From 370a132bb2227ff76278f98370e0e701d86ff752 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Tue, 31 Jul 2018 07:27:39 -0400 Subject: [PATCH 1/7] x86/microcode: Make sure boot_cpu_data.microcode is up-to-date When preparing an MCE record for logging, boot_cpu_data.microcode is used to read out the microcode revision on the box. However, on systems where late microcode update has happened, the microcode revision output in a MCE log record is wrong because boot_cpu_data.microcode is not updated when the microcode gets updated. But, the microcode revision saved in boot_cpu_data's microcode member should be kept up-to-date, regardless, for consistency. Make it so. Fixes: fa94d0c6e0f3 ("x86/MCE: Save microcode revision in machine check records") Signed-off-by: Prarit Bhargava Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Cc: Tony Luck Cc: sironi@amazon.de Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/20180731112739.32338-1-prarit@redhat.com --- arch/x86/kernel/cpu/microcode/amd.c | 4 ++++ arch/x86/kernel/cpu/microcode/intel.c | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 0624957aa068..602f17134103 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -537,6 +537,10 @@ static enum ucode_state apply_microcode_amd(int cpu) uci->cpu_sig.rev = mc_amd->hdr.patch_id; c->microcode = mc_amd->hdr.patch_id; + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = mc_amd->hdr.patch_id; + return UCODE_UPDATED; } diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 97ccf4c3b45b..256d336cbc04 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -851,6 +851,10 @@ static enum ucode_state apply_microcode_intel(int cpu) uci->cpu_sig.rev = rev; c->microcode = rev; + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + return UCODE_UPDATED; } From 8da38ebaad23fe1b0c4a205438676f6356607cfc Mon Sep 17 00:00:00 2001 From: Filippo Sironi Date: Tue, 31 Jul 2018 17:29:30 +0200 Subject: [PATCH 2/7] x86/microcode: Update the new microcode revision unconditionally Handle the case where microcode gets loaded on the BSP's hyperthread sibling first and the boot_cpu_data's microcode revision doesn't get updated because of early exit due to the siblings sharing a microcode engine. For that, simply write the updated revision on all CPUs unconditionally. Signed-off-by: Filippo Sironi Signed-off-by: Borislav Petkov Signed-off-by: Thomas Gleixner Cc: prarit@redhat.com Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1533050970-14385-1-git-send-email-sironi@amazon.de --- arch/x86/kernel/cpu/microcode/amd.c | 22 +++++++++++++--------- arch/x86/kernel/cpu/microcode/intel.c | 13 ++++++++----- 2 files changed, 21 insertions(+), 14 deletions(-) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 602f17134103..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,17 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); + +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; /* Update boot_cpu_data's revision too, if we're on the BSP: */ if (c->cpu_index == boot_cpu_data.cpu_index) - boot_cpu_data.microcode = mc_amd->hdr.patch_id; + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 256d336cbc04..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -848,14 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; /* Update boot_cpu_data's revision too, if we're on the BSP: */ if (c->cpu_index == boot_cpu_data.cpu_index) boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, From 4331f4d5ada5684fc77fa16e3f6177f077c9e6ec Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Sun, 2 Sep 2018 19:30:53 -0700 Subject: [PATCH 3/7] x86: Fix kernel-doc atomic.h warnings Fix kernel-doc warnings in arch/x86/include/asm/atomic.h that are caused by having a #define macro between the kernel-doc notation and the function name. Fixed by moving the #define macro to after the function implementation. Make the same change for atomic64_{32,64}.h for consistency even though there were no kernel-doc warnings found in these header files, but there would be if they were used in generation of documentation. Fixes these kernel-doc warnings: ../arch/x86/include/asm/atomic.h:84: warning: Excess function parameter 'i' description in 'arch_atomic_sub_and_test' ../arch/x86/include/asm/atomic.h:84: warning: Excess function parameter 'v' description in 'arch_atomic_sub_and_test' ../arch/x86/include/asm/atomic.h:96: warning: Excess function parameter 'v' description in 'arch_atomic_inc' ../arch/x86/include/asm/atomic.h:109: warning: Excess function parameter 'v' description in 'arch_atomic_dec' ../arch/x86/include/asm/atomic.h:124: warning: Excess function parameter 'v' description in 'arch_atomic_dec_and_test' ../arch/x86/include/asm/atomic.h:138: warning: Excess function parameter 'v' description in 'arch_atomic_inc_and_test' ../arch/x86/include/asm/atomic.h:153: warning: Excess function parameter 'i' description in 'arch_atomic_add_negative' ../arch/x86/include/asm/atomic.h:153: warning: Excess function parameter 'v' description in 'arch_atomic_add_negative' Fixes: 18cc1814d4e7 ("atomics/treewide: Make test ops optional") Signed-off-by: Randy Dunlap Signed-off-by: Thomas Gleixner Cc: Mark Rutland Link: https://lkml.kernel.org/r/0a1e678d-c8c5-b32c-2640-ed4e94d399d2@infradead.org --- arch/x86/include/asm/atomic.h | 12 ++++++------ arch/x86/include/asm/atomic64_32.h | 8 ++++---- arch/x86/include/asm/atomic64_64.h | 12 ++++++------ 3 files changed, 16 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b143717b92b3..ce84388e540c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); } +#define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable @@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); } +#define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable @@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); } +#define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test @@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); } +#define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test @@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); } +#define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative @@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); } +#define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index ef959f02d070..6a5b0ec460da 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_add_unless - add unless the number is a given value @@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) "S" (v) : "ecx", "edx", "memory"); return r; } +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; @@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) "S" (v) : "ecx", "memory"); return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #undef alternative_atomic64 #undef __alternative_atomic64 diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 4343d9b4f30e..5f851d92eecd 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); } +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test /** * arch_atomic64_inc - increment atomic64 variable @@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_dec_and_test - decrement and test @@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); } +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test /** * arch_atomic64_inc_and_test - increment and test @@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); } +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test /** * arch_atomic64_add_negative - add and test if negative @@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); } +#define arch_atomic64_add_negative arch_atomic64_add_negative /** * arch_atomic64_add_return - add and return From 17f6bac2249356c795339e03a0742cd79be3cab8 Mon Sep 17 00:00:00 2001 From: Chuanhua Lei Date: Thu, 6 Sep 2018 18:03:23 +0800 Subject: [PATCH 4/7] x86/tsc: Prevent result truncation on 32bit Loops per jiffy is calculated by multiplying tsc_khz with 1e3 and then dividing it by HZ. Both tsc_khz and the temporary variable holding the multiplication result are of type unsigned long, so on 32bit the result is truncated to the lower 32bit. Use u64 as type for the temporary variable and cast tsc_khz to it before multiplying. [ tglx: Massaged changelog and removed pointless braces ] Fixes: cf7a63ef4e02 ("x86/tsc: Calibrate tsc only once") Signed-off-by: Chuanhua Lei Signed-off-by: Thomas Gleixner Cc: yixin.zhu@linux.intel.com Cc: "H. Peter Anvin" Cc: Peter Zijlstra Cc: Len Brown Cc: Pavel Tatashin Cc: Rajvi Jingar Cc: Dou Liyang Link: https://lkml.kernel.org/r/1536228203-18701-1-git-send-email-chuanhua.lei@linux.intel.com --- arch/x86/kernel/tsc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1463468ba9a0..6490f618e096 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1415,7 +1415,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early) static unsigned long __init get_loops_per_jiffy(void) { - unsigned long lpj = tsc_khz * KHZ; + u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; From 9fe6299dde587788f245e9f7a5a1b296fad4e8c7 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 31 Aug 2018 21:41:51 +0200 Subject: [PATCH 5/7] x86/process: Don't mix user/kernel regs in 64bit __show_regs() When the kernel.print-fatal-signals sysctl has been enabled, a simple userspace crash will cause the kernel to write a crash dump that contains, among other things, the kernel gsbase into dmesg. As suggested by Andy, limit output to pt_regs, FS_BASE and KERNEL_GS_BASE in this case. This also moves the bitness-specific logic from show_regs() into process_{32,64}.c. Fixes: 45807a1df9f5 ("vdso: print fatal signals") Signed-off-by: Jann Horn Signed-off-by: Thomas Gleixner Cc: "H. Peter Anvin" Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Greg Kroah-Hartman Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180831194151.123586-1-jannh@google.com --- arch/x86/include/asm/kdebug.h | 12 +++++++++++- arch/x86/kernel/dumpstack.c | 11 +++-------- arch/x86/kernel/process_32.c | 4 ++-- arch/x86/kernel/process_64.c | 12 ++++++++++-- 4 files changed, 26 insertions(+), 13 deletions(-) diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 395c9631e000..75f1e35e7c15 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -22,10 +22,20 @@ enum die_val { DIE_NMIUNKNOWN, }; +enum show_regs_mode { + SHOW_REGS_SHORT, + /* + * For when userspace crashed, but we don't think it's our fault, and + * therefore don't print kernel registers. + */ + SHOW_REGS_USER, + SHOW_REGS_ALL +}; + extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); -extern void __show_regs(struct pt_regs *regs, int all); +extern void __show_regs(struct pt_regs *regs, enum show_regs_mode); extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f56895106ccf..2b5886401e5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -146,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * they can be printed in the right context. */ if (!partial && on_stack(info, regs, sizeof(*regs))) { - __show_regs(regs, 0); + __show_regs(regs, SHOW_REGS_SHORT); } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, IRET_FRAME_SIZE)) { @@ -344,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) oops_exit(); /* Executive summary in case the oops scrolled away */ - __show_regs(&exec_summary_regs, true); + __show_regs(&exec_summary_regs, SHOW_REGS_ALL); if (!signr) return; @@ -407,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err) void show_regs(struct pt_regs *regs) { - bool all = true; - show_regs_print_info(KERN_DEFAULT); - if (IS_ENABLED(CONFIG_X86_32)) - all = !user_mode(regs); - - __show_regs(regs, all); + __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL); /* * When in-kernel, we also print out the stack at the time of the fault.. diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2924fd447e61..5046a3c9dec2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,7 +59,7 @@ #include #include -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); - if (!all) + if (mode != SHOW_REGS_ALL) return; cr0 = read_cr0(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..ea5ea850348d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,7 @@ __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -87,9 +87,17 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); - if (!all) + if (mode == SHOW_REGS_SHORT) return; + if (mode == SHOW_REGS_USER) { + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", + fs, shadowgs); + return; + } + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); From 47b7360ce563e18c524ce92b55fb4da72b3b3578 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 8 Sep 2018 12:07:26 +0200 Subject: [PATCH 6/7] x86/apic/vector: Make error return value negative activate_managed() returns EINVAL instead of -EINVAL in case of error. While this is unlikely to happen, the positive return value would cause further malfunction at the call site. Fixes: 2db1f959d9dc ("x86/vector: Handle managed interrupts proper") Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org --- arch/x86/kernel/apic/vector.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..7654febd5102 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -413,7 +413,7 @@ static int activate_managed(struct irq_data *irqd) if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { /* Something in the core code broke! Survive gracefully */ pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); - return EINVAL; + return -EINVAL; } ret = assign_managed_vector(irqd, vector_searchmask); From 9bc4f28af75a91aea0ae383f50b0a430c4509303 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 2 Sep 2018 11:14:50 -0700 Subject: [PATCH 7/7] x86/mm: Use WRITE_ONCE() when setting PTEs When page-table entries are set, the compiler might optimize their assignment by using multiple instructions to set the PTE. This might turn into a security hazard if the user somehow manages to use the interim PTE. L1TF does not make our lives easier, making even an interim non-present PTE a security hazard. Using WRITE_ONCE() to set PTEs and friends should prevent this potential security hazard. I skimmed the differences in the binary with and without this patch. The differences are (obviously) greater when CONFIG_PARAVIRT=n as more code optimizations are possible. For better and worse, the impact on the binary with this patch is pretty small. Skimming the code did not cause anything to jump out as a security hazard, but it seems that at least move_soft_dirty_pte() caused set_pte_at() to use multiple writes. Signed-off-by: Nadav Amit Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra (Intel) Cc: Dave Hansen Cc: Andi Kleen Cc: Josh Poimboeuf Cc: Michal Hocko Cc: Vlastimil Babka Cc: Sean Christopherson Cc: Andy Lutomirski Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20180902181451.80520-1-namit@vmware.com --- arch/x86/include/asm/pgtable.h | 2 +- arch/x86/include/asm/pgtable_64.h | 22 +++++++++++----------- arch/x86/mm/pgtable.c | 8 ++++---- 3 files changed, 16 insertions(+), 16 deletions(-) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e4ffa565a69f..690c0307afed 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1195,7 +1195,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); return old; } } diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f773d5e6c8cc..ce2b59047cb8 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -55,15 +55,15 @@ struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); +static inline void native_set_pte(pte_t *ptep, pte_t pte) +{ + WRITE_ONCE(*ptep, pte); +} + static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - *ptep = native_make_pte(0); -} - -static inline void native_set_pte(pte_t *ptep, pte_t pte) -{ - *ptep = pte; + native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) @@ -73,7 +73,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) @@ -109,7 +109,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) static inline void native_set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) @@ -137,13 +137,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); - *p4dp = native_make_p4d(native_pgd_val(pgd)); + WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) @@ -153,7 +153,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgtbl(pgdp, pgd); + WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index e848a4811785..ae394552fb94 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -269,7 +269,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - *pgdp = native_make_pgd(0); + pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); @@ -494,7 +494,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed && dirty) - *ptep = entry; + set_pte(ptep, entry); return changed; } @@ -509,7 +509,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { - *pmdp = entry; + set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -529,7 +529,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { - *pudp = entry; + set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that,