diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-12-18 08:59:15 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-12-18 08:59:15 -0800 |
commit | 64a48099b3b31568ac45716b7fafcb74a0c2fcfe (patch) | |
tree | 0652431aeb450bbfa74b9be8b7d813ac8511aec3 /arch/x86/kernel/traps.c | |
parent | 1291a0d5049dbc06baaaf66a9ff3f53db493b19b (diff) | |
parent | 6cbd2171e89b13377261d15e64384df60ecb530e (diff) | |
download | op-kernel-dev-64a48099b3b31568ac45716b7fafcb74a0c2fcfe.zip op-kernel-dev-64a48099b3b31568ac45716b7fafcb74a0c2fcfe.tar.gz |
Merge branch 'WIP.x86-pti.entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 syscall entry code changes for PTI from Ingo Molnar:
"The main changes here are Andy Lutomirski's changes to switch the
x86-64 entry code to use the 'per CPU entry trampoline stack'. This,
besides helping fix KASLR leaks (the pending Page Table Isolation
(PTI) work), also robustifies the x86 entry code"
* 'WIP.x86-pti.entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
x86/cpufeatures: Make CPU bugs sticky
x86/paravirt: Provide a way to check for hypervisors
x86/paravirt: Dont patch flush_tlb_single
x86/entry/64: Make cpu_entry_area.tss read-only
x86/entry: Clean up the SYSENTER_stack code
x86/entry/64: Remove the SYSENTER stack canary
x86/entry/64: Move the IST stacks into struct cpu_entry_area
x86/entry/64: Create a per-CPU SYSCALL entry trampoline
x86/entry/64: Return to userspace from the trampoline stack
x86/entry/64: Use a per-CPU trampoline stack for IDT entries
x86/espfix/64: Stop assuming that pt_regs is on the entry stack
x86/entry/64: Separate cpu_current_top_of_stack from TSS.sp0
x86/entry: Remap the TSS into the CPU entry area
x86/entry: Move SYSENTER_stack to the beginning of struct tss_struct
x86/dumpstack: Handle stack overflow on all stacks
x86/entry: Fix assumptions that the HW TSS is at the beginning of cpu_tss
x86/kasan/64: Teach KASAN about the cpu_entry_area
x86/mm/fixmap: Generalize the GDT fixmap mechanism, introduce struct cpu_entry_area
x86/entry/gdt: Put per-CPU GDT remaps in ascending order
x86/dumpstack: Add get_stack_info() support for the SYSENTER stack
...
Diffstat (limited to 'arch/x86/kernel/traps.c')
-rw-r--r-- | arch/x86/kernel/traps.c | 69 |
1 files changed, 42 insertions, 27 deletions
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 989514c..e98f8b6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -348,9 +348,15 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) /* * If IRET takes a non-IST fault on the espfix64 stack, then we - * end up promoting it to a doublefault. In that case, modify - * the stack to make it look like we just entered the #GP - * handler from user space, similar to bad_iret. + * end up promoting it to a doublefault. In that case, take + * advantage of the fact that we're not using the normal (TSS.sp0) + * stack right now. We can write a fake #GP(0) frame at TSS.sp0 + * and then modify our own IRET frame so that, when we return, + * we land directly at the #GP(0) vector with the stack already + * set up according to its expectations. + * + * The net result is that our #GP handler will think that we + * entered from usermode with the bad user context. * * No need for ist_enter here because we don't use RCU. */ @@ -358,13 +364,26 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) regs->cs == __KERNEL_CS && regs->ip == (unsigned long)native_irq_return_iret) { - struct pt_regs *normal_regs = task_pt_regs(current); + struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; - /* Fake a #GP(0) from userspace. */ - memmove(&normal_regs->ip, (void *)regs->sp, 5*8); - normal_regs->orig_ax = 0; /* Missing (lost) #GP error code */ + /* + * regs->sp points to the failing IRET frame on the + * ESPFIX64 stack. Copy it to the entry stack. This fills + * in gpregs->ss through gpregs->ip. + * + */ + memmove(&gpregs->ip, (void *)regs->sp, 5*8); + gpregs->orig_ax = 0; /* Missing (lost) #GP error code */ + + /* + * Adjust our frame so that we return straight to the #GP + * vector with the expected RSP value. This is safe because + * we won't enable interupts or schedule before we invoke + * general_protection, so nothing will clobber the stack + * frame we just set up. + */ regs->ip = (unsigned long)general_protection; - regs->sp = (unsigned long)&normal_regs->orig_ax; + regs->sp = (unsigned long)&gpregs->orig_ax; return; } @@ -389,7 +408,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) * * Processors update CR2 whenever a page fault is detected. If a * second page fault occurs while an earlier page fault is being - * deliv- ered, the faulting linear address of the second fault will + * delivered, the faulting linear address of the second fault will * overwrite the contents of CR2 (replacing the previous * address). These updates to CR2 occur even if the page fault * results in a double fault or occurs during the delivery of a @@ -605,14 +624,15 @@ NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* - * Help handler running on IST stack to switch off the IST stack if the - * interrupted code was in user mode. The actual stack switch is done in - * entry_64.S + * Help handler running on a per-cpu (IST or entry trampoline) stack + * to switch to the normal thread stack if the interrupted code was in + * user mode. The actual stack switch is done in entry_64.S */ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = task_pt_regs(current); - *regs = *eregs; + struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; + if (regs != eregs) + *regs = *eregs; return regs; } NOKPROBE_SYMBOL(sync_regs); @@ -628,13 +648,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) /* * This is called from entry_64.S early in handling a fault * caused by a bad iret to user mode. To handle the fault - * correctly, we want move our stack frame to task_pt_regs - * and we want to pretend that the exception came from the - * iret target. + * correctly, we want to move our stack frame to where it would + * be had we entered directly on the entry stack (rather than + * just below the IRET frame) and we want to pretend that the + * exception came from the IRET target. */ struct bad_iret_stack *new_stack = - container_of(task_pt_regs(current), - struct bad_iret_stack, regs); + (struct bad_iret_stack *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the new stack. */ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); @@ -795,14 +815,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: -#if defined(CONFIG_X86_32) - /* - * This is the most likely code path that involves non-trivial use - * of the SYSENTER stack. Check that we haven't overrun it. - */ - WARN(this_cpu_read(cpu_tss.SYSENTER_stack_canary) != STACK_END_MAGIC, - "Overran or corrupted SYSENTER stack\n"); -#endif ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); @@ -929,6 +941,9 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) void __init trap_init(void) { + /* Init cpu_entry_area before IST entries are set up */ + setup_cpu_entry_areas(); + idt_setup_traps(); /* |