFIG_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 4d34bb548b41..46e71a74e612 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -29,7 +29,8 @@ #include <asm/errno.h> #include <asm/asm.h> #include <asm/export.h> - +#include <asm/nospec-branch.h> + /* * computes a partial checksum, e.g. for TCP/UDP fragments */ @@ -156,7 +157,7 @@ ENTRY(csum_partial) negl %ebx lea 45f(%ebx,%ebx,2), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx # Handle 2-byte-aligned regions 20: addw (%esi), %ax @@ -439,7 +440,7 @@ ENTRY(csum_partial_copy_generic) andl $-32,%edx lea 3f(%ebx,%ebx), %ebx testl %esi, %esi - jmp *%ebx + JMP_NOSPEC %ebx 1: addl $64,%esi addl $64,%edi SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S new file mode 100644 index 000000000000..cb45c6cb465f --- /dev/null +++ b/arch/x86/lib/retpoline.S @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/stringify.h> +#include <linux/linkage.h> +#include <asm/dwarf2.h> +#include <asm/cpufeatures.h> +#include <asm/alternative-asm.h> +#include <asm/export.h> +#include <asm/nospec-branch.h> + +.macro THUNK reg + .section .text.__x86.indirect_thunk.\reg + +ENTRY(__x86_indirect_thunk_\reg) + CFI_STARTPROC + JMP_NOSPEC %\reg + CFI_ENDPROC +ENDPROC(__x86_indirect_thunk_\reg) +.endm + +/* + * Despite being an assembler file we can't just use .irp here + * because __KSYM_DEPS__ only uses the C preprocessor and would + * only see one instance of "__x86_indirect_thunk_\reg" rather + * than one per register with the correct names. So we do it + * the simple and nasty way... + */ +#define EXPORT_THUNK(reg) EXPORT_SYMBOL(__x86_indirect_thunk_ ## reg) +#define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg) + +GENERATE_THUNK(_ASM_AX) +GENERATE_THUNK(_ASM_BX) +GENERATE_THUNK(_ASM_CX) +GENERATE_THUNK(_ASM_DX) +GENERATE_THUNK(_ASM_SI) +GENERATE_THUNK(_ASM_DI) +GENERATE_THUNK(_ASM_BP) +GENERATE_THUNK(_ASM_SP) +#ifdef CONFIG_64BIT +GENERATE_THUNK(r8) +GENERATE_THUNK(r9) +GENERATE_THUNK(r10) +GENERATE_THUNK(r11) +GENERATE_THUNK(r12) +GENERATE_THUNK(r13) +GENERATE_THUNK(r14) +GENERATE_THUNK(r15) +#endif diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 43d4a4a29037..ce38f165489b 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -149,7 +149,7 @@ pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) * * Returns a pointer to a P4D on success, or NULL on failure. */ -static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) +static __init 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); @@ -164,12 +164,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) 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); + set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); } BUILD_BUG_ON(pgd_large(*pgd) != 0); @@ -182,7 +177,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) * * Returns a pointer to a PMD on success, or NULL on failure. */ -static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) +static __init 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); @@ -194,12 +189,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) 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); + set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); } pud = pud_offset(p4d, address); @@ -213,12 +203,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) 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); + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); } return pmd_offset(pud, address); @@ -251,12 +236,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) 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); + set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); } pte = pte_offset_kernel(pmd, address); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 7a5350d08cef..563049c483a1 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -594,6 +594,11 @@ char *__init pcibios_setup(char *str) } else if (!strcmp(str, "nocrs")) { pci_probe |= PCI_ROOT_NO_CRS; return NULL; +#ifdef CONFIG_PHYS_ADDR_T_64BIT + } else if (!strcmp(str, "big_root_window")) { + pci_probe |= PCI_BIG_ROOT_WINDOW; + return NULL; +#endif } else if (!strcmp(str, "earlydump")) { pci_early_dump_regs = 1; return NULL; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e663d6bf1328..f6a26e3cb476 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -662,10 +662,14 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2033, quirk_no_aersid); */ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) { - unsigned i; u32 base, limit, high; - struct resource *res, *conflict; struct pci_dev *other; + struct resource *res; + unsigned i; + int r; + + if (!(pci_probe & PCI_BIG_ROOT_WINDOW)) + return; /* Check that we are the only device of that type */ other = pci_get_device(dev->vendor, dev->device, NULL); @@ -699,22 +703,25 @@ static void pci_amd_enable_64bit_bar(struct pci_dev *dev) if (!res) return; + /* + * Allocate a 256GB window directly below the 0xfd00000000 hardware + * limit (see AMD Family 15h Models 30h-3Fh BKDG, sec 2.4.6). + */ res->name = "PCI Bus 0000:00"; res->flags = IORESOURCE_PREFETCH | IORESOURCE_MEM | IORESOURCE_MEM_64 | IORESOURCE_WINDOW; - res->start = 0x100000000ull; + res->start = 0xbd00000000ull; res->end = 0xfd00000000ull - 1; - /* Just grab the free area behind system memory for this */ - while ((conflict = request_resource_conflict(&iomem_resource, res))) { - if (conflict->end >= res->end) { - kfree(res); - return; - } - res->start = conflict->end + 1; + r = request_resource(&iomem_resource, res); + if (r) { + kfree(res); + return; } - dev_info(&dev->dev, "adding root bus resource %pR\n", res); + dev_info(&dev->dev, "adding root bus resource %pR (tainting kernel)\n", + res); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); base = ((res->start >> 8) & AMD_141b_MMIO_BASE_MMIOBASE_MASK) | AMD_141b_MMIO_BASE_RE_MASK | AMD_141b_MMIO_BASE_WE_MASK; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index d87ac96e37ed..2dd15e967c3f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -135,7 +135,9 @@ pgd_t * __init efi_call_phys_prolog(void) pud[j] = *pud_offset(p4d_k, vaddr); } } + pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; } + out: __flush_tlb_all(); diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bt.c b/arch/x86/platform/intel-mid/device_libs/platform_bt.c index dc036e511f48..5a0483e7bf66 100644 --- a/arch/x86/platform/intel-mid/device_libs/platform_bt.c +++ b/arch/x86/platform/intel-mid/device_libs/platform_bt.c @@ -60,7 +60,7 @@ static int __init tng_bt_sfi_setup(struct bt_sfi_data *ddata) return 0; } -static const struct bt_sfi_data tng_bt_sfi_data __initdata = { +static struct bt_sfi_data tng_bt_sfi_data __initdata = { .setup = tng_bt_sfi_setup, }; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 4d62c071b166..d85076223a69 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1325,20 +1325,18 @@ static void xen_flush_tlb_others(const struct cpumask *cpus, { struct { struct mmuext_op op; -#ifdef CONFIG_SMP - DECLARE_BITMAP(mask, num_processors); -#else DECLARE_BITMAP(mask, NR_CPUS); -#endif } *args; struct multicall_space mcs; + const size_t mc_entry_size = sizeof(args->op) + + sizeof(args->mask[0]) * BITS_TO_LONGS(num_possible_cpus()); trace_xen_mmu_flush_tlb_others(cpus, info->mm, info->start, info->end); if (cpumask_empty(cpus)) return; /* nothing to do */ - mcs = xen_mc_entry(sizeof(*args)); + mcs = xen_mc_entry(mc_entry_size); args = mcs.args; args->op.arg2.vcpumask = to_cpumask(args->mask); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 75011b80660f..3b34745d0a52 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -72,7 +72,7 @@ u64 xen_clocksource_read(void); void xen_setup_cpu_clockevents(void); void xen_save_time_memory_area(void); void xen_restore_time_memory_area(void); -void __init xen_init_time_ops(void); +void __ref xen_init_time_ops(void); void __init xen_hvm_init_time_ops(void); irqreturn_t xen_debug_interrupt(int irq, void *dev_id); diff --git a/crypto/algapi.c b/crypto/algapi.c index 60d7366ed343..9a636f961572 100644 --- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -167,6 +167,18 @@ void crypto_remove_spawns(struct crypto_alg *alg, struct list_head *list, spawn->alg = NULL; spawns = &inst->alg.cra_users; + + /* + * We may encounter an unregistered instance here, since + * an instance's spawns are set up prior to the instance + * being registered. An unregistered instance will have + * NULL ->cra_users.next, since ->cra_users isn't + * properly initialized until registration. But an + * unregistered instance cannot have any users, so treat + * it the same as ->cra_users being empty. + */ + if (spawns->next == NULL) + break; } } while ((spawns = crypto_more_spawns(alg, &stack, &top, &secondary_spawns))); diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index bdc87907d6a1..2415ad9f6dd4 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -236,6 +236,9 @@ config GENERIC_CPU_DEVICES config GENERIC_CPU_AUTOPROBE bool +config GENERIC_CPU_VULNERABILITIES + bool + config SOC_BUS bool select GLOB diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 58a9b608d821..d99038487a0d 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -511,10 +511,58 @@ static void __init cpu_dev_register_generic(void) #endif } +#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES + +ssize_t __weak cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +ssize_t __weak cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Not affected\n"); +} + +static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); +static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); +static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL); + +static struct attribute *cpu_root_vulnerabilities_attrs[] = { + &dev_attr_meltdown.attr, + &dev_attr_spectre_v1.attr, + &dev_attr_spectre_v2.attr, + NULL +}; + +static const struct attribute_group cpu_root_vulnerabilities_group = { + .name = "vulnerabilities", + .attrs = cpu_root_vulnerabilities_attrs, +}; + +static void __init cpu_register_vulnerabilities(void) +{ + if (sysfs_create_group(&cpu_subsys.dev_root->kobj, + &cpu_root_vulnerabilities_group)) + pr_err("Unable to register CPU vulnerabilities\n"); +} + +#else +static inline void cpu_register_vulnerabilities(void) { } +#endif + void __init cpu_dev_init(void) { if (subsys_system_register(&cpu_subsys, cpu_root_attr_groups)) panic("Failed to register CPU subsystem"); cpu_dev_register_generic(); + cpu_register_vulnerabilities(); } diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 85d4c57870fb..49af94627c8a 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -2777,12 +2777,12 @@ int intel_gvt_scan_and_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx) } static struct cmd_info *find_cmd_entry_any_ring(struct intel_gvt *gvt, - unsigned int opcode, int rings) + unsigned int opcode, unsigned long rings) { struct cmd_info *info = NULL; unsigned int ring; - for_each_set_bit(ring, (unsigned long *)&rings, I915_NUM_ENGINES) { + for_each_set_bit(ring, &rings, I915_NUM_ENGINES) { info = find_cmd_entry(gvt, opcode, ring); if (info) break; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 8e331142badb..64d67ff9bf08 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1359,12 +1359,15 @@ static int ppgtt_handle_guest_write_page_table_bytes(void *gp, return ret; } else { if (!test_bit(index, spt->post_shadow_bitmap)) { + int type = spt->shadow_page.type; + ppgtt_get_shadow_entry(spt, &se, index); ret = ppgtt_handle_guest_entry_removal(gpt, &se, index); if (ret) return ret; + ops->set_pfn(&se, vgpu->gtt.scratch_pt[type].page_mfn); + ppgtt_set_shadow_entry(spt, &se, index); } - ppgtt_set_post_shadow(spt, index); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 18de6569d04a..5cfba89ed586 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -467,7 +467,7 @@ static void __fence_set_priority(struct dma_fence *fence, int prio) struct drm_i915_gem_request *rq; struct intel_engine_cs *engine; - if (!dma_fence_is_i915(fence)) + if (dma_fence_is_signaled(fence) || !dma_fence_is_i915(fence)) return; rq = to_request(fence); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 333f40bc03bb..7923dfd9963c 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7027,6 +7027,8 @@ enum { #define GEN9_SLICE_COMMON_ECO_CHICKEN0 _MMIO(0x7308) #define DISABLE_PIXEL_MASK_CAMMING (1<<14) +#define GEN9_SLICE_COMMON_ECO_CHICKEN1 _MMIO(0x731c) + #define GEN7_L3SQCREG1 _MMIO(0xB010) #define VLV_B0_WA_L3SQCREG1_VALUE 0x00D30000 diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index ab5bf4e2e28e..6074e04dc99f 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1390,6 +1390,11 @@ static int glk_init_workarounds(struct intel_engine_cs *engine) if (ret) return ret; + /* WA #0862: Userspace has to set "Barrier Mode" to avoid hangs. */ + ret = wa_ring_whitelist_reg(engine, GEN9_SLICE_COMMON_ECO_CHICKEN1); + if (ret) + return ret; + /* WaToEnableHwFixForPushConstHWBug:glk */ WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index d36e25607435..e71a8cd50498 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -974,6 +974,9 @@ static void execlists_schedule(struct drm_i915_gem_request *request, int prio) GEM_BUG_ON(prio == I915_PRIORITY_INVALID); + if (i915_gem_request_completed(request)) + return; + if (prio <= READ_ONCE(request->priotree.priority)) return; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c index a2978a37b4f3..700fc754f28a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorgf119.c @@ -174,6 +174,7 @@ gf119_sor = { .links = gf119_sor_dp_links, .power = g94_sor_dp_power, .pattern = gf119_sor_dp_pattern, + .drive = gf119_sor_dp_drive, .vcpi = gf119_sor_dp_vcpi, .audio = gf119_sor_dp_audio, .audio_sym = gf119_sor_dp_audio_sym, diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index b0a1dedac802..476079f1255f 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -2656,6 +2656,9 @@ static int tegra_sor_probe(struct platform_device *pdev) name, err); goto remove; } + } else { + /* fall back to the module clock on SOR0 (eDP/LVDS only) */ + sor->clk_out = sor->clk; } sor->clk_parent = devm_clk_get(&pdev->dev, "parent"); diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index 26eddbb62893..3dd62d75f531 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -209,9 +209,6 @@ vc4_irq_postinstall(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); - /* Undo the effects of a previous vc4_irq_uninstall. */ - enable_irq(dev->irq); - /* Enable both the render done and out of memory interrupts. */ V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS); diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index 622cd43840b8..493f392b3a0a 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -327,6 +327,9 @@ static int vc4_v3d_runtime_resume(struct device *dev) return ret; vc4_v3d_init_hw(vc4->dev); + + /* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */ + enable_irq(vc4->dev->irq); vc4_irq_postinstall(vc4->dev); return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 21c62a34e558..87e8af5776a3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -2731,6 +2731,8 @@ static int vmw_cmd_dx_view_define(struct vmw_private *dev_priv, } view_type = vmw_view_cmd_to_type(header->id); + if (view_type == vmw_view_max) + return -EINVAL; cmd = container_of(header, typeof(*cmd), header); ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface, user_surface_converter, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 0545740b3724..641294aef165 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -697,7 +697,6 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane) vps->pinned = 0; /* Mapping is managed by prepare_fb/cleanup_fb */ - memset(&vps->guest_map, 0, sizeof(vps->guest_map)); memset(&vps->host_map, 0, sizeof(vps->host_map)); vps->cpp = 0; @@ -760,11 +759,6 @@ vmw_du_plane_destroy_state(struct drm_plane *plane, /* Should have been freed by cleanup_fb */ - if (vps->guest_map.virtual) { - DRM_ERROR("Guest mapping not freed\n"); - ttm_bo_kunmap(&vps->guest_map); - } - if (vps->host_map.virtual) { DRM_ERROR("Host mapping not freed\n"); ttm_bo_kunmap(&vps->host_map); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index ff9c8389ff21..cd9da2dd79af 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -175,7 +175,7 @@ struct vmw_plane_state { int pinned; /* For CPU Blit */ - struct ttm_bo_kmap_obj host_map, guest_map; + struct ttm_bo_kmap_obj host_map; unsigned int cpp; }; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 90b5437fd787..b68d74888ab1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -114,7 +114,7 @@ struct vmw_screen_target_display_unit { bool defined; /* For CPU Blit */ - struct ttm_bo_kmap_obj host_map, guest_map; + struct ttm_bo_kmap_obj host_map; unsigned int cpp; }; @@ -695,7 +695,8 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty) s32 src_pitch, dst_pitch; u8 *src, *dst; bool not_used; - + struct ttm_bo_kmap_obj guest_map; + int ret; if (!dirty->num_hits) return; @@ -706,6 +707,13 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty) if (width == 0 || height == 0) return; + ret = ttm_bo_kmap(&ddirty->buf->base, 0, ddirty->buf->base.num_pages, + &guest_map); + if (ret) { + DRM_ERROR("Failed mapping framebuffer for blit: %d\n", + ret); + goto out_cleanup; + } /* Assume we are blitting from Host (display_srf) to Guest (dmabuf) */ src_pitch = stdu->display_srf->base_size.width * stdu->cpp; @@ -713,7 +721,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty) src += ddirty->top * src_pitch + ddirty->left * stdu->cpp; dst_pitch = ddirty->pitch; - dst = ttm_kmap_obj_virtual(&stdu->guest_map, ¬_used); + dst = ttm_kmap_obj_virtual(&guest_map, ¬_used); dst += ddirty->fb_top * dst_pitch + ddirty->fb_left * stdu->cpp; @@ -772,6 +780,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty) vmw_fifo_commit(dev_priv, sizeof(*cmd)); } + ttm_bo_kunmap(&guest_map); out_cleanup: ddirty->left = ddirty->top = ddirty->fb_left = ddirty->fb_top = S32_MAX; ddirty->right = ddirty->bottom = S32_MIN; @@ -1109,9 +1118,6 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane, { struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state); - if (vps->guest_map.virtual) - ttm_bo_kunmap(&vps->guest_map); - if (vps->host_map.virtual) ttm_bo_kunmap(&vps->host_map); @@ -1277,33 +1283,11 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane, */ if (vps->content_fb_type == SEPARATE_DMA && !(dev_priv->capabilities & SVGA_CAP_3D)) { - - struct vmw_framebuffer_dmabuf *new_vfbd; - - new_vfbd = vmw_framebuffer_to_vfbd(new_fb); - - ret = ttm_bo_reserve(&new_vfbd->buffer->base, false, false, - NULL); - if (ret) - goto out_srf_unpin; - - ret = ttm_bo_kmap(&new_vfbd->buffer->base, 0, - new_vfbd->buffer->base.num_pages, - &vps->guest_map); - - ttm_bo_unreserve(&new_vfbd->buffer->base); - - if (ret) { - DRM_ERROR("Failed to map content buffer to CPU\n"); - goto out_srf_unpin; - } - ret = ttm_bo_kmap(&vps->surf->res.backup->base, 0, vps->surf->res.backup->base.num_pages, &vps->host_map); if (ret) { DRM_ERROR("Failed to map display buffer to CPU\n"); - ttm_bo_kunmap(&vps->guest_map); goto out_srf_unpin; } @@ -1350,7 +1334,6 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane, stdu->display_srf = vps->surf; stdu->content_fb_type = vps->content_fb_type; stdu->cpp = vps->cpp; - memcpy(&stdu->guest_map, &vps->guest_map, sizeof(vps->guest_map)); memcpy(&stdu->host_map, &vps->host_map, sizeof(vps->host_map)); if (!stdu->defined) diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 7750a9c38b06..1df7da47f431 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -763,11 +763,11 @@ static int complete_subctxt(struct hfi1_filedata *fd) } if (ret) { - hfi1_rcd_put(fd->uctxt); - fd->uctxt = NULL; spin_lock_irqsave(&fd->dd->uctxt_lock, flags); __clear_bit(fd->subctxt, fd->uctxt->in_use_ctxts); spin_unlock_irqrestore(&fd->dd->uctxt_lock, flags); + hfi1_rcd_put(fd->uctxt); + fd->uctxt = NULL; } return ret; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 8ac50de2b242..262c1aa2e028 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1324,7 +1324,8 @@ static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn) return err; if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) || - !MLX5_CAP_GEN(dev->mdev, disable_local_lb)) + (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) && + !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc))) return err; mutex_lock(&dev->lb_mutex); @@ -1342,7 +1343,8 @@ static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn) mlx5_core_dealloc_transport_domain(dev->mdev, tdn); if ((MLX5_CAP_GEN(dev->mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) || - !MLX5_CAP_GEN(dev->mdev, disable_local_lb)) + (!MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) && + !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc))) return; mutex_lock(&dev->lb_mutex); @@ -4158,7 +4160,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) goto err_cnt; dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev); - if (!dev->mdev->priv.uar) + if (IS_ERR(dev->mdev->priv.uar)) goto err_cong; err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false); @@ -4187,7 +4189,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) } if ((MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && - MLX5_CAP_GEN(mdev, disable_local_lb)) + (MLX5_CAP_GEN(mdev, disable_local_lb_uc) || + MLX5_CAP_GEN(mdev, disable_local_lb_mc))) mutex_init(&dev->lb_mutex); dev->ib_active = true; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 31ad28853efa..cffe5966aef9 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -4362,12 +4362,11 @@ static void to_rdma_ah_attr(struct mlx5_ib_dev *ibdev, memset(ah_attr, 0, sizeof(*ah_attr)); - ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, path->port); - rdma_ah_set_port_num(ah_attr, path->port); - if (rdma_ah_get_port_num(ah_attr) == 0 || - rdma_ah_get_port_num(ah_attr) > MLX5_CAP_GEN(dev, num_ports)) + if (!path->port || path->port > MLX5_CAP_GEN(dev, num_ports)) return; + ah_attr->type = rdma_ah_find_type(&ibdev->ib_dev, path->port); + rdma_ah_set_port_num(ah_attr, path->port); rdma_ah_set_sl(ah_attr, path->dci_cfi_prio_sl & 0xf); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index 720dfb3a1ac2..1b02283ce20e 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -741,6 +741,7 @@ isert_connect_error(struct rdma_cm_id *cma_id) { struct isert_conn *isert_conn = cma_id->qp->qp_context; + ib_drain_qp(isert_conn->qp); list_del_init(&isert_conn->node); isert_conn->cm_id = NULL; isert_put_conn(isert_conn); diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index fcf7235d5742..157e1d9e7725 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -24,6 +24,7 @@ #include <linux/kernel.h> #include <linux/clk.h> #include <linux/slab.h> +#include <linux/module.h> #include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/mmc/host.h> @@ -667,3 +668,5 @@ int renesas_sdhi_remove(struct platform_device *pdev) return 0; } EXPORT_SYMBOL_GPL(renesas_sdhi_remove); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c index f7f157a62a4a..555c7f133eb8 100644 --- a/drivers/mmc/host/s3cmci.c +++ b/drivers/mmc/host/s3cmci.c @@ -1424,7 +1424,9 @@ static const struct file_operations s3cmci_fops_state = { struct s3cmci_reg { unsigned short addr; unsigned char *name; -} debug_regs[] = { +}; + +static const struct s3cmci_reg debug_regs[] = { DBG_REG(CON), DBG_REG(PRE), DBG_REG(CMDARG), @@ -1446,7 +1448,7 @@ struct s3cmci_reg { static int s3cmci_regs_show(struct seq_file *seq, void *v) { struct s3cmci_host *host = seq->private; - struct s3cmci_reg *rptr = debug_regs; + const struct s3cmci_reg *rptr = debug_regs; for (; rptr->name; rptr++) seq_printf(seq, "SDI%s\t=0x%08x\n", rptr->name, diff --git a/drivers/mux/core.c b/drivers/mux/core.c index 2260063b0ea8..6e5cf9d9cd99 100644 --- a/drivers/mux/core.c +++ b/drivers/mux/core.c @@ -413,6 +413,7 @@ static int of_dev_node_match(struct device *dev, const void *data) return dev->of_node == data; } +/* Note this function returns a reference to the mux_chip dev. */ static struct mux_chip *of_find_mux_chip_by_node(struct device_node *np) { struct device *dev; @@ -466,6 +467,7 @@ struct mux_control *mux_control_get(struct device *dev, const char *mux_name) (!args.args_count && (mux_chip->controllers > 1))) { dev_err(dev, "%pOF: wrong #mux-control-cells for %pOF\n", np, args.np); + put_device(&mux_chip->dev); return ERR_PTR(-EINVAL); } @@ -476,10 +478,10 @@ struct mux_control *mux_control_get(struct device *dev, const char *mux_name) if (controller >= mux_chip->controllers) { dev_err(dev, "%pOF: bad mux controller %u specified in %pOF\n", np, controller, args.np); + put_device(&mux_chip->dev); return ERR_PTR(-EINVAL); } - get_device(&mux_chip->dev); return &mux_chip->mux[controller]; } EXPORT_SYMBOL_GPL(mux_control_get); diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index 410a0a95130b..b3e7fafee3df 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1913,3 +1913,7 @@ static struct platform_driver cs89x0_driver = { module_platform_driver_probe(cs89x0_driver, cs89x0_platform_probe); #endif /* CONFIG_CS89x0_PLATFORM */ + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Crystal Semiconductor (Now Cirrus Logic) CS89[02]0 network driver"); +MODULE_AUTHOR("Russell Nelson <nelson@crynwr.com>"); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 461014b7ccdd..736df59c16f5 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -757,6 +757,12 @@ static int ibmvnic_login(struct net_device *netdev) } } while (adapter->renegotiate); + /* handle pending MAC address changes after successful login */ + if (adapter->mac_change_pending) { + __ibmvnic_set_mac(netdev, &adapter->desired.mac); + adapter->mac_change_pending = false; + } + return 0; } @@ -994,11 +1000,6 @@ static int ibmvnic_open(struct net_device *netdev) mutex_lock(&adapter->reset_lock); - if (adapter->mac_change_pending) { - __ibmvnic_set_mac(netdev, &adapter->desired.mac); - adapter->mac_change_pending = false; - } - if (adapter->state != VNIC_CLOSED) { rc = ibmvnic_login(netdev); if (rc) { @@ -1532,7 +1533,7 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p) struct ibmvnic_adapter *adapter = netdev_priv(netdev); struct sockaddr *addr = p; - if (adapter->state != VNIC_OPEN) { + if (adapter->state == VNIC_PROBED) { memcpy(&adapter->desired.mac, addr, sizeof(struct sockaddr)); adapter->mac_change_pending = true; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index d629da213511..7b988595ac5f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -865,7 +865,7 @@ int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto, u16 vid); void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv); void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); -void mlx5e_timestamp_set(struct mlx5e_priv *priv); +void mlx5e_timestamp_init(struct mlx5e_priv *priv); struct mlx5e_redirect_rqt_param { bool is_rss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 9bcf38f4123b..3d46ef48d5b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -922,8 +922,9 @@ static void mlx5e_dcbnl_query_dcbx_mode(struct mlx5e_priv *priv, static void mlx5e_ets_init(struct mlx5e_priv *priv) { - int i; struct ieee_ets ets; + int err; + int i; if (!MLX5_CAP_GEN(priv->mdev, ets)) return; @@ -936,11 +937,16 @@ static void mlx5e_ets_init(struct mlx5e_priv *priv) ets.prio_tc[i] = i; } - /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ - ets.prio_tc[0] = 1; - ets.prio_tc[1] = 0; + if (ets.ets_cap > 1) { + /* tclass[prio=0]=1, tclass[prio=1]=0, tclass[prio=i]=i (for i>1) */ + ets.prio_tc[0] = 1; + ets.prio_tc[1] = 0; + } - mlx5e_dcbnl_ieee_setets_core(priv, &ets); + err = mlx5e_dcbnl_ieee_setets_core(priv, &ets); + if (err) + netdev_err(priv->netdev, + "%s, Failed to init ETS: %d\n", __func__, err); } enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index bd5af7f37198..2d1395015ab5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -207,8 +207,7 @@ void mlx5e_ethtool_get_ethtool_stats(struct mlx5e_priv *priv, return; mutex_lock(&priv->state_lock); - if (test_bit(MLX5E_STATE_OPENED, &priv->state)) - mlx5e_update_stats(priv, true); + mlx5e_update_stats(priv, true); mutex_unlock(&priv->state_lock); for (i = 0; i < mlx5e_num_stats_grps; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bbbdb5c0086b..466a4e1244d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2685,7 +2685,7 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv, netif_carrier_on(netdev); } -void mlx5e_timestamp_set(struct mlx5e_priv *priv) +void mlx5e_timestamp_init(struct mlx5e_priv *priv) { priv->tstamp.tx_type = HWTSTAMP_TX_OFF; priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; @@ -2706,7 +2706,6 @@ int mlx5e_open_locked(struct net_device *netdev) mlx5e_activate_priv_channels(priv); if (priv->profile->update_carrier) priv->profile->update_carrier(priv); - mlx5e_timestamp_set(priv); if (priv->profile->update_stats) queue_delayed_work(priv->wq, &priv->update_stats_work, 0); @@ -3238,12 +3237,12 @@ static int mlx5e_set_mac(struct net_device *netdev, void *addr) return 0; } -#define MLX5E_SET_FEATURE(netdev, feature, enable) \ +#define MLX5E_SET_FEATURE(features, feature, enable) \ do { \ if (enable) \ - netdev->features |= feature; \ + *features |= feature; \ else \ - netdev->features &= ~feature; \ + *features &= ~feature; \ } while (0) typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable); @@ -3366,6 +3365,7 @@ static int set_feature_arfs(struct net_device *netdev, bool enable) #endif static int mlx5e_handle_feature(struct net_device *netdev, + netdev_features_t *features, netdev_features_t wanted_features, netdev_features_t feature, mlx5e_feature_handler feature_handler) @@ -3384,34 +3384,40 @@ static int mlx5e_handle_feature(struct net_device *netdev, return err; } - MLX5E_SET_FEATURE(netdev, feature, enable); + MLX5E_SET_FEATURE(features, feature, enable); return 0; } static int mlx5e_set_features(struct net_device *netdev, netdev_features_t features) { + netdev_features_t oper_features = netdev->features; int err; - err = mlx5e_handle_feature(netdev, features, NETIF_F_LRO, - set_feature_lro); - err |= mlx5e_handle_feature(netdev, features, + err = mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_LRO, set_feature_lro); + err |= mlx5e_handle_feature(netdev, &oper_features, features, NETIF_F_HW_VLAN_CTAG_FILTER, set_feature_cvlan_filter); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_TC, - set_feature_tc_num_filters); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL, - set_feature_rx_all); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS, - set_feature_rx_fcs); - err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX, - set_feature_rx_vlan); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_HW_TC, set_feature_tc_num_filters); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_RXALL, set_feature_rx_all); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_RXFCS, set_feature_rx_fcs); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan); #ifdef CONFIG_RFS_ACCEL - err |= mlx5e_handle_feature(netdev, features, NETIF_F_NTUPLE, - set_feature_arfs); + err |= mlx5e_handle_feature(netdev, &oper_features, features, + NETIF_F_NTUPLE, set_feature_arfs); #endif - return err ? -EINVAL : 0; + if (err) { + netdev->features = oper_features; + return -EINVAL; + } + + return 0; } static netdev_features_t mlx5e_fix_features(struct net_device *netdev, @@ -4167,6 +4173,8 @@ static void mlx5e_build_nic_netdev_priv(struct mlx5_core_dev *mdev, INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work); INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work); INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work); + + mlx5e_timestamp_init(priv); } static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 4d1b0ff4b6e4..10fa6a18fcf9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -934,6 +934,8 @@ static void mlx5e_init_rep(struct mlx5_core_dev *mdev, mlx5e_build_rep_params(mdev, &priv->channels.params); mlx5e_build_rep_netdev(netdev); + + mlx5e_timestamp_init(priv); } static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 1f1f8af87d4d..5a4608281f38 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -238,15 +238,19 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, int err = 0; /* Temporarily enable local_lb */ - if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) { - mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb); - if (!lbtp->local_lb) - mlx5_nic_vport_update_local_lb(priv->mdev, true); + err = mlx5_nic_vport_query_local_lb(priv->mdev, &lbtp->local_lb); + if (err) + return err; + + if (!lbtp->local_lb) { + err = mlx5_nic_vport_update_local_lb(priv->mdev, true); + if (err) + return err; } err = mlx5e_refresh_tirs(priv, true); if (err) - return err; + goto out; lbtp->loopback_ok = false; init_completion(&lbtp->comp); @@ -256,16 +260,21 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, lbtp->pt.dev = priv->netdev; lbtp->pt.af_packet_priv = lbtp; dev_add_pack(&lbtp->pt); + + return 0; + +out: + if (!lbtp->local_lb) + mlx5_nic_vport_update_local_lb(priv->mdev, false); + return err; } static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, struct mlx5e_lbt_priv *lbtp) { - if (MLX5_CAP_GEN(priv->mdev, disable_local_lb)) { - if (!lbtp->local_lb) - mlx5_nic_vport_update_local_lb(priv->mdev, false); - } + if (!lbtp->local_lb) + mlx5_nic_vport_update_local_lb(priv->mdev, false); dev_remove_pack(&lbtp->pt); mlx5e_refresh_tirs(priv, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 3b2363e93ba5..ef1e787e6140 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -85,6 +85,8 @@ void mlx5i_init(struct mlx5_core_dev *mdev, mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev)); mlx5i_build_nic_params(mdev, &priv->channels.params); + mlx5e_timestamp_init(priv); + /* netdev init */ netdev->hw_features |= NETIF_F_SG; netdev->hw_features |= NETIF_F_IP_CSUM; @@ -449,7 +451,6 @@ static int mlx5i_open(struct net_device *netdev) mlx5e_refresh_tirs(epriv, false); mlx5e_activate_priv_channels(epriv); - mlx5e_timestamp_set(epriv); mutex_unlock(&epriv->state_lock); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index fa8aed62b231..5701f125e99c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -423,9 +423,13 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, switch (clock->ptp_info.pin_config[pin].func) { case PTP_PF_EXTTS: + ptp_event.index = pin; + ptp_event.timestamp = timecounter_cyc2time(&clock->tc, + be64_to_cpu(eqe->data.pps.time_stamp)); if (clock->pps_info.enabled) { ptp_event.type = PTP_CLOCK_PPSUSR; - ptp_event.pps_times.ts_real = ns_to_timespec64(eqe->data.pps.time_stamp); + ptp_event.pps_times.ts_real = + ns_to_timespec64(ptp_event.timestamp); } else { ptp_event.type = PTP_CLOCK_EXTTS; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8a89c7e8cd63..0f88fd30a09a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -319,6 +319,7 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) struct mlx5_eq_table *table = &priv->eq_table; int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq); int nvec; + int err; nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + MLX5_EQ_VEC_COMP_BASE; @@ -328,21 +329,23 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev) priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL); if (!priv->irq_info) - goto err_free_msix; + return -ENOMEM; nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1, nvec, PCI_IRQ_MSIX); - if (nvec < 0) - return nvec; + if (nvec < 0) { + err = nvec; + goto err_free_irq_info; + } table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE; return 0; -err_free_msix: +err_free_irq_info: kfree(priv->irq_info); - return -ENOMEM; + return err; } static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev) @@ -578,8 +581,7 @@ static int mlx5_core_set_hca_defaults(struct mlx5_core_dev *dev) int ret = 0; /* Disable local_lb by default */ - if ((MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && - MLX5_CAP_GEN(dev, disable_local_lb)) + if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_ETH) ret = mlx5_nic_vport_update_local_lb(dev, false); return ret; @@ -1121,9 +1123,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_stop_poll; } - if (boot && mlx5_init_once(dev, priv)) { - dev_err(&pdev->dev, "sw objs init failed\n"); - goto err_stop_poll; + if (boot) { + err = mlx5_init_once(dev, priv); + if (err) { + dev_err(&pdev->dev, "sw objs init failed\n"); + goto err_stop_poll; + } } err = mlx5_alloc_irq_vectors(dev); @@ -1133,8 +1138,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, } dev->priv.uar = mlx5_get_uars_page(dev); - if (!dev->priv.uar) { + if (IS_ERR(dev->priv.uar)) { dev_err(&pdev->dev, "Failed allocating uar, aborting\n"); + err = PTR_ERR(dev->priv.uar); goto err_disable_msix; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index 222b25908d01..8b97066dd1f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -168,18 +168,16 @@ struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev) struct mlx5_uars_page *ret; mutex_lock(&mdev->priv.bfregs.reg_head.lock); - if (list_empty(&mdev->priv.bfregs.reg_head.list)) { - ret = alloc_uars_page(mdev, false); - if (IS_ERR(ret)) { - ret = NULL; - goto out; - } - list_add(&ret->list, &mdev->priv.bfregs.reg_head.list); - } else { + if (!list_empty(&mdev->priv.bfregs.reg_head.list)) { ret = list_first_entry(&mdev->priv.bfregs.reg_head.list, struct mlx5_uars_page, list); kref_get(&ret->ref_count); + goto out; } + ret = alloc_uars_page(mdev, false); + if (IS_ERR(ret)) + goto out; + list_add(&ret->list, &mdev->priv.bfregs.reg_head.list); out: mutex_unlock(&mdev->priv.bfregs.reg_head.lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index d653b0025b13..a1296a62497d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -908,23 +908,33 @@ int mlx5_nic_vport_update_local_lb(struct mlx5_core_dev *mdev, bool enable) void *in; int err; - mlx5_core_dbg(mdev, "%s local_lb\n", enable ? "enable" : "disable"); + if (!MLX5_CAP_GEN(mdev, disable_local_lb_mc) && + !MLX5_CAP_GEN(mdev, disable_local_lb_uc)) + return 0; + in = kvzalloc(inlen, GFP_KERNEL); if (!in) return -ENOMEM; MLX5_SET(modify_nic_vport_context_in, in, - field_select.disable_mc_local_lb, 1); - MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.disable_mc_local_lb, !enable); - - MLX5_SET(modify_nic_vport_context_in, in, - field_select.disable_uc_local_lb, 1); MLX5_SET(modify_nic_vport_context_in, in, nic_vport_context.disable_uc_local_lb, !enable); + if (MLX5_CAP_GEN(mdev, disable_local_lb_mc)) + MLX5_SET(modify_nic_vport_context_in, in, + field_select.disable_mc_local_lb, 1); + + if (MLX5_CAP_GEN(mdev, disable_local_lb_uc)) + MLX5_SET(modify_nic_vport_context_in, in, + field_select.disable_uc_local_lb, 1); + err = mlx5_modify_nic_vport_context(mdev, in, inlen); + if (!err) + mlx5_core_dbg(mdev, "%s local_lb\n", + enable ? "enable" : "disable"); + kvfree(in); return err; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 00b8c642e672..e1dae0616f52 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -331,7 +331,7 @@ nfp_net_get_link_ksettings(struct net_device *netdev, ls >= ARRAY_SIZE(ls_to_ethtool)) return 0; - cmd->base.speed = ls_to_ethtool[sts]; + cmd->base.speed = ls_to_ethtool[ls]; cmd->base.duplex = DUPLEX_FULL; return 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 217b62a3f587..3e57bf5d3d03 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -776,6 +776,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, int rc = 0; struct qed_spq *p_spq = p_hwfn ? p_hwfn->p_spq : NULL; bool b_ret_ent = true; + bool eblock; if (!p_hwfn) return -EINVAL; @@ -794,6 +795,11 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, if (rc) goto spq_post_fail; + /* Check if entry is in block mode before qed_spq_add_entry, + * which might kfree p_ent. + */ + eblock = (p_ent->comp_mode == QED_SPQ_MODE_EBLOCK); + /* Add the request to the pending queue */ rc = qed_spq_add_entry(p_hwfn, p_ent, p_ent->priority); if (rc) @@ -811,7 +817,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, spin_unlock_bh(&p_spq->lock); - if (p_ent->comp_mode == QED_SPQ_MODE_EBLOCK) { + if (eblock) { /* For entries in QED BLOCK mode, the completion code cannot * perform the necessary cleanup - if it did, we couldn't * access p_ent here to see whether it's successful or not. diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index a0fe05968348..a197e11f3a56 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2089,8 +2089,8 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) add_reg(CSMR); if (cd->select_mii) add_reg(RMII_MII); - add_reg(ARSTR); if (cd->tsu) { + add_tsu_reg(ARSTR); add_tsu_reg(TSU_CTRST); add_tsu_reg(TSU_FWEN0); add_tsu_reg(TSU_FWEN1); diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index d8e5747ff4e3..264d4af0bf69 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1006,17 +1006,18 @@ static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); + mutex_unlock(&pn->all_ppp_mutex); + ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); - mutex_unlock(&pn->all_ppp_mutex); - return 0; err_unit: + mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 94c7804903c4..ec56ff29aac4 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2396,6 +2396,7 @@ static int lan78xx_reset(struct lan78xx_net *dev) buf = DEFAULT_BURST_CAP_SIZE / FS_USB_PKT_SIZE; dev->rx_urb_size = DEFAULT_BURST_CAP_SIZE; dev->rx_qlen = 4; + dev->tx_qlen = 4; } ret = lan78xx_write_reg(dev, BURST_CAP, buf); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 78367373185f..e54255597fac 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -489,6 +489,7 @@ static const struct ieee80211_iface_combination hwsim_if_comb_p2p_dev[] = { static spinlock_t hwsim_radio_lock; static LIST_HEAD(hwsim_radios); +static struct workqueue_struct *hwsim_wq; static int hwsim_radio_idx; static struct platform_driver mac80211_hwsim_driver = { @@ -3125,6 +3126,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_CHANNELS]) param.channels = nla_get_u32(info->attrs[HWSIM_ATTR_CHANNELS]); + if (param.channels > CFG80211_MAX_NUM_DIFFERENT_CHANNELS) { + GENL_SET_ERR_MSG(info, "too many channels specified"); + return -EINVAL; + } + if (info->attrs[HWSIM_ATTR_NO_VIF]) param.no_vif = true; @@ -3347,7 +3353,7 @@ static void remove_user_radios(u32 portid) if (entry->destroy_on_close && entry->portid == portid) { list_del(&entry->list); INIT_WORK(&entry->destroy_work, destroy_radio); - schedule_work(&entry->destroy_work); + queue_work(hwsim_wq, &entry->destroy_work); } } spin_unlock_bh(&hwsim_radio_lock); @@ -3422,7 +3428,7 @@ static void __net_exit hwsim_exit_net(struct net *net) list_del(&data->list); INIT_WORK(&data->destroy_work, destroy_radio); - schedule_work(&data->destroy_work); + queue_work(hwsim_wq, &data->destroy_work); } spin_unlock_bh(&hwsim_radio_lock); } @@ -3454,6 +3460,10 @@ static int __init init_mac80211_hwsim(void) spin_lock_init(&hwsim_radio_lock); + hwsim_wq = alloc_workqueue("hwsim_wq",WQ_MEM_RECLAIM,0); + if (!hwsim_wq) + return -ENOMEM; + err = register_pernet_device(&hwsim_net_ops); if (err) return err; @@ -3592,8 +3602,11 @@ static void __exit exit_mac80211_hwsim(void) hwsim_exit_netlink(); mac80211_hwsim_free(); + flush_workqueue(hwsim_wq); + unregister_netdev(hwsim_mon); platform_driver_unregister(&mac80211_hwsim_driver); unregister_pernet_device(&hwsim_net_ops); + destroy_workqueue(hwsim_wq); } module_exit(exit_mac80211_hwsim); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 76b4fe6816a0..894c2ccb3891 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -74,6 +74,7 @@ static struct nvmf_host *nvmf_host_default(void) return NULL; kref_init(&host->ref); + uuid_gen(&host->id); snprintf(host->nqn, NVMF_NQN_SIZE, "nqn.2014-08.org.nvmexpress:uuid:%pUb", &host->id); diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c index 0f695df14c9d..372ce9913e6d 100644 --- a/drivers/staging/android/ashmem.c +++ b/drivers/staging/android/ashmem.c @@ -765,10 +765,12 @@ static long ashmem_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; case ASHMEM_SET_SIZE: ret = -EINVAL; + mutex_lock(&ashmem_mutex); if (!asma->file) { ret = 0; asma->size = (size_t)arg; } + mutex_unlock(&ashmem_mutex); break; case ASHMEM_GET_SIZE: ret = asma->size; diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index 93eff7dec2f5..1b3efb14aec7 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1147,11 +1147,7 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, udc = kzalloc(sizeof(*udc), GFP_KERNEL); if (!udc) - goto err1; - - ret = device_add(&gadget->dev); - if (ret) - goto err2; + goto err_put_gadget; device_initialize(&udc->dev); udc->dev.release = usb_udc_release; @@ -1160,7 +1156,11 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, udc->dev.parent = parent; ret = dev_set_name(&udc->dev, "%s", kobject_name(&parent->kobj)); if (ret) - goto err3; + goto err_put_udc; + + ret = device_add(&gadget->dev); + if (ret) + goto err_put_udc; udc->gadget = gadget; gadget->udc = udc; @@ -1170,7 +1170,7 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, ret = device_add(&udc->dev); if (ret) - goto err4; + goto err_unlist_udc; usb_gadget_set_state(gadget, USB_STATE_NOTATTACHED); udc->vbus = true; @@ -1178,27 +1178,25 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, /* pick up one of pending gadget drivers */ ret = check_pending_gadget_drivers(udc); if (ret) - goto err5; + goto err_del_udc; mutex_unlock(&udc_lock); return 0; -err5: + err_del_udc: device_del(&udc->dev); -err4: + err_unlist_udc: list_del(&udc->list); mutex_unlock(&udc_lock); -err3: - put_device(&udc->dev); device_del(&gadget->dev); -err2: - kfree(udc); + err_put_udc: + put_device(&udc->dev); -err1: + err_put_gadget: put_device(&gadget->dev); return ret; } diff --git a/drivers/usb/misc/usb3503.c b/drivers/usb/misc/usb3503.c index 465dbf68b463..f723f7b8c9ac 100644 --- a/drivers/usb/misc/usb3503.c +++ b/drivers/usb/misc/usb3503.c @@ -279,6 +279,8 @@ static int usb3503_probe(struct usb3503 *hub) if (gpio_is_valid(hub->gpio_reset)) { err = devm_gpio_request_one(dev, hub->gpio_reset, GPIOF_OUT_INIT_LOW, "usb3503 reset"); + /* Datasheet defines a hardware reset to be at least 100us */ + usleep_range(100, 10000); if (err) { dev_err(dev, "unable to request GPIO %d as reset pin (%d)\n", diff --git a/drivers/usb/mon/mon_bin.c b/drivers/usb/mon/mon_bin.c index f6ae753ab99b..f932f40302df 100644 --- a/drivers/usb/mon/mon_bin.c +++ b/drivers/usb/mon/mon_bin.c @@ -1004,7 +1004,9 @@ static long mon_bin_ioctl(struct file *file, unsigned int cmd, unsigned long arg break; case MON_IOCQ_RING_SIZE: + mutex_lock(&rp->fetch_lock); ret = rp->b_size; + mutex_unlock(&rp->fetch_lock); break; case MON_IOCT_RING_SIZE: @@ -1231,12 +1233,16 @@ static int mon_bin_vma_fault(struct vm_fault *vmf) unsigned long offset, chunk_idx; struct page *pageptr; + mutex_lock(&rp->fetch_lock); offset = vmf->pgoff << PAGE_SHIFT; - if (offset >= rp->b_size) + if (offset >= rp->b_size) { + mutex_unlock(&rp->fetch_lock); return VM_FAULT_SIGBUS; + } chunk_idx = offset / CHUNK_SIZE; pageptr = rp->b_vec[chunk_idx].pg; get_page(pageptr); + mutex_unlock(&rp->fetch_lock); vmf->page = pageptr; return 0; } diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 7c6273bf5beb..06d502b3e913 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -124,6 +124,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x10C4, 0x8470) }, /* Juniper Networks BX Series System Console */ { USB_DEVICE(0x10C4, 0x8477) }, /* Balluff RFID */ { USB_DEVICE(0x10C4, 0x84B6) }, /* Starizona Hyperion */ + { USB_DEVICE(0x10C4, 0x85A7) }, /* LifeScan OneTouch Verio IQ */ { USB_DEVICE(0x10C4, 0x85EA) }, /* AC-Services IBUS-IF */ { USB_DEVICE(0x10C4, 0x85EB) }, /* AC-Services CIS-IBUS */ { USB_DEVICE(0x10C4, 0x85F8) }, /* Virtenio Preon32 */ @@ -174,6 +175,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x18EF, 0xE030) }, /* ELV ALC 8xxx Battery Charger */ { USB_DEVICE(0x18EF, 0xE032) }, /* ELV TFD500 Data Logger */ { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index e6127fb21c12..a7d08ae0adad 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -143,6 +143,13 @@ UNUSUAL_DEV(0x2109, 0x0711, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_ATA_1X), +/* Reported-by: Icenowy Zheng <icenowy@aosc.io> */ +UNUSUAL_DEV(0x2537, 0x1068, 0x0000, 0x9999, + "Norelsys", + "NS1068X", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_IGNORE_UAS), + /* Reported-by: Takeo Nakayama <javhera@gmx.com> */ UNUSUAL_DEV(0x357d, 0x7788, 0x0000, 0x9999, "JMicron", diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 7b219d9109b4..ee2bbce24584 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -91,7 +91,7 @@ static void usbip_dump_usb_device(struct usb_device *udev) dev_dbg(dev, " devnum(%d) devpath(%s) usb speed(%s)", udev->devnum, udev->devpath, usb_speed_string(udev->speed)); - pr_debug("tt %p, ttport %d\n", udev->tt, udev->ttport); + pr_debug("tt hub ttport %d\n", udev->ttport); dev_dbg(dev, " "); for (i = 0; i < 16; i++) @@ -124,12 +124,8 @@ static void usbip_dump_usb_device(struct usb_device *udev) } pr_debug("\n"); - dev_dbg(dev, "parent %p, bus %p\n", udev->parent, udev->bus); - - dev_dbg(dev, - "descriptor %p, config %p, actconfig %p, rawdescriptors %p\n", - &udev->descriptor, udev->config, - udev->actconfig, udev->rawdescriptors); + dev_dbg(dev, "parent %s, bus %s\n", dev_name(&udev->parent->dev), + udev->bus->bus_name); dev_dbg(dev, "have_langid %d, string_langid %d\n", udev->have_langid, udev->string_langid); @@ -237,9 +233,6 @@ void usbip_dump_urb(struct urb *urb) dev = &urb->dev->dev; - dev_dbg(dev, " urb :%p\n", urb); - dev_dbg(dev, " dev :%p\n", urb->dev); - usbip_dump_usb_device(urb->dev); dev_dbg(dev, " pipe :%08x ", urb->pipe); @@ -248,11 +241,9 @@ void usbip_dump_urb(struct urb *urb) dev_dbg(dev, " status :%d\n", urb->status); dev_dbg(dev, " transfer_flags :%08X\n", urb->transfer_flags); - dev_dbg(dev, " transfer_buffer :%p\n", urb->transfer_buffer); dev_dbg(dev, " transfer_buffer_length:%d\n", urb->transfer_buffer_length); dev_dbg(dev, " actual_length :%d\n", urb->actual_length); - dev_dbg(dev, " setup_packet :%p\n", urb->setup_packet); if (urb->setup_packet && usb_pipetype(urb->pipe) == PIPE_CONTROL) usbip_dump_usb_ctrlrequest( @@ -262,8 +253,6 @@ void usbip_dump_urb(struct urb *urb) dev_dbg(dev, " number_of_packets :%d\n", urb->number_of_packets); dev_dbg(dev, " interval :%d\n", urb->interval); dev_dbg(dev, " error_count :%d\n", urb->error_count); - dev_dbg(dev, " context :%p\n", urb->context); - dev_dbg(dev, " complete :%p\n", urb->complete); } EXPORT_SYMBOL_GPL(usbip_dump_urb); diff --git a/drivers/usb/usbip/vudc_rx.c b/drivers/usb/usbip/vudc_rx.c index df1e30989148..1e8a23d92cb4 100644 --- a/drivers/usb/usbip/vudc_rx.c +++ b/drivers/usb/usbip/vudc_rx.c @@ -120,6 +120,25 @@ static int v_recv_cmd_submit(struct vudc *udc, urb_p->new = 1; urb_p->seqnum = pdu->base.seqnum; + if (urb_p->ep->type == USB_ENDPOINT_XFER_ISOC) { + /* validate packet size and number of packets */ + unsigned int maxp, packets, bytes; + + maxp = usb_endpoint_maxp(urb_p->ep->desc); + maxp *= usb_endpoint_maxp_mult(urb_p->ep->desc); + bytes = pdu->u.cmd_submit.transfer_buffer_length; + packets = DIV_ROUND_UP(bytes, maxp); + + if (pdu->u.cmd_submit.number_of_packets < 0 || + pdu->u.cmd_submit.number_of_packets > packets) { + dev_err(&udc->gadget.dev, + "CMD_SUBMIT: isoc invalid num packets %d\n", + pdu->u.cmd_submit.number_of_packets); + ret = -EMSGSIZE; + goto free_urbp; + } + } + ret = alloc_urb_from_cmd(&urb_p->urb, pdu, urb_p->ep->type); if (ret) { usbip_event_add(&udc->ud, VUDC_EVENT_ERROR_MALLOC); diff --git a/drivers/usb/usbip/vudc_tx.c b/drivers/usb/usbip/vudc_tx.c index 1440ae0919ec..3ccb17c3e840 100644 --- a/drivers/usb/usbip/vudc_tx.c +++ b/drivers/usb/usbip/vudc_tx.c @@ -85,6 +85,13 @@ static int v_send_ret_submit(struct vudc *udc, struct urbp *urb_p) memset(&pdu_header, 0, sizeof(pdu_header)); memset(&msg, 0, sizeof(msg)); + if (urb->actual_length > 0 && !urb->transfer_buffer) { + dev_err(&udc->gadget.dev, + "urb: actual_length %d transfer_buffer null\n", + urb->actual_length); + return -1; + } + if (urb_p->type == USB_ENDPOINT_XFER_ISOC) iovnum = 2 + urb->number_of_packets; else @@ -100,8 +107,8 @@ static int v_send_ret_submit(struct vudc *udc, struct urbp *urb_p) /* 1. setup usbip_header */ setup_ret_submit_pdu(&pdu_header, urb_p); - 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/xen/gntdev.c b/drivers/xen/gntdev.c index 57efbd3b053b..bd56653b9bbc 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -380,10 +380,8 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages) } range = 0; while (range < pages) { - if (map->unmap_ops[offset+range].handle == -1) { - range--; + if (map->unmap_ops[offset+range].handle == -1) break; - } range++; } err = __unmap_grant_pages(map, offset, range); @@ -1073,8 +1071,10 @@ unlock_out: out_unlock_put: mutex_unlock(&priv->lock); out_put_map: - if (use_ptemod) + if (use_ptemod) { map->vma = NULL; + unmap_grant_pages(map, 0, map->count); + } gntdev_put_map(priv, map); return err; } diff --git a/include/linux/completion.h b/include/linux/completion.h index 94a59ba7d422..519e94915d18 100644 --- a/include/linux/completion.h +++ b/include/linux/completion.h @@ -32,7 +32,6 @@ struct completion { #define init_completion(x) __init_completion(x) static inline void complete_acquire(struct completion *x) {} static inline void complete_release(struct completion *x) {} -static inline void complete_release_commit(struct completion *x) {} #define COMPLETION_INITIALIZER(work) \ { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } diff --git a/include/linux/cpu.h b/include/linux/cpu.h index a04ef7c15c6a..7b01bc11c692 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -47,6 +47,13 @@ extern void cpu_remove_dev_attr(struct device_attribute *attr); extern int cpu_add_dev_attr_group(struct attribute_group *attrs); extern void cpu_remove_dev_attr_group(struct attribute_group *attrs); +extern ssize_t cpu_show_meltdown(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf); + extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h index 06097ef30449..b511f6d24b42 100644 --- a/include/linux/crash_core.h +++ b/include/linux/crash_core.h @@ -42,6 +42,8 @@ phys_addr_t paddr_vmcoreinfo_note(void); vmcoreinfo_append_str("PAGESIZE=%ld\n", value) #define VMCOREINFO_SYMBOL(name) \ vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name) +#define VMCOREINFO_SYMBOL_ARRAY(name) \ + vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name) #define VMCOREINFO_SIZE(name) \ vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \ (unsigned long)sizeof(name)) diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 46cb57d5eb13..1b3996ff3f16 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -27,22 +27,18 @@ # define trace_hardirq_enter() \ do { \ current->hardirq_context++; \ - crossrelease_hist_start(XHLOCK_HARD); \ } while (0) # define trace_hardirq_exit() \ do { \ current->hardirq_context--; \ - crossrelease_hist_end(XHLOCK_HARD); \ } while (0) # define lockdep_softirq_enter() \ do { \ current->softirq_context++; \ - crossrelease_hist_start(XHLOCK_SOFT); \ } while (0) # define lockdep_softirq_exit() \ do { \ current->softirq_context--; \ - crossrelease_hist_end(XHLOCK_SOFT); \ } while (0) # define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1, #else diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 2e75dc34bff5..3251d9c0d313 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -475,8 +475,6 @@ enum xhlock_context_t { #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \ { .name = (_name), .key = (void *)(_key), } -static inline void crossrelease_hist_start(enum xhlock_context_t c) {} -static inline void crossrelease_hist_end(enum xhlock_context_t c) {} static inline void lockdep_invariant_state(bool force) {} static inline void lockdep_init_task(struct task_struct *task) {} static inline void lockdep_free_task(struct task_struct *task) {} diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 1f509d072026..a0610427e168 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -36,6 +36,7 @@ #include <linux/kernel.h> #include <linux/completion.h> #include <linux/pci.h> +#include <linux/irq.h> #include <linux/spinlock_types.h> #include <linux/semaphore.h> #include <linux/slab.h> @@ -1231,7 +1232,23 @@ enum { static inline const struct cpumask * mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector) { - return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector); + const struct cpumask *mask; + struct irq_desc *desc; + unsigned int irq; + int eqn; + int err; + + err = mlx5_vector2eqn(dev, vector, &eqn, &irq); + if (err) + return NULL; + + desc = irq_to_desc(irq); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + mask = irq_data_get_effective_affinity_mask(&desc->irq_data); +#else + mask = desc->irq_common_data.affinity; +#endif + return mask; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 78e36fc2609e..94135c03d52b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1037,6 +1037,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 nic_vport_change_event[0x1]; u8 disable_local_lb[0x1]; u8 reserved_at_3e2[0x1]; + u8 disable_local_lb_uc[0x1]; + u8 disable_local_lb_mc[0x1]; u8 log_min_hairpin_wq_data_sz[0x5]; u8 reserved_at_3e8[0x3]; u8 log_max_vlan_list[0x5]; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 49b4257ce1ea..f3075d6c7e82 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -85,7 +85,7 @@ struct netlink_ext_ack { * to the lack of an output buffer.) */ #define NL_SET_ERR_MSG(extack, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) \ @@ -101,7 +101,7 @@ struct netlink_ext_ack { } while (0) #define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \ - static const char __msg[] = (msg); \ + static const char __msg[] = msg; \ struct netlink_ext_ack *__extack = (extack); \ \ if (__extack) { \ diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 13fb06a103c6..9ca1726ff963 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -174,6 +174,15 @@ static inline int ptr_ring_produce_bh(struct ptr_ring *r, void *ptr) * if they dereference the pointer - see e.g. PTR_RING_PEEK_CALL. * If ring is never resized, and if the pointer is merely * tested, there's no need to take the lock - see e.g. __ptr_ring_empty. + * However, if called outside the lock, and if some other CPU + * consumes ring entries at the same time, the value returned + * is not guaranteed to be correct. + * In this case - to avoid incorrectly detecting the ring + * as empty - the CPU consuming the ring entries is responsible + * for either consuming all ring entries until the ring is empty, + * or synchronizing with some other CPU and causing it to + * execute __ptr_ring_peek and/or consume the ring enteries + * after the synchronization point. */ static inline void *__ptr_ring_peek(struct ptr_ring *r) { @@ -182,10 +191,7 @@ static inline void *__ptr_ring_peek(struct ptr_ring *r) return NULL; } -/* Note: callers invoking this in a loop must use a compiler barrier, - * for example cpu_relax(). Callers must take consumer_lock - * if the ring is ever resized - see e.g. ptr_ring_empty. - */ +/* See __ptr_ring_peek above for locking rules. */ static inline bool __ptr_ring_empty(struct ptr_ring *r) { return !__ptr_ring_peek(r); diff --git a/include/net/arp.h b/include/net/arp.h index dc8cd47f883b..977aabfcdc03 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -20,6 +20,9 @@ static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + key = INADDR_ANY; + return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ab30a22ef4fd..81174f9b8d14 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -815,6 +815,8 @@ struct cfg80211_csa_settings { u8 count; }; +#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 + /** * struct iface_combination_params - input parameters for interface combinations * diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index ac029d5d88e4..bd9125b0481f 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -473,6 +473,7 @@ void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n, struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack); +void qdisc_free(struct Qdisc *qdisc); struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, u32 parentid, struct netlink_ext_ack *extack); diff --git a/include/net/tls.h b/include/net/tls.h index 936cfc5cab7d..9185e53a743c 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -170,7 +170,7 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) static inline void tls_err_abort(struct sock *sk) { - sk->sk_err = -EBADMSG; + sk->sk_err = EBADMSG; sk->sk_error_report(sk); } diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 4265d7f9e1f2..dcfab5e3b55c 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -363,7 +363,6 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ OVS_TUNNEL_KEY_ATTR_PAD, - OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, /* be32 ERSPAN index. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/init/Kconfig b/init/Kconfig index 19a6b845d834..a9a2e2c86671 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -461,6 +461,7 @@ endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION bool "CPU isolation" + depends on SMP || COMPILE_TEST default y help Make sure that CPUs running critical tasks are not disturbed by diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index aaa319848e7d..ab94d304a634 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -56,7 +56,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) u32 elem_size, index_mask, max_entries; bool unpriv = !capable(CAP_SYS_ADMIN); struct bpf_array *array; - u64 array_size; + u64 array_size, mask64; /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 4 || @@ -74,13 +74,25 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) elem_size = round_up(attr->value_size, 8); max_entries = attr->max_entries; - index_mask = roundup_pow_of_two(max_entries) - 1; - if (unpriv) + /* On 32 bit archs roundup_pow_of_two() with max_entries that has + * upper most bit set in u32 space is undefined behavior due to + * resulting 1U << 32, so do it manually here in u64 space. + */ + mask64 = fls_long(max_entries - 1); + mask64 = 1ULL << mask64; + mask64 -= 1; + + index_mask = mask64; + if (unpriv) { /* round up array size to nearest power of 2, * since cpu will speculate within index_mask limits */ max_entries = index_mask + 1; + /* Check for overflows. */ + if (max_entries < attr->max_entries) + return ERR_PTR(-E2BIG); + } array_size = sizeof(*array); if (percpu) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ceabb394d2dc..2e7a43edf264 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3091,6 +3091,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } + if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) { + verbose(env, "BPF_ARSH not supported for 32 bit ALU\n"); + return -EINVAL; + } + if ((opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) { int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32; @@ -5361,7 +5366,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) */ map_ptr = env->insn_aux_data[i + delta].map_ptr; if (map_ptr == BPF_MAP_PTR_POISON) { - verbose(env, "tail_call obusing map_ptr\n"); + verbose(env, "tail_call abusing map_ptr\n"); return -EINVAL; } if (!map_ptr->unpriv_array) diff --git a/kernel/crash_core.c b/kernel/crash_core.c index b3663896278e..4f63597c824d 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -410,7 +410,7 @@ static int __init crash_save_vmcoreinfo_init(void) VMCOREINFO_SYMBOL(contig_page_data); #endif #ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL(mem_section); + VMCOREINFO_SYMBOL_ARRAY(mem_section); VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); VMCOREINFO_STRUCT_SIZE(mem_section); VMCOREINFO_OFFSET(mem_section, section_mem_map); diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 2ddaec40956f..0926aef10dad 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -34,11 +34,6 @@ void complete(struct completion *x) spin_lock_irqsave(&x->wait.lock, flags); - /* - * Perform commit of crossrelease here. - */ - complete_release_commit(x); - if (x->done != UINT_MAX) x->done++; __wake_up_locked(&x->wait, TASK_NORMAL, 1); diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index dd7908743dab..9bcbacba82a8 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -89,7 +89,9 @@ static int membarrier_private_expedited(void) rcu_read_unlock(); } if (!fallback) { + preempt_disable(); smp_call_function_many(tmpmask, ipi_mb, NULL, 1); + preempt_enable(); free_cpumask_var(tmpmask); } cpus_read_unlock(); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 7114c885a78a..0b249e2f0c3c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -355,7 +355,7 @@ config PROFILE_ANNOTATED_BRANCHES on if you need to profile the system's use of these macros. config PROFILE_ALL_BRANCHES - bool "Profile all if conditionals" + bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING help This tracer profiles all branch conditions. Every if () diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 9ab18995ff1e..0cddf60186da 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2534,29 +2534,59 @@ rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer) * The lock and unlock are done within a preempt disable section. * The current_context per_cpu variable can only be modified * by the current task between lock and unlock. But it can - * be modified more than once via an interrupt. There are four - * different contexts that we need to consider. + * be modified more than once via an interrupt. To pass this + * information from the lock to the unlock without having to + * access the 'in_interrupt()' functions again (which do show + * a bit of overhead in something as critical as function tracing, + * we use a bitmask trick. * - * Normal context. - * SoftIRQ context - * IRQ context - * NMI context + * bit 0 = NMI context + * bit 1 = IRQ context + * bit 2 = SoftIRQ context + * bit 3 = normal context. * - * If for some reason the ring buffer starts to recurse, we - * only allow that to happen at most 4 times (one for each - * context). If it happens 5 times, then we consider this a - * recusive loop and do not let it go further. + * This works because this is the order of contexts that can + * preempt other contexts. A SoftIRQ never preempts an IRQ + * context. + * + * When the context is determined, the corresponding bit is + * checked and set (if it was set, then a recursion of that context + * happened). + * + * On unlock, we need to clear this bit. To do so, just subtract + * 1 from the current_context and AND it to itself. + * + * (binary) + * 101 - 1 = 100 + * 101 & 100 = 100 (clearing bit zero) + * + * 1010 - 1 = 1001 + * 1010 & 1001 = 1000 (clearing bit 1) + * + * The least significant bit can be cleared this way, and it + * just so happens that it is the same bit corresponding to + * the current context. */ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { - if (cpu_buffer->current_context >= 4) + unsigned int val = cpu_buffer->current_context; + unsigned long pc = preempt_count(); + int bit; + + if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) + bit = RB_CTX_NORMAL; + else + bit = pc & NMI_MASK ? RB_CTX_NMI : + pc & HARDIRQ_MASK ? RB_CTX_IRQ : + pc & SOFTIRQ_OFFSET ? 2 : RB_CTX_SOFTIRQ; + + if (unlikely(val & (1 << bit))) return 1; - cpu_buffer->current_context++; - /* Interrupts must see this update */ - barrier(); + val |= (1 << bit); + cpu_buffer->current_context = val; return 0; } @@ -2564,9 +2594,7 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) static __always_inline void trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer) { - /* Don't let the dec leak out */ - barrier(); - cpu_buffer->current_context--; + cpu_buffer->current_context &= cpu_buffer->current_context - 1; } /** diff --git a/mm/kmemleak.c b/mm/kmemleak.c index d73c14294f3a..f656ca27f6c2 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -127,7 +127,7 @@ /* GFP bitmask for kmemleak internal allocations */ #define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ - __GFP_NOWARN) + __GFP_NOWARN | __GFP_NOFAIL) /* scanning area inside a memory block */ struct kmemleak_scan_area { diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 325c56043007..086a4abdfa7c 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -543,3 +543,7 @@ static void p9_trans_xen_exit(void) return xenbus_unregister_driver(&xen_9pfs_front_driver); } module_exit(p9_trans_xen_exit); + +MODULE_AUTHOR("Stefano Stabellini <stefano@aporeto.com>"); +MODULE_DESCRIPTION("Xen Transport for 9P"); +MODULE_LICENSE("GPL"); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 43ba91c440bc..fc6615d59165 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3363,9 +3363,10 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data break; case L2CAP_CONF_EFS: - remote_efs = 1; - if (olen == sizeof(efs)) + if (olen == sizeof(efs)) { + remote_efs = 1; memcpy(&efs, (void *) val, olen); + } break; case L2CAP_CONF_EWS: @@ -3584,16 +3585,17 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, break; case L2CAP_CONF_EFS: - if (olen == sizeof(efs)) + if (olen == sizeof(efs)) { memcpy(&efs, (void *)val, olen); - if (chan->local_stype != L2CAP_SERV_NOTRAFIC && - efs.stype != L2CAP_SERV_NOTRAFIC && - efs.stype != chan->local_stype) - return -ECONNREFUSED; + if (chan->local_stype != L2CAP_SERV_NOTRAFIC && + efs.stype != L2CAP_SERV_NOTRAFIC && + efs.stype != chan->local_stype) + return -ECONNREFUSED; - l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), - (unsigned long) &efs, endptr - ptr); + l2cap_add_conf_opt(&ptr, L2CAP_CONF_EFS, sizeof(efs), + (unsigned long) &efs, endptr - ptr); + } break; case L2CAP_CONF_FCS: diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f96f9f58b894..7b7a14abba28 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -532,7 +532,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) nht = neigh_hash_grow(tbl, nht->hash_shift + 1); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + hash_val = tbl->hash(n->primary_key, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); @@ -544,7 +544,7 @@ struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, n1 != NULL; n1 = rcu_dereference_protected(n1->next, lockdep_is_held(&tbl->lock))) { - if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { + if (dev == n1->dev && !memcmp(n1->primary_key, n->primary_key, key_len)) { if (want_ref) neigh_hold(n1); rc = n1; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 56aef027df31..f28f06c91ead 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -223,11 +223,16 @@ static bool arp_key_eq(const struct neighbour *neigh, const void *pkey) static int arp_constructor(struct neighbour *neigh) { - __be32 addr = *(__be32 *)neigh->primary_key; + __be32 addr; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; + u32 inaddr_any = INADDR_ANY; + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + memcpy(neigh->primary_key, &inaddr_any, arp_tbl.key_len); + + addr = *(__be32 *)neigh->primary_key; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) { diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 6f00e43120a8..296d0b956bfe 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -991,6 +991,7 @@ static int esp_init_state(struct xfrm_state *x) switch (encap->encap_type) { default: + err = -EINVAL; goto error; case UDP_ENCAP_ESPINUDP: x->props.header_len += sizeof(struct udphdr); diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index c359f3cfeec3..32fbd9ba3609 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -38,7 +38,8 @@ static struct sk_buff **esp4_gro_receive(struct sk_buff **head, __be32 spi; int err; - skb_pull(skb, offset); + if (!pskb_pull(skb, offset)) + return NULL; if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0) goto out; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index b7d90b48d821..49cc1c1df1ba 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2759,6 +2759,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { + fl4.flowi4_iif = LOOPBACK_IFINDEX; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 7c888c6e53a9..97513f35bcc5 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -900,13 +900,12 @@ static int esp6_init_state(struct xfrm_state *x) x->props.header_len += IPV4_BEET_PHMAXLEN + (sizeof(struct ipv6hdr) - sizeof(struct iphdr)); break; + default: case XFRM_MODE_TRANSPORT: break; case XFRM_MODE_TUNNEL: x->props.header_len += sizeof(struct ipv6hdr); break; - default: - goto error; } align = ALIGN(crypto_aead_blocksize(aead), 4); diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 0bb7d54cf2cb..44d109c435bc 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -60,7 +60,8 @@ static struct sk_buff **esp6_gro_receive(struct sk_buff **head, int nhoff; int err; - skb_pull(skb, offset); + if (!pskb_pull(skb, offset)) + return NULL; if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0) goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 18547a44bdaf..a4a94452132b 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1215,14 +1215,16 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, v6_cork->tclass = ipc6->tclass; if (rt->dst.flags & DST_XFRM_TUNNEL) mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(&rt->dst); + READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst); else mtu = np->pmtudisc >= IPV6_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(xfrm_dst_path(&rt->dst)); + READ_ONCE(rt->dst.dev->mtu) : dst_mtu(xfrm_dst_path(&rt->dst)); if (np->frag_size < mtu) { if (np->frag_size) mtu = np->frag_size; } + if (mtu < IPV6_MIN_MTU) + return -EINVAL; cork->base.fragsize = mtu; if (dst_allfrag(xfrm_dst_path(&rt->dst))) cork->base.flags |= IPCORK_ALLFRAG; @@ -1742,6 +1744,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, cork.base.flags = 0; cork.base.addr = 0; cork.base.opt = NULL; + cork.base.dst = NULL; v6_cork.opt = NULL; err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6); if (err) { diff --git a/net/key/af_key.c b/net/key/af_key.c index 3dffb892d52c..7e2e7188e7f4 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -401,6 +401,11 @@ static int verify_address_len(const void *p) #endif int len; + if (sp->sadb_address_len < + DIV_ROUND_UP(sizeof(*sp) + offsetofend(typeof(*addr), sa_family), + sizeof(uint64_t))) + return -EINVAL; + switch (addr->sa_family) { case AF_INET: len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin), sizeof(uint64_t)); @@ -511,6 +516,9 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void * uint16_t ext_type; int ext_len; + if (len < sizeof(*ehdr)) + return -EINVAL; + ext_len = ehdr->sadb_ext_len; ext_len *= sizeof(uint64_t); ext_type = ehdr->sadb_ext_type; @@ -2194,8 +2202,10 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev return PTR_ERR(out_skb); err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); return err; + } out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = PF_KEY_V2; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 1e52f6012d5d..54cbf5b9864c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2417,7 +2417,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)) { - struct netlink_ext_ack extack = {}; + struct netlink_ext_ack extack; struct nlmsghdr *nlh; int err; @@ -2438,6 +2438,7 @@ int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, if (nlh->nlmsg_type < NLMSG_MIN_TYPE) goto ack; + memset(&extack, 0, sizeof(extack)); err = cb(skb, nlh, &extack); if (err == -EINTR) goto skip; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index bce1f78b0de5..f143908b651d 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -49,7 +49,6 @@ #include <net/mpls.h> #include <net/vxlan.h> #include <net/tun_proto.h> -#include <net/erspan.h> #include "flow_netlink.h" @@ -334,8 +333,7 @@ size_t ovs_tun_key_attr_size(void) * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it. */ + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_SRC */ - + nla_total_size(2) /* OVS_TUNNEL_KEY_ATTR_TP_DST */ - + nla_total_size(4); /* OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS */ + + nla_total_size(2); /* OVS_TUNNEL_KEY_ATTR_TP_DST */ } static size_t ovs_nsh_key_attr_size(void) @@ -402,7 +400,6 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] .next = ovs_vxlan_ext_key_lens }, [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, - [OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS] = { .len = sizeof(u32) }, }; static const struct ovs_len_tbl @@ -634,33 +631,6 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } -static int erspan_tun_opt_from_nlattr(const struct nlattr *attr, - struct sw_flow_match *match, bool is_mask, - bool log) -{ - unsigned long opt_key_offset; - struct erspan_metadata opts; - - BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts)); - - memset(&opts, 0, sizeof(opts)); - opts.u.index = nla_get_be32(attr); - - /* Index has only 20-bit */ - if (ntohl(opts.u.index) & ~INDEX_MASK) { - OVS_NLERR(log, "ERSPAN index number %x too large.", - ntohl(opts.u.index)); - return -EINVAL; - } - - SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), is_mask); - opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts)); - SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts), - is_mask); - - return 0; -} - static int ip_tun_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool log) @@ -768,19 +738,6 @@ static int ip_tun_from_nlattr(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_PAD: break; - case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - if (opts_type) { - OVS_NLERR(log, "Multiple metadata blocks provided"); - return -EINVAL; - } - - err = erspan_tun_opt_from_nlattr(a, match, is_mask, log); - if (err) - return err; - - tun_flags |= TUNNEL_ERSPAN_OPT; - opts_type = type; - break; default: OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); @@ -905,10 +862,6 @@ static int __ip_tun_to_nlattr(struct sk_buff *skb, else if (output->tun_flags & TUNNEL_VXLAN_OPT && vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len)) return -EMSGSIZE; - else if (output->tun_flags & TUNNEL_ERSPAN_OPT && - nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS, - ((struct erspan_metadata *)tun_opts)->u.index)) - return -EMSGSIZE; } return 0; @@ -2533,8 +2486,6 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, break; case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS: break; - case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS: - break; } }; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 0038a1c44ee9..7dffa9dce28b 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1094,17 +1094,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, goto err_out5; } - if (qdisc_is_percpu_stats(sch)) { - sch->cpu_bstats = - netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu); - if (!sch->cpu_bstats) - goto err_out4; - - sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); - if (!sch->cpu_qstats) - goto err_out4; - } - if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { @@ -1151,7 +1140,7 @@ err_out5: ops->destroy(sch); err_out3: dev_put(dev); - kfree((char *) sch - sch->padded); + qdisc_free(sch); err_out2: module_put(ops->owner); err_out: @@ -1159,8 +1148,6 @@ err_out: return NULL; err_out4: - free_percpu(sch->cpu_bstats); - free_percpu(sch->cpu_qstats); /* * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index a883c501d5ec..ef8b4ecde2ac 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -907,7 +907,7 @@ void qdisc_reset(struct Qdisc *qdisc) } EXPORT_SYMBOL(qdisc_reset); -static void qdisc_free(struct Qdisc *qdisc) +void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 7ca2be20dd6f..3372dd5e984d 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -68,7 +68,6 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, { struct ingress_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); - int err; net_inc_ingress_queue(); @@ -78,13 +77,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt, q->block_info.chain_head_change = clsact_chain_head_change; q->block_info.chain_head_change_priv = &q->miniqp; - err = tcf_block_get_ext(&q->block, sch, &q->block_info, extack); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->block, sch, &q->block_info, extack); } static void ingress_destroy(struct Qdisc *sch) @@ -123,6 +116,7 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = { .cl_ops = &ingress_class_ops, .id = "ingress", .priv_size = sizeof(struct ingress_sched_data), + .static_flags = TCQ_F_CPUSTATS, .init = ingress_init, .destroy = ingress_destroy, .dump = ingress_dump, @@ -197,14 +191,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt, q->egress_block_info.chain_head_change = clsact_chain_head_change; q->egress_block_info.chain_head_change_priv = &q->miniqp_egress; - err = tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info, - extack); - if (err) - return err; - - sch->flags |= TCQ_F_CPUSTATS; - - return 0; + return tcf_block_get_ext(&q->egress_block, sch, &q->egress_block_info, extack); } static void clsact_destroy(struct Qdisc *sch) @@ -231,6 +218,7 @@ static struct Qdisc_ops clsact_qdisc_ops __read_mostly = { .cl_ops = &clsact_class_ops, .id = "clsact", .priv_size = sizeof(struct clsact_sched_data), + .static_flags = TCQ_F_CPUSTATS, .init = clsact_init, .destroy = clsact_destroy, .dump = ingress_dump, diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 3b18085e3b10..5d4c15bf66d2 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -826,6 +826,7 @@ static int sctp_inet6_af_supported(sa_family_t family, struct sctp_sock *sp) case AF_INET: if (!__ipv6_only_sock(sctp_opt2sk(sp))) return 1; + /* fallthru */ default: return 0; } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index af9b5ebcae50..f211b3db6a35 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -916,9 +916,9 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp) break; case SCTP_CID_ABORT: - if (sctp_test_T_bit(chunk)) { + if (sctp_test_T_bit(chunk)) packet->vtag = asoc->c.my_vtag; - } + /* fallthru */ /* The following chunks are "response" chunks, i.e. * they are generated in response to something we * received. If we are sending these, then we can diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6a54ff06c9da..7ff444ecee75 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -85,7 +85,7 @@ static int sctp_writeable(struct sock *sk); static void sctp_wfree(struct sk_buff *skb); static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len, struct sock **orig_sk); + size_t msg_len); static int sctp_wait_for_packet(struct sock *sk, int *err, long *timeo_p); static int sctp_wait_for_connect(struct sctp_association *, long *timeo_p); static int sctp_wait_for_accept(struct sock *sk, long timeo); @@ -351,16 +351,14 @@ static struct sctp_af *sctp_sockaddr_af(struct sctp_sock *opt, if (len < sizeof (struct sockaddr)) return NULL; + if (!opt->pf->af_supported(addr->sa.sa_family, opt)) + return NULL; + /* V4 mapped address are really of AF_INET family */ if (addr->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr->v6.sin6_addr)) { - if (!opt->pf->af_supported(AF_INET, opt)) - return NULL; - } else { - /* Does this PF support this AF? */ - if (!opt->pf->af_supported(addr->sa.sa_family, opt)) - return NULL; - } + ipv6_addr_v4mapped(&addr->v6.sin6_addr) && + !opt->pf->af_supported(AF_INET, opt)) + return NULL; /* If we get this far, af is valid. */ af = sctp_get_af_specific(addr->sa.sa_family); @@ -1900,8 +1898,14 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) */ if (sinit) { if (sinit->sinit_num_ostreams) { - asoc->c.sinit_num_ostreams = - sinit->sinit_num_ostreams; + __u16 outcnt = sinit->sinit_num_ostreams; + + asoc->c.sinit_num_ostreams = outcnt; + /* outcnt has been changed, so re-init stream */ + err = sctp_stream_init(&asoc->stream, outcnt, 0, + GFP_KERNEL); + if (err) + goto out_free; } if (sinit->sinit_max_instreams) { asoc->c.sinit_max_instreams = @@ -1988,7 +1992,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); if (!sctp_wspace(asoc)) { /* sk can be changed by peel off when waiting for buf. */ - err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len, &sk); + err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len); if (err) { if (err == -ESRCH) { /* asoc is already dead. */ @@ -8121,12 +8125,12 @@ void sctp_sock_rfree(struct sk_buff *skb) /* Helper function to wait for space in the sndbuf. */ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, - size_t msg_len, struct sock **orig_sk) + size_t msg_len) { struct sock *sk = asoc->base.sk; - int err = 0; long current_timeo = *timeo_p; DEFINE_WAIT(wait); + int err = 0; pr_debug("%s: asoc:%p, timeo:%ld, msg_len:%zu\n", __func__, asoc, *timeo_p, msg_len); @@ -8155,17 +8159,13 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, release_sock(sk); current_timeo = schedule_timeout(current_timeo); lock_sock(sk); - if (sk != asoc->base.sk) { - release_sock(sk); - sk = asoc->base.sk; - lock_sock(sk); - } + if (sk != asoc->base.sk) + goto do_error; *timeo_p = current_timeo; } out: - *orig_sk = sk; finish_wait(&asoc->wait, &wait); /* Release the association's refcnt. */ diff --git a/net/tipc/node.c b/net/tipc/node.c index 507017fe0f1b..9036d8756e73 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1880,36 +1880,38 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) if (strcmp(name, tipc_bclink_name) == 0) { err = tipc_nl_add_bc_link(net, &msg); - if (err) { - nlmsg_free(msg.skb); - return err; - } + if (err) + goto err_free; } else { int bearer_id; struct tipc_node *node; struct tipc_link *link; node = tipc_node_find_by_name(net, name, &bearer_id); - if (!node) - return -EINVAL; + if (!node) { + err = -EINVAL; + goto err_free; + } tipc_node_read_lock(node); link = node->links[bearer_id].link; if (!link) { tipc_node_read_unlock(node); - nlmsg_free(msg.skb); - return -EINVAL; + err = -EINVAL; + goto err_free; } err = __tipc_nl_add_link(net, &msg, link, 0); tipc_node_read_unlock(node); - if (err) { - nlmsg_free(msg.skb); - return err; - } + if (err) + goto err_free; } return genlmsg_reply(msg.skb, info); + +err_free: + nlmsg_free(msg.skb); + return err; } int tipc_nl_node_reset_link_stats(struct sk_buff *skb, struct genl_info *info) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 73d19210dd49..9773571b6a34 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -391,7 +391,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) while (msg_data_left(msg)) { if (sk->sk_err) { - ret = sk->sk_err; + ret = -sk->sk_err; goto send_end; } @@ -544,7 +544,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, size_t copy, required_size; if (sk->sk_err) { - ret = sk->sk_err; + ret = -sk->sk_err; goto sendpage_end; } diff --git a/net/wireless/core.c b/net/wireless/core.c index fdde0d98fde1..a6f3cac8c640 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -439,6 +439,8 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv, if (rv) goto use_default_name; } else { + int rv; + use_default_name: /* NOTE: This is *probably* safe w/out holding rtnl because of * the restrictions on phy names. Probably this call could @@ -446,7 +448,11 @@ use_default_name: * phyX. But, might should add some locking and check return * value, and use a different name if this one exists? */ - dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx); + rv = dev_set_name(&rdev->wiphy.dev, PHY_NAME "%d", rdev->wiphy_idx); + if (rv < 0) { + kfree(rdev); + return NULL; + } } INIT_LIST_HEAD(&rdev->wiphy.wdev_list); diff --git a/net/wireless/core.h b/net/wireless/core.h index d2f7e8b8a097..eaff636169c2 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -507,8 +507,6 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev, void cfg80211_stop_nan(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); -#define CFG80211_MAX_NUM_DIFFERENT_CHANNELS 10 - #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS #define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) #else diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c084dd2205ac..b48eb6d104c9 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -2642,12 +2642,13 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag const u8 *ssid_ie; if (!wdev->current_bss) break; + rcu_read_lock(); ssid_ie = ieee80211_bss_get_ie(&wdev->current_bss->pub, WLAN_EID_SSID); - if (!ssid_ie) - break; - if (nla_put(msg, NL80211_ATTR_SSID, ssid_ie[1], ssid_ie + 2)) - goto nla_put_failure_locked; + if (ssid_ie && + nla_put(msg, NL80211_ATTR_SSID, ssid_ie[1], ssid_ie + 2)) + goto nla_put_failure_rcu_locked; + rcu_read_unlock(); break; } default: @@ -2659,6 +2660,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag genlmsg_end(msg, hdr); return 0; + nla_put_failure_rcu_locked: + rcu_read_unlock(); nla_put_failure_locked: wdev_unlock(wdev); nla_put_failure: diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 78e71b0390be..7b42f0bacfd8 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1769,8 +1769,7 @@ static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, if (wiphy->regulatory_flags & REGULATORY_DISABLE_BEACON_HINTS) return; - chan_before.center_freq = chan->center_freq; - chan_before.flags = chan->flags; + chan_before = *chan; if (chan->flags & IEEE80211_CHAN_NO_IR) { chan->flags &= ~IEEE80211_CHAN_NO_IR; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 26b10eb7a206..1472c0857975 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -517,7 +517,7 @@ int xfrm_trans_queue(struct sk_buff *skb, return -ENOBUFS; XFRM_TRANS_SKB_CB(skb)->finish = finish; - skb_queue_tail(&trans->queue, skb); + __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d8a8129b9232..7a23078132cf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -609,7 +609,8 @@ static void xfrm_hash_rebuild(struct work_struct *work) /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { - if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { + if (policy->walk.dead || + xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { /* skip socket policies */ continue; } @@ -974,8 +975,6 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) } if (!cnt) err = -ESRCH; - else - xfrm_policy_cache_flush(); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; @@ -1744,6 +1743,8 @@ void xfrm_policy_cache_flush(void) bool found = 0; int cpu; + might_sleep(); + local_bh_disable(); rcu_read_lock(); for_each_possible_cpu(cpu) { @@ -2064,8 +2065,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, if (num_xfrms <= 0) goto make_dummy_bundle; + local_bh_disable(); xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, - xflo->dst_orig); + xflo->dst_orig); + local_bh_enable(); + if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err != -EAGAIN) @@ -2152,9 +2156,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } + local_bh_disable(); xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); + local_bh_enable(); + if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index cc4c519cad76..20b1e414dbee 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -313,13 +313,14 @@ retry: if ((type && !try_module_get(type->owner))) type = NULL; + rcu_read_unlock(); + if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); try_load = 0; goto retry; } - rcu_read_unlock(); return type; } @@ -1534,8 +1535,12 @@ out: err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { - if (x->encap && x1->encap) + if (x->encap && x1->encap && + x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); + else if (x->encap || x1->encap) + goto fail; + if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } @@ -1552,6 +1557,8 @@ out: x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } + +fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); diff --git a/scripts/genksyms/.gitignore b/scripts/genksyms/.gitignore index 86dc07a01b43..e7836b47f060 100644 --- a/scripts/genksyms/.gitignore +++ b/scripts/genksyms/.gitignore @@ -1,4 +1,3 @@ -*.hash.c *.lex.c *.tab.c *.tab.h diff --git a/scripts/kconfig/expr.c b/scripts/kconfig/expr.c index cbf4996dd9c1..8cee597d33a5 100644 --- a/scripts/kconfig/expr.c +++ b/scripts/kconfig/expr.c @@ -893,7 +893,10 @@ static enum string_value_kind expr_parse_string(const char *str, switch (type) { case S_BOOLEAN: case S_TRISTATE: - return k_string; + val->s = !strcmp(str, "n") ? 0 : + !strcmp(str, "m") ? 1 : + !strcmp(str, "y") ? 2 : -1; + return k_signed; case S_INT: val->s = strtoll(str, &tail, 10); kind = k_signed; diff --git a/security/Kconfig b/security/Kconfig index 3d4debd0257e..b0cb9a5f9448 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -63,7 +63,7 @@ config PAGE_TABLE_ISOLATION ensuring that the majority of kernel addresses are not mapped into userspace. - See Documentation/x86/pagetable-isolation.txt for more details. + See Documentation/x86/pti.txt for more details. config SECURITY_INFINIBAND bool "Infiniband Security Hooks" diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 04ba9d0718ea..6a54d2ffa840 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -330,10 +330,7 @@ static struct aa_profile *__attach_match(const char *name, continue; if (profile->xmatch) { - if (profile->xmatch_len == len) { - conflict = true; - continue; - } else if (profile->xmatch_len > len) { + if (profile->xmatch_len >= len) { unsigned int state; u32 perm; @@ -342,6 +339,10 @@ static struct aa_profile *__attach_match(const char *name, perm = dfa_user_allow(profile->xmatch, state); /* any accepting state means a valid match. */ if (perm & MAY_EXEC) { + if (profile->xmatch_len == len) { + conflict = true; + continue; + } candidate = profile; len = profile->xmatch_len; conflict = false; diff --git a/security/apparmor/include/perms.h b/security/apparmor/include/perms.h index 2b27bb79aec4..d7b7e7115160 100644 --- a/security/apparmor/include/perms.h +++ b/security/apparmor/include/perms.h @@ -133,6 +133,9 @@ extern struct aa_perms allperms; #define xcheck_labels_profiles(L1, L2, FN, args...) \ xcheck_ns_labels((L1), (L2), xcheck_ns_profile_label, (FN), args) +#define xcheck_labels(L1, L2, P, FN1, FN2) \ + xcheck(fn_for_each((L1), (P), (FN1)), fn_for_each((L2), (P), (FN2))) + void aa_perm_mask_to_str(char *str, const char *chrs, u32 mask); void aa_audit_perm_names(struct audit_buffer *ab, const char **names, u32 mask); diff --git a/security/apparmor/ipc.c b/security/apparmor/ipc.c index 7ca0032e7ba9..b40678f3c1d5 100644 --- a/security/apparmor/ipc.c +++ b/security/apparmor/ipc.c @@ -64,40 +64,48 @@ static void audit_ptrace_cb(struct audit_buffer *ab, void *va) FLAGS_NONE, GFP_ATOMIC); } +/* assumes check for PROFILE_MEDIATES is already done */ /* TODO: conditionals */ static int profile_ptrace_perm(struct aa_profile *profile, - struct aa_profile *peer, u32 request, - struct common_audit_data *sa) + struct aa_label *peer, u32 request, + struct common_audit_data *sa) { struct aa_perms perms = { }; - /* need because of peer in cross check */ - if (profile_unconfined(profile) || - !PROFILE_MEDIATES(profile, AA_CLASS_PTRACE)) - return 0; - - aad(sa)->peer = &peer->label; - aa_profile_match_label(profile, &peer->label, AA_CLASS_PTRACE, request, + aad(sa)->peer = peer; + aa_profile_match_label(profile, peer, AA_CLASS_PTRACE, request, &perms); aa_apply_modes_to_perms(profile, &perms); return aa_check_perms(profile, &perms, request, sa, audit_ptrace_cb); } -static int cross_ptrace_perm(struct aa_profile *tracer, - struct aa_profile *tracee, u32 request, - struct common_audit_data *sa) +static int profile_tracee_perm(struct aa_profile *tracee, + struct aa_label *tracer, u32 request, + struct common_audit_data *sa) { + if (profile_unconfined(tracee) || unconfined(tracer) || + !PROFILE_MEDIATES(tracee, AA_CLASS_PTRACE)) + return 0; + + return profile_ptrace_perm(tracee, tracer, request, sa); +} + +static int profile_tracer_perm(struct aa_profile *tracer, + struct aa_label *tracee, u32 request, + struct common_audit_data *sa) +{ + if (profile_unconfined(tracer)) + return 0; + if (PROFILE_MEDIATES(tracer, AA_CLASS_PTRACE)) - return xcheck(profile_ptrace_perm(tracer, tracee, request, sa), - profile_ptrace_perm(tracee, tracer, - request << PTRACE_PERM_SHIFT, - sa)); - /* policy uses the old style capability check for ptrace */ - if (profile_unconfined(tracer) || tracer == tracee) + return profile_ptrace_perm(tracer, tracee, request, sa); + + /* profile uses the old style capability check for ptrace */ + if (&tracer->label == tracee) return 0; aad(sa)->label = &tracer->label; - aad(sa)->peer = &tracee->label; + aad(sa)->peer = tracee; aad(sa)->request = 0; aad(sa)->error = aa_capable(&tracer->label, CAP_SYS_PTRACE, 1); @@ -115,10 +123,13 @@ static int cross_ptrace_perm(struct aa_profile *tracer, int aa_may_ptrace(struct aa_label *tracer, struct aa_label *tracee, u32 request) { + struct aa_profile *profile; + u32 xrequest = request << PTRACE_PERM_SHIFT; DEFINE_AUDIT_DATA(sa, LSM_AUDIT_DATA_NONE, OP_PTRACE); - return xcheck_labels_profiles(tracer, tracee, cross_ptrace_perm, - request, &sa); + return xcheck_labels(tracer, tracee, profile, + profile_tracer_perm(profile, tracee, request, &sa), + profile_tracee_perm(profile, tracer, xrequest, &sa)); } diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index db7894bb028c..faa67861cbc1 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -560,7 +560,6 @@ static inline unsigned int muldiv32(unsigned int a, unsigned int b, { u_int64_t n = (u_int64_t) a * b; if (c == 0) { - snd_BUG_ON(!n); *r = 0; return UINT_MAX; } diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 6e22eea72654..d01913404581 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -221,6 +221,7 @@ static struct snd_seq_client *seq_create_client1(int client_index, int poolsize) rwlock_init(&client->ports_lock); mutex_init(&client->ports_mutex); INIT_LIST_HEAD(&client->ports_list_head); + mutex_init(&client->ioctl_mutex); /* find free slot in the client table */ spin_lock_irqsave(&clients_lock, flags); @@ -2130,7 +2131,9 @@ static long snd_seq_ioctl(struct file *file, unsigned int cmd, return -EFAULT; } + mutex_lock(&client->ioctl_mutex); err = handler->func(client, &buf); + mutex_unlock(&client->ioctl_mutex); if (err >= 0) { /* Some commands includes a bug in 'dir' field. */ if (handler->cmd == SNDRV_SEQ_IOCTL_SET_QUEUE_CLIENT || diff --git a/sound/core/seq/seq_clientmgr.h b/sound/core/seq/seq_clientmgr.h index c6614254ef8a..0611e1e0ed5b 100644 --- a/sound/core/seq/seq_clientmgr.h +++ b/sound/core/seq/seq_clientmgr.h @@ -61,6 +61,7 @@ struct snd_seq_client { struct list_head ports_list_head; rwlock_t ports_lock; struct mutex ports_mutex; + struct mutex ioctl_mutex; int convert32; /* convert 32->64bit */ /* output pool */ diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 80bbadc83721..d6e079f4ec09 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -408,6 +408,7 @@ static const struct snd_pci_quirk cs420x_fixup_tbl[] = { /*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/ /* codec SSID */ + SND_PCI_QUIRK(0x106b, 0x0600, "iMac 14,1", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x1c00, "MacBookPro 8,1", CS420X_MBP81), SND_PCI_QUIRK(0x106b, 0x2000, "iMac 12,2", CS420X_IMAC27_122), SND_PCI_QUIRK(0x106b, 0x2800, "MacBookPro 10,1", CS420X_MBP101), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 8fd2d9c62c96..9aafc6c86132 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6196,6 +6196,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER), + SND_PCI_QUIRK(0x1028, 0x082a, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile index ae0272f9a091..e6acc281dd37 100644 --- a/tools/objtool/Makefile +++ b/tools/objtool/Makefile @@ -46,7 +46,7 @@ $(OBJTOOL_IN): fixdep FORCE @$(MAKE) $(build)=objtool $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN) - @./sync-check.sh + @$(CONFIG_SHELL) ./sync-check.sh $(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@ diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 9b341584eb1b..f40d46e24bcc 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -428,6 +428,40 @@ static void add_ignores(struct objtool_file *file) } /* + * FIXME: For now, just ignore any alternatives which add retpolines. This is + * a temporary hack, as it doesn't allow ORC to unwind from inside a retpoline. + * But it at least allows objtool to understand the control flow *around* the + * retpoline. + */ +static int add_nospec_ignores(struct objtool_file *file) +{ + struct section *sec; + struct rela *rela; + struct instruction *insn; + + sec = find_section_by_name(file->elf, ".rela.discard.nospec"); + if (!sec) + return 0; + + list_for_each_entry(rela, &sec->rela_list, list) { + if (rela->sym->type != STT_SECTION) { + WARN("unexpected relocation symbol type in %s", sec->name); + return -1; + } + + insn = find_insn(file, rela->sym->sec, rela->addend); + if (!insn) { + WARN("bad .discard.nospec entry"); + return -1; + } + + insn->ignore_alts = true; + } + + return 0; +} + +/* * Find the destination instructions for all jumps. */ static int add_jump_destinations(struct objtool_file *file) @@ -456,6 +490,13 @@ static int add_jump_destinations(struct objtool_file *file) } else if (rela->sym->sec->idx) { dest_sec = rela->sym->sec; dest_off = rela->sym->sym.st_value + rela->addend + 4; + } else if (strstr(rela->sym->name, "_indirect_thunk_")) { + /* + * Retpoline jumps are really dynamic jumps in + * disguise, so convert them accordingly. + */ + insn->type = INSN_JUMP_DYNAMIC; + continue; } else { /* sibling call */ insn->jump_dest = 0; @@ -502,11 +543,18 @@ static int add_call_destinations(struct objtool_file *file) dest_off = insn->offset + insn->len + insn->immediate; insn->call_dest = find_symbol_by_offset(insn->sec, dest_off); + /* + * FIXME: Thanks to retpolines, it's now considered + * normal for a function to call within itself. So + * disable this warning for now. + */ +#if 0 if (!insn->call_dest) { WARN_FUNC("can't find call dest symbol at offset 0x%lx", insn->sec, insn->offset, dest_off); return -1; } +#endif } else if (rela->sym->type == STT_SECTION) { insn->call_dest = find_symbol_by_offset(rela->sym->sec, rela->addend+4); @@ -671,12 +719,6 @@ static int add_special_section_alts(struct objtool_file *file) return ret; list_for_each_entry_safe(special_alt, tmp, &special_alts, list) { - alt = malloc(sizeof(*alt)); - if (!alt) { - WARN("malloc failed"); - ret = -1; - goto out; - } orig_insn = find_insn(file, special_alt->orig_sec, special_alt->orig_off); @@ -687,6 +729,10 @@ static int add_special_section_alts(struct objtool_file *file) goto out; } + /* Ignore retpoline alternatives. */ + if (orig_insn->ignore_alts) + continue; + new_insn = NULL; if (!special_alt->group || special_alt->new_len) { new_insn = find_insn(file, special_alt->new_sec, @@ -712,6 +758,13 @@ static int add_special_section_alts(struct objtool_file *file) goto out; } + alt = malloc(sizeof(*alt)); + if (!alt) { + WARN("malloc failed"); + ret = -1; + goto out; + } + alt->insn = new_insn; list_add_tail(&alt->list, &orig_insn->alts); @@ -1028,6 +1081,10 @@ static int decode_sections(struct objtool_file *file) add_ignores(file); + ret = add_nospec_ignores(file); + if (ret) + return ret; + ret = add_jump_destinations(file); if (ret) return ret; diff --git a/tools/objtool/check.h b/tools/objtool/check.h index 47d9ea70a83d..dbadb304a410 100644 --- a/tools/objtool/check.h +++ b/tools/objtool/check.h @@ -44,7 +44,7 @@ struct instruction { unsigned int len; unsigned char type; unsigned long immediate; - bool alt_group, visited, dead_end, ignore, hint, save, restore; + bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts; struct symbol *call_dest; struct instruction *jump_dest; struct list_head alts; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 543847957fdd..960179882a1c 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -274,6 +274,46 @@ static struct bpf_test tests[] = { .result = REJECT, }, { + "arsh32 on imm", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_ARSH not supported for 32 bit ALU", + }, + { + "arsh32 on reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = REJECT, + .errstr = "BPF_ARSH not supported for 32 bit ALU", + }, + { + "arsh64 on imm", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_0, 5), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { + "arsh64 on reg", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_MOV64_IMM(BPF_REG_1, 5), + BPF_ALU64_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1), + BPF_EXIT_INSN(), + }, + .result = ACCEPT, + }, + { "no bpf_exit", .insns = { BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2), diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index 939a337128db..5d4f10ac2af2 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -7,7 +7,7 @@ include ../lib.mk TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \ check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \ - protection_keys test_vdso + protection_keys test_vdso test_vsyscall TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \ test_FCMOV test_FCOMI test_FISTTP \ vdso_restorer diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c new file mode 100644 index 000000000000..7a744fa7b786 --- /dev/null +++ b/tools/testing/selftests/x86/test_vsyscall.c @@ -0,0 +1,500 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define _GNU_SOURCE + +#include <stdio.h> +#include <sys/time.h> +#include <time.h> +#include <stdlib.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <dlfcn.h> +#include <string.h> +#include <inttypes.h> +#include <signal.h> +#include <sys/ucontext.h> +#include <errno.h> +#include <err.h> +#include <sched.h> +#include <stdbool.h> +#include <setjmp.h> + +#ifdef __x86_64__ +# define VSYS(x) (x) +#else +# define VSYS(x) 0 +#endif + +#ifndef SYS_getcpu +# ifdef __x86_64__ +# define SYS_getcpu 309 +# else +# define SYS_getcpu 318 +# endif +#endif + +static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), + int flags) +{ + struct sigaction sa; + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handler; + sa.sa_flags = SA_SIGINFO | flags; + sigemptyset(&sa.sa_mask); + if (sigaction(sig, &sa, 0)) + err(1, "sigaction"); +} + +/* vsyscalls and vDSO */ +bool should_read_vsyscall = false; + +typedef long (*gtod_t)(struct timeval *tv, struct timezone *tz); +gtod_t vgtod = (gtod_t)VSYS(0xffffffffff600000); +gtod_t vdso_gtod; + +typedef int (*vgettime_t)(clockid_t, struct timespec *); +vgettime_t vdso_gettime; + +typedef long (*time_func_t)(time_t *t); +time_func_t vtime = (time_func_t)VSYS(0xffffffffff600400); +time_func_t vdso_time; + +typedef long (*getcpu_t)(unsigned *, unsigned *, void *); +getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800); +getcpu_t vdso_getcpu; + +static void init_vdso(void) +{ + void *vdso = dlopen("linux-vdso.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) + vdso = dlopen("linux-gate.so.1", RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD); + if (!vdso) { + printf("[WARN]\tfailed to find vDSO\n"); + return; + } + + vdso_gtod = (gtod_t)dlsym(vdso, "__vdso_gettimeofday"); + if (!vdso_gtod) + printf("[WARN]\tfailed to find gettimeofday in vDSO\n"); + + vdso_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime"); + if (!vdso_gettime) + printf("[WARN]\tfailed to find clock_gettime in vDSO\n"); + + vdso_time = (time_func_t)dlsym(vdso, "__vdso_time"); + if (!vdso_time) + printf("[WARN]\tfailed to find time in vDSO\n"); + + vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu"); + if (!vdso_getcpu) { + /* getcpu() was never wired up in the 32-bit vDSO. */ + printf("[%s]\tfailed to find getcpu in vDSO\n", + sizeof(long) == 8 ? "WARN" : "NOTE"); + } +} + +static int init_vsys(void) +{ +#ifdef __x86_64__ + int nerrs = 0; + FILE *maps; + char line[128]; + bool found = false; + + maps = fopen("/proc/self/maps", "r"); + if (!maps) { + printf("[WARN]\tCould not open /proc/self/maps -- assuming vsyscall is r-x\n"); + should_read_vsyscall = true; + return 0; + } + + while (fgets(line, sizeof(line), maps)) { + char r, x; + void *start, *end; + char name[128]; + if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s", + &start, &end, &r, &x, name) != 5) + continue; + + if (strcmp(name, "[vsyscall]")) + continue; + + printf("\tvsyscall map: %s", line); + + if (start != (void *)0xffffffffff600000 || + end != (void *)0xffffffffff601000) { + printf("[FAIL]\taddress range is nonsense\n"); + nerrs++; + } + + printf("\tvsyscall permissions are %c-%c\n", r, x); + should_read_vsyscall = (r == 'r'); + if (x != 'x') { + vgtod = NULL; + vtime = NULL; + vgetcpu = NULL; + } + + found = true; + break; + } + + fclose(maps); + + if (!found) { + printf("\tno vsyscall map in /proc/self/maps\n"); + should_read_vsyscall = false; + vgtod = NULL; + vtime = NULL; + vgetcpu = NULL; + } + + return nerrs; +#else + return 0; +#endif +} + +/* syscalls */ +static inline long sys_gtod(struct timeval *tv, struct timezone *tz) +{ + return syscall(SYS_gettimeofday, tv, tz); +} + +static inline int sys_clock_gettime(clockid_t id, struct timespec *ts) +{ + return syscall(SYS_clock_gettime, id, ts); +} + +static inline long sys_time(time_t *t) +{ + return syscall(SYS_time, t); +} + +static inline long sys_getcpu(unsigned * cpu, unsigned * node, + void* cache) +{ + return syscall(SYS_getcpu, cpu, node, cache); +} + +static jmp_buf jmpbuf; + +static void sigsegv(int sig, siginfo_t *info, void *ctx_void) +{ + siglongjmp(jmpbuf, 1); +} + +static double tv_diff(const struct timeval *a, const struct timeval *b) +{ + return (double)(a->tv_sec - b->tv_sec) + + (double)((int)a->tv_usec - (int)b->tv_usec) * 1e-6; +} + +static int check_gtod(const struct timeval *tv_sys1, + const struct timeval *tv_sys2, + const struct timezone *tz_sys, + const char *which, + const struct timeval *tv_other, + const struct timezone *tz_other) +{ + int nerrs = 0; + double d1, d2; + + if (tz_other && (tz_sys->tz_minuteswest != tz_other->tz_minuteswest || tz_sys->tz_dsttime != tz_other->tz_dsttime)) { + printf("[FAIL] %s tz mismatch\n", which); + nerrs++; + } + + d1 = tv_diff(tv_other, tv_sys1); + d2 = tv_diff(tv_sys2, tv_other); + printf("\t%s time offsets: %lf %lf\n", which, d1, d2); + + if (d1 < 0 || d2 < 0) { + printf("[FAIL]\t%s time was inconsistent with the syscall\n", which); + nerrs++; + } else { + printf("[OK]\t%s gettimeofday()'s timeval was okay\n", which); + } + + return nerrs; +} + +static int test_gtod(void) +{ + struct timeval tv_sys1, tv_sys2, tv_vdso, tv_vsys; + struct timezone tz_sys, tz_vdso, tz_vsys; + long ret_vdso = -1; + long ret_vsys = -1; + int nerrs = 0; + + printf("[RUN]\ttest gettimeofday()\n"); + + if (sys_gtod(&tv_sys1, &tz_sys) != 0) + err(1, "syscall gettimeofday"); + if (vdso_gtod) + ret_vdso = vdso_gtod(&tv_vdso, &tz_vdso); + if (vgtod) + ret_vsys = vgtod(&tv_vsys, &tz_vsys); + if (sys_gtod(&tv_sys2, &tz_sys) != 0) + err(1, "syscall gettimeofday"); + + if (vdso_gtod) { + if (ret_vdso == 0) { + nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vDSO", &tv_vdso, &tz_vdso); + } else { + printf("[FAIL]\tvDSO gettimeofday() failed: %ld\n", ret_vdso); + nerrs++; + } + } + + if (vgtod) { + if (ret_vsys == 0) { + nerrs += check_gtod(&tv_sys1, &tv_sys2, &tz_sys, "vsyscall", &tv_vsys, &tz_vsys); + } else { + printf("[FAIL]\tvsys gettimeofday() failed: %ld\n", ret_vsys); + nerrs++; + } + } + + return nerrs; +} + +static int test_time(void) { + int nerrs = 0; + + printf("[RUN]\ttest time()\n"); + long t_sys1, t_sys2, t_vdso = 0, t_vsys = 0; + long t2_sys1 = -1, t2_sys2 = -1, t2_vdso = -1, t2_vsys = -1; + t_sys1 = sys_time(&t2_sys1); + if (vdso_time) + t_vdso = vdso_time(&t2_vdso); + if (vtime) + t_vsys = vtime(&t2_vsys); + t_sys2 = sys_time(&t2_sys2); + if (t_sys1 < 0 || t_sys1 != t2_sys1 || t_sys2 < 0 || t_sys2 != t2_sys2) { + printf("[FAIL]\tsyscall failed (ret1:%ld output1:%ld ret2:%ld output2:%ld)\n", t_sys1, t2_sys1, t_sys2, t2_sys2); + nerrs++; + return nerrs; + } + + if (vdso_time) { + if (t_vdso < 0 || t_vdso != t2_vdso) { + printf("[FAIL]\tvDSO failed (ret:%ld output:%ld)\n", t_vdso, t2_vdso); + nerrs++; + } else if (t_vdso < t_sys1 || t_vdso > t_sys2) { + printf("[FAIL]\tvDSO returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vdso, t_sys2); + nerrs++; + } else { + printf("[OK]\tvDSO time() is okay\n"); + } + } + + if (vtime) { + if (t_vsys < 0 || t_vsys != t2_vsys) { + printf("[FAIL]\tvsyscall failed (ret:%ld output:%ld)\n", t_vsys, t2_vsys); + nerrs++; + } else if (t_vsys < t_sys1 || t_vsys > t_sys2) { + printf("[FAIL]\tvsyscall returned the wrong time (%ld %ld %ld)\n", t_sys1, t_vsys, t_sys2); + nerrs++; + } else { + printf("[OK]\tvsyscall time() is okay\n"); + } + } + + return nerrs; +} + +static int test_getcpu(int cpu) +{ + int nerrs = 0; + long ret_sys, ret_vdso = -1, ret_vsys = -1; + + printf("[RUN]\tgetcpu() on CPU %d\n", cpu); + + cpu_set_t cpuset; + CPU_ZERO(&cpuset); + CPU_SET(cpu, &cpuset); + if (sched_setaffinity(0, sizeof(cpuset), &cpuset) != 0) { + printf("[SKIP]\tfailed to force CPU %d\n", cpu); + return nerrs; + } + + unsigned cpu_sys, cpu_vdso, cpu_vsys, node_sys, node_vdso, node_vsys; + unsigned node = 0; + bool have_node = false; + ret_sys = sys_getcpu(&cpu_sys, &node_sys, 0); + if (vdso_getcpu) + ret_vdso = vdso_getcpu(&cpu_vdso, &node_vdso, 0); + if (vgetcpu) + ret_vsys = vgetcpu(&cpu_vsys, &node_vsys, 0); + + if (ret_sys == 0) { + if (cpu_sys != cpu) { + printf("[FAIL]\tsyscall reported CPU %hu but should be %d\n", cpu_sys, cpu); + nerrs++; + } + + have_node = true; + node = node_sys; + } + + if (vdso_getcpu) { + if (ret_vdso) { + printf("[FAIL]\tvDSO getcpu() failed\n"); + nerrs++; + } else { + if (!have_node) { + have_node = true; + node = node_vdso; + } + + if (cpu_vdso != cpu) { + printf("[FAIL]\tvDSO reported CPU %hu but should be %d\n", cpu_vdso, cpu); + nerrs++; + } else { + printf("[OK]\tvDSO reported correct CPU\n"); + } + + if (node_vdso != node) { + printf("[FAIL]\tvDSO reported node %hu but should be %hu\n", node_vdso, node); + nerrs++; + } else { + printf("[OK]\tvDSO reported correct node\n"); + } + } + } + + if (vgetcpu) { + if (ret_vsys) { + printf("[FAIL]\tvsyscall getcpu() failed\n"); + nerrs++; + } else { + if (!have_node) { + have_node = true; + node = node_vsys; + } + + if (cpu_vsys != cpu) { + printf("[FAIL]\tvsyscall reported CPU %hu but should be %d\n", cpu_vsys, cpu); + nerrs++; + } else { + printf("[OK]\tvsyscall reported correct CPU\n"); + } + + if (node_vsys != node) { + printf("[FAIL]\tvsyscall reported node %hu but should be %hu\n", node_vsys, node); + nerrs++; + } else { + printf("[OK]\tvsyscall reported correct node\n"); + } + } + } + + return nerrs; +} + +static int test_vsys_r(void) +{ +#ifdef __x86_64__ + printf("[RUN]\tChecking read access to the vsyscall page\n"); + bool can_read; + if (sigsetjmp(jmpbuf, 1) == 0) { + *(volatile int *)0xffffffffff600000; + can_read = true; + } else { + can_read = false; + } + + if (can_read && !should_read_vsyscall) { + printf("[FAIL]\tWe have read access, but we shouldn't\n"); + return 1; + } else if (!can_read && should_read_vsyscall) { + printf("[FAIL]\tWe don't have read access, but we should\n"); + return 1; + } else { + printf("[OK]\tgot expected result\n"); + } +#endif + + return 0; +} + + +#ifdef __x86_64__ +#define X86_EFLAGS_TF (1UL << 8) +static volatile sig_atomic_t num_vsyscall_traps; + +static unsigned long get_eflags(void) +{ + unsigned long eflags; + asm volatile ("pushfq\n\tpopq %0" : "=rm" (eflags)); + return eflags; +} + +static void set_eflags(unsigned long eflags) +{ + asm volatile ("pushq %0\n\tpopfq" : : "rm" (eflags) : "flags"); +} + +static void sigtrap(int sig, siginfo_t *info, void *ctx_void) +{ + ucontext_t *ctx = (ucontext_t *)ctx_void; + unsigned long ip = ctx->uc_mcontext.gregs[REG_RIP]; + + if (((ip ^ 0xffffffffff600000UL) & ~0xfffUL) == 0) + num_vsyscall_traps++; +} + +static int test_native_vsyscall(void) +{ + time_t tmp; + bool is_native; + + if (!vtime) + return 0; + + printf("[RUN]\tchecking for native vsyscall\n"); + sethandler(SIGTRAP, sigtrap, 0); + set_eflags(get_eflags() | X86_EFLAGS_TF); + vtime(&tmp); + set_eflags(get_eflags() & ~X86_EFLAGS_TF); + + /* + * If vsyscalls are emulated, we expect a single trap in the + * vsyscall page -- the call instruction will trap with RIP + * pointing to the entry point before emulation takes over. + * In native mode, we expect two traps, since whatever code + * the vsyscall page contains will be more than just a ret + * instruction. + */ + is_native = (num_vsyscall_traps > 1); + + printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n", + (is_native ? "native" : "emulated"), + (int)num_vsyscall_traps); + + return 0; +} +#endif + +int main(int argc, char **argv) +{ + int nerrs = 0; + + init_vdso(); + nerrs += init_vsys(); + + nerrs += test_gtod(); + nerrs += test_time(); + nerrs += test_getcpu(0); + nerrs += test_getcpu(1); + + sethandler(SIGSEGV, sigsegv, 0); + nerrs += test_vsys_r(); + +#ifdef __x86_64__ + nerrs += test_native_vsyscall(); +#endif + + return nerrs ? 1 : 0; +} |