linux-stable/arch/x86/mm/extable.c

232 lines
6.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#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 13:00:09 +00:00
#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>
2016-07-04 22:31:27 +00:00
#include <asm/kdebug.h>
typedef bool (*ex_handler_t)(const struct exception_table_entry *,
struct pt_regs *, int, unsigned long,
unsigned long);
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,
unsigned long error_code,
unsigned long fault_addr)
{
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,
unsigned long error_code,
unsigned long fault_addr)
{
regs->ip = ex_fixup_addr(fixup);
regs->ax = trapnr;
return true;
}
EXPORT_SYMBOL_GPL(ex_handler_fault);
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 13:00:09 +00:00
/*
* 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,
unsigned long error_code,
unsigned long fault_addr)
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 13:00:09 +00:00
{
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,
unsigned long error_code,
unsigned long fault_addr)
{
x86-64: add warning for non-canonical user access address dereferences This adds a warning (once) for any kernel dereference that has a user exception handler, but accesses a non-canonical address. It basically is a simpler - and more limited - version of commit 9da3f2b74054 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses") that got reverted. Note that unlike that original commit, this only causes a warning, because there are real situations where we currently can do this (notably speculative argument fetching for uprobes etc). Also, unlike that original commit, this _only_ triggers for #GP accesses, so the cases of valid kernel pointers that cross into a non-mapped page aren't affected. The intent of this is two-fold: - the uprobe/tracing accesses really do need to be more careful. In particular, from a portability standpoint it's just wrong to think that "a pointer is a pointer", and use the same logic for any random pointer value you find on the stack. It may _work_ on x86-64, but it doesn't necessarily work on other architectures (where the same pointer value can be either a kernel pointer _or_ a user pointer, and you really need to be much more careful in how you try to access it) The warning can hopefully end up being a reminder that just any random pointer access won't do. - Kees in particular wanted a way to actually report invalid uses of wild pointers to user space accessors, instead of just silently failing them. Automated fuzzers want a way to get reports if the kernel ever uses invalid values that the fuzzer fed it. The non-canonical address range is a fair chunk of the address space, and with this you can teach syzkaller to feed in invalid pointer values and find cases where we do not properly validate user addresses (possibly due to bad uses of "set_fs()"). Acked-by: Kees Cook <keescook@chromium.org> Cc: Jann Horn <jannh@google.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-02-26 17:16:04 +00:00
WARN_ONCE(trapnr == X86_TRAP_GP, "General protection fault in user access. Non-canonical address?");
regs->ip = ex_fixup_addr(fixup);
return true;
}
EXPORT_SYMBOL(ex_handler_uaccess);
__visible bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
struct pt_regs *regs, int trapnr,
unsigned long error_code,
unsigned long fault_addr)
{
2019-03-25 19:32:28 +00:00
if (pr_warn_once("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n",
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>
2016-07-04 22:31:27 +00:00
(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,
unsigned long error_code,
unsigned long fault_addr)
{
2019-03-25 19:32:28 +00:00
if (pr_warn_once("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n",
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>
2016-07-04 22:31:27 +00:00
(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,
unsigned long error_code,
unsigned long fault_addr)
{
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, error_code, fault_addr);
}
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, unsigned long error_code,
unsigned long fault_addr)
{
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, error_code, fault_addr);
}
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 02:42:40 +00:00
/*
* 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 02:42:40 +00:00
*/
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
* page faults, for example, are special.
*/
if (fixup_exception(regs, trapnr, regs->orig_ax, 0))
return;
if (trapnr == X86_TRAP_UD) {
if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) {
/* Skip the ud2. */
regs->ip += LEN_UD2;
return;
}
/*
* If this was a BUG and report_bug returns or if this
* was just a normal #UD, we want to continue onward and
* crash.
*/
}
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();
}