From 1a79797b58cddfa948420a7553241c79c013e3ca Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:12 +0100 Subject: x86/entry/64: Allocate and enable the SYSENTER stack This will simplify future changes that want scratch variables early in the SYSENTER handler -- they'll be able to spill registers to the stack. It also lets us get rid of a SWAPGS_UNSAFE_STACK user. This does not depend on CONFIG_IA32_EMULATION=y because we'll want the stack space even without IA32 emulation. As far as I can tell, the reason that this wasn't done from day 1 is that we use IST for #DB and #BP, which is IMO rather nasty and causes a lot more problems than it solves. But, since #DB uses IST, we don't actually need a real stack for SYSENTER (because SYSENTER with TF set will invoke #DB on the IST stack rather than the SYSENTER stack). I want to remove IST usage from these vectors some day, and this patch is a prerequisite for that as well. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150605.312726423@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86/kernel/traps.c') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d366adfc61da..d3e3bbd5d3a0 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -794,14 +794,13 @@ 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); -- cgit v1.2.3 From 6d9256f0a89eaff97fca6006100bcaea8d1d8bdb Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:22 +0100 Subject: x86/espfix/64: Stop assuming that pt_regs is on the entry stack When we start using an entry trampoline, a #GP from userspace will be delivered on the entry stack, not on the task stack. Fix the espfix64 #DF fixup to set up #GP according to TSS.SP0, rather than assuming that pt_regs + 1 == SP0. This won't change anything without an entry stack, but it will make the code continue to work when an entry stack is added. While we're at it, improve the comments to explain what's actually going on. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.130778051@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) (limited to 'arch/x86/kernel/traps.c') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d3e3bbd5d3a0..f0029d17b14b 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.x86_tss.sp0) - 1; + + /* + * 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 */ - /* 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 */ + /* + * 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 -- cgit v1.2.3 From 7f2590a110b837af5679d08fc25c6227c5a8c497 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:23 +0100 Subject: x86/entry/64: Use a per-CPU trampoline stack for IDT entries Historically, IDT entries from usermode have always gone directly to the running task's kernel stack. Rearrange it so that we enter on a per-CPU trampoline stack and then manually switch to the task's stack. This touches a couple of extra cachelines, but it gives us a chance to run some code before we touch the kernel stack. The asm isn't exactly beautiful, but I think that fully refactoring it can wait. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Reviewed-by: Thomas Gleixner Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.225330557@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel/traps.c') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f0029d17b14b..ee9ca0ad4388 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -619,14 +619,15 @@ 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); @@ -642,13 +643,13 @@ 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.x86_tss.sp0) - 1; /* Copy the IRET target to the new stack. */ memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8); -- cgit v1.2.3 From 40e7f949e0d9a33968ebde5d67f7e3a47c97742a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:26 +0100 Subject: x86/entry/64: Move the IST stacks into struct cpu_entry_area The IST stacks are needed when an IST exception occurs and are accessed before any kernel code at all runs. Move them into struct cpu_entry_area. The IST stacks are unlike the rest of cpu_entry_area: they're used even for entries from kernel mode. This means that they should be set up before we load the final IDT. Move cpu_entry_area setup to trap_init() for the boot CPU and set it up for all possible CPUs at once in native_smp_prepare_cpus(). Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.480598743@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/x86/kernel/traps.c') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ee9ca0ad4388..3e29aad5c7cc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -947,6 +947,9 @@ 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(); /* -- cgit v1.2.3 From 7fbbd5cbebf118a9e09f5453f686656a167c3d1c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:27 +0100 Subject: x86/entry/64: Remove the SYSENTER stack canary Now that the SYSENTER stack has a guard page, there's no need for a canary to detect overflow after the fact. Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.572577316@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'arch/x86/kernel/traps.c') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 3e29aad5c7cc..5ade4f89a6d1 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -814,13 +814,6 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - /* - * 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"); - ist_exit(regs); } NOKPROBE_SYMBOL(do_debug); -- cgit v1.2.3 From c482feefe1aeb150156248ba0fd3e029bc886605 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:29 +0100 Subject: x86/entry/64: Make cpu_entry_area.tss read-only The TSS is a fairly juicy target for exploits, and, now that the TSS is in the cpu_entry_area, it's no longer protected by kASLR. Make it read-only on x86_64. On x86_32, it can't be RO because it's written by the CPU during task switches, and we use a task gate for double faults. I'd also be nervous about errata if we tried to make it RO even on configurations without double fault handling. [ tglx: AMD confirmed that there is no problem on 64-bit with TSS RO. So it's probably safe to assume that it's a non issue, though Intel might have been creative in that area. Still waiting for confirmation. ] Signed-off-by: Andy Lutomirski Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko Cc: Eduardo Valentin Cc: Greg KH Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Kees Cook Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rik van Riel Cc: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Link: https://lkml.kernel.org/r/20171204150606.733700132@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/traps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/traps.c') diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 5ade4f89a6d1..74136fd16f49 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -364,7 +364,7 @@ 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 *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss.x86_tss.sp0) - 1; + struct pt_regs *gpregs = (struct pt_regs *)this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* * regs->sp points to the failing IRET frame on the @@ -649,7 +649,7 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) * exception came from the IRET target. */ struct bad_iret_stack *new_stack = - (struct bad_iret_stack *)this_cpu_read(cpu_tss.x86_tss.sp0) - 1; + (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); -- cgit v1.2.3