From c26665ab5c49ad3e142e0f054ca3204f259ba09c Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Fri, 20 Jan 2017 21:29:40 +0100 Subject: x86/microcode/intel: Drop stashed AP patch pointer optimization This was meant to save us the scanning of the microcode containter in the initrd since the first AP had already done that but it can also hurt us: Imagine a single hyperthreaded CPU (Intel(R) Atom(TM) CPU N270, for example) which updates the microcode on the BSP but since the microcode engine is shared between the two threads, the update on CPU1 doesn't happen because it has already happened on CPU0 and we don't find a newer microcode revision on CPU1. Which doesn't set the intel_ucode_patch pointer and at initrd jettisoning time we don't save the microcode patch for later application. Now, when we suspend to RAM, the loaded microcode gets cleared so we need to reload but there's no patch saved in the cache. Removing the optimization fixes this issue and all is fine and dandy. Fixes: 06b8534cb728 ("x86/microcode: Rework microcode loading") Signed-off-by: Borislav Petkov Reviewed-by: Thomas Gleixner Link: http://lkml.kernel.org/r/20170120202955.4091-2-bp@alien8.de Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/microcode/intel.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 3f329b74e040..8325d8a09ab0 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -41,7 +41,7 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; -/* Current microcode patch used in early patching */ +/* Current microcode patch used in early patching on the APs. */ struct microcode_intel *intel_ucode_patch; static inline bool cpu_signatures_match(unsigned int s1, unsigned int p1, @@ -607,12 +607,6 @@ int __init save_microcode_in_initrd_intel(void) struct ucode_cpu_info uci; struct cpio_data cp; - /* - * AP loading didn't find any microcode patch, no need to save anything. - */ - if (!intel_ucode_patch || IS_ERR(intel_ucode_patch)) - return 0; - if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path, false); @@ -628,7 +622,6 @@ int __init save_microcode_in_initrd_intel(void) return 0; } - /* * @res_patch, output: a pointer to the patch we found. */ -- cgit v1.2.3 From 4c833368f0bf748d4147bf301b1f95bc8eccb3c0 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Sun, 22 Jan 2017 16:50:23 +0800 Subject: x86/fpu: Set the xcomp_bv when we fake up a XSAVES area I got the following calltrace on a Apollo Lake SoC with 32-bit kernel: WARNING: CPU: 2 PID: 261 at arch/x86/include/asm/fpu/internal.h:363 fpu__restore+0x1f5/0x260 [...] Hardware name: Intel Corp. Broxton P/NOTEBOOK, BIOS APLIRVPA.X64.0138.B35.1608091058 08/09/2016 Call Trace: dump_stack() __warn() ? fpu__restore() warn_slowpath_null() fpu__restore() __fpu__restore_sig() fpu__restore_sig() restore_sigcontext.isra.9() sys_sigreturn() do_int80_syscall_32() entry_INT80_32() The reason is that a #GP occurs when executing XRSTORS. The root cause is that we forget to set the xcomp_bv when we fake up the XSAVES area in the copyin_to_xsaves() function. Signed-off-by: Kevin Hao Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Denys Vlasenko Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Quentin Casasnovas Cc: Rik van Riel Cc: Thomas Gleixner Cc: Yu-cheng Yu Link: http://lkml.kernel.org/r/1485075023-30161-1-git-send-email-haokexin@gmail.com Signed-off-by: Ingo Molnar Signed-off-by: Thomas Gleixner --- arch/x86/kernel/fpu/xstate.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 1d7770447b3e..e287b9075527 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1070,6 +1070,7 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= xfeatures; + xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xsave->header.xfeatures; return 0; } -- cgit v1.2.3 From dffba9a31c7769be3231c420d4b364c92ba3f1ac Mon Sep 17 00:00:00 2001 From: Yu-cheng Yu Date: Mon, 23 Jan 2017 14:54:44 -0800 Subject: x86/fpu/xstate: Fix xcomp_bv in XSAVES header The compacted-format XSAVES area is determined at boot time and never changed after. The field xsave.header.xcomp_bv indicates which components are in the fixed XSAVES format. In fpstate_init() we did not set xcomp_bv to reflect the XSAVES format since at the time there is no valid data. However, after we do copy_init_fpstate_to_fpregs() in fpu__clear(), as in commit: b22cbe404a9c x86/fpu: Fix invalid FPU ptrace state after execve() and when __fpu_restore_sig() does fpu__restore() for a COMPAT-mode app, a #GP occurs. This can be easily triggered by doing valgrind on a COMPAT-mode "Hello World," as reported by Joakim Tjernlund and others: https://bugzilla.kernel.org/show_bug.cgi?id=190061 Fix it by setting xcomp_bv correctly. This patch also moves the xcomp_bv initialization to the proper place, which was in copyin_to_xsaves() as of: 4c833368f0bf x86/fpu: Set the xcomp_bv when we fake up a XSAVES area which fixed the bug too, but it's more efficient and cleaner to initialize things once per boot, not for every signal handling operation. Reported-by: Kevin Hao Reported-by: Joakim Tjernlund Signed-off-by: Yu-cheng Yu Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Fenghua Yu Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Ravi V. Shankar Cc: Thomas Gleixner Cc: haokexin@gmail.com Link: http://lkml.kernel.org/r/1485212084-4418-1-git-send-email-yu-cheng.yu@intel.com [ Combined it with 4c833368f0bf. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/fpu/core.c | 4 +++- arch/x86/kernel/fpu/xstate.c | 1 - 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e4e97a5355ce..de7234401275 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include @@ -183,7 +184,8 @@ void fpstate_init(union fpregs_state *state) * it will #GP. Make sure it is replaced after the memset(). */ if (static_cpu_has(X86_FEATURE_XSAVES)) - state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT; + state->xsave.header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | + xfeatures_mask; if (static_cpu_has(X86_FEATURE_FXSR)) fpstate_init_fxstate(&state->fxsave); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index e287b9075527..1d7770447b3e 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1070,7 +1070,6 @@ int copyin_to_xsaves(const void *kbuf, const void __user *ubuf, * Add back in the features that came in from userspace: */ xsave->header.xfeatures |= xfeatures; - xsave->header.xcomp_bv = XCOMP_BV_COMPACTED_FORMAT | xsave->header.xfeatures; return 0; } -- cgit v1.2.3 From 24c2503255d35c269b67162c397a1a1c1e02f6ce Mon Sep 17 00:00:00 2001 From: Borislav Petkov Date: Wed, 25 Jan 2017 21:00:48 +0100 Subject: x86/microcode: Do not access the initrd after it has been freed When we look for microcode blobs, we first try builtin and if that doesn't succeed, we fallback to the initrd supplied to the kernel. However, at some point doing boot, that initrd gets jettisoned and we shouldn't access it anymore. But we do, as the below KASAN report shows. That's because find_microcode_in_initrd() doesn't check whether the initrd is still valid or not. So do that. ================================================================== BUG: KASAN: use-after-free in find_cpio_data Read of size 1 by task swapper/1/0 page:ffffea0000db9d40 count:0 mapcount:0 mapping: (null) index:0x1 flags: 0x100000000000000() raw: 0100000000000000 0000000000000000 0000000000000001 00000000ffffffff raw: dead000000000100 dead000000000200 0000000000000000 0000000000000000 page dumped because: kasan: bad access detected CPU: 1 PID: 0 Comm: swapper/1 Tainted: G W 4.10.0-rc5-debug-00075-g2dbde22 #3 Hardware name: Dell Inc. XPS 13 9360/0839Y6, BIOS 1.2.3 12/01/2016 Call Trace: dump_stack ? _atomic_dec_and_lock ? __dump_page kasan_report_error ? pointer ? find_cpio_data __asan_report_load1_noabort ? find_cpio_data find_cpio_data ? vsprintf ? dump_stack ? get_ucode_user ? print_usage_bug find_microcode_in_initrd __load_ucode_intel ? collect_cpu_info_early ? debug_check_no_locks_freed load_ucode_intel_ap ? collect_cpu_info ? trace_hardirqs_on ? flat_send_IPI_mask_allbutself load_ucode_ap ? get_builtin_firmware ? flush_tlb_func ? do_raw_spin_trylock ? cpumask_weight cpu_init ? trace_hardirqs_off ? play_dead_common ? native_play_dead ? hlt_play_dead ? syscall_init ? arch_cpu_idle_dead ? do_idle start_secondary start_cpu Memory state around the buggy address: ffff880036e74f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff880036e74f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff >ffff880036e75000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ^ ffff880036e75080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ffff880036e75100: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ================================================================== Reported-by: Andrey Ryabinin Tested-by: Andrey Ryabinin Signed-off-by: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170126165833.evjemhbqzaepirxo@pd.tnic Signed-off-by: Ingo Molnar --- arch/x86/include/asm/microcode.h | 1 + arch/x86/kernel/cpu/microcode/amd.c | 5 +++-- arch/x86/kernel/cpu/microcode/core.c | 22 +++++++++++++++++----- 3 files changed, 21 insertions(+), 7 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 38711df3bcb5..2266f864b747 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -140,6 +140,7 @@ extern void __init load_ucode_bsp(void); extern void load_ucode_ap(void); void reload_early_microcode(void); extern bool get_builtin_firmware(struct cpio_data *cd, const char *name); +extern bool initrd_gone; #else static inline int __init microcode_init(void) { return 0; }; static inline void __init load_ucode_bsp(void) { } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 6a31e2691f3a..079e81733a58 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -384,8 +384,9 @@ void load_ucode_amd_ap(unsigned int family) reget: if (!get_builtin_microcode(&cp, family)) { #ifdef CONFIG_BLK_DEV_INITRD - cp = find_cpio_data(ucode_path, (void *)initrd_start, - initrd_end - initrd_start, NULL); + if (!initrd_gone) + cp = find_cpio_data(ucode_path, (void *)initrd_start, + initrd_end - initrd_start, NULL); #endif if (!(cp.data && cp.size)) { /* diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 2af69d27da62..73102d932760 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -46,6 +46,8 @@ static struct microcode_ops *microcode_ops; static bool dis_ucode_ldr = true; +bool initrd_gone; + LIST_HEAD(microcode_cache); /* @@ -190,21 +192,24 @@ void load_ucode_ap(void) static int __init save_microcode_in_initrd(void) { struct cpuinfo_x86 *c = &boot_cpu_data; + int ret = -EINVAL; switch (c->x86_vendor) { case X86_VENDOR_INTEL: if (c->x86 >= 6) - return save_microcode_in_initrd_intel(); + ret = save_microcode_in_initrd_intel(); break; case X86_VENDOR_AMD: if (c->x86 >= 0x10) - return save_microcode_in_initrd_amd(c->x86); + ret = save_microcode_in_initrd_amd(c->x86); break; default: break; } - return -EINVAL; + initrd_gone = true; + + return ret; } struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) @@ -247,9 +252,16 @@ struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. + * + * initrd_gone is for the hotplug case where we've thrown out initrd + * already. */ - if (!use_pa && initrd_start) - start = initrd_start; + if (!use_pa) { + if (initrd_gone) + return (struct cpio_data){ NULL, 0, "" }; + if (initrd_start) + start = initrd_start; + } return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ -- cgit v1.2.3 From 0becc0ae5b42828785b589f686725ff5bc3b9b25 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 31 Jan 2017 09:37:34 +0100 Subject: x86/mce: Make timer handling more robust Erik reported that on a preproduction hardware a CMCI storm triggers the BUG_ON in add_timer_on(). The reason is that the per CPU MCE timer is started by the CMCI logic before the MCE CPU hotplug callback starts the timer with add_timer_on(). So the timer is already queued which triggers the BUG. Using add_timer_on() is pretty pointless in this code because the timer is strictlty per CPU, initialized as pinned and all operations which arm the timer happen on the CPU to which the timer belongs. Simplify the whole machinery by using mod_timer() instead of add_timer_on() which avoids the problem because mod_timer() can handle already queued timers. Use __start_timer() everywhere so the earliest armed expiry time is preserved. Reported-by: Erik Veijola Tested-by: Borislav Petkov Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Tony Luck Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1701310936080.3457@nanos Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/mcheck/mce.c | 31 ++++++++++++------------------- 1 file changed, 12 insertions(+), 19 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 00ef43233e03..537c6647d84c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -1373,20 +1373,15 @@ static unsigned long mce_adjust_timer_default(unsigned long interval) static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; -static void __restart_timer(struct timer_list *t, unsigned long interval) +static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; unsigned long flags; local_irq_save(flags); - if (timer_pending(t)) { - if (time_before(when, t->expires)) - mod_timer(t, when); - } else { - t->expires = round_jiffies(when); - add_timer_on(t, smp_processor_id()); - } + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); local_irq_restore(flags); } @@ -1421,7 +1416,7 @@ static void mce_timer_fn(unsigned long data) done: __this_cpu_write(mce_next_interval, iv); - __restart_timer(t, iv); + __start_timer(t, iv); } /* @@ -1432,7 +1427,7 @@ void mce_timer_kick(unsigned long interval) struct timer_list *t = this_cpu_ptr(&mce_timer); unsigned long iv = __this_cpu_read(mce_next_interval); - __restart_timer(t, interval); + __start_timer(t, interval); if (interval < iv) __this_cpu_write(mce_next_interval, interval); @@ -1779,17 +1774,15 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) } } -static void mce_start_timer(unsigned int cpu, struct timer_list *t) +static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; if (mca_cfg.ignore_ce || !iv) return; - per_cpu(mce_next_interval, cpu) = iv; - - t->expires = round_jiffies(jiffies + iv); - add_timer_on(t, cpu); + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); } static void __mcheck_cpu_setup_timer(void) @@ -1806,7 +1799,7 @@ static void __mcheck_cpu_init_timer(void) unsigned int cpu = smp_processor_id(); setup_pinned_timer(t, mce_timer_fn, cpu); - mce_start_timer(cpu, t); + mce_start_timer(t); } /* Handle unconfigured int18 (should never happen) */ @@ -2566,7 +2559,7 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); int ret; mce_device_create(cpu); @@ -2577,13 +2570,13 @@ static int mce_cpu_online(unsigned int cpu) return ret; } mce_reenable_cpu(); - mce_start_timer(cpu, t); + mce_start_timer(t); return 0; } static int mce_cpu_pre_down(unsigned int cpu) { - struct timer_list *t = &per_cpu(mce_timer, cpu); + struct timer_list *t = this_cpu_ptr(&mce_timer); mce_disable_cpu(); del_timer_sync(t); -- cgit v1.2.3