From b02fcf9ba1211097754b286043cd87a8b4907e75 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 4 Dec 2017 15:07:09 +0100 Subject: x86/unwinder: Handle stack overflows more gracefully There are at least two unwinder bugs hindering the debugging of stack-overflow crashes: - It doesn't deal gracefully with the case where the stack overflows and the stack pointer itself isn't on a valid stack but the to-be-dereferenced data *is*. - The ORC oops dump code doesn't know how to print partial pt_regs, for the case where if we get an interrupt/exception in *early* entry code before the full pt_regs have been saved. Fix both issues. http://lkml.kernel.org/r/20171126024031.uxi4numpbjm5rlbr@treble Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Reviewed-by: Borislav Petkov Cc: Andy Lutomirski 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: 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/20171204150605.071425003@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/dumpstack.c | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f13b4c00a5de..0bc95be5c638 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -50,6 +50,28 @@ static void printk_stack_address(unsigned long address, int reliable, printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address); } +void show_iret_regs(struct pt_regs *regs) +{ + printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip); + printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss, + regs->sp, regs->flags); +} + +static void show_regs_safe(struct stack_info *info, struct pt_regs *regs) +{ + if (on_stack(info, regs, sizeof(*regs))) + __show_regs(regs, 0); + else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET, + IRET_FRAME_SIZE)) { + /* + * When an interrupt or exception occurs in entry code, the + * full pt_regs might not have been saved yet. In that case + * just print the iret frame. + */ + show_iret_regs(regs); + } +} + void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, unsigned long *stack, char *log_lvl) { @@ -94,8 +116,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, if (stack_name) printk("%s <%s>\n", log_lvl, stack_name); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); /* * Scan the stack, printing any text addresses we find. At the @@ -119,7 +141,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, /* * Don't print regs->ip again if it was already printed - * by __show_regs() below. + * by show_regs_safe() below. */ if (regs && stack == ®s->ip) goto next; @@ -155,8 +177,8 @@ next: /* if the frame has entry regs, print them */ regs = unwind_get_entry_regs(&state); - if (regs && on_stack(&stack_info, regs, sizeof(*regs))) - __show_regs(regs, 0); + if (regs) + show_regs_safe(&stack_info, regs); } if (stack_name) -- cgit v1.2.3 From 33a2f1a6c4d7c0a02d1c006fb0379cc5ca3b96bb Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:13 +0100 Subject: x86/dumpstack: Add get_stack_info() support for the SYSENTER stack get_stack_info() doesn't currently know about the SYSENTER stack, so unwinding will fail if we entered the kernel on the SYSENTER stack and haven't fully switched off. Teach get_stack_info() about the SYSENTER stack. With future patches applied that run part of the entry code on the SYSENTER stack and introduce an intentional BUG(), I would get: PANIC: double fault, error_code: 0x0 ... RIP: 0010:do_error_trap+0x33/0x1c0 ... Call Trace: Code: ... With this patch, I get: PANIC: double fault, error_code: 0x0 ... Call Trace: ? async_page_fault+0x36/0x60 ? invalid_op+0x22/0x40 ? async_page_fault+0x36/0x60 ? sync_regs+0x3c/0x40 ? sync_regs+0x2e/0x40 ? error_entry+0x6c/0xd0 ? async_page_fault+0x36/0x60 Code: ... which is a lot more informative. Signed-off-by: Andy Lutomirski Signed-off-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/20171204150605.392711508@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 3 +++ arch/x86/kernel/dumpstack.c | 19 +++++++++++++++++++ arch/x86/kernel/dumpstack_32.c | 6 ++++++ arch/x86/kernel/dumpstack_64.c | 6 ++++++ 4 files changed, 34 insertions(+) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 8da111b3c342..f8062bfd43a0 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -16,6 +16,7 @@ enum stack_type { STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, + STACK_TYPE_SYSENTER, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; @@ -28,6 +29,8 @@ 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); + 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/dumpstack.c b/arch/x86/kernel/dumpstack.c index 0bc95be5c638..a33a1373a252 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -43,6 +43,25 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, return true; } +bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) +{ + struct tss_struct *tss = this_cpu_ptr(&cpu_tss); + + /* Treat the canary as part of the stack for unwinding purposes. */ + void *begin = &tss->SYSENTER_stack_canary; + void *end = (void *)&tss->SYSENTER_stack + sizeof(tss->SYSENTER_stack); + + if ((void *)stack < begin || (void *)stack >= end) + return false; + + info->type = STACK_TYPE_SYSENTER; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, char *log_lvl) { diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index daefae83a3aa..5ff13a6b3680 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type) if (type == STACK_TYPE_SOFTIRQ) return "SOFTIRQ"; + if (type == STACK_TYPE_SYSENTER) + return "SYSENTER"; + return NULL; } @@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, if (task != current) goto unknown; + if (in_sysenter_stack(stack, info)) + goto recursion_check; + if (in_hardirq_stack(stack, info)) goto recursion_check; diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 88ce2ffdb110..abc828f8c297 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -37,6 +37,9 @@ 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_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST) return exception_stack_names[type - STACK_TYPE_EXCEPTION]; @@ -115,6 +118,9 @@ 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)) + goto recursion_check; + goto unknown; recursion_check: -- cgit v1.2.3 From 6e60e583426c2f8751c22c2dfe5c207083b4483a Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:18 +0100 Subject: x86/dumpstack: Handle stack overflow on all stacks We currently special-case stack overflow on the task stack. We're going to start putting special stacks in the fixmap with a custom layout, so they'll have guard pages, too. Teach the unwinder to be able to unwind an overflow of any of the stacks. Signed-off-by: Andy Lutomirski Signed-off-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/20171204150605.802057305@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/kernel/dumpstack.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index a33a1373a252..64f8ed2a4827 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -112,24 +112,28 @@ 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 * - * x86-32 can have up to three stacks: + * x86-32 can have up to four stacks: * - task stack * - softirq stack * - hardirq stack + * - SYSENTER stack */ for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) { const char *stack_name; - /* - * If we overflowed the task stack into a guard page, jump back - * to the bottom of the usable stack. - */ - if (task_stack_page(task) - (void *)stack < PAGE_SIZE) - stack = task_stack_page(task); - - if (get_stack_info(stack, task, &stack_info, &visit_mask)) - break; + if (get_stack_info(stack, task, &stack_info, &visit_mask)) { + /* + * We weren't on a valid stack. It's possible that + * we overflowed a valid stack into a guard page. + * See if the next page up is valid so that we can + * generate some kind of backtrace if this happens. + */ + stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack); + if (get_stack_info(stack, task, &stack_info, &visit_mask)) + break; + } stack_name = stack_type_name(stack_info.type); if (stack_name) -- cgit v1.2.3 From 72f5e08dbba2d01aa90b592cf76c378ea233b00b Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Mon, 4 Dec 2017 15:07:20 +0100 Subject: x86/entry: Remap the TSS into the CPU entry area This has a secondary purpose: it puts the entry stack into a region with a well-controlled layout. A subsequent patch will take advantage of this to streamline the SYSCALL entry code to be able to find it more easily. 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/20171204150605.962042855@linutronix.de Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 6 ++++-- arch/x86/include/asm/fixmap.h | 7 +++++++ arch/x86/kernel/asm-offsets.c | 3 +++ arch/x86/kernel/cpu/common.c | 41 +++++++++++++++++++++++++++++++++++------ arch/x86/kernel/dumpstack.c | 3 ++- arch/x86/kvm/vmx.c | 2 +- arch/x86/power/cpu.c | 11 ++++++----- 7 files changed, 58 insertions(+), 15 deletions(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 4838037f97f6..0ab316c46806 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -941,7 +941,8 @@ ENTRY(debug) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_tss + CPU_TSS_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 @@ -984,7 +985,8 @@ ENTRY(nmi) movl %esp, %eax # pt_regs pointer /* Are we currently on the SYSENTER stack? */ - PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx) + movl PER_CPU_VAR(cpu_entry_area), %ecx + addl $CPU_ENTRY_AREA_tss + CPU_TSS_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/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index b61f0242f9d0..84558b611ad3 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -54,6 +54,13 @@ extern unsigned long __FIXADDR_TOP; */ 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. + */ + struct tss_struct tss; }; #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 b275863128eb..55858b277cf6 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -98,4 +98,7 @@ void common(void) { OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack); /* Size of SYSENTER_stack */ DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->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 60b2dfd2a58b..e5837bd6c672 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -466,6 +466,22 @@ void load_percpu_segment(int cpu) load_stack_canary_segment(); } +static void set_percpu_fixmap_pages(int fixmap_index, void *ptr, + int pages, pgprot_t prot) +{ + int i; + + for (i = 0; i < pages; i++) { + __set_fixmap(fixmap_index - i, + per_cpu_ptr_to_phys(ptr + i * PAGE_SIZE), prot); + } +} + +#ifdef CONFIG_X86_32 +/* The 32-bit entry code needs to find cpu_entry_area. */ +DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); +#endif + /* Setup the fixmap mappings only once per-processor */ static inline void setup_cpu_entry_area(int cpu) { @@ -507,7 +523,15 @@ static inline void setup_cpu_entry_area(int cpu) */ BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ 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), + sizeof(struct tss_struct) / PAGE_SIZE, + PAGE_KERNEL); +#ifdef CONFIG_X86_32 + this_cpu_write(cpu_entry_area, get_cpu_entry_area(cpu)); +#endif } /* Load the original GDT from the per-cpu structure */ @@ -1257,7 +1281,8 @@ void enable_sep_cpu(void) wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0); wrmsr(MSR_IA32_SYSENTER_ESP, - (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack), + (unsigned long)&get_cpu_entry_area(cpu)->tss + + offsetofend(struct tss_struct, SYSENTER_stack), 0); wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0); @@ -1370,6 +1395,8 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks /* May not be marked __init: used by software suspend */ void syscall_init(void) { + int cpu = smp_processor_id(); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); @@ -1383,7 +1410,7 @@ void syscall_init(void) */ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); wrmsrl_safe(MSR_IA32_SYSENTER_ESP, - (unsigned long)this_cpu_ptr(&cpu_tss) + + (unsigned long)&get_cpu_entry_area(cpu)->tss + offsetofend(struct tss_struct, SYSENTER_stack)); wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); #else @@ -1593,11 +1620,13 @@ void cpu_init(void) initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, me); + setup_cpu_entry_area(cpu); + /* * Initialize the TSS. Don't bother initializing sp0, as the initial * task never enters user mode. */ - set_tss_desc(cpu, &t->x86_tss); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); load_mm_ldt(&init_mm); @@ -1610,7 +1639,6 @@ void cpu_init(void) if (is_uv_system()) uv_cpu_init(); - setup_cpu_entry_area(cpu); load_fixmap_gdt(cpu); } @@ -1651,11 +1679,13 @@ void cpu_init(void) initialize_tlbstate_and_flush(); enter_lazy_tlb(&init_mm, curr); + setup_cpu_entry_area(cpu); + /* * Initialize the TSS. Don't bother initializing sp0, as the initial * task never enters user mode. */ - set_tss_desc(cpu, &t->x86_tss); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); load_TR_desc(); load_mm_ldt(&init_mm); @@ -1672,7 +1702,6 @@ void cpu_init(void) fpu__init_cpu(); - setup_cpu_entry_area(cpu); load_fixmap_gdt(cpu); } #endif diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 64f8ed2a4827..60267850125e 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -45,7 +45,8 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task, bool in_sysenter_stack(unsigned long *stack, struct stack_info *info) { - struct tss_struct *tss = this_cpu_ptr(&cpu_tss); + int cpu = smp_processor_id(); + struct tss_struct *tss = &get_cpu_entry_area(cpu)->tss; /* Treat the canary as part of the stack for unwinding purposes. */ void *begin = &tss->SYSENTER_stack_canary; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 2abe0073b573..62ee4362e1c1 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -2291,7 +2291,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) * processors. See 22.2.4. */ vmcs_writel(HOST_TR_BASE, - (unsigned long)this_cpu_ptr(&cpu_tss.x86_tss)); + (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss); vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt); /* 22.2.4 */ /* diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 50593e138281..04d5157fe7f8 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -160,18 +160,19 @@ static void do_fpu_end(void) static void fix_processor_context(void) { int cpu = smp_processor_id(); - struct tss_struct *t = &per_cpu(cpu_tss, cpu); #ifdef CONFIG_X86_64 struct desc_struct *desc = get_cpu_gdt_rw(cpu); tss_desc tss; #endif /* - * This just modifies memory; should not be necessary. But... This is - * necessary, because 386 hardware has concept of busy TSS or some - * similar stupidity. + * We need to reload TR, which requires that we change the + * GDT entry to indicate "available" first. + * + * XXX: This could probably all be replaced by a call to + * force_reload_TR(). */ - set_tss_desc(cpu, &t->x86_tss); + set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); #ifdef CONFIG_X86_64 memcpy(&tss, &desc[GDT_ENTRY_TSS], sizeof(tss_desc)); -- 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/include/asm/processor.h | 1 - arch/x86/kernel/dumpstack.c | 3 +-- arch/x86/kernel/process.c | 1 - arch/x86/kernel/traps.c | 7 ------- 4 files changed, 1 insertion(+), 11 deletions(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b0cf0612a454..d34ac13c5866 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -341,7 +341,6 @@ struct tss_struct { * Space for the temporary SYSENTER stack, used for SYSENTER * and the entry trampoline as well. */ - unsigned long SYSENTER_stack_canary; unsigned long SYSENTER_stack[64]; /* diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 60267850125e..ae1ce2e3f132 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -48,8 +48,7 @@ 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; - /* Treat the canary as part of the stack for unwinding purposes. */ - void *begin = &tss->SYSENTER_stack_canary; + void *begin = &tss->SYSENTER_stack; void *end = (void *)&tss->SYSENTER_stack + sizeof(tss->SYSENTER_stack); if ((void *)stack < begin || (void *)stack >= end) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 86e83762e3b3..6a04287f222b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -81,7 +81,6 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { */ .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif - .SYSENTER_stack_canary = STACK_END_MAGIC, }; EXPORT_PER_CPU_SYMBOL(cpu_tss); 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 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/kernel/dumpstack.c') 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 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/kernel/dumpstack.c') 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 92a0f81d89571e3e8759366e050ee05cc545ef99 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 20 Dec 2017 18:51:31 +0100 Subject: x86/cpu_entry_area: Move it out of the fixmap Put the cpu_entry_area into a separate P4D entry. The fixmap gets too big and 0-day already hit a case where the fixmap PTEs were cleared by cleanup_highmap(). Aside of that the fixmap API is a pain as it's all backwards. Signed-off-by: Thomas Gleixner Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Juergen Gross Cc: Linus Torvalds Cc: Peter Zijlstra Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- Documentation/x86/x86_64/mm.txt | 2 + arch/x86/include/asm/cpu_entry_area.h | 18 ++++++++- arch/x86/include/asm/desc.h | 1 + arch/x86/include/asm/fixmap.h | 32 +--------------- arch/x86/include/asm/pgtable_32_types.h | 15 ++++++-- arch/x86/include/asm/pgtable_64_types.h | 47 +++++++++++++---------- arch/x86/kernel/dumpstack.c | 1 + arch/x86/kernel/traps.c | 5 ++- arch/x86/mm/cpu_entry_area.c | 66 +++++++++++++++++++++++++-------- arch/x86/mm/dump_pagetables.c | 6 ++- arch/x86/mm/init_32.c | 6 +++ arch/x86/mm/kasan_init_64.c | 29 ++++++++------- arch/x86/mm/pgtable_32.c | 1 + arch/x86/xen/mmu_pv.c | 2 - 14 files changed, 143 insertions(+), 88 deletions(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 63a41671d25b..51101708a03a 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -12,6 +12,7 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) ... unused hole ... ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB) ... unused hole ... +fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ... unused hole ... ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space @@ -35,6 +36,7 @@ ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB) ... unused hole ... ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB) ... unused hole ... +fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ... unused hole ... ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 5471826803af..2fbc69a0916e 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -43,10 +43,26 @@ struct cpu_entry_area { }; #define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) -#define CPU_ENTRY_AREA_PAGES (CPU_ENTRY_AREA_SIZE / PAGE_SIZE) +#define CPU_ENTRY_AREA_TOT_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); extern void setup_cpu_entry_areas(void); +extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); + +#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE +#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) + +#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +#define CPU_ENTRY_AREA_MAP_SIZE \ + (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE) + +extern struct cpu_entry_area *get_cpu_entry_area(int cpu); + +static inline struct entry_stack *cpu_entry_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->entry_stack_page.stack; +} #endif diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 2ace1f90d138..bc359dd2f7f6 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -7,6 +7,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index fb801662a230..64c4a30e0d39 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -25,7 +25,6 @@ #else #include #endif -#include /* * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall @@ -84,7 +83,6 @@ enum fixed_addresses { FIX_IO_APIC_BASE_0, FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, #endif - FIX_RO_IDT, /* Virtual mapping for read-only IDT */ #ifdef CONFIG_X86_32 FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1, @@ -100,9 +98,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_INTEL_MID FIX_LNW_VRTC, #endif - /* Fixmap entries to remap the GDTs, one per processor. */ - FIX_CPU_ENTRY_AREA_TOP, - FIX_CPU_ENTRY_AREA_BOTTOM = FIX_CPU_ENTRY_AREA_TOP + (CPU_ENTRY_AREA_PAGES * NR_CPUS) - 1, #ifdef CONFIG_ACPI_APEI_GHES /* Used for GHES mapping from assorted contexts */ @@ -143,7 +138,7 @@ enum fixed_addresses { extern void reserve_top_address(unsigned long reserve); #define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) extern int fixmaps_set; @@ -191,30 +186,5 @@ void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, void __early_set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags); -static inline unsigned int __get_cpu_entry_area_page_index(int cpu, int page) -{ - BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); - - return FIX_CPU_ENTRY_AREA_BOTTOM - cpu*CPU_ENTRY_AREA_PAGES - page; -} - -#define __get_cpu_entry_area_offset_index(cpu, offset) ({ \ - BUILD_BUG_ON(offset % PAGE_SIZE != 0); \ - __get_cpu_entry_area_page_index(cpu, offset / PAGE_SIZE); \ - }) - -#define get_cpu_entry_area_index(cpu, field) \ - __get_cpu_entry_area_offset_index((cpu), offsetof(struct cpu_entry_area, field)) - -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 entry_stack *cpu_entry_stack(int cpu) -{ - return &get_cpu_entry_area(cpu)->entry_stack_page.stack; -} - #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index f2ca9b28fd68..ce245b0cdfca 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */ #define LAST_PKMAP 1024 #endif -#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1)) \ - & PMD_MASK) +/* + * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c + * to avoid include recursion hell + */ +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * 40) + +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK) + +#define PKMAP_BASE \ + ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) #ifdef CONFIG_HIGHMEM # define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) #else -# define VMALLOC_END (FIXADDR_START - 2 * PAGE_SIZE) +# define VMALLOC_END (CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE) #endif #define MODULES_VADDR VMALLOC_START diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 6d5f45dcd4a1..3d27831bc58d 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -76,32 +76,41 @@ typedef struct { pteval_t pte; } pte_t; #define PGDIR_MASK (~(PGDIR_SIZE - 1)) /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ -#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) +#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) + #ifdef CONFIG_X86_5LEVEL -#define VMALLOC_SIZE_TB _AC(16384, UL) -#define __VMALLOC_BASE _AC(0xff92000000000000, UL) -#define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) +# define VMALLOC_SIZE_TB _AC(16384, UL) +# define __VMALLOC_BASE _AC(0xff92000000000000, UL) +# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL) #else -#define VMALLOC_SIZE_TB _AC(32, UL) -#define __VMALLOC_BASE _AC(0xffffc90000000000, UL) -#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) +# define VMALLOC_SIZE_TB _AC(32, UL) +# define __VMALLOC_BASE _AC(0xffffc90000000000, UL) +# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) #endif + #ifdef CONFIG_RANDOMIZE_MEMORY -#define VMALLOC_START vmalloc_base -#define VMEMMAP_START vmemmap_base +# define VMALLOC_START vmalloc_base +# define VMEMMAP_START vmemmap_base #else -#define VMALLOC_START __VMALLOC_BASE -#define VMEMMAP_START __VMEMMAP_BASE +# define VMALLOC_START __VMALLOC_BASE +# define VMEMMAP_START __VMEMMAP_BASE #endif /* CONFIG_RANDOMIZE_MEMORY */ -#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) -#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) + +#define VMALLOC_END (VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL)) + +#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) /* The module sections ends with the start of the fixmap */ -#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) -#define MODULES_LEN (MODULES_END - MODULES_VADDR) -#define ESPFIX_PGD_ENTRY _AC(-2, UL) -#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) -#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) -#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) +#define MODULES_END __fix_to_virt(__end_of_fixed_addresses + 1) +#define MODULES_LEN (MODULES_END - MODULES_VADDR) + +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) + +#define CPU_ENTRY_AREA_PGD _AC(-3, UL) +#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT) + +#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) +#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 1dd3f533d78c..36b17e0febe8 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -18,6 +18,7 @@ #include #include +#include #include #include diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 464daed6894f..7c16fe0b60c2 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -951,8 +951,9 @@ void __init trap_init(void) * "sidt" instruction will not leak the location of the kernel, and * to defend the IDT against arbitrary memory write vulnerabilities. * It will be reloaded in cpu_init() */ - __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); - idt_descr.address = fix_to_virt(FIX_RO_IDT); + cea_set_pte(CPU_ENTRY_AREA_RO_IDT_VADDR, __pa_symbol(idt_table), + PAGE_KERNEL_RO); + idt_descr.address = CPU_ENTRY_AREA_RO_IDT; /* * Should be a barrier for any external CPU state: diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index 235ff9cfaaf4..21e8b595cbb1 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -15,11 +15,27 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); #endif +struct cpu_entry_area *get_cpu_entry_area(int cpu) +{ + unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; + BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); + + return (struct cpu_entry_area *) va; +} +EXPORT_SYMBOL(get_cpu_entry_area); + +void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags) +{ + unsigned long va = (unsigned long) cea_vaddr; + + set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags)); +} + static void __init -set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) +cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) { - for ( ; pages; pages--, idx--, ptr += PAGE_SIZE) - __set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot); + for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE) + cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); } /* Setup the fixmap mappings only once per-processor */ @@ -47,10 +63,12 @@ static void __init setup_cpu_entry_area(int cpu) 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, entry_stack_page), - per_cpu_ptr(&entry_stack_storage, cpu), 1, - PAGE_KERNEL); + cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu), + gdt_prot); + + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page, + per_cpu_ptr(&entry_stack_storage, cpu), 1, + PAGE_KERNEL); /* * The Intel SDM says (Volume 3, 7.2.1): @@ -72,10 +90,9 @@ static void __init setup_cpu_entry_area(int cpu) BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ 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_rw, cpu), - sizeof(struct tss_struct) / PAGE_SIZE, - tss_prot); + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss, + &per_cpu(cpu_tss_rw, cpu), + sizeof(struct tss_struct) / PAGE_SIZE, tss_prot); #ifdef CONFIG_X86_32 per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu); @@ -85,20 +102,37 @@ static void __init setup_cpu_entry_area(int cpu) BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0); BUILD_BUG_ON(sizeof(exception_stacks) != sizeof(((struct cpu_entry_area *)0)->exception_stacks)); - set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks), - &per_cpu(exception_stacks, cpu), - sizeof(exception_stacks) / PAGE_SIZE, - PAGE_KERNEL); + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks, + &per_cpu(exception_stacks, cpu), + sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL); - __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline), + cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline, __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); #endif } +static __init void setup_cpu_entry_area_ptes(void) +{ +#ifdef CONFIG_X86_32 + unsigned long start, end; + + BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE); + BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK); + + start = CPU_ENTRY_AREA_BASE; + end = start + CPU_ENTRY_AREA_MAP_SIZE; + + for (; start < end; start += PMD_SIZE) + populate_extra_pte(start); +#endif +} + void __init setup_cpu_entry_areas(void) { unsigned int cpu; + setup_cpu_entry_area_ptes(); + for_each_possible_cpu(cpu) setup_cpu_entry_area(cpu); } diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index fdf09d8f98da..43dedbfb7257 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -58,6 +58,7 @@ enum address_markers_idx { KASAN_SHADOW_START_NR, KASAN_SHADOW_END_NR, #endif + CPU_ENTRY_AREA_NR, #ifdef CONFIG_X86_ESPFIX64 ESPFIX_START_NR, #endif @@ -81,6 +82,7 @@ static struct addr_marker address_markers[] = { [KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" }, [KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" }, #endif + [CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" }, #ifdef CONFIG_X86_ESPFIX64 [ESPFIX_START_NR] = { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, #endif @@ -104,6 +106,7 @@ enum address_markers_idx { #ifdef CONFIG_HIGHMEM PKMAP_BASE_NR, #endif + CPU_ENTRY_AREA_NR, FIXADDR_START_NR, END_OF_SPACE_NR, }; @@ -116,6 +119,7 @@ static struct addr_marker address_markers[] = { #ifdef CONFIG_HIGHMEM [PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" }, #endif + [CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" }, [FIXADDR_START_NR] = { 0UL, "Fixmap area" }, [END_OF_SPACE_NR] = { -1, NULL } }; @@ -541,8 +545,8 @@ static int __init pt_dump_init(void) address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE; # endif address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; + address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE; #endif - return 0; } __initcall(pt_dump_init); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8a64a6f2848d..135c9a7898c7 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include "mm_internal.h" @@ -766,6 +767,7 @@ void __init mem_init(void) mem_init_print_info(NULL); printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" + " cpu_entry : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HIGHMEM " pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #endif @@ -777,6 +779,10 @@ void __init mem_init(void) FIXADDR_START, FIXADDR_TOP, (FIXADDR_TOP - FIXADDR_START) >> 10, + CPU_ENTRY_AREA_BASE, + CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE, + CPU_ENTRY_AREA_MAP_SIZE >> 10, + #ifdef CONFIG_HIGHMEM PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, (LAST_PKMAP*PAGE_SIZE) >> 10, diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 9ec70d780f1f..47388f0c0e59 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -15,6 +15,7 @@ #include #include #include +#include extern struct range pfn_mapped[E820_MAX_ENTRIES]; @@ -322,31 +323,33 @@ void __init kasan_init(void) map_range(&pfn_mapped[i]); } - kasan_populate_zero_shadow( - kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), - kasan_mem_to_shadow((void *)__START_KERNEL_map)); - - kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), - (unsigned long)kasan_mem_to_shadow(_end), - early_pfn_to_nid(__pa(_stext))); - - shadow_cpu_entry_begin = (void *)__fix_to_virt(FIX_CPU_ENTRY_AREA_BOTTOM); + shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE; shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin); shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin, PAGE_SIZE); - shadow_cpu_entry_end = (void *)(__fix_to_virt(FIX_CPU_ENTRY_AREA_TOP) + PAGE_SIZE); + shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE + + CPU_ENTRY_AREA_MAP_SIZE); shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end); shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end, PAGE_SIZE); - kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), - shadow_cpu_entry_begin); + kasan_populate_zero_shadow( + kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), + shadow_cpu_entry_begin); kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, (unsigned long)shadow_cpu_entry_end, 0); - kasan_populate_zero_shadow(shadow_cpu_entry_end, (void *)KASAN_SHADOW_END); + kasan_populate_zero_shadow(shadow_cpu_entry_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); + + kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), + (unsigned long)kasan_mem_to_shadow(_end), + early_pfn_to_nid(__pa(_stext))); + + kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), + (void *)KASAN_SHADOW_END); load_cr3(init_top_pgt); __flush_tlb_all(); diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 6b9bf023a700..c3c5274410a9 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -10,6 +10,7 @@ #include #include +#include #include #include #include diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index c2454237fa67..a0e2b8c6e5c7 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2261,7 +2261,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) switch (idx) { case FIX_BTMAP_END ... FIX_BTMAP_BEGIN: - case FIX_RO_IDT: #ifdef CONFIG_X86_32 case FIX_WP_TEST: # ifdef CONFIG_HIGHMEM @@ -2272,7 +2271,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: - case FIX_CPU_ENTRY_AREA_TOP ... FIX_CPU_ENTRY_AREA_BOTTOM: /* All local page mappings */ pte = pfn_pte(phys, prot); break; -- cgit v1.2.3 From 5f26d76c3fd67c48806415ef8b1116c97beff8ba Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 19 Dec 2017 22:33:46 +0100 Subject: x86/dumpstack: Indicate in Oops whether PTI is configured and enabled CONFIG_PAGE_TABLE_ISOLATION is relatively new and intrusive feature that may still have some corner cases which could take some time to manifest and be fixed. It would be useful to have Oops messages indicate whether it was enabled for building the kernel, and whether it was disabled during boot. Example of fully enabled: Oops: 0001 [#1] SMP PTI Example of enabled during build, but disabled during boot: Oops: 0001 [#1] SMP NOPTI We can decide to remove this after the feature has been tested in the field long enough. [ tglx: Made it use boot_cpu_has() as requested by Borislav ] Signed-off-by: Vlastimil Babka Signed-off-by: Thomas Gleixner Reviewed-by: Eduardo Valentin Acked-by: Dave Hansen Cc: Andy Lutomirski Cc: Andy Lutomirsky Cc: Boris Ostrovsky Cc: Borislav Petkov Cc: Brian Gerst Cc: Dave Hansen Cc: David Laight Cc: Denys Vlasenko 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: bpetkov@suse.de Cc: daniel.gruss@iaik.tugraz.at Cc: hughd@google.com Cc: jkosina@suse.cz Cc: keescook@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/dumpstack.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86/kernel/dumpstack.c') diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 36b17e0febe8..5fa110699ed2 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -297,11 +297,13 @@ int __die(const char *str, struct pt_regs *regs, long err) unsigned long sp; #endif printk(KERN_DEFAULT - "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter, + "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter, IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "", IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", - IS_ENABLED(CONFIG_KASAN) ? " KASAN" : ""); + IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", + IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? + (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); if (notify_die(DIE_OOPS, str, regs, err, current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP) -- cgit v1.2.3