linux/arch/x86/mm/extable.c

260 lines
7.8 KiB
C
Raw Normal View History

#include <linux/extable.h>
#include <linux/uaccess.h>
#include <linux/sched/debug.h>
#include <xen/xen.h>
x86/fpu: Reinitialize FPU registers if restoring FPU state fails Userspace can change the FPU state of a task using the ptrace() or rt_sigreturn() system calls. Because reserved bits in the FPU state can cause the XRSTOR instruction to fail, the kernel has to carefully validate that no reserved bits or other invalid values are being set. Unfortunately, there have been bugs in this validation code. For example, we were not checking that the 'xcomp_bv' field in the xstate_header was 0. As-is, such bugs are exploitable to read the FPU registers of other processes on the system. To do so, an attacker can create a task, assign to it an invalid FPU state, then spin in a loop and monitor the values of the FPU registers. Because the task's FPU registers are not being restored, sometimes the FPU registers will have the values from another process. This is likely to continue to be a problem in the future because the validation done by the CPU instructions like XRSTOR is not immediately visible to kernel developers. Nor will invalid FPU states ever be encountered during ordinary use --- they will only be seen during fuzzing or exploits. There can even be reserved bits outside the xstate_header which are easy to forget about. For example, the MXCSR register contains reserved bits, which were not validated by the KVM_SET_XSAVE ioctl until commit a575813bfe4b ("KVM: x86: Fix load damaged SSEx MXCSR register"). Therefore, mitigate this class of vulnerability by restoring the FPU registers from init_fpstate if restoring from the task's state fails. We actually used to do this, but it was (perhaps unwisely) removed by commit 9ccc27a5d297 ("x86/fpu: Remove error return values from copy_kernel_to_*regs() functions"). This new patch is also a bit different. First, it only clears the registers, not also the bad in-memory state; this is simpler and makes it easier to make the mitigation cover all callers of __copy_kernel_to_fpregs(). Second, it does the register clearing in an exception handler so that no extra instructions are added to context switches. In fact, we *remove* instructions, since previously we were always zeroing the register containing 'err' even if CONFIG_X86_DEBUG_FPU was disabled. Signed-off-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael Halcrow <mhalcrow@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wanpeng Li <wanpeng.li@hotmail.com> Cc: Yu-cheng Yu <yu-cheng.yu@intel.com> Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170922174156.16780-4-ebiggers3@gmail.com Link: http://lkml.kernel.org/r/20170923130016.21448-27-mingo@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-23 21:00:09 +08:00
#include <asm/fpu/internal.h>
#include <asm/traps.h>
x86/dumpstack: Add show_stack_regs() and use it Add a helper to dump supplied pt_regs and use it in the MSR exception handling code to have precise stack traces pointing to the actual function causing the MSR access exception and not the stack frame of the exception handler itself. The new output looks like this: unchecked MSR access error: RDMSR from 0xdeadbeef at rIP: 0xffffffff8102ddb6 (early_init_intel+0x16/0x3a0) 00000000756e6547 ffffffff81c03f68 ffffffff81dd0940 ffffffff81c03f10 ffffffff81d42e65 0000000001000000 ffffffff81c03f58 ffffffff81d3e5a3 0000800000000000 ffffffff81800080 ffffffffffffffff 0000000000000000 Call Trace: [<ffffffff81d42e65>] early_cpu_init+0xe7/0x136 [<ffffffff81d3e5a3>] setup_arch+0xa5/0x9df [<ffffffff81d38bb9>] start_kernel+0x9f/0x43a [<ffffffff81d38294>] x86_64_start_reservations+0x2f/0x31 [<ffffffff81d383fe>] x86_64_start_kernel+0x168/0x176 Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1467671487-10344-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-05 06:31:27 +08:00
#include <asm/kdebug.h>
typedef bool (*ex_handler_t)(const struct exception_table_entry *,
struct pt_regs *, int);
static inline unsigned long
ex_fixup_addr(const struct exception_table_entry *x)
{
return (unsigned long)&x->fixup + x->fixup;
}
static inline ex_handler_t
ex_fixup_handler(const struct exception_table_entry *x)
{
return (ex_handler_t)((unsigned long)&x->handler + x->handler);
}
__visible bool ex_handler_default(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
regs->ip = ex_fixup_addr(fixup);
return true;
}
EXPORT_SYMBOL(ex_handler_default);
__visible bool ex_handler_fault(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
return true;
}
EXPORT_SYMBOL_GPL(ex_handler_fault);
locking/refcounts, x86/asm: Implement fast refcount overflow protection This implements refcount_t overflow protection on x86 without a noticeable performance impact, though without the fuller checking of REFCOUNT_FULL. This is done by duplicating the existing atomic_t refcount implementation but with normally a single instruction added to detect if the refcount has gone negative (e.g. wrapped past INT_MAX or below zero). When detected, the handler saturates the refcount_t to INT_MIN / 2. With this overflow protection, the erroneous reference release that would follow a wrap back to zero is blocked from happening, avoiding the class of refcount-overflow use-after-free vulnerabilities entirely. Only the overflow case of refcounting can be perfectly protected, since it can be detected and stopped before the reference is freed and left to be abused by an attacker. There isn't a way to block early decrements, and while REFCOUNT_FULL stops increment-from-zero cases (which would be the state _after_ an early decrement and stops potential double-free conditions), this fast implementation does not, since it would require the more expensive cmpxchg loops. Since the overflow case is much more common (e.g. missing a "put" during an error path), this protection provides real-world protection. For example, the two public refcount overflow use-after-free exploits published in 2016 would have been rendered unexploitable: http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/ http://cyseclabs.com/page?n=02012016 This implementation does, however, notice an unchecked decrement to zero (i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it resulted in a zero). Decrements under zero are noticed (since they will have resulted in a negative value), though this only indicates that a use-after-free may have already happened. Such notifications are likely avoidable by an attacker that has already exploited a use-after-free vulnerability, but it's better to have them reported than allow such conditions to remain universally silent. On first overflow detection, the refcount value is reset to INT_MIN / 2 (which serves as a saturation value) and a report and stack trace are produced. When operations detect only negative value results (such as changing an already saturated value), saturation still happens but no notification is performed (since the value was already saturated). On the matter of races, since the entire range beyond INT_MAX but before 0 is negative, every operation at INT_MIN / 2 will trap, leaving no overflow-only race condition. As for performance, this implementation adds a single "js" instruction to the regular execution flow of a copy of the standard atomic_t refcount operations. (The non-"and_test" refcount_dec() function, which is uncommon in regular refcount design patterns, has an additional "jz" instruction to detect reaching exactly zero.) Since this is a forward jump, it is by default the non-predicted path, which will be reinforced by dynamic branch prediction. The result is this protection having virtually no measurable change in performance over standard atomic_t operations. The error path, located in .text.unlikely, saves the refcount location and then uses UD0 to fire a refcount exception handler, which resets the refcount, handles reporting, and returns to regular execution. This keeps the changes to .text size minimal, avoiding return jumps and open-coded calls to the error reporting routine. Example assembly comparison: refcount_inc() before: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) refcount_inc() after: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3 ... .text.unlikely: ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx ffffffff816c36d7: 0f ff (bad) These are the cycle counts comparing a loop of refcount_inc() from 1 to INT_MAX and back down to 0 (via refcount_dec_and_test()), between unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL (refcount_t-full), and this overflow-protected refcount (refcount_t-fast): 2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s: cycles protections atomic_t 82249267387 none refcount_t-fast 82211446892 overflow, untested dec-to-zero refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero This code is a modified version of the x86 PAX_REFCOUNT atomic_t overflow defense from the last public patch of PaX/grsecurity, based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Thanks to PaX Team for various suggestions for improvement for repurposing this code to be a refcount-only protection. Signed-off-by: Kees Cook <keescook@chromium.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Elena Reshetova <elena.reshetova@intel.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Hans Liljestrand <ishkamiel@gmail.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Jann Horn <jannh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Serge E. Hallyn <serge@hallyn.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch <linux-arch@vger.kernel.org> Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-16 00:19:24 +08:00
/*
* Handler for UD0 exception following a failed test against the
* result of a refcount inc/dec/add/sub.
*/
__visible bool ex_handler_refcount(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
locking/refcounts, x86/asm: Implement fast refcount overflow protection This implements refcount_t overflow protection on x86 without a noticeable performance impact, though without the fuller checking of REFCOUNT_FULL. This is done by duplicating the existing atomic_t refcount implementation but with normally a single instruction added to detect if the refcount has gone negative (e.g. wrapped past INT_MAX or below zero). When detected, the handler saturates the refcount_t to INT_MIN / 2. With this overflow protection, the erroneous reference release that would follow a wrap back to zero is blocked from happening, avoiding the class of refcount-overflow use-after-free vulnerabilities entirely. Only the overflow case of refcounting can be perfectly protected, since it can be detected and stopped before the reference is freed and left to be abused by an attacker. There isn't a way to block early decrements, and while REFCOUNT_FULL stops increment-from-zero cases (which would be the state _after_ an early decrement and stops potential double-free conditions), this fast implementation does not, since it would require the more expensive cmpxchg loops. Since the overflow case is much more common (e.g. missing a "put" during an error path), this protection provides real-world protection. For example, the two public refcount overflow use-after-free exploits published in 2016 would have been rendered unexploitable: http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/ http://cyseclabs.com/page?n=02012016 This implementation does, however, notice an unchecked decrement to zero (i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it resulted in a zero). Decrements under zero are noticed (since they will have resulted in a negative value), though this only indicates that a use-after-free may have already happened. Such notifications are likely avoidable by an attacker that has already exploited a use-after-free vulnerability, but it's better to have them reported than allow such conditions to remain universally silent. On first overflow detection, the refcount value is reset to INT_MIN / 2 (which serves as a saturation value) and a report and stack trace are produced. When operations detect only negative value results (such as changing an already saturated value), saturation still happens but no notification is performed (since the value was already saturated). On the matter of races, since the entire range beyond INT_MAX but before 0 is negative, every operation at INT_MIN / 2 will trap, leaving no overflow-only race condition. As for performance, this implementation adds a single "js" instruction to the regular execution flow of a copy of the standard atomic_t refcount operations. (The non-"and_test" refcount_dec() function, which is uncommon in regular refcount design patterns, has an additional "jz" instruction to detect reaching exactly zero.) Since this is a forward jump, it is by default the non-predicted path, which will be reinforced by dynamic branch prediction. The result is this protection having virtually no measurable change in performance over standard atomic_t operations. The error path, located in .text.unlikely, saves the refcount location and then uses UD0 to fire a refcount exception handler, which resets the refcount, handles reporting, and returns to regular execution. This keeps the changes to .text size minimal, avoiding return jumps and open-coded calls to the error reporting routine. Example assembly comparison: refcount_inc() before: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) refcount_inc() after: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3 ... .text.unlikely: ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx ffffffff816c36d7: 0f ff (bad) These are the cycle counts comparing a loop of refcount_inc() from 1 to INT_MAX and back down to 0 (via refcount_dec_and_test()), between unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL (refcount_t-full), and this overflow-protected refcount (refcount_t-fast): 2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s: cycles protections atomic_t 82249267387 none refcount_t-fast 82211446892 overflow, untested dec-to-zero refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero This code is a modified version of the x86 PAX_REFCOUNT atomic_t overflow defense from the last public patch of PaX/grsecurity, based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Thanks to PaX Team for various suggestions for improvement for repurposing this code to be a refcount-only protection. Signed-off-by: Kees Cook <keescook@chromium.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Elena Reshetova <elena.reshetova@intel.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Hans Liljestrand <ishkamiel@gmail.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Jann Horn <jannh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Serge E. Hallyn <serge@hallyn.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch <linux-arch@vger.kernel.org> Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-16 00:19:24 +08:00
{
/* First unconditionally saturate the refcount. */
*(int *)regs->cx = INT_MIN / 2;
/*
* Strictly speaking, this reports the fixup destination, not
* the fault location, and not the actually overflowing
* instruction, which is the instruction before the "js", but
* since that instruction could be a variety of lengths, just
* report the location after the overflow, which should be close
* enough for finding the overflow, as it's at least back in
* the function, having returned from .text.unlikely.
*/
regs->ip = ex_fixup_addr(fixup);
/*
* This function has been called because either a negative refcount
* value was seen by any of the refcount functions, or a zero
* refcount value was seen by refcount_dec().
*
* If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result
* wrapped around) will be set. Additionally, seeing the refcount
* reach 0 will set ZF (Zero Flag: result was zero). In each of
* these cases we want a report, since it's a boundary condition.
locking/refcounts, x86/asm: Use unique .text section for refcount exceptions Using .text.unlikely for refcount exceptions isn't safe because gcc may move entire functions into .text.unlikely (e.g. in6_dev_dev()), which would cause any uses of a protected refcount_t function to stay inline with the function, triggering the protection unconditionally: .section .text.unlikely,"ax",@progbits .type in6_dev_get, @function in6_dev_getx: .LFB4673: .loc 2 4128 0 .cfi_startproc ... lock; incl 480(%rbx) js 111f .pushsection .text.unlikely 111: lea 480(%rbx), %rcx 112: .byte 0x0f, 0xff .popsection 113: This creates a unique .text..refcount section and adds an additional test to the exception handler to WARN in the case of having none of OF, SF, nor ZF set so we can see things like this more easily in the future. The double dot for the section name keeps it out of the TEXT_MAIN macro namespace, to avoid collisions and so it can be put at the end with text.unlikely to keep the cold code together. See commit: cb87481ee89db ("kbuild: linker script do not match C names unless LD_DEAD_CODE_DATA_ELIMINATION is configured") ... which matches C names: [a-zA-Z0-9_] but not ".". Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Elena <elena.reshetova@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-arch <linux-arch@vger.kernel.org> Fixes: 7a46ec0e2f48 ("locking/refcounts, x86/asm: Implement fast refcount overflow protection") Link: http://lkml.kernel.org/r/1504382986-49301-2-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-03 04:09:45 +08:00
* The SF case is not reported since it indicates post-boundary
* manipulations below zero or above INT_MAX. And if none of the
* flags are set, something has gone very wrong, so report it.
locking/refcounts, x86/asm: Implement fast refcount overflow protection This implements refcount_t overflow protection on x86 without a noticeable performance impact, though without the fuller checking of REFCOUNT_FULL. This is done by duplicating the existing atomic_t refcount implementation but with normally a single instruction added to detect if the refcount has gone negative (e.g. wrapped past INT_MAX or below zero). When detected, the handler saturates the refcount_t to INT_MIN / 2. With this overflow protection, the erroneous reference release that would follow a wrap back to zero is blocked from happening, avoiding the class of refcount-overflow use-after-free vulnerabilities entirely. Only the overflow case of refcounting can be perfectly protected, since it can be detected and stopped before the reference is freed and left to be abused by an attacker. There isn't a way to block early decrements, and while REFCOUNT_FULL stops increment-from-zero cases (which would be the state _after_ an early decrement and stops potential double-free conditions), this fast implementation does not, since it would require the more expensive cmpxchg loops. Since the overflow case is much more common (e.g. missing a "put" during an error path), this protection provides real-world protection. For example, the two public refcount overflow use-after-free exploits published in 2016 would have been rendered unexploitable: http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/ http://cyseclabs.com/page?n=02012016 This implementation does, however, notice an unchecked decrement to zero (i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it resulted in a zero). Decrements under zero are noticed (since they will have resulted in a negative value), though this only indicates that a use-after-free may have already happened. Such notifications are likely avoidable by an attacker that has already exploited a use-after-free vulnerability, but it's better to have them reported than allow such conditions to remain universally silent. On first overflow detection, the refcount value is reset to INT_MIN / 2 (which serves as a saturation value) and a report and stack trace are produced. When operations detect only negative value results (such as changing an already saturated value), saturation still happens but no notification is performed (since the value was already saturated). On the matter of races, since the entire range beyond INT_MAX but before 0 is negative, every operation at INT_MIN / 2 will trap, leaving no overflow-only race condition. As for performance, this implementation adds a single "js" instruction to the regular execution flow of a copy of the standard atomic_t refcount operations. (The non-"and_test" refcount_dec() function, which is uncommon in regular refcount design patterns, has an additional "jz" instruction to detect reaching exactly zero.) Since this is a forward jump, it is by default the non-predicted path, which will be reinforced by dynamic branch prediction. The result is this protection having virtually no measurable change in performance over standard atomic_t operations. The error path, located in .text.unlikely, saves the refcount location and then uses UD0 to fire a refcount exception handler, which resets the refcount, handles reporting, and returns to regular execution. This keeps the changes to .text size minimal, avoiding return jumps and open-coded calls to the error reporting routine. Example assembly comparison: refcount_inc() before: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) refcount_inc() after: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3 ... .text.unlikely: ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx ffffffff816c36d7: 0f ff (bad) These are the cycle counts comparing a loop of refcount_inc() from 1 to INT_MAX and back down to 0 (via refcount_dec_and_test()), between unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL (refcount_t-full), and this overflow-protected refcount (refcount_t-fast): 2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s: cycles protections atomic_t 82249267387 none refcount_t-fast 82211446892 overflow, untested dec-to-zero refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero This code is a modified version of the x86 PAX_REFCOUNT atomic_t overflow defense from the last public patch of PaX/grsecurity, based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Thanks to PaX Team for various suggestions for improvement for repurposing this code to be a refcount-only protection. Signed-off-by: Kees Cook <keescook@chromium.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Elena Reshetova <elena.reshetova@intel.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Hans Liljestrand <ishkamiel@gmail.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Jann Horn <jannh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Serge E. Hallyn <serge@hallyn.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch <linux-arch@vger.kernel.org> Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-16 00:19:24 +08:00
*/
if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
bool zero = regs->flags & X86_EFLAGS_ZF;
refcount_error_report(regs, zero ? "hit zero" : "overflow");
locking/refcounts, x86/asm: Use unique .text section for refcount exceptions Using .text.unlikely for refcount exceptions isn't safe because gcc may move entire functions into .text.unlikely (e.g. in6_dev_dev()), which would cause any uses of a protected refcount_t function to stay inline with the function, triggering the protection unconditionally: .section .text.unlikely,"ax",@progbits .type in6_dev_get, @function in6_dev_getx: .LFB4673: .loc 2 4128 0 .cfi_startproc ... lock; incl 480(%rbx) js 111f .pushsection .text.unlikely 111: lea 480(%rbx), %rcx 112: .byte 0x0f, 0xff .popsection 113: This creates a unique .text..refcount section and adds an additional test to the exception handler to WARN in the case of having none of OF, SF, nor ZF set so we can see things like this more easily in the future. The double dot for the section name keeps it out of the TEXT_MAIN macro namespace, to avoid collisions and so it can be put at the end with text.unlikely to keep the cold code together. See commit: cb87481ee89db ("kbuild: linker script do not match C names unless LD_DEAD_CODE_DATA_ELIMINATION is configured") ... which matches C names: [a-zA-Z0-9_] but not ".". Reported-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Kees Cook <keescook@chromium.org> Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org> Cc: Elena <elena.reshetova@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: linux-arch <linux-arch@vger.kernel.org> Fixes: 7a46ec0e2f48 ("locking/refcounts, x86/asm: Implement fast refcount overflow protection") Link: http://lkml.kernel.org/r/1504382986-49301-2-git-send-email-keescook@chromium.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-03 04:09:45 +08:00
} else if ((regs->flags & X86_EFLAGS_SF) == 0) {
/* Report if none of OF, ZF, nor SF are set. */
refcount_error_report(regs, "unexpected saturation");
locking/refcounts, x86/asm: Implement fast refcount overflow protection This implements refcount_t overflow protection on x86 without a noticeable performance impact, though without the fuller checking of REFCOUNT_FULL. This is done by duplicating the existing atomic_t refcount implementation but with normally a single instruction added to detect if the refcount has gone negative (e.g. wrapped past INT_MAX or below zero). When detected, the handler saturates the refcount_t to INT_MIN / 2. With this overflow protection, the erroneous reference release that would follow a wrap back to zero is blocked from happening, avoiding the class of refcount-overflow use-after-free vulnerabilities entirely. Only the overflow case of refcounting can be perfectly protected, since it can be detected and stopped before the reference is freed and left to be abused by an attacker. There isn't a way to block early decrements, and while REFCOUNT_FULL stops increment-from-zero cases (which would be the state _after_ an early decrement and stops potential double-free conditions), this fast implementation does not, since it would require the more expensive cmpxchg loops. Since the overflow case is much more common (e.g. missing a "put" during an error path), this protection provides real-world protection. For example, the two public refcount overflow use-after-free exploits published in 2016 would have been rendered unexploitable: http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/ http://cyseclabs.com/page?n=02012016 This implementation does, however, notice an unchecked decrement to zero (i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it resulted in a zero). Decrements under zero are noticed (since they will have resulted in a negative value), though this only indicates that a use-after-free may have already happened. Such notifications are likely avoidable by an attacker that has already exploited a use-after-free vulnerability, but it's better to have them reported than allow such conditions to remain universally silent. On first overflow detection, the refcount value is reset to INT_MIN / 2 (which serves as a saturation value) and a report and stack trace are produced. When operations detect only negative value results (such as changing an already saturated value), saturation still happens but no notification is performed (since the value was already saturated). On the matter of races, since the entire range beyond INT_MAX but before 0 is negative, every operation at INT_MIN / 2 will trap, leaving no overflow-only race condition. As for performance, this implementation adds a single "js" instruction to the regular execution flow of a copy of the standard atomic_t refcount operations. (The non-"and_test" refcount_dec() function, which is uncommon in regular refcount design patterns, has an additional "jz" instruction to detect reaching exactly zero.) Since this is a forward jump, it is by default the non-predicted path, which will be reinforced by dynamic branch prediction. The result is this protection having virtually no measurable change in performance over standard atomic_t operations. The error path, located in .text.unlikely, saves the refcount location and then uses UD0 to fire a refcount exception handler, which resets the refcount, handles reporting, and returns to regular execution. This keeps the changes to .text size minimal, avoiding return jumps and open-coded calls to the error reporting routine. Example assembly comparison: refcount_inc() before: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) refcount_inc() after: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3 ... .text.unlikely: ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx ffffffff816c36d7: 0f ff (bad) These are the cycle counts comparing a loop of refcount_inc() from 1 to INT_MAX and back down to 0 (via refcount_dec_and_test()), between unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL (refcount_t-full), and this overflow-protected refcount (refcount_t-fast): 2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s: cycles protections atomic_t 82249267387 none refcount_t-fast 82211446892 overflow, untested dec-to-zero refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero This code is a modified version of the x86 PAX_REFCOUNT atomic_t overflow defense from the last public patch of PaX/grsecurity, based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Thanks to PaX Team for various suggestions for improvement for repurposing this code to be a refcount-only protection. Signed-off-by: Kees Cook <keescook@chromium.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Elena Reshetova <elena.reshetova@intel.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Hans Liljestrand <ishkamiel@gmail.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Jann Horn <jannh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Serge E. Hallyn <serge@hallyn.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch <linux-arch@vger.kernel.org> Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-16 00:19:24 +08:00
}
return true;
}
EXPORT_SYMBOL(ex_handler_refcount);
locking/refcounts, x86/asm: Implement fast refcount overflow protection This implements refcount_t overflow protection on x86 without a noticeable performance impact, though without the fuller checking of REFCOUNT_FULL. This is done by duplicating the existing atomic_t refcount implementation but with normally a single instruction added to detect if the refcount has gone negative (e.g. wrapped past INT_MAX or below zero). When detected, the handler saturates the refcount_t to INT_MIN / 2. With this overflow protection, the erroneous reference release that would follow a wrap back to zero is blocked from happening, avoiding the class of refcount-overflow use-after-free vulnerabilities entirely. Only the overflow case of refcounting can be perfectly protected, since it can be detected and stopped before the reference is freed and left to be abused by an attacker. There isn't a way to block early decrements, and while REFCOUNT_FULL stops increment-from-zero cases (which would be the state _after_ an early decrement and stops potential double-free conditions), this fast implementation does not, since it would require the more expensive cmpxchg loops. Since the overflow case is much more common (e.g. missing a "put" during an error path), this protection provides real-world protection. For example, the two public refcount overflow use-after-free exploits published in 2016 would have been rendered unexploitable: http://perception-point.io/2016/01/14/analysis-and-exploitation-of-a-linux-kernel-vulnerability-cve-2016-0728/ http://cyseclabs.com/page?n=02012016 This implementation does, however, notice an unchecked decrement to zero (i.e. caller used refcount_dec() instead of refcount_dec_and_test() and it resulted in a zero). Decrements under zero are noticed (since they will have resulted in a negative value), though this only indicates that a use-after-free may have already happened. Such notifications are likely avoidable by an attacker that has already exploited a use-after-free vulnerability, but it's better to have them reported than allow such conditions to remain universally silent. On first overflow detection, the refcount value is reset to INT_MIN / 2 (which serves as a saturation value) and a report and stack trace are produced. When operations detect only negative value results (such as changing an already saturated value), saturation still happens but no notification is performed (since the value was already saturated). On the matter of races, since the entire range beyond INT_MAX but before 0 is negative, every operation at INT_MIN / 2 will trap, leaving no overflow-only race condition. As for performance, this implementation adds a single "js" instruction to the regular execution flow of a copy of the standard atomic_t refcount operations. (The non-"and_test" refcount_dec() function, which is uncommon in regular refcount design patterns, has an additional "jz" instruction to detect reaching exactly zero.) Since this is a forward jump, it is by default the non-predicted path, which will be reinforced by dynamic branch prediction. The result is this protection having virtually no measurable change in performance over standard atomic_t operations. The error path, located in .text.unlikely, saves the refcount location and then uses UD0 to fire a refcount exception handler, which resets the refcount, handles reporting, and returns to regular execution. This keeps the changes to .text size minimal, avoiding return jumps and open-coded calls to the error reporting routine. Example assembly comparison: refcount_inc() before: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) refcount_inc() after: .text: ffffffff81546149: f0 ff 45 f4 lock incl -0xc(%rbp) ffffffff8154614d: 0f 88 80 d5 17 00 js ffffffff816c36d3 ... .text.unlikely: ffffffff816c36d3: 48 8d 4d f4 lea -0xc(%rbp),%rcx ffffffff816c36d7: 0f ff (bad) These are the cycle counts comparing a loop of refcount_inc() from 1 to INT_MAX and back down to 0 (via refcount_dec_and_test()), between unprotected refcount_t (atomic_t), fully protected REFCOUNT_FULL (refcount_t-full), and this overflow-protected refcount (refcount_t-fast): 2147483646 refcount_inc()s and 2147483647 refcount_dec_and_test()s: cycles protections atomic_t 82249267387 none refcount_t-fast 82211446892 overflow, untested dec-to-zero refcount_t-full 144814735193 overflow, untested dec-to-zero, inc-from-zero This code is a modified version of the x86 PAX_REFCOUNT atomic_t overflow defense from the last public patch of PaX/grsecurity, based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Thanks to PaX Team for various suggestions for improvement for repurposing this code to be a refcount-only protection. Signed-off-by: Kees Cook <keescook@chromium.org> Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Elena Reshetova <elena.reshetova@intel.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Hans Liljestrand <ishkamiel@gmail.com> Cc: James Bottomley <James.Bottomley@hansenpartnership.com> Cc: Jann Horn <jannh@google.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Serge E. Hallyn <serge@hallyn.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: arozansk@redhat.com Cc: axboe@kernel.dk Cc: kernel-hardening@lists.openwall.com Cc: linux-arch <linux-arch@vger.kernel.org> Link: http://lkml.kernel.org/r/20170815161924.GA133115@beast Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-08-16 00:19:24 +08:00
x86/fpu: Reinitialize FPU registers if restoring FPU state fails Userspace can change the FPU state of a task using the ptrace() or rt_sigreturn() system calls. Because reserved bits in the FPU state can cause the XRSTOR instruction to fail, the kernel has to carefully validate that no reserved bits or other invalid values are being set. Unfortunately, there have been bugs in this validation code. For example, we were not checking that the 'xcomp_bv' field in the xstate_header was 0. As-is, such bugs are exploitable to read the FPU registers of other processes on the system. To do so, an attacker can create a task, assign to it an invalid FPU state, then spin in a loop and monitor the values of the FPU registers. Because the task's FPU registers are not being restored, sometimes the FPU registers will have the values from another process. This is likely to continue to be a problem in the future because the validation done by the CPU instructions like XRSTOR is not immediately visible to kernel developers. Nor will invalid FPU states ever be encountered during ordinary use --- they will only be seen during fuzzing or exploits. There can even be reserved bits outside the xstate_header which are easy to forget about. For example, the MXCSR register contains reserved bits, which were not validated by the KVM_SET_XSAVE ioctl until commit a575813bfe4b ("KVM: x86: Fix load damaged SSEx MXCSR register"). Therefore, mitigate this class of vulnerability by restoring the FPU registers from init_fpstate if restoring from the task's state fails. We actually used to do this, but it was (perhaps unwisely) removed by commit 9ccc27a5d297 ("x86/fpu: Remove error return values from copy_kernel_to_*regs() functions"). This new patch is also a bit different. First, it only clears the registers, not also the bad in-memory state; this is simpler and makes it easier to make the mitigation cover all callers of __copy_kernel_to_fpregs(). Second, it does the register clearing in an exception handler so that no extra instructions are added to context switches. In fact, we *remove* instructions, since previously we were always zeroing the register containing 'err' even if CONFIG_X86_DEBUG_FPU was disabled. Signed-off-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael Halcrow <mhalcrow@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wanpeng Li <wanpeng.li@hotmail.com> Cc: Yu-cheng Yu <yu-cheng.yu@intel.com> Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170922174156.16780-4-ebiggers3@gmail.com Link: http://lkml.kernel.org/r/20170923130016.21448-27-mingo@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-23 21:00:09 +08:00
/*
* Handler for when we fail to restore a task's FPU state. We should never get
* here because the FPU state of a task using the FPU (task->thread.fpu.state)
* should always be valid. However, past bugs have allowed userspace to set
* reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
* These caused XRSTOR to fail when switching to the task, leaking the FPU
* registers of the task previously executing on the CPU. Mitigate this class
* of vulnerability by restoring from the initial state (essentially, zeroing
* out all the FPU registers) if we can't restore from the task's FPU state.
*/
__visible bool ex_handler_fprestore(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
x86/fpu: Reinitialize FPU registers if restoring FPU state fails Userspace can change the FPU state of a task using the ptrace() or rt_sigreturn() system calls. Because reserved bits in the FPU state can cause the XRSTOR instruction to fail, the kernel has to carefully validate that no reserved bits or other invalid values are being set. Unfortunately, there have been bugs in this validation code. For example, we were not checking that the 'xcomp_bv' field in the xstate_header was 0. As-is, such bugs are exploitable to read the FPU registers of other processes on the system. To do so, an attacker can create a task, assign to it an invalid FPU state, then spin in a loop and monitor the values of the FPU registers. Because the task's FPU registers are not being restored, sometimes the FPU registers will have the values from another process. This is likely to continue to be a problem in the future because the validation done by the CPU instructions like XRSTOR is not immediately visible to kernel developers. Nor will invalid FPU states ever be encountered during ordinary use --- they will only be seen during fuzzing or exploits. There can even be reserved bits outside the xstate_header which are easy to forget about. For example, the MXCSR register contains reserved bits, which were not validated by the KVM_SET_XSAVE ioctl until commit a575813bfe4b ("KVM: x86: Fix load damaged SSEx MXCSR register"). Therefore, mitigate this class of vulnerability by restoring the FPU registers from init_fpstate if restoring from the task's state fails. We actually used to do this, but it was (perhaps unwisely) removed by commit 9ccc27a5d297 ("x86/fpu: Remove error return values from copy_kernel_to_*regs() functions"). This new patch is also a bit different. First, it only clears the registers, not also the bad in-memory state; this is simpler and makes it easier to make the mitigation cover all callers of __copy_kernel_to_fpregs(). Second, it does the register clearing in an exception handler so that no extra instructions are added to context switches. In fact, we *remove* instructions, since previously we were always zeroing the register containing 'err' even if CONFIG_X86_DEBUG_FPU was disabled. Signed-off-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Rik van Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Eric Biggers <ebiggers3@gmail.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: Kevin Hao <haokexin@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michael Halcrow <mhalcrow@google.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wanpeng Li <wanpeng.li@hotmail.com> Cc: Yu-cheng Yu <yu-cheng.yu@intel.com> Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20170922174156.16780-4-ebiggers3@gmail.com Link: http://lkml.kernel.org/r/20170923130016.21448-27-mingo@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-23 21:00:09 +08:00
{
regs->ip = ex_fixup_addr(fixup);
WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
(void *)instruction_pointer(regs));
__copy_kernel_to_fpregs(&init_fpstate, -1);
return true;
}
EXPORT_SYMBOL_GPL(ex_handler_fprestore);
__visible bool ex_handler_uaccess(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
regs->ip = ex_fixup_addr(fixup);
return true;
}
EXPORT_SYMBOL(ex_handler_uaccess);
__visible bool ex_handler_ext(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
/* Special hack for uaccess_err */
current->thread.uaccess_err = 1;
regs->ip = ex_fixup_addr(fixup);
return true;
}
EXPORT_SYMBOL(ex_handler_ext);
__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
x86/dumpstack: Add show_stack_regs() and use it Add a helper to dump supplied pt_regs and use it in the MSR exception handling code to have precise stack traces pointing to the actual function causing the MSR access exception and not the stack frame of the exception handler itself. The new output looks like this: unchecked MSR access error: RDMSR from 0xdeadbeef at rIP: 0xffffffff8102ddb6 (early_init_intel+0x16/0x3a0) 00000000756e6547 ffffffff81c03f68 ffffffff81dd0940 ffffffff81c03f10 ffffffff81d42e65 0000000001000000 ffffffff81c03f58 ffffffff81d3e5a3 0000800000000000 ffffffff81800080 ffffffffffffffff 0000000000000000 Call Trace: [<ffffffff81d42e65>] early_cpu_init+0xe7/0x136 [<ffffffff81d3e5a3>] setup_arch+0xa5/0x9df [<ffffffff81d38bb9>] start_kernel+0x9f/0x43a [<ffffffff81d38294>] x86_64_start_reservations+0x2f/0x31 [<ffffffff81d383fe>] x86_64_start_kernel+0x168/0x176 Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1467671487-10344-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-05 06:31:27 +08:00
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, regs->ip, (void *)regs->ip))
show_stack_regs(regs);
/* Pretend that the read succeeded and returned 0. */
regs->ip = ex_fixup_addr(fixup);
regs->ax = 0;
regs->dx = 0;
return true;
}
EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
__visible bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
x86/dumpstack: Add show_stack_regs() and use it Add a helper to dump supplied pt_regs and use it in the MSR exception handling code to have precise stack traces pointing to the actual function causing the MSR access exception and not the stack frame of the exception handler itself. The new output looks like this: unchecked MSR access error: RDMSR from 0xdeadbeef at rIP: 0xffffffff8102ddb6 (early_init_intel+0x16/0x3a0) 00000000756e6547 ffffffff81c03f68 ffffffff81dd0940 ffffffff81c03f10 ffffffff81d42e65 0000000001000000 ffffffff81c03f58 ffffffff81d3e5a3 0000800000000000 ffffffff81800080 ffffffffffffffff 0000000000000000 Call Trace: [<ffffffff81d42e65>] early_cpu_init+0xe7/0x136 [<ffffffff81d3e5a3>] setup_arch+0xa5/0x9df [<ffffffff81d38bb9>] start_kernel+0x9f/0x43a [<ffffffff81d38294>] x86_64_start_reservations+0x2f/0x31 [<ffffffff81d383fe>] x86_64_start_kernel+0x168/0x176 Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Andy Lutomirski <luto@kernel.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1467671487-10344-4-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-05 06:31:27 +08:00
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pF)\n",
(unsigned int)regs->cx, (unsigned int)regs->dx,
(unsigned int)regs->ax, regs->ip, (void *)regs->ip))
show_stack_regs(regs);
/* Pretend that the write succeeded. */
regs->ip = ex_fixup_addr(fixup);
return true;
}
EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
__visible bool ex_handler_clear_fs(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr)
{
if (static_cpu_has(X86_BUG_NULL_SEG))
asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS));
asm volatile ("mov %0, %%fs" : : "rm" (0));
return ex_handler_default(fixup, regs, trapnr);
}
EXPORT_SYMBOL(ex_handler_clear_fs);
__visible bool ex_has_fault_handler(unsigned long ip)
{
const struct exception_table_entry *e;
ex_handler_t handler;
e = search_exception_tables(ip);
if (!e)
return false;
handler = ex_fixup_handler(e);
return handler == ex_handler_fault;
}
int fixup_exception(struct pt_regs *regs, int trapnr)
{
const struct exception_table_entry *e;
ex_handler_t handler;
#ifdef CONFIG_PNPBIOS
if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) {
extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp;
extern u32 pnp_bios_is_utter_crap;
pnp_bios_is_utter_crap = 1;
printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n");
__asm__ volatile(
"movl %0, %%esp\n\t"
"jmp *%1\n\t"
: : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip));
panic("do_trap: can't hit this");
}
#endif
e = search_exception_tables(regs->ip);
if (!e)
return 0;
handler = ex_fixup_handler(e);
return handler(e, regs, trapnr);
}
extern unsigned int early_recursion_flag;
/* Restricted version used during very early boot */
void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
{
/* Ignore early NMIs. */
if (trapnr == X86_TRAP_NMI)
return;
if (early_recursion_flag > 2)
goto halt_loop;
x86/traps: Ignore high word of regs->cs in early_fixup_exception() On the 80486 DX, it seems that some exceptions may leave garbage in the high bits of CS. This causes sporadic failures in which early_fixup_exception() refuses to fix up an exception. As far as I can tell, this has been buggy for a long time, but the problem seems to have been exacerbated by commits: 1e02ce4cccdc ("x86: Store a per-cpu shadow copy of CR4") e1bfc11c5a6f ("x86/init: Fix cr4_init_shadow() on CR4-less machines") This appears to have broken for as long as we've had early exception handling. [ Note to stable maintainers: This patch is needed all the way back to 3.4, but it will only apply to 4.6 and up, as it depends on commit: 0e861fbb5bda ("x86/head: Move early exception panic code into early_fixup_exception()") If you want to backport to kernels before 4.6, please don't backport the prerequisites (there was a big chain of them that rewrote a lot of the early exception machinery); instead, ask me and I can send you a one-liner that will apply. ] Reported-by: Matthew Whitehead <tedheadster@gmail.com> Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org Fixes: 4c5023a3fa2e ("x86-32: Handle exception table entries during early boot") Link: http://lkml.kernel.org/r/cb32c69920e58a1a58e7b5cad975038a69c0ce7d.1479609510.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-11-20 10:42:40 +08:00
/*
* Old CPUs leave the high bits of CS on the stack
* undefined. I'm not sure which CPUs do this, but at least
* the 486 DX works this way.
* Xen pv domains are not using the default __KERNEL_CS.
x86/traps: Ignore high word of regs->cs in early_fixup_exception() On the 80486 DX, it seems that some exceptions may leave garbage in the high bits of CS. This causes sporadic failures in which early_fixup_exception() refuses to fix up an exception. As far as I can tell, this has been buggy for a long time, but the problem seems to have been exacerbated by commits: 1e02ce4cccdc ("x86: Store a per-cpu shadow copy of CR4") e1bfc11c5a6f ("x86/init: Fix cr4_init_shadow() on CR4-less machines") This appears to have broken for as long as we've had early exception handling. [ Note to stable maintainers: This patch is needed all the way back to 3.4, but it will only apply to 4.6 and up, as it depends on commit: 0e861fbb5bda ("x86/head: Move early exception panic code into early_fixup_exception()") If you want to backport to kernels before 4.6, please don't backport the prerequisites (there was a big chain of them that rewrote a lot of the early exception machinery); instead, ask me and I can send you a one-liner that will apply. ] Reported-by: Matthew Whitehead <tedheadster@gmail.com> Signed-off-by: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org Fixes: 4c5023a3fa2e ("x86-32: Handle exception table entries during early boot") Link: http://lkml.kernel.org/r/cb32c69920e58a1a58e7b5cad975038a69c0ce7d.1479609510.git.luto@kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-11-20 10:42:40 +08:00
*/
if (!xen_pv_domain() && regs->cs != __KERNEL_CS)
goto fail;
/*
* The full exception fixup machinery is available as soon as
* the early IDT is loaded. This means that it is the
* responsibility of extable users to either function correctly
* when handlers are invoked early or to simply avoid causing
* exceptions before they're ready to handle them.
*
* This is better than filtering which handlers can be used,
* because refusing to call a handler here is guaranteed to
* result in a hard-to-debug panic.
*
* Keep in mind that not all vectors actually get here. Early
* fage faults, for example, are special.
*/
if (fixup_exception(regs, trapnr))
return;
if (fixup_bug(regs, trapnr))
return;
fail:
early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n",
(unsigned)trapnr, (unsigned long)regs->cs, regs->ip,
regs->orig_ax, read_cr2());
show_regs(regs);
halt_loop:
while (true)
halt();
}