From e17f8234538d1ff708673f287a42457c4dee720d Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Mon, 4 Dec 2017 15:07:07 +0100 Subject: x86/entry/64/paravirt: Use paravirt-safe macro to access eflags Commit 1d3e53e8624a ("x86/entry/64: Refactor IRQ stacks and make them NMI-safe") added DEBUG_ENTRY_ASSERT_IRQS_OFF macro that acceses eflags using 'pushfq' instruction when testing for IF bit. On PV Xen guests looking at IF flag directly will always see it set, resulting in 'ud2'. Introduce SAVE_FLAGS() macro that will use appropriate save_fl pv op when running paravirt. Signed-off-by: Boris Ostrovsky Signed-off-by: Thomas Gleixner Reviewed-by: Juergen Gross Cc: Andy Lutomirski 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: 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 Cc: xen-devel@lists.xenproject.org Link: https://lkml.kernel.org/r/20171204150604.899457242@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a2b30ec69497..32306788821c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -462,12 +462,13 @@ END(irq_entries_start) .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY - pushfq - testl $X86_EFLAGS_IF, (%rsp) + pushq %rax + SAVE_FLAGS(CLBR_RAX) + testl $X86_EFLAGS_IF, %eax jz .Lokay_\@ ud2 .Lokay_\@: - addq $8, %rsp + popq %rax #endif .endm -- 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/entry/entry_64.S | 67 ++++++++++++++++++++++++++++++---------- arch/x86/entry/entry_64_compat.S | 5 ++- arch/x86/include/asm/switch_to.h | 4 ++- arch/x86/include/asm/traps.h | 1 - arch/x86/kernel/cpu/common.c | 6 ++-- arch/x86/kernel/traps.c | 21 +++++++------ 6 files changed, 72 insertions(+), 32 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 32306788821c..35b8e949ac2f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -560,6 +560,13 @@ END(irq_entries_start) /* 0(%rsp): ~(interrupt number) */ .macro interrupt func cld + + testb $3, CS-ORIG_RAX(%rsp) + jz 1f + SWAPGS + call switch_to_thread_stack +1: + ALLOC_PT_GPREGS_ON_STACK SAVE_C_REGS SAVE_EXTRA_REGS @@ -569,12 +576,8 @@ END(irq_entries_start) jz 1f /* - * IRQ from user mode. Switch to kernel gsbase and inform context - * tracking that we're in kernel mode. - */ - SWAPGS - - /* + * IRQ from user mode. + * * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode * (which can take locks). Since TRACE_IRQS_OFF idempotent, @@ -828,6 +831,32 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt */ #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) +/* + * Switch to the thread stack. This is called with the IRET frame and + * orig_ax on the stack. (That is, RDI..R12 are not on the stack and + * space has not been allocated for them.) + */ +ENTRY(switch_to_thread_stack) + UNWIND_HINT_FUNC + + pushq %rdi + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI + + pushq 7*8(%rdi) /* regs->ss */ + pushq 6*8(%rdi) /* regs->rsp */ + pushq 5*8(%rdi) /* regs->eflags */ + pushq 4*8(%rdi) /* regs->cs */ + pushq 3*8(%rdi) /* regs->ip */ + pushq 2*8(%rdi) /* regs->orig_ax */ + pushq 8(%rdi) /* return address */ + UNWIND_HINT_FUNC + + movq (%rdi), %rdi + ret +END(switch_to_thread_stack) + .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) UNWIND_HINT_IRET_REGS offset=\has_error_code*8 @@ -845,11 +874,12 @@ ENTRY(\sym) ALLOC_PT_GPREGS_ON_STACK - .if \paranoid - .if \paranoid == 1 + .if \paranoid < 2 testb $3, CS(%rsp) /* If coming from userspace, switch stacks */ - jnz 1f + jnz .Lfrom_usermode_switch_stack_\@ .endif + + .if \paranoid call paranoid_entry .else call error_entry @@ -891,20 +921,15 @@ ENTRY(\sym) jmp error_exit .endif - .if \paranoid == 1 + .if \paranoid < 2 /* - * Paranoid entry from userspace. Switch stacks and treat it + * Entry from userspace. Switch stacks and treat it * as a normal entry. This means that paranoid handlers * run in real process context if user_mode(regs). */ -1: +.Lfrom_usermode_switch_stack_\@: call error_entry - - movq %rsp, %rdi /* pt_regs pointer */ - call sync_regs - movq %rax, %rsp /* switch stack */ - movq %rsp, %rdi /* pt_regs pointer */ .if \has_error_code @@ -1165,6 +1190,14 @@ ENTRY(error_entry) SWAPGS .Lerror_entry_from_usermode_after_swapgs: + /* Put us onto the real thread stack. */ + popq %r12 /* save return addr in %12 */ + movq %rsp, %rdi /* arg0 = pt_regs pointer */ + call sync_regs + movq %rax, %rsp /* switch stack */ + ENCODE_FRAME_POINTER + pushq %r12 + /* * We need to tell lockdep that IRQs are off. We can't do this until * we fix gsbase, and we should do it before enter_from_user_mode diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index dcc6987f9bae..95ad40eb7eff 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -306,8 +306,11 @@ ENTRY(entry_INT80_compat) */ movl %eax, %eax - /* Construct struct pt_regs on stack (iret frame is already on stack) */ pushq %rax /* pt_regs->orig_ax */ + + /* switch to thread stack expects orig_ax to be pushed */ + call switch_to_thread_stack + pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ pushq %rdx /* pt_regs->dx */ diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8c6bd6863db9..cbc71e73bd32 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -90,10 +90,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread) /* This is used when switching tasks or entering/exiting vm86 mode. */ static inline void update_sp0(struct task_struct *task) { + /* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 load_sp0(task->thread.sp0); #else - load_sp0(task_top_of_stack(task)); + if (static_cpu_has(X86_FEATURE_XENPV)) + load_sp0(task_top_of_stack(task)); #endif } diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 1fadd310ff68..31051f35cbb7 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long); dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e5837bd6c672..57968880e39b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1623,11 +1623,13 @@ void cpu_init(void) setup_cpu_entry_area(cpu); /* - * Initialize the TSS. Don't bother initializing sp0, as the initial - * task never enters user mode. + * Initialize the TSS. sp0 points to the entry trampoline stack + * regardless of what task is running. */ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); + load_sp0((unsigned long)&get_cpu_entry_area(cpu)->tss + + offsetofend(struct tss_struct, SYSENTER_stack)); load_mm_ldt(&init_mm); 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 3e3b9293d392c577b62e24e4bc9982320438e749 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:24 +0100 Subject: x86/entry/64: Return to userspace from the trampoline stack By itself, this is useless. It gives us the ability to run some final code before exit that cannnot run on the kernel stack. This could include a CR3 switch a la PAGE_TABLE_ISOLATION or some kernel stack erasing, for example. (Or even weird things like *changing* which kernel stack gets used as an ASLR-strengthening mechanism.) The SYSRET32 path is not covered yet. It could be in the future or we could just ignore it and force the slow path if needed. 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/20171204150606.306546484@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 55 +++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 51 insertions(+), 4 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 35b8e949ac2f..42a9379f7acb 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -326,8 +326,24 @@ syscall_return_via_sysret: popq %rsi /* skip rcx */ popq %rdx popq %rsi + + /* + * Now all regs are restored except RSP and RDI. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp + + pushq RSP-RDI(%rdi) /* RSP */ + pushq (%rdi) /* RDI */ + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + popq %rdi - movq RSP-ORIG_RAX(%rsp), %rsp + popq %rsp USERGS_SYSRET64 END(entry_SYSCALL_64) @@ -630,10 +646,41 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) ud2 1: #endif - SWAPGS POP_EXTRA_REGS - POP_C_REGS - addq $8, %rsp /* skip regs->orig_ax */ + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + + /* + * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS. + * Save old stack pointer and switch to trampoline stack. + */ + movq %rsp, %rdi + movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp + + /* Copy the IRET frame to the trampoline stack. */ + pushq 6*8(%rdi) /* SS */ + pushq 5*8(%rdi) /* RSP */ + pushq 4*8(%rdi) /* EFLAGS */ + pushq 3*8(%rdi) /* CS */ + pushq 2*8(%rdi) /* RIP */ + + /* Push user RDI on the trampoline stack. */ + pushq (%rdi) + + /* + * We are on the trampoline stack. All regs except RDI are live. + * We can do future final exit work right here. + */ + + /* Restore RDI. */ + popq %rdi + SWAPGS INTERRUPT_RETURN -- cgit v1.2.3 From 3386bc8aed825e9f1f65ce38df4b109b2019b71a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:25 +0100 Subject: x86/entry/64: Create a per-CPU SYSCALL entry trampoline Handling SYSCALL is tricky: the SYSCALL handler is entered with every single register (except FLAGS), including RSP, live. It somehow needs to set RSP to point to a valid stack, which means it needs to save the user RSP somewhere and find its own stack pointer. The canonical way to do this is with SWAPGS, which lets us access percpu data using the %gs prefix. With PAGE_TABLE_ISOLATION-like pagetable switching, this is problematic. Without a scratch register, switching CR3 is impossible, so %gs-based percpu memory would need to be mapped in the user pagetables. Doing that without information leaks is difficult or impossible. Instead, use a different sneaky trick. Map a copy of the first part of the SYSCALL asm at a different address for each CPU. Now RIP varies depending on the CPU, so we can use RIP-relative memory access to access percpu memory. By putting the relevant information (one scratch slot and the stack address) at a constant offset relative to RIP, we can make SYSCALL work without relying on %gs. A nice thing about this approach is that we can easily switch it on and off if we want pagetable switching to be configurable. The compat variant of SYSCALL doesn't have this problem in the first place -- there are plenty of scratch registers, since we don't care about preserving r8-r15. This patch therefore doesn't touch SYSCALL32 at all. This patch actually seems to be a small speedup. With this patch, SYSCALL touches an extra cache line and an extra virtual page, but the pipeline no longer stalls waiting for SWAPGS. It seems that, at least in a tight loop, the latter outweights the former. Thanks to David Laight for an optimization tip. 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: 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/20171204150606.403607157@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64.S | 58 +++++++++++++++++++++++++++++++++++++++++++ arch/x86/include/asm/fixmap.h | 2 ++ arch/x86/kernel/asm-offsets.c | 1 + arch/x86/kernel/cpu/common.c | 15 ++++++++++- arch/x86/kernel/vmlinux.lds.S | 9 +++++++ 5 files changed, 84 insertions(+), 1 deletion(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 42a9379f7acb..2582984ffb4b 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -136,6 +136,64 @@ END(native_usergs_sysret64) * with them due to bugs in both AMD and Intel CPUs. */ + .pushsection .entry_trampoline, "ax" + +/* + * The code in here gets remapped into cpu_entry_area's trampoline. This means + * that the assembler and linker have the wrong idea as to where this code + * lives (and, in fact, it's mapped more than once, so it's not even at a + * fixed address). So we can't reference any symbols outside the entry + * trampoline and expect it to work. + * + * Instead, we carefully abuse %rip-relative addressing. + * _entry_trampoline(%rip) refers to the start of the remapped) entry + * trampoline. We can thus find cpu_entry_area with this macro: + */ + +#define CPU_ENTRY_AREA \ + _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) + +/* The top word of the SYSENTER stack is hot and is usable as scratch space. */ +#define RSP_SCRATCH CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + \ + SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA + +ENTRY(entry_SYSCALL_64_trampoline) + UNWIND_HINT_EMPTY + swapgs + + /* Stash the user RSP. */ + movq %rsp, RSP_SCRATCH + + /* Load the top of the task stack into RSP */ + movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp + + /* Start building the simulated IRET frame. */ + pushq $__USER_DS /* pt_regs->ss */ + pushq RSP_SCRATCH /* pt_regs->sp */ + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + + /* + * x86 lacks a near absolute jump, and we can't jump to the real + * entry text with a relative jump. We could push the target + * address and then use retq, but this destroys the pipeline on + * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead, + * spill RDI and restore it in a second-stage trampoline. + */ + pushq %rdi + movq $entry_SYSCALL_64_stage2, %rdi + jmp *%rdi +END(entry_SYSCALL_64_trampoline) + + .popsection + +ENTRY(entry_SYSCALL_64_stage2) + UNWIND_HINT_EMPTY + popq %rdi + jmp entry_SYSCALL_64_after_hwframe +END(entry_SYSCALL_64_stage2) + ENTRY(entry_SYSCALL_64) UNWIND_HINT_EMPTY /* diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 84558b611ad3..6a699474c2c7 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -61,6 +61,8 @@ struct cpu_entry_area { * of the TSS region. */ struct tss_struct tss; + + char entry_trampoline[PAGE_SIZE]; }; #define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE) diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 55858b277cf6..61b1af88ac07 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -101,4 +101,5 @@ void common(void) { /* Layout info for cpu_entry_area */ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); + OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 57968880e39b..430f950b0b7f 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -486,6 +486,8 @@ DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); static inline void setup_cpu_entry_area(int cpu) { #ifdef CONFIG_X86_64 + extern char _entry_trampoline[]; + /* On 64-bit systems, we use a read-only fixmap GDT. */ pgprot_t gdt_prot = PAGE_KERNEL_RO; #else @@ -532,6 +534,11 @@ static inline void setup_cpu_entry_area(int cpu) #ifdef CONFIG_X86_32 this_cpu_write(cpu_entry_area, get_cpu_entry_area(cpu)); #endif + +#ifdef CONFIG_X86_64 + __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline), + __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); +#endif } /* Load the original GDT from the per-cpu structure */ @@ -1395,10 +1402,16 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks /* May not be marked __init: used by software suspend */ void syscall_init(void) { + extern char _entry_trampoline[]; + extern char entry_SYSCALL_64_trampoline[]; + int cpu = smp_processor_id(); + unsigned long SYSCALL64_entry_trampoline = + (unsigned long)get_cpu_entry_area(cpu)->entry_trampoline + + (entry_SYSCALL_64_trampoline - _entry_trampoline); wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); - wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); + wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline); #ifdef CONFIG_IA32_EMULATION wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a4009fb9be87..d2a8b5a24a44 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -107,6 +107,15 @@ SECTIONS SOFTIRQENTRY_TEXT *(.fixup) *(.gnu.warning) + +#ifdef CONFIG_X86_64 + . = ALIGN(PAGE_SIZE); + _entry_trampoline = .; + *(.entry_trampoline) + . = ALIGN(PAGE_SIZE); + ASSERT(. - _entry_trampoline == PAGE_SIZE, "entry trampoline is too big"); +#endif + /* End of text section */ _etext = .; } :text = 0x9090 -- cgit v1.2.3 From 0f9a48100fba3f189724ae88a450c2261bf91c80 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:28 +0100 Subject: x86/entry: Clean up the SYSENTER_stack code The existing code was a mess, mainly because C arrays are nasty. Turn SYSENTER_stack into a struct, add a helper to find it, and do all the obvious cleanups this enables. 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: 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/20171204150606.653244723@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 4 ++-- arch/x86/entry/entry_64.S | 2 +- arch/x86/include/asm/fixmap.h | 5 +++++ arch/x86/include/asm/processor.h | 6 +++++- arch/x86/kernel/asm-offsets.c | 6 ++---- arch/x86/kernel/cpu/common.c | 14 +++----------- arch/x86/kernel/dumpstack.c | 7 +++---- 7 files changed, 21 insertions(+), 23 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 0ab316c46806..3629bcbf85a2 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -942,7 +942,7 @@ ENTRY(debug) /* Are we currently on the SYSENTER stack? */ movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx + addl $CPU_ENTRY_AREA_tss + TSS_STRUCT_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Ldebug_from_sysenter_stack @@ -986,7 +986,7 @@ ENTRY(nmi) /* Are we currently on the SYSENTER stack? */ movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx + addl $CPU_ENTRY_AREA_tss + TSS_STRUCT_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Lnmi_from_sysenter_stack diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 2582984ffb4b..575b184f377f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -154,7 +154,7 @@ END(native_usergs_sysret64) _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) /* The top word of the SYSENTER stack is hot and is usable as scratch space. */ -#define RSP_SCRATCH CPU_ENTRY_AREA_tss + CPU_TSS_SYSENTER_stack + \ +#define RSP_SCRATCH CPU_ENTRY_AREA_tss + TSS_STRUCT_SYSENTER_stack + \ SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA ENTRY(entry_SYSCALL_64_trampoline) diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 451da7d9a502..cc5d98bdca37 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -245,5 +245,10 @@ static inline struct cpu_entry_area *get_cpu_entry_area(int cpu) return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0)); } +static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->tss.SYSENTER_stack; +} + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index d34ac13c5866..f933869470b8 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -336,12 +336,16 @@ struct x86_hw_tss { #define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) #define INVALID_IO_BITMAP_OFFSET 0x8000 +struct SYSENTER_stack { + unsigned long words[64]; +}; + struct tss_struct { /* * Space for the temporary SYSENTER stack, used for SYSENTER * and the entry trampoline as well. */ - unsigned long SYSENTER_stack[64]; + struct SYSENTER_stack SYSENTER_stack; /* * The fixed hardware portion. This must not cross a page boundary diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 61b1af88ac07..46c0995344aa 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -94,10 +94,8 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); - /* Offset from cpu_tss to SYSENTER_stack */ - OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); - /* Size of SYSENTER_stack */ - DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); + OFFSET(TSS_STRUCT_SYSENTER_stack, tss_struct, SYSENTER_stack); + DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack)); /* Layout info for cpu_entry_area */ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index fb01a8e5e9b7..3de7480e4f32 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1314,12 +1314,7 @@ void enable_sep_cpu(void) tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - - wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)&get_cpu_entry_area(cpu)->tss + - offsetofend(struct tss_struct, SYSENTER_stack), - 0); - + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1436,9 +1431,7 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, - (unsigned long)&get_cpu_entry_area(cpu)->tss + - offsetofend(struct tss_struct, SYSENTER_stack)); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1653,8 +1646,7 @@ void cpu_init(void) */ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); - load_sp0((unsigned long)&get_cpu_entry_area(cpu)->tss + - offsetofend(struct tss_struct, SYSENTER_stack)); + load_sp0((unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); load_mm_ldt(&init_mm); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index ae1ce2e3f132..bbd6d986e2d0 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -45,11 +45,10 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) { - int cpu = smp_processor_id(); - struct tss_struct *tss = &get_cpu_entry_area(cpu)->tss; + struct SYSENTER_stack *ss = cpu_SYSENTER_stack(smp_processor_id()); - void *begin = &tss->SYSENTER_stack; - void *end = (void *)&tss->SYSENTER_stack + sizeof(tss->SYSENTER_stack); + void *begin = ss; + void *end = ss + 1; if ((void *)stack < begin || (void *)stack >= end) return false; -- 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/entry/entry_32.S | 4 ++-- arch/x86/entry/entry_64.S | 8 ++++---- arch/x86/include/asm/fixmap.h | 13 +++++++++---- arch/x86/include/asm/processor.h | 17 ++++++++--------- arch/x86/include/asm/switch_to.h | 4 ++-- arch/x86/include/asm/thread_info.h | 2 +- arch/x86/kernel/asm-offsets.c | 5 ++--- arch/x86/kernel/asm-offsets_32.c | 4 ++-- arch/x86/kernel/cpu/common.c | 29 +++++++++++++++++++---------- arch/x86/kernel/ioport.c | 2 +- arch/x86/kernel/process.c | 6 +++--- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- arch/x86/kernel/traps.c | 4 ++-- arch/x86/lib/delay.c | 4 ++-- arch/x86/xen/enlighten_pv.c | 2 +- 16 files changed, 60 insertions(+), 48 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 3629bcbf85a2..bd8b57a5c874 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -942,7 +942,7 @@ ENTRY(debug) /* Are we currently on the SYSENTER stack? */ movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_tss + TSS_STRUCT_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx + addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Ldebug_from_sysenter_stack @@ -986,7 +986,7 @@ ENTRY(nmi) /* Are we currently on the SYSENTER stack? */ movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_tss + TSS_STRUCT_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx + addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ cmpl $SIZEOF_SYSENTER_stack, %ecx jb .Lnmi_from_sysenter_stack diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 575b184f377f..2812ce043a7a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -154,7 +154,7 @@ END(native_usergs_sysret64) _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) /* The top word of the SYSENTER stack is hot and is usable as scratch space. */ -#define RSP_SCRATCH CPU_ENTRY_AREA_tss + TSS_STRUCT_SYSENTER_stack + \ +#define RSP_SCRATCH CPU_ENTRY_AREA_SYSENTER_stack + \ SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA ENTRY(entry_SYSCALL_64_trampoline) @@ -390,7 +390,7 @@ syscall_return_via_sysret: * Save old stack pointer and switch to trampoline stack. */ movq %rsp, %rdi - movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -719,7 +719,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) * Save old stack pointer and switch to trampoline stack. */ movq %rsp, %rdi - movq PER_CPU_VAR(cpu_tss + TSS_sp0), %rsp + movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -934,7 +934,7 @@ apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt /* * Exception entry points. */ -#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8) /* * Switch to the thread stack. This is called with the IRET frame and diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index cc5d98bdca37..94fc4fa14127 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -56,9 +56,14 @@ struct cpu_entry_area { char gdt[PAGE_SIZE]; /* - * The GDT is just below cpu_tss and thus serves (on x86_64) as a - * a read-only guard page for the SYSENTER stack at the bottom - * of the TSS region. + * The GDT is just below SYSENTER_stack and thus serves (on x86_64) as + * a a read-only guard page. + */ + struct SYSENTER_stack_page SYSENTER_stack_page; + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. */ struct tss_struct tss; @@ -247,7 +252,7 @@ static inline struct cpu_entry_area *get_cpu_entry_area(int cpu) static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu) { - return &get_cpu_entry_area(cpu)->tss.SYSENTER_stack; + return &get_cpu_entry_area(cpu)->SYSENTER_stack_page.stack; } #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f933869470b8..e8991d7f7034 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -340,13 +340,11 @@ struct SYSENTER_stack { unsigned long words[64]; }; -struct tss_struct { - /* - * Space for the temporary SYSENTER stack, used for SYSENTER - * and the entry trampoline as well. - */ - struct SYSENTER_stack SYSENTER_stack; +struct SYSENTER_stack_page { + struct SYSENTER_stack stack; +} __aligned(PAGE_SIZE); +struct tss_struct { /* * The fixed hardware portion. This must not cross a page boundary * at risk of violating the SDM's advice and potentially triggering @@ -363,7 +361,7 @@ struct tss_struct { unsigned long io_bitmap[IO_BITMAP_LONGS + 1]; } __aligned(PAGE_SIZE); -DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss); +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); /* * sizeof(unsigned long) coming from an extra "long" at the end @@ -378,7 +376,8 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss); #ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); #else -#define cpu_current_top_of_stack cpu_tss.x86_tss.sp1 +/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ +#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 #endif /* @@ -538,7 +537,7 @@ static inline void native_set_iopl_mask(unsigned mask) static inline void native_load_sp0(unsigned long sp0) { - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } static inline void native_swapgs(void) diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index cbc71e73bd32..9b6df68d8fd1 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -79,10 +79,10 @@ do { \ static inline void refresh_sysenter_cs(struct thread_struct *thread) { /* Only happens when SEP is enabled, no need to test "SEP"arately: */ - if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs)) + if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs)) return; - this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs); + this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs); wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0); } #endif diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 44a04999791e..00223333821a 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack, #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss + TSS_sp1) +# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1) #endif #endif diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 46c0995344aa..cd360a5e0dca 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -94,10 +94,9 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); - OFFSET(TSS_STRUCT_SYSENTER_stack, tss_struct, SYSENTER_stack); - DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack)); - /* Layout info for cpu_entry_area */ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); + OFFSET(CPU_ENTRY_AREA_SYSENTER_stack, cpu_entry_area, SYSENTER_stack_page); + DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack)); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 52ce4ea16e53..7d20d9c0b3d6 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -47,8 +47,8 @@ void foo(void) BLANK(); /* Offset from the sysenter stack to tss.sp0 */ - DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - - offsetofend(struct tss_struct, SYSENTER_stack)); + DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - + offsetofend(struct cpu_entry_area, SYSENTER_stack_page.stack)); #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3de7480e4f32..c2eada1056de 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -487,6 +487,9 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); #endif +static DEFINE_PER_CPU_PAGE_ALIGNED(struct SYSENTER_stack_page, + SYSENTER_stack_storage); + static void __init set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) { @@ -500,23 +503,29 @@ static void __init setup_cpu_entry_area(int cpu) #ifdef CONFIG_X86_64 extern char _entry_trampoline[]; - /* On 64-bit systems, we use a read-only fixmap GDT. */ + /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ pgprot_t gdt_prot = PAGE_KERNEL_RO; + pgprot_t tss_prot = PAGE_KERNEL_RO; #else /* * On native 32-bit systems, the GDT cannot be read-only because * our double fault handler uses a task gate, and entering through - * a task gate needs to change an available TSS to busy. If the GDT - * is read-only, that will triple fault. + * a task gate needs to change an available TSS to busy. If the + * GDT is read-only, that will triple fault. The TSS cannot be + * read-only because the CPU writes to it on task switches. * - * On Xen PV, the GDT must be read-only because the hypervisor requires - * it. + * On Xen PV, the GDT must be read-only because the hypervisor + * requires it. */ pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ? PAGE_KERNEL_RO : PAGE_KERNEL; + pgprot_t tss_prot = PAGE_KERNEL; #endif __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, SYSENTER_stack_page), + per_cpu_ptr(&SYSENTER_stack_storage, cpu), 1, + PAGE_KERNEL); /* * The Intel SDM says (Volume 3, 7.2.1): @@ -539,9 +548,9 @@ static void __init setup_cpu_entry_area(int cpu) offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0); set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, tss), - &per_cpu(cpu_tss, cpu), + &per_cpu(cpu_tss_rw, cpu), sizeof(struct tss_struct) / PAGE_SIZE, - PAGE_KERNEL); + tss_prot); #ifdef CONFIG_X86_32 per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu); @@ -1305,7 +1314,7 @@ void enable_sep_cpu(void) return; cpu = get_cpu(); - tss = &per_cpu(cpu_tss, cpu); + tss = &per_cpu(cpu_tss_rw, cpu); /* * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field -- @@ -1575,7 +1584,7 @@ void cpu_init(void) if (cpu) load_ucode_ap(); - t = &per_cpu(cpu_tss, cpu); + t = &per_cpu(cpu_tss_rw, cpu); oist = &per_cpu(orig_ist, cpu); #ifdef CONFIG_NUMA @@ -1667,7 +1676,7 @@ void cpu_init(void) { int cpu = smp_processor_id(); struct task_struct *curr = current; - struct tss_struct *t = &per_cpu(cpu_tss, cpu); + struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu); wait_for_master_cpu(cpu); diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 3feb648781c4..2f723301eb58 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on) * because the ->io_bitmap_max value must match the bitmap * contents: */ - tss = &per_cpu(cpu_tss, get_cpu()); + tss = &per_cpu(cpu_tss_rw, get_cpu()); if (turn_on) bitmap_clear(t->io_bitmap_ptr, from, num); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 6a04287f222b..517415978409 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -47,7 +47,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss_rw) = { .x86_tss = { /* * .sp0 is only used when entering ring 0 from a lower @@ -82,7 +82,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif }; -EXPORT_PER_CPU_SYMBOL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss_rw); DEFINE_PER_CPU(bool, __tss_limit_invalid); EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid); @@ -111,7 +111,7 @@ void exit_thread(struct task_struct *tsk) struct fpu *fpu = &t->fpu; if (bp) { - struct tss_struct *tss = &per_cpu(cpu_tss, get_cpu()); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, get_cpu()); t->io_bitmap_ptr = NULL; clear_thread_flag(TIF_IO_BITMAP); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 45bf0c5f93e1..5224c6099184 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -234,7 +234,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 157f81816915..c75466232016 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -399,7 +399,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss, cpu); + struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(irq_count) != -1); 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); diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 553f8fd23cc4..4846eff7e4c8 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -107,10 +107,10 @@ static void delay_mwaitx(unsigned long __loops) delay = min_t(u64, MWAITX_MAX_LOOPS, loops); /* - * Use cpu_tss as a cacheline-aligned, seldomly + * Use cpu_tss_rw as a cacheline-aligned, seldomly * accessed per-cpu variable as the monitor target. */ - __monitorx(raw_cpu_ptr(&cpu_tss), 0, 0); + __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); /* * AMD, like Intel, supports the EAX hint and EAX=0xf diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index fbd054d6ac97..ae3a071e1d0f 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -818,7 +818,7 @@ static void xen_load_sp0(unsigned long sp0) mcs = xen_mc_entry(0); MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0); xen_mc_issue(PARAVIRT_LAZY_CPU); - this_cpu_write(cpu_tss.x86_tss.sp0, sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } void xen_set_iopl_mask(unsigned mask) -- cgit v1.2.3 From 4fe2d8b11a370af286287a2661de9d4e6c9a145a Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 4 Dec 2017 17:25:07 -0800 Subject: x86/entry: Rename SYSENTER_stack to CPU_ENTRY_AREA_entry_stack If the kernel oopses while on the trampoline stack, it will print "" even if SYSENTER is not involved. That is rather confusing. The "SYSENTER" stack is used for a lot more than SYSENTER now. Give it a better string to display in stack dumps, and rename the kernel code to match. Also move the 32-bit code over to the new naming even though it still uses the entry stack only for SYSENTER. Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 12 ++++++------ arch/x86/entry/entry_64.S | 4 ++-- arch/x86/include/asm/fixmap.h | 8 ++++---- arch/x86/include/asm/processor.h | 6 +++--- arch/x86/include/asm/stacktrace.h | 4 ++-- arch/x86/kernel/asm-offsets.c | 4 ++-- arch/x86/kernel/asm-offsets_32.c | 2 +- arch/x86/kernel/cpu/common.c | 14 +++++++------- arch/x86/kernel/dumpstack.c | 10 +++++----- arch/x86/kernel/dumpstack_32.c | 6 +++--- arch/x86/kernel/dumpstack_64.c | 12 +++++++++--- 11 files changed, 44 insertions(+), 38 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index bd8b57a5c874..ace8f321a5a1 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -942,9 +942,9 @@ ENTRY(debug) /* Are we currently on the SYSENTER stack? */ movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx - subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ - cmpl $SIZEOF_SYSENTER_stack, %ecx + addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx + subl %eax, %ecx /* ecx = (end of entry_stack) - esp */ + cmpl $SIZEOF_entry_stack, %ecx jb .Ldebug_from_sysenter_stack TRACE_IRQS_OFF @@ -986,9 +986,9 @@ ENTRY(nmi) /* Are we currently on the SYSENTER stack? */ movl PER_CPU_VAR(cpu_entry_area), %ecx - addl $CPU_ENTRY_AREA_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx - subl %eax, %ecx /* ecx = (end of SYSENTER_stack) - esp */ - cmpl $SIZEOF_SYSENTER_stack, %ecx + addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx + subl %eax, %ecx /* ecx = (end of entry_stack) - esp */ + cmpl $SIZEOF_entry_stack, %ecx jb .Lnmi_from_sysenter_stack /* Not on SYSENTER stack. */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 2812ce043a7a..87cebe78bbef 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -154,8 +154,8 @@ END(native_usergs_sysret64) _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip) /* The top word of the SYSENTER stack is hot and is usable as scratch space. */ -#define RSP_SCRATCH CPU_ENTRY_AREA_SYSENTER_stack + \ - SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA +#define RSP_SCRATCH CPU_ENTRY_AREA_entry_stack + \ + SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA ENTRY(entry_SYSCALL_64_trampoline) UNWIND_HINT_EMPTY diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 94fc4fa14127..8153b8d86a3c 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -56,10 +56,10 @@ struct cpu_entry_area { char gdt[PAGE_SIZE]; /* - * The GDT is just below SYSENTER_stack and thus serves (on x86_64) as + * The GDT is just below entry_stack and thus serves (on x86_64) as * a a read-only guard page. */ - struct SYSENTER_stack_page SYSENTER_stack_page; + struct entry_stack_page entry_stack_page; /* * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because @@ -250,9 +250,9 @@ static inline struct cpu_entry_area *get_cpu_entry_area(int cpu) return (struct cpu_entry_area *)__fix_to_virt(__get_cpu_entry_area_page_index(cpu, 0)); } -static inline struct SYSENTER_stack *cpu_SYSENTER_stack(int cpu) +static inline struct entry_stack *cpu_entry_stack(int cpu) { - return &get_cpu_entry_area(cpu)->SYSENTER_stack_page.stack; + return &get_cpu_entry_area(cpu)->entry_stack_page.stack; } #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index da943411d3d8..9e482d8b0b97 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -336,12 +336,12 @@ struct x86_hw_tss { #define IO_BITMAP_OFFSET (offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss)) #define INVALID_IO_BITMAP_OFFSET 0x8000 -struct SYSENTER_stack { +struct entry_stack { unsigned long words[64]; }; -struct SYSENTER_stack_page { - struct SYSENTER_stack stack; +struct entry_stack_page { + struct entry_stack stack; } __aligned(PAGE_SIZE); struct tss_struct { diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f8062bfd43a0..f73706878772 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -16,7 +16,7 @@ enum stack_type { STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, - STACK_TYPE_SYSENTER, + STACK_TYPE_ENTRY, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; @@ -29,7 +29,7 @@ struct stack_info { bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); -bool in_sysenter_stack(unsigned long *stack, struct stack_info *info); +bool in_entry_stack(unsigned long *stack, struct stack_info *info); int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index cd360a5e0dca..676b7cf4b62b 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -97,6 +97,6 @@ void common(void) { /* Layout info for cpu_entry_area */ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); - OFFSET(CPU_ENTRY_AREA_SYSENTER_stack, cpu_entry_area, SYSENTER_stack_page); - DEFINE(SIZEOF_SYSENTER_stack, sizeof(struct SYSENTER_stack)); + OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page); + DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack)); } diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 7d20d9c0b3d6..fa1261eefa16 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -48,7 +48,7 @@ void foo(void) /* Offset from the sysenter stack to tss.sp0 */ DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) - - offsetofend(struct cpu_entry_area, SYSENTER_stack_page.stack)); + offsetofend(struct cpu_entry_area, entry_stack_page.stack)); #ifdef CONFIG_CC_STACKPROTECTOR BLANK(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 034900623adf..ed4acbce37a8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -487,8 +487,8 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); #endif -static DEFINE_PER_CPU_PAGE_ALIGNED(struct SYSENTER_stack_page, - SYSENTER_stack_storage); +static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, + entry_stack_storage); static void __init set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) @@ -523,8 +523,8 @@ static void __init setup_cpu_entry_area(int cpu) #endif __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); - set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, SYSENTER_stack_page), - per_cpu_ptr(&SYSENTER_stack_storage, cpu), 1, + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, entry_stack_page), + per_cpu_ptr(&entry_stack_storage, cpu), 1, PAGE_KERNEL); /* @@ -1323,7 +1323,7 @@ void enable_sep_cpu(void) tss->x86_tss.ss1 = __KERNEL_CS; wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); - wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1), 0); + wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); put_cpu(); @@ -1440,7 +1440,7 @@ void syscall_init(void) * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret); @@ -1655,7 +1655,7 @@ void cpu_init(void) */ set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); - load_sp0((unsigned long)(cpu_SYSENTER_stack(cpu) + 1)); + load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1)); load_mm_ldt(&init_mm); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index bbd6d986e2d0..1dd3f533d78c 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -43,9 +43,9 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } -bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) +bool in_entry_stack(unsigned long *stack, struct stack_info *info) { - struct SYSENTER_stack *ss = cpu_SYSENTER_stack(smp_processor_id()); + struct entry_stack *ss = cpu_entry_stack(smp_processor_id()); void *begin = ss; void *end = ss + 1; @@ -53,7 +53,7 @@ bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) if ((void *)stack < begin || (void *)stack >= end) return false; - info->type = STACK_TYPE_SYSENTER; + info->type = STACK_TYPE_ENTRY; info->begin = begin; info->end = end; info->next_sp = NULL; @@ -111,13 +111,13 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, * - task stack * - interrupt stack * - HW exception stacks (double fault, nmi, debug, mce) - * - SYSENTER stack + * - entry stack * * x86-32 can have up to four stacks: * - task stack * - softirq stack * - hardirq stack - * - SYSENTER stack + * - entry stack */ for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 5ff13a6b3680..04170f63e3a1 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -26,8 +26,8 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_SOFTIRQ) return "SOFTIRQ"; - if (type == STACK_TYPE_SYSENTER) - return "SYSENTER"; + if (type == STACK_TYPE_ENTRY) + return "ENTRY_TRAMPOLINE"; return NULL; } @@ -96,7 +96,7 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (task != current) goto unknown; - if (in_sysenter_stack(stack, info)) + if (in_entry_stack(stack, info)) goto recursion_check; if (in_hardirq_stack(stack, info)) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index abc828f8c297..563e28d14f2c 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -37,8 +37,14 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_IRQ) return "IRQ"; - if (type == STACK_TYPE_SYSENTER) - return "SYSENTER"; + if (type == STACK_TYPE_ENTRY) { + /* + * On 64-bit, we have a generic entry stack that we + * use for all the kernel entry points, including + * SYSENTER. + */ + return "ENTRY_TRAMPOLINE"; + } if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST) return exception_stack_names[type - STACK_TYPE_EXCEPTION]; @@ -118,7 +124,7 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (in_irq_stack(stack, info)) goto recursion_check; - if (in_sysenter_stack(stack, info)) + if (in_entry_stack(stack, info)) goto recursion_check; goto unknown; -- cgit v1.2.3 From 8a09317b895f073977346779df52f67c1056d81d Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 4 Dec 2017 15:07:35 +0100 Subject: x86/mm/pti: Prepare the x86/entry assembly code for entry/exit CR3 switching PAGE_TABLE_ISOLATION needs to switch to a different CR3 value when it enters the kernel and switch back when it exits. This essentially needs to be done before leaving assembly code. This is extra challenging because the switching context is tricky: the registers that can be clobbered can vary. It is also hard to store things on the stack because there is an established ABI (ptregs) or the stack is entirely unsafe to use. Establish a set of macros that allow changing to the user and kernel CR3 values. Interactions with SWAPGS: Previous versions of the PAGE_TABLE_ISOLATION code relied on having per-CPU scratch space to save/restore a register that can be used for the CR3 MOV. The %GS register is used to index into our per-CPU space, so SWAPGS *had* to be done before the CR3 switch. That scratch space is gone now, but the semantic that SWAPGS must be done before the CR3 MOV is retained. This is good to keep because it is not that hard to do and it allows to do things like add per-CPU debugging information. What this does in the NMI code is worth pointing out. NMIs can interrupt *any* context and they can also be nested with NMIs interrupting other NMIs. The comments below ".Lnmi_from_kernel" explain the format of the stack during this situation. Changing the format of this stack is hard. Instead of storing the old CR3 value on the stack, this depends on the *regular* register save/restore mechanism and then uses %r14 to keep CR3 during the NMI. It is callee-saved and will not be clobbered by the C NMI handlers that get called. [ PeterZ: ESPFIX optimization ] Based-on-code-from: Andy Lutomirski Signed-off-by: Dave Hansen Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Reviewed-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst 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: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Cc: linux-mm@kvack.org Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 66 ++++++++++++++++++++++++++++++++++++++++ arch/x86/entry/entry_64.S | 45 +++++++++++++++++++++++---- arch/x86/entry/entry_64_compat.S | 24 ++++++++++++++- 3 files changed, 128 insertions(+), 7 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3fd8bc560fae..a9d17a7686ab 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,6 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include #include +#include +#include /* @@ -187,6 +189,70 @@ For 32-bit we have the following conventions - kernel is built with #endif .endm +#ifdef CONFIG_PAGE_TABLE_ISOLATION + +/* PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two halves: */ +#define PTI_SWITCH_MASK (1< in kernel */ SWAPGS xorl %ebx, %ebx -1: ret + +1: + SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14 + + ret END(paranoid_entry) /* @@ -1266,6 +1287,7 @@ ENTRY(paranoid_exit) testl %ebx, %ebx /* swapgs needed? */ jnz .Lparanoid_exit_no_swapgs TRACE_IRQS_IRETQ + RESTORE_CR3 save_reg=%r14 SWAPGS_UNSAFE_STACK jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: @@ -1293,6 +1315,8 @@ ENTRY(error_entry) * from user mode due to an IRET fault. */ SWAPGS + /* We have user CR3. Change to kernel CR3. */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax .Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ @@ -1339,6 +1363,7 @@ ENTRY(error_entry) * .Lgs_change's error handler with kernel gsbase. */ SWAPGS + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax jmp .Lerror_entry_done .Lbstep_iret: @@ -1348,10 +1373,11 @@ ENTRY(error_entry) .Lerror_bad_iret: /* - * We came from an IRET to user mode, so we have user gsbase. - * Switch to kernel gsbase: + * We came from an IRET to user mode, so we have user + * gsbase and CR3. Switch to kernel gsbase and CR3: */ SWAPGS + SWITCH_TO_KERNEL_CR3 scratch_reg=%rax /* * Pretend that the exception came from user mode: set up pt_regs @@ -1383,6 +1409,10 @@ END(error_exit) /* * Runs on exception stack. Xen PV does not go through this path at all, * so we can use real assembly here. + * + * Registers: + * %r14: Used to save/restore the CR3 of the interrupted context + * when PAGE_TABLE_ISOLATION is in use. Do not clobber. */ ENTRY(nmi) UNWIND_HINT_IRET_REGS @@ -1446,6 +1476,7 @@ ENTRY(nmi) swapgs cld + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp UNWIND_HINT_IRET_REGS base=%rdx offset=8 @@ -1698,6 +1729,8 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi + RESTORE_CR3 save_reg=%r14 + testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore nmi_swapgs: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 95ad40eb7eff..05238b29895e 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -49,6 +49,10 @@ ENTRY(entry_SYSENTER_compat) /* Interrupts are off on entry. */ SWAPGS + + /* We are about to clobber %rsp anyway, clobbering here is OK */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp + movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp /* @@ -215,6 +219,12 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe) pushq $0 /* pt_regs->r14 = 0 */ pushq $0 /* pt_regs->r15 = 0 */ + /* + * We just saved %rdi so it is safe to clobber. It is not + * preserved during the C calls inside TRACE_IRQS_OFF anyway. + */ + SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi + /* * User mode is traced as though IRQs are on, and SYSENTER * turned them off. @@ -256,10 +266,22 @@ sysret32_from_system_call: * when the system call started, which is already known to user * code. We zero R8-R10 to avoid info leaks. */ + movq RSP-ORIG_RAX(%rsp), %rsp + + /* + * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored + * on the process stack which is not mapped to userspace and + * not readable after we SWITCH_TO_USER_CR3. Delay the CR3 + * switch until after after the last reference to the process + * stack. + * + * %r8 is zeroed before the sysret, thus safe to clobber. + */ + SWITCH_TO_USER_CR3 scratch_reg=%r8 + xorq %r8, %r8 xorq %r9, %r9 xorq %r10, %r10 - movq RSP-ORIG_RAX(%rsp), %rsp swapgs sysretl END(entry_SYSCALL_compat) -- cgit v1.2.3 From 6fd166aae78c0ab738d49bda653cbd9e3b1491cf Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Dec 2017 15:07:59 +0100 Subject: x86/mm: Use/Fix PCID to optimize user/kernel switches We can use PCID to retain the TLBs across CR3 switches; including those now part of the user/kernel switch. This increases performance of kernel entry/exit at the cost of more expensive/complicated TLB flushing. Now that we have two address spaces, one for kernel and one for user space, we need two PCIDs per mm. We use the top PCID bit to indicate a user PCID (just like we use the PFN LSB for the PGD). Since we do TLB invalidation from kernel space, the existing code will only invalidate the kernel PCID, we augment that by marking the corresponding user PCID invalid, and upon switching back to userspace, use a flushing CR3 write for the switch. In order to access the user_pcid_flush_mask we use PER_CPU storage, which means the previously established SWAPGS vs CR3 ordering is now mandatory and required. Having to do this memory access does require additional registers, most sites have a functioning stack and we can spill one (RAX), sites without functional stack need to otherwise provide the second scratch register. Note: PCID is generally available on Intel Sandybridge and later CPUs. Note: Up until this point TLB flushing was broken in this series. Based-on-code-from: Dave Hansen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst 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: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 72 ++++++++++++++++++----- arch/x86/entry/entry_64.S | 9 +-- arch/x86/entry/entry_64_compat.S | 4 +- arch/x86/include/asm/processor-flags.h | 5 ++ arch/x86/include/asm/tlbflush.h | 91 +++++++++++++++++++++++++---- arch/x86/include/uapi/asm/processor-flags.h | 7 ++- arch/x86/kernel/asm-offsets.c | 4 ++ arch/x86/mm/init.c | 2 +- arch/x86/mm/tlb.c | 1 + 9 files changed, 162 insertions(+), 33 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3d3389a92c33..7894e5c0eef7 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -3,6 +3,9 @@ #include #include #include +#include +#include +#include /* @@ -191,17 +194,21 @@ For 32-bit we have the following conventions - kernel is built with #ifdef CONFIG_PAGE_TABLE_ISOLATION -/* PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two halves: */ -#define PTI_SWITCH_MASK (1< #include #include -#include "calling.h" #include #include #include @@ -40,6 +39,8 @@ #include #include +#include "calling.h" + .code64 .section .entry.text, "ax" @@ -406,7 +407,7 @@ syscall_return_via_sysret: * We are on the trampoline stack. All regs except RDI are live. * We can do future final exit work right here. */ - SWITCH_TO_USER_CR3 scratch_reg=%rdi + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi popq %rdi popq %rsp @@ -744,7 +745,7 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode) * We can do future final exit work right here. */ - SWITCH_TO_USER_CR3 scratch_reg=%rdi + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi /* Restore RDI. */ popq %rdi @@ -857,7 +858,7 @@ native_irq_return_ldt: */ orq PER_CPU_VAR(espfix_stack), %rax - SWITCH_TO_USER_CR3 scratch_reg=%rdi /* to user CR3 */ + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi SWAPGS /* to user GS */ popq %rdi /* Restore user RDI */ diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 05238b29895e..40f17009ec20 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -275,9 +275,9 @@ sysret32_from_system_call: * switch until after after the last reference to the process * stack. * - * %r8 is zeroed before the sysret, thus safe to clobber. + * %r8/%r9 are zeroed before the sysret, thus safe to clobber. */ - SWITCH_TO_USER_CR3 scratch_reg=%r8 + SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9 xorq %r8, %r8 xorq %r9, %r9 diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index 43212a43ee69..6a60fea90b9d 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -38,6 +38,11 @@ #define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull) #define CR3_PCID_MASK 0xFFFull #define CR3_NOFLUSH BIT_ULL(63) + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define X86_CR3_PTI_SWITCH_BIT 11 +#endif + #else /* * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 490a706fdba8..5dcc38b16604 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -10,6 +10,8 @@ #include #include #include +#include +#include static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) { @@ -24,24 +26,54 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) /* There are 12 bits of space for ASIDS in CR3 */ #define CR3_HW_ASID_BITS 12 + /* * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for * user/kernel switches */ -#define PTI_CONSUMED_ASID_BITS 0 +#ifdef CONFIG_PAGE_TABLE_ISOLATION +# define PTI_CONSUMED_PCID_BITS 1 +#else +# define PTI_CONSUMED_PCID_BITS 0 +#endif + +#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS) -#define CR3_AVAIL_ASID_BITS (CR3_HW_ASID_BITS - PTI_CONSUMED_ASID_BITS) /* * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account * for them being zero-based. Another -1 is because ASID 0 is reserved for * use by non-PCID-aware users. */ -#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_ASID_BITS) - 2) +#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2) + +/* + * 6 because 6 should be plenty and struct tlb_state will fit in two cache + * lines. + */ +#define TLB_NR_DYN_ASIDS 6 static inline u16 kern_pcid(u16 asid) { VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + /* + * Make sure that the dynamic ASID space does not confict with the + * bit we are using to switch between user and kernel ASIDs. + */ + BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT)); + /* + * The ASID being passed in here should have respected the + * MAX_ASID_AVAILABLE and thus never have the switch bit set. + */ + VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT)); +#endif + /* + * The dynamically-assigned ASIDs that get passed in are small + * (mm == NULL then we borrow a mm which may change during a - * task switch and therefore we must not be preempted while we write CR3 - * back: + * If current->mm == NULL then we borrow a mm which may change + * during a task switch and therefore we must not be preempted + * while we write CR3 back: */ preempt_disable(); native_write_cr3(__native_read_cr3()); @@ -301,7 +361,14 @@ static inline void __native_flush_tlb_global(void) */ static inline void __native_flush_tlb_single(unsigned long addr) { + u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + invalidate_user_asid(loaded_mm_asid); } /* diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index 53b4ca55ebb6..97abdaab9535 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -78,7 +78,12 @@ #define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT) #define X86_CR3_PCD_BIT 4 /* Page Cache Disable */ #define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT) -#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */ + +#define X86_CR3_PCID_BITS 12 +#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL)) + +#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */ +#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT) /* * Intel CPU features in CR4 diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 676b7cf4b62b..76417a9aab73 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -17,6 +17,7 @@ #include #include #include +#include #ifdef CONFIG_XEN #include @@ -94,6 +95,9 @@ void common(void) { BLANK(); DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); + /* TLB state for the entry code */ + OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); + /* Layout info for cpu_entry_area */ OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss); OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index af75069fb116..caeb8a7bf0a4 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -855,7 +855,7 @@ void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } -DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 42a8875f73fe..a1561957dccb 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -105,6 +105,7 @@ static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush) unsigned long new_mm_cr3; if (need_flush) { + invalidate_user_asid(new_asid); new_mm_cr3 = build_cr3(pgdir, new_asid); } else { new_mm_cr3 = build_cr3_noflush(pgdir, new_asid); -- cgit v1.2.3 From 21e94459110252d41b45c0c8ba50fd72a664d50c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 4 Dec 2017 15:08:00 +0100 Subject: x86/mm: Optimize RESTORE_CR3 Most NMI/paranoid exceptions will not in fact change pagetables and would thus not require TLB flushing, however RESTORE_CR3 uses flushing CR3 writes. Restores to kernel PCIDs can be NOFLUSH, because we explicitly flush the kernel mappings and now that we track which user PCIDs need flushing we can avoid those too when possible. This does mean RESTORE_CR3 needs an additional scratch_reg, luckily both sites have plenty available. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst 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: Will Deacon Cc: aliguori@amazon.com Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: keescook@google.com Signed-off-by: Ingo Molnar --- arch/x86/entry/calling.h | 30 ++++++++++++++++++++++++++++-- arch/x86/entry/entry_64.S | 4 ++-- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'arch/x86/entry/entry_64.S') diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 7894e5c0eef7..45a63e00a6af 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -281,8 +281,34 @@ For 32-bit we have the following conventions - kernel is built with .Ldone_\@: .endm -.macro RESTORE_CR3 save_reg:req +.macro RESTORE_CR3 scratch_reg:req save_reg:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID + + /* + * KERNEL pages can always resume with NOFLUSH as we do + * explicit flushes. + */ + bt $X86_CR3_PTI_SWITCH_BIT, \save_reg + jnc .Lnoflush_\@ + + /* + * Check if there's a pending flush for the user ASID we're + * about to set. + */ + movq \save_reg, \scratch_reg + andq $(0x7FF), \scratch_reg + bt \scratch_reg, THIS_CPU_user_pcid_flush_mask + jnc .Lnoflush_\@ + + btr \scratch_reg, THIS_CPU_user_pcid_flush_mask + jmp .Lwrcr3_\@ + +.Lnoflush_\@: + SET_NOFLUSH_BIT \save_reg + +.Lwrcr3_\@: /* * The CR3 write could be avoided when not changing its value, * but would require a CR3 read *and* a scratch register. @@ -301,7 +327,7 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req .endm -.macro RESTORE_CR3 save_reg:req +.macro RESTORE_CR3 scratch_reg:req save_reg:req .endm #endif diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index fd501844af1f..ed31d00dc5ee 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1288,7 +1288,7 @@ ENTRY(paranoid_exit) testl %ebx, %ebx /* swapgs needed? */ jnz .Lparanoid_exit_no_swapgs TRACE_IRQS_IRETQ - RESTORE_CR3 save_reg=%r14 + RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 SWAPGS_UNSAFE_STACK jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: @@ -1730,7 +1730,7 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi - RESTORE_CR3 save_reg=%r14 + RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 testl %ebx, %ebx /* swapgs needed? */ jnz nmi_restore -- cgit v1.2.3