From 404f6aac9b3ef595735feca99979db084ea48315 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 8 Aug 2016 16:29:06 -0700 Subject: x86: Apply more __ro_after_init and const Guided by grsecurity's analogous __read_only markings in arch/x86, this applies several uses of __ro_after_init to structures that are only updated during __init, and const for some structures that are never updated. Additionally extends __init markings to some functions that are only used during __init, and cleans up some missing C99 style static initializers. Signed-off-by: Kees Cook Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Brad Spengler Cc: Brian Gerst Cc: David Brown Cc: Denys Vlasenko Cc: Emese Revfy Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Mathias Krause Cc: Michael Ellerman Cc: PaX Team Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/20160808232906.GA29731@www.outflux.net Signed-off-by: Ingo Molnar --- arch/x86/include/asm/desc.h | 2 +- arch/x86/include/asm/fpu/xstate.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 4e10d73cf018..12080d87da3b 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -36,7 +36,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in extern struct desc_ptr idt_descr; extern gate_desc idt_table[]; -extern struct desc_ptr debug_idt_descr; +extern const struct desc_ptr debug_idt_descr; extern gate_desc debug_idt_table[]; struct gdt_page { diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index ae55a43e09c0..d4957ac72b48 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -45,7 +45,8 @@ extern u64 xfeatures_mask; extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); +extern void __init update_regset_xstate_info(unsigned int size, + u64 xstate_mask); void fpu__xstate_clear_all_cpu_caps(void); void *get_xsave_addr(struct xregs_state *xsave, int xstate); -- cgit From 25dfe4785332723f09311dcb7fd91015a60c022f Mon Sep 17 00:00:00 2001 From: Thomas Garnier Date: Wed, 27 Jul 2016 08:59:56 -0700 Subject: x86/mm/64: Enable KASLR for vmemmap memory region Add vmemmap in the list of randomized memory regions. The vmemmap region holds a representation of the physical memory (through a struct page array). An attacker could use this region to disclose the kernel memory layout (walking the page linked list). Signed-off-by: Thomas Garnier Signed-off-by: Kees Cook Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: kernel-hardening@lists.openwall.com Link: http://lkml.kernel.org/r/1469635196-122447-1-git-send-email-thgarnie@google.com [ Minor edits. ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/kaslr.h | 1 + arch/x86/include/asm/pgtable_64_types.h | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h index 2674ee3de748..1052a797d71d 100644 --- a/arch/x86/include/asm/kaslr.h +++ b/arch/x86/include/asm/kaslr.h @@ -6,6 +6,7 @@ unsigned long kaslr_get_random_long(const char *purpose); #ifdef CONFIG_RANDOMIZE_MEMORY extern unsigned long page_offset_base; extern unsigned long vmalloc_base; +extern unsigned long vmemmap_base; void kernel_randomize_memory(void); #else diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 6fdef9eef2d5..3a264200c62f 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -57,11 +57,13 @@ typedef struct { pteval_t pte; } pte_t; #define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL) #define VMALLOC_SIZE_TB _AC(32, UL) #define __VMALLOC_BASE _AC(0xffffc90000000000, UL) -#define VMEMMAP_START _AC(0xffffea0000000000, UL) +#define __VMEMMAP_BASE _AC(0xffffea0000000000, UL) #ifdef CONFIG_RANDOMIZE_MEMORY #define VMALLOC_START vmalloc_base +#define VMEMMAP_START vmemmap_base #else #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) -- cgit From bf255bdaada6d497536aadee5406f6ded318978b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 18 Aug 2016 10:59:01 -0500 Subject: x86/dumpstack: Remove show_trace() There are a bewildering array of options for dumping the stack. Simplify things a little by removing show_trace(), which is unused. Signed-off-by: Josh Poimboeuf Reviewed-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/fe02292eac9d409001ec0cf6d06f90ced242570d.1471535549.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/kdebug.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 1ef9d581b5d9..d31881188431 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -24,8 +24,6 @@ enum die_val { extern void printk_address(unsigned long address); extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); -extern void show_trace(struct task_struct *t, struct pt_regs *regs, - unsigned long *sp, unsigned long bp); extern void show_stack_regs(struct pt_regs *regs); extern void __show_regs(struct pt_regs *regs, int all); extern unsigned long oops_begin(void); -- cgit From 32541b47bd34940d836fbdf713d16c7ac70d51be Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 18 Aug 2016 10:59:02 -0500 Subject: x86/asm/head: Remove unused init_rsp variable extern There is no init_rsp variable. Remove its extern. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/c183bbecd5730d84e8c6aff3824537c1c1bf3591.1471535549.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/realmode.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index b2988c0ed829..3327ffb38926 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -44,7 +44,6 @@ struct trampoline_header { extern struct real_mode_header *real_mode_header; extern unsigned char real_mode_blob_end[]; -extern unsigned long init_rsp; extern unsigned long initial_code; extern unsigned long initial_gs; -- cgit From b32f96c75d0dcbb9bf9cc7994e8022c8ce20a668 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 18 Aug 2016 10:59:03 -0500 Subject: x86/asm/head: Rename 'stack_start' -> 'initial_stack' The 'stack_start' variable is similar in usage to 'initial_code' and 'initial_gs': they're all stored in head_64.S and they're all updated by SMP and ACPI suspend before starting a CPU. Rename it to 'initial_stack' to be consistent with the others. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/87063d773a3212051b77e17b0ee427f6582a5050.1471535549.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/realmode.h | 1 + arch/x86/include/asm/smp.h | 3 --- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 3327ffb38926..230e1903acf0 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -46,6 +46,7 @@ extern unsigned char real_mode_blob_end[]; extern unsigned long initial_code; extern unsigned long initial_gs; +extern unsigned long initial_stack; extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index ebd0c164cd4e..19980b36f394 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -39,9 +39,6 @@ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid); #endif -/* Static state in head.S used to set up a CPU */ -extern unsigned long stack_start; /* Initial stack pointer address */ - struct task_struct; struct smp_ops { -- cgit From e37e43a497d5a8b7c0cc1736d56986f432c394c9 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 11 Aug 2016 02:35:23 -0700 Subject: x86/mm/64: Enable vmapped stacks (CONFIG_HAVE_ARCH_VMAP_STACK=y) This allows x86_64 kernels to enable vmapped stacks by setting HAVE_ARCH_VMAP_STACK=y - which enables the CONFIG_VMAP_STACK=y high level Kconfig option. There are a couple of interesting bits: First, x86 lazily faults in top-level paging entries for the vmalloc area. This won't work if we get a page fault while trying to access the stack: the CPU will promote it to a double-fault and we'll die. To avoid this problem, probe the new stack when switching stacks and forcibly populate the pgd entry for the stack when switching mms. Second, once we have guard pages around the stack, we'll want to detect and handle stack overflow. I didn't enable it on x86_32. We'd need to rework the double-fault code a bit and I'm concerned about running out of vmalloc virtual addresses under some workloads. This patch, by itself, will behave somewhat erratically when the stack overflows while RSP is still more than a few tens of bytes above the bottom of the stack. Specifically, we'll get #PF and make it to no_context and them oops without reliably triggering a double-fault, and no_context doesn't know about stack overflows. The next patch will improve that case. Thank you to Nadav and Brian for helping me pay enough attention to the SDM to hopefully get this right. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Nadav Amit Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/c88f3e2920b18e6cc621d772a04a62c06869037e.1470907718.git.luto@kernel.org [ Minor edits. ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/switch_to.h | 28 +++++++++++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8f321a1b03a1..14e4b20f0aaf 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -8,6 +8,28 @@ struct tss_struct; void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss); +/* This runs runs on the previous thread's stack. */ +static inline void prepare_switch_to(struct task_struct *prev, + struct task_struct *next) +{ +#ifdef CONFIG_VMAP_STACK + /* + * If we switch to a stack that has a top-level paging entry + * that is not present in the current mm, the resulting #PF will + * will be promoted to a double-fault and we'll panic. Probe + * the new stack now so that vmalloc_fault can fix up the page + * tables if needed. This can only happen if we use a stack + * in vmap space. + * + * We assume that the stack is aligned so that it never spans + * more than one top-level paging entry. + * + * To minimize cache pollution, just follow the stack pointer. + */ + READ_ONCE(*(unsigned char *)next->thread.sp); +#endif +} + #ifdef CONFIG_X86_32 #ifdef CONFIG_CC_STACKPROTECTOR @@ -39,6 +61,8 @@ do { \ */ \ unsigned long ebx, ecx, edx, esi, edi; \ \ + prepare_switch_to(prev, next); \ + \ asm volatile("pushl %%ebp\n\t" /* save EBP */ \ "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ @@ -103,7 +127,9 @@ do { \ * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL * has no effect. */ -#define switch_to(prev, next, last) \ +#define switch_to(prev, next, last) \ + prepare_switch_to(prev, next); \ + \ asm volatile(SAVE_CONTEXT \ "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ -- cgit From e4a744ef2fef5c803348b650a3a2d01da7797a9b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 19 Aug 2016 06:52:55 -0500 Subject: ftrace: Remove CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST from config Make HAVE_FUNCTION_GRAPH_FP_TEST a normal define, independent from kconfig. This removes some config file pollution and simplifies the checking for the fp test. Suggested-by: Steven Rostedt Signed-off-by: Josh Poimboeuf Acked-by: Steven Rostedt Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/2c4e5f05054d6d367f702fd153af7a0109dd5c81.1471607358.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/ftrace.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index a4820d4df617..37f67cbba1c6 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -6,6 +6,7 @@ # define MCOUNT_ADDR ((unsigned long)(__fentry__)) #else # define MCOUNT_ADDR ((unsigned long)(mcount)) +# define HAVE_FUNCTION_GRAPH_FP_TEST #endif #define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ -- cgit From 471bd10f5e2880bd91a2627d887f6062494cfe9c Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 19 Aug 2016 06:53:00 -0500 Subject: ftrace/x86: Implement HAVE_FUNCTION_GRAPH_RET_ADDR_PTR Use the more reliable version of ftrace_graph_ret_addr() so we no longer have to worry about the unwinder getting out of sync with the function graph ret_stack index, which can happen if the unwinder skips any frames before calling ftrace_graph_ret_addr(). This fixes this issue (and several others like it): $ cat /proc/self/stack [] save_stack_trace_tsk+0x22/0x40 [] proc_pid_stack+0xb9/0x110 [] proc_single_show+0x54/0x80 [] seq_read+0x108/0x3e0 [] __vfs_read+0x37/0x140 [] vfs_read+0x99/0x140 [] SyS_read+0x58/0xc0 [] entry_SYSCALL_64_fastpath+0x1f/0xbd [] 0xffffffffffffffff $ echo function_graph > /sys/kernel/debug/tracing/current_tracer $ cat /proc/self/stack [] return_to_handler+0x0/0x27 [] print_context_stack+0xfc/0x100 [] return_to_handler+0x0/0x27 [] dump_trace+0x12b/0x350 [] return_to_handler+0x0/0x27 [] save_stack_trace_tsk+0x22/0x40 [] return_to_handler+0x0/0x27 [] proc_pid_stack+0xb9/0x110 [] return_to_handler+0x0/0x27 [] proc_single_show+0x54/0x80 [] return_to_handler+0x0/0x27 [] seq_read+0x108/0x3e0 [] return_to_handler+0x0/0x27 [] __vfs_read+0x37/0x140 [] return_to_handler+0x0/0x27 [] vfs_read+0x99/0x140 [] 0xffffffffffffffff Enabling function graph tracing causes the stack trace to change in two ways: First, the real call addresses are confusingly interspersed with 'return_to_handler' addresses. This issue will be fixed by the next patch. Second, the stack trace is offset by two frames, because the unwinder skipped the first two frames and got out of sync with the ret_stack index. This patch fixes this issue. Signed-off-by: Josh Poimboeuf Acked-by: Steven Rostedt Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/a6d623e36f8d08f9a17bd74d804d201177a23afd.1471607358.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/ftrace.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 37f67cbba1c6..eccd0ac6bc38 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -14,6 +14,8 @@ #define ARCH_SUPPORTS_FTRACE_OPS 1 #endif +#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + #ifndef __ASSEMBLY__ extern void mcount(void); extern atomic_t modifying_ftrace_code; -- cgit From 7b32aeadbc95d4a41402c1c0da6aa3ab51af4c10 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:18 -0400 Subject: sched/x86: Add 'struct inactive_task_frame' to better document the sleeping task stack frame Add 'struct inactive_task_frame', which defines the layout of the stack for a sleeping process. For now, the only defined field is the BP register (frame pointer). Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-4-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 4 ++-- arch/x86/include/asm/switch_to.h | 5 +++++ 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 0944218af9e2..7646fb2772f8 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -8,6 +8,7 @@ #include #include +#include extern int kstack_depth_to_print; @@ -70,8 +71,7 @@ stack_frame(struct task_struct *task, struct pt_regs *regs) return bp; } - /* bp is the last reg pushed by switch_to */ - return *(unsigned long *)task->thread.sp; + return ((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 14e4b20f0aaf..ec689c62c01f 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -30,6 +30,11 @@ static inline void prepare_switch_to(struct task_struct *prev, #endif } +/* data that is pointed to by thread.sp */ +struct inactive_task_frame { + unsigned long bp; +}; + #ifdef CONFIG_X86_32 #ifdef CONFIG_CC_STACKPROTECTOR -- cgit From 0100301bfdf56a2a370c7157b5ab0fbf9313e1cd Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:19 -0400 Subject: sched/x86: Rewrite the switch_to() code Move the low-level context switch code to an out-of-line asm stub instead of using complex inline asm. This allows constructing a new stack frame for the child process to make it seamlessly flow to ret_from_fork without an extra test and branch in __switch_to(). It also improves code generation for __schedule() by using the C calling convention instead of clobbering all registers. Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-5-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 3 - arch/x86/include/asm/switch_to.h | 139 ++++++------------------------------- arch/x86/include/asm/thread_info.h | 2 - 3 files changed, 21 insertions(+), 123 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 63def9537a2d..6fee8635340b 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -389,9 +389,6 @@ struct thread_struct { unsigned short fsindex; unsigned short gsindex; #endif -#ifdef CONFIG_X86_32 - unsigned long ip; -#endif #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index ec689c62c01f..886d5ea09dba 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -2,8 +2,12 @@ #define _ASM_X86_SWITCH_TO_H struct task_struct; /* one of the stranger aspects of C forward declarations */ + +struct task_struct *__switch_to_asm(struct task_struct *prev, + struct task_struct *next); + __visible struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next); + struct task_struct *next); struct tss_struct; void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss); @@ -32,131 +36,30 @@ static inline void prepare_switch_to(struct task_struct *prev, /* data that is pointed to by thread.sp */ struct inactive_task_frame { +#ifdef CONFIG_X86_64 + unsigned long r15; + unsigned long r14; + unsigned long r13; + unsigned long r12; +#else + unsigned long si; + unsigned long di; +#endif + unsigned long bx; unsigned long bp; + unsigned long ret_addr; }; -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movl %P[task_canary](%[next]), %%ebx\n\t" \ - "movl %%ebx, "__percpu_arg([stack_canary])"\n\t" -#define __switch_canary_oparam \ - , [stack_canary] "=m" (stack_canary.canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ +struct fork_frame { + struct inactive_task_frame frame; + struct pt_regs regs; +}; -/* - * Saving eflags is important. It switches not only IOPL between tasks, - * it also protects other tasks from NT leaking through sysenter etc. - */ #define switch_to(prev, next, last) \ do { \ - /* \ - * Context-switching clobbers all registers, so we clobber \ - * them explicitly, via unused output variables. \ - * (EAX and EBP is not listed because EBP is saved/restored \ - * explicitly for wchan access and EAX is the return value of \ - * __switch_to()) \ - */ \ - unsigned long ebx, ecx, edx, esi, edi; \ - \ prepare_switch_to(prev, next); \ \ - asm volatile("pushl %%ebp\n\t" /* save EBP */ \ - "movl %%esp,%[prev_sp]\n\t" /* save ESP */ \ - "movl %[next_sp],%%esp\n\t" /* restore ESP */ \ - "movl $1f,%[prev_ip]\n\t" /* save EIP */ \ - "pushl %[next_ip]\n\t" /* restore EIP */ \ - __switch_canary \ - "jmp __switch_to\n" /* regparm call */ \ - "1:\t" \ - "popl %%ebp\n\t" /* restore EBP */ \ - \ - /* output parameters */ \ - : [prev_sp] "=m" (prev->thread.sp), \ - [prev_ip] "=m" (prev->thread.ip), \ - "=a" (last), \ - \ - /* clobbered output registers: */ \ - "=b" (ebx), "=c" (ecx), "=d" (edx), \ - "=S" (esi), "=D" (edi) \ - \ - __switch_canary_oparam \ - \ - /* input parameters: */ \ - : [next_sp] "m" (next->thread.sp), \ - [next_ip] "m" (next->thread.ip), \ - \ - /* regparm parameters for __switch_to(): */ \ - [prev] "a" (prev), \ - [next] "d" (next) \ - \ - __switch_canary_iparam \ - \ - : /* reloaded segment registers */ \ - "memory"); \ + ((last) = __switch_to_asm((prev), (next))); \ } while (0) -#else /* CONFIG_X86_32 */ - -/* frame pointer must be last for get_wchan */ -#define SAVE_CONTEXT "pushq %%rbp ; movq %%rsi,%%rbp\n\t" -#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t" - -#define __EXTRA_CLOBBER \ - , "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \ - "r12", "r13", "r14", "r15", "flags" - -#ifdef CONFIG_CC_STACKPROTECTOR -#define __switch_canary \ - "movq %P[task_canary](%%rsi),%%r8\n\t" \ - "movq %%r8,"__percpu_arg([gs_canary])"\n\t" -#define __switch_canary_oparam \ - , [gs_canary] "=m" (irq_stack_union.stack_canary) -#define __switch_canary_iparam \ - , [task_canary] "i" (offsetof(struct task_struct, stack_canary)) -#else /* CC_STACKPROTECTOR */ -#define __switch_canary -#define __switch_canary_oparam -#define __switch_canary_iparam -#endif /* CC_STACKPROTECTOR */ - -/* - * There is no need to save or restore flags, because flags are always - * clean in kernel mode, with the possible exception of IOPL. Kernel IOPL - * has no effect. - */ -#define switch_to(prev, next, last) \ - prepare_switch_to(prev, next); \ - \ - asm volatile(SAVE_CONTEXT \ - "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */ \ - "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */ \ - "call __switch_to\n\t" \ - "movq "__percpu_arg([current_task])",%%rsi\n\t" \ - __switch_canary \ - "movq %P[thread_info](%%rsi),%%r8\n\t" \ - "movq %%rax,%%rdi\n\t" \ - "testl %[_tif_fork],%P[ti_flags](%%r8)\n\t" \ - "jnz ret_from_fork\n\t" \ - RESTORE_CONTEXT \ - : "=a" (last) \ - __switch_canary_oparam \ - : [next] "S" (next), [prev] "D" (prev), \ - [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \ - [ti_flags] "i" (offsetof(struct thread_info, flags)), \ - [_tif_fork] "i" (_TIF_FORK), \ - [thread_info] "i" (offsetof(struct task_struct, stack)), \ - [current_task] "m" (current_task) \ - __switch_canary_iparam \ - : "memory", "cc" __EXTRA_CLOBBER) - -#endif /* CONFIG_X86_32 */ - #endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 8b7c8d8e0852..494c4b5ada34 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -95,7 +95,6 @@ struct thread_info { #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ #define TIF_IA32 17 /* IA32 compatibility process */ -#define TIF_FORK 18 /* ret_from_fork */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ @@ -119,7 +118,6 @@ struct thread_info { #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_NOTSC (1 << TIF_NOTSC) #define _TIF_IA32 (1 << TIF_IA32) -#define _TIF_FORK (1 << TIF_FORK) #define _TIF_NOHZ (1 << TIF_NOHZ) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) -- cgit From 616d24835eeafa8ef3466479db028abfdfc77531 Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:20 -0400 Subject: sched/x86: Pass kernel thread parameters in 'struct fork_frame' Instead of setting up a fake pt_regs context, put the kernel thread function pointer and arg into the unused callee-restored registers of 'struct fork_frame'. Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-6-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/switch_to.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 886d5ea09dba..5cb436acd463 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -34,6 +34,8 @@ static inline void prepare_switch_to(struct task_struct *prev, #endif } +asmlinkage void ret_from_fork(void); + /* data that is pointed to by thread.sp */ struct inactive_task_frame { #ifdef CONFIG_X86_64 -- cgit From ffcb043ba524d3fbd979a9dac2c9ce8ad352000d Mon Sep 17 00:00:00 2001 From: Brian Gerst Date: Sat, 13 Aug 2016 12:38:21 -0400 Subject: sched/x86: Fix thread_saved_pc() thread_saved_pc() was using a completely bogus method to get the return address. Since switch_to() was previously inlined, there was no sane way to know where on the stack the return address was stored. Now with the frame of a sleeping thread well defined, this can be implemented correctly. Signed-off-by: Brian Gerst Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1471106302-10159-7-git-send-email-brgerst@gmail.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 6fee8635340b..b22fb5a4ff3c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -721,8 +721,6 @@ static inline void spin_lock_prefetch(const void *x) .addr_limit = KERNEL_DS, \ } -extern unsigned long thread_saved_pc(struct task_struct *tsk); - /* * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack. * This is necessary to guarantee that the entire "struct pt_regs" @@ -773,17 +771,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk); .addr_limit = KERNEL_DS, \ } -/* - * Return saved PC of a blocked thread. - * What is this good for? it will be always the scheduler or ret_from_fork. - */ -#define thread_saved_pc(t) READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8)) - #define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.sp0 - 1) extern unsigned long KSTK_ESP(struct task_struct *task); #endif /* CONFIG_X86_64 */ +extern unsigned long thread_saved_pc(struct task_struct *tsk); + extern void start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp); -- cgit From 6271cfdfc0e4731b76921ef02fdd87409d71dfdf Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 30 Aug 2016 17:27:57 -0700 Subject: x86/mm: Improve stack-overflow #PF handling If we get a page fault indicating kernel stack overflow, invoke handle_stack_overflow(). To prevent us from overflowing the stack again while handling the overflow (because we are likely to have very little stack space left), call handle_stack_overflow() on the double-fault stack. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/6d6cf96b3fb9b4c9aa303817e1dc4de0c7c36487.1472603235.git.luto@kernel.org [ Minor edit. ] Signed-off-by: Ingo Molnar --- arch/x86/include/asm/traps.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index c3496619740a..01fd0a7f48cd 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -117,6 +117,12 @@ extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); extern void ist_end_non_atomic(void); +#ifdef CONFIG_VMAP_STACK +void __noreturn handle_stack_overflow(const char *message, + struct pt_regs *regs, + unsigned long fault_address); +#endif + /* Interrupts/Exceptions */ enum { X86_TRAP_DE = 0, /* 0, Divide-by-zero */ -- cgit From 4b8afafbe743be1a81c96ddcd75b19c534d5e262 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 24 Aug 2016 11:50:17 -0500 Subject: x86/dumpstack: Add get_stack_pointer() and get_frame_pointer() The various functions involved in dumping the stack all do similar things with regard to getting the stack pointer and the frame pointer based on the regs and task arguments. Create helper functions to do that instead. Signed-off-by: Josh Poimboeuf Reviewed-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Brian Gerst Cc: Byungchul Park Cc: Frederic Weisbecker Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/f448914885a35f333fe04da1b97a6c2cc1f80974.1472057064.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 41 ++++++++++++++++++++++----------------- 1 file changed, 23 insertions(+), 18 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 7646fb2772f8..3552f5e7189e 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -50,36 +50,41 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, #ifdef CONFIG_X86_32 #define STACKSLOTS_PER_LINE 8 -#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) #else #define STACKSLOTS_PER_LINE 4 -#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) #endif #ifdef CONFIG_FRAME_POINTER -static inline unsigned long -stack_frame(struct task_struct *task, struct pt_regs *regs) +static inline unsigned long * +get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { - unsigned long bp; - if (regs) - return regs->bp; + return (unsigned long *)regs->bp; - if (task == current) { - /* Grab bp right from our regs */ - get_bp(bp); - return bp; - } + if (!task || task == current) + return __builtin_frame_address(0); - return ((struct inactive_task_frame *)task->thread.sp)->bp; + return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; } #else -static inline unsigned long -stack_frame(struct task_struct *task, struct pt_regs *regs) +static inline unsigned long * +get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { - return 0; + return NULL; +} +#endif /* CONFIG_FRAME_POINTER */ + +static inline unsigned long * +get_stack_pointer(struct task_struct *task, struct pt_regs *regs) +{ + if (regs) + return (unsigned long *)kernel_stack_pointer(regs); + + if (!task || task == current) + return __builtin_frame_address(0); + + return (unsigned long *)task->thread.sp; } -#endif extern void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, @@ -106,7 +111,7 @@ static inline unsigned long caller_frame_pointer(void) { struct stack_frame *frame; - get_bp(frame); + frame = __builtin_frame_address(0); #ifdef CONFIG_FRAME_POINTER frame = frame->next_frame; -- cgit From cb76c93982404273d746f3ccd5085b47689099a8 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 14 Sep 2016 21:07:42 -0500 Subject: x86/dumpstack: Add get_stack_info() interface valid_stack_ptr() is buggy: it assumes that all stacks are of size THREAD_SIZE, which is not true for exception stacks. So the walk_stack() callbacks will need to know the location of the beginning of the stack as well as the end. Another issue is that in general the various features of a stack (type, size, next stack pointer, description string) are scattered around in various places throughout the stack dump code. Encapsulate all that information in a single place with a new stack_info struct and a get_stack_info() interface. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/8164dd0db96b7e6a279fa17ae5e6dc375eecb4a9.1473905218.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 41 +++++++++++++++++++++++++++++++++++---- 1 file changed, 37 insertions(+), 4 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 3552f5e7189e..780a83efcfd3 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -10,6 +10,39 @@ #include #include +enum stack_type { + STACK_TYPE_UNKNOWN, + STACK_TYPE_TASK, + STACK_TYPE_IRQ, + STACK_TYPE_SOFTIRQ, + STACK_TYPE_EXCEPTION, + STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, +}; + +struct stack_info { + enum stack_type type; + unsigned long *begin, *end, *next_sp; +}; + +bool in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info); + +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask); + +void stack_type_str(enum stack_type type, const char **begin, + const char **end); + +static inline bool on_stack(struct stack_info *info, void *addr, size_t len) +{ + void *begin = info->begin; + void *end = info->end; + + return (info->type != STACK_TYPE_UNKNOWN && + addr >= begin && addr < end && + addr + len > begin && addr + len <= end); +} + extern int kstack_depth_to_print; struct thread_info; @@ -20,27 +53,27 @@ typedef unsigned long (*walk_stack_t)(struct task_struct *task, unsigned long bp, const struct stacktrace_ops *ops, void *data, - unsigned long *end, + struct stack_info *info, int *graph); extern unsigned long print_context_stack(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph); + struct stack_info *info, int *graph); extern unsigned long print_context_stack_bp(struct task_struct *task, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data, - unsigned long *end, int *graph); + struct stack_info *info, int *graph); /* Generic stack tracer with callbacks */ struct stacktrace_ops { int (*address)(void *data, unsigned long address, int reliable); /* On negative return stop dumping */ - int (*stack)(void *data, char *name); + int (*stack)(void *data, const char *name); walk_stack_t walk_stack; }; -- cgit From b9d989c7218ac922185d82ad46f3e58b27a4bea9 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 13 Sep 2016 14:29:21 -0700 Subject: x86/asm: Move the thread_info::status field to thread_struct Because sched.h and thread_info.h are a tangled mess, I turned in_compat_syscall() into a macro. If we had current_thread_struct() or similar and we could use it from thread_info.h, then this would be a bit cleaner. Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jann Horn Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/ccc8a1b2f41f9c264a41f771bb4a6539a642ad72.1473801993.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 12 ++++++++++++ arch/x86/include/asm/syscall.h | 20 +++++--------------- arch/x86/include/asm/thread_info.h | 23 ++++------------------- 3 files changed, 21 insertions(+), 34 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index b22fb5a4ff3c..984a7bf17f6a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -389,6 +389,9 @@ struct thread_struct { unsigned short fsindex; unsigned short gsindex; #endif + + u32 status; /* thread synchronous flags */ + #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -434,6 +437,15 @@ struct thread_struct { */ }; +/* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + /* * Set IOPL bits in EFLAGS from given mask */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 4e23dd15c661..e3c95e8e61c5 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task, * TS_COMPAT is set for 32-bit syscall entries and then * remains set until we return to user mode. */ - if (task_thread_info(task)->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) /* * Sign-extend the value so (int)-EFOO becomes (long)-EFOO * and will match correctly in comparisons. @@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task_thread_info(task)->status & TS_COMPAT) + if (task->thread.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task_thread_info(task)->status & TS_COMPAT) + if (task->thread.status & TS_COMPAT) switch (i) { case 0: if (!n--) break; @@ -234,18 +234,8 @@ static inline void syscall_set_arguments(struct task_struct *task, static inline int syscall_get_arch(void) { -#ifdef CONFIG_IA32_EMULATION - /* - * TS_COMPAT is set for 32-bit syscall entry and then - * remains set until we return to user mode. - * - * x32 tasks should be considered AUDIT_ARCH_X86_64. - */ - if (task_thread_info(current)->status & TS_COMPAT) - return AUDIT_ARCH_I386; -#endif - /* Both x32 and x86_64 are considered "64-bit". */ - return AUDIT_ARCH_X86_64; + /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ + return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 494c4b5ada34..c9dcfe7c7e4b 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -55,7 +55,6 @@ struct task_struct; struct thread_info { struct task_struct *task; /* main task structure */ __u32 flags; /* low level flags */ - __u32 status; /* thread synchronous flags */ __u32 cpu; /* current CPU */ }; @@ -253,31 +252,17 @@ static inline int arch_within_stack_frames(const void * const stack, #endif -/* - * Thread-synchronous status. - * - * This is different from the flags in that nobody else - * ever touches our thread-synchronous status, so we don't - * have to worry about atomic accesses. - */ -#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ #ifdef CONFIG_COMPAT #define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ #endif - #ifndef __ASSEMBLY__ -static inline bool in_ia32_syscall(void) -{ #ifdef CONFIG_X86_32 - return true; -#endif -#ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & TS_COMPAT) - return true; +#define in_ia32_syscall() true +#else +#define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ + current->thread.status & TS_COMPAT) #endif - return false; -} /* * Force syscall return via IRET by making it look as if there was -- cgit From 15f4eae70d365bba26854c90b6002aaabb18c8aa Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 13 Sep 2016 14:29:25 -0700 Subject: x86: Move thread_info into task_struct Now that most of the thread_info users have been cleaned up, this is straightforward. Most of this code was written by Linus. Originally-from: Linus Torvalds Signed-off-by: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Jann Horn Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/a50eab40abeaec9cb9a9e3cbdeafd32190206654.1473801993.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/thread_info.h | 46 -------------------------------------- 1 file changed, 46 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index c9dcfe7c7e4b..2aaca53c0974 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -52,20 +52,6 @@ struct task_struct; #include #include -struct thread_info { - struct task_struct *task; /* main task structure */ - __u32 flags; /* low level flags */ - __u32 cpu; /* current CPU */ -}; - -#define INIT_THREAD_INFO(tsk) \ -{ \ - .task = &tsk, \ - .flags = 0, \ - .cpu = 0, \ -} - -#define init_thread_info (init_thread_union.thread_info) #define init_stack (init_thread_union.stack) #else /* !__ASSEMBLY__ */ @@ -157,11 +143,6 @@ struct thread_info { */ #ifndef __ASSEMBLY__ -static inline struct thread_info *current_thread_info(void) -{ - return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE); -} - static inline unsigned long current_stack_pointer(void) { unsigned long sp; @@ -223,33 +204,6 @@ static inline int arch_within_stack_frames(const void * const stack, # define cpu_current_top_of_stack (cpu_tss + TSS_sp0) #endif -/* - * ASM operand which evaluates to a 'thread_info' address of - * the current task, if it is known that "reg" is exactly "off" - * bytes below the top of the stack currently. - * - * ( The kernel stack's size is known at build time, it is usually - * 2 or 4 pages, and the bottom of the kernel stack contains - * the thread_info structure. So to access the thread_info very - * quickly from assembly code we can calculate down from the - * top of the kernel stack to the bottom, using constant, - * build-time calculations only. ) - * - * For example, to fetch the current thread_info->flags value into %eax - * on x86-64 defconfig kernels, in syscall entry code where RSP is - * currently at exactly SIZEOF_PTREGS bytes away from the top of the - * stack: - * - * mov ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS), %eax - * - * will translate to: - * - * 8b 84 24 b8 c0 ff ff mov -0x3f48(%rsp), %eax - * - * which is below the current RSP by almost 16K. - */ -#define ASM_THREAD_INFO(field, reg, off) ((field)+(off)-THREAD_SIZE)(reg) - #endif #ifdef CONFIG_COMPAT -- cgit From 81539169f283329fd8bc58457cc15754f683ba69 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 16 Sep 2016 08:05:20 -0500 Subject: x86/dumpstack: Remove NULL task pointer convention show_stack_log_lvl() and friends allow a NULL pointer for the task_struct to indicate the current task. This creates confusion and can cause sneaky bugs. Instead require the caller to pass 'current' directly. This only changes the internal workings of the dumpstack code. The dump_trace() and show_stack() interfaces still allow a NULL task pointer. Those interfaces should also probably be fixed as well. Signed-off-by: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 780a83efcfd3..ed2be1b5ada8 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -94,7 +94,7 @@ get_frame_pointer(struct task_struct *task, struct pt_regs *regs) if (regs) return (unsigned long *)regs->bp; - if (!task || task == current) + if (task == current) return __builtin_frame_address(0); return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp; @@ -113,7 +113,7 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs) if (regs) return (unsigned long *)kernel_stack_pointer(regs); - if (!task || task == current) + if (task == current) return __builtin_frame_address(0); return (unsigned long *)task->thread.sp; -- cgit From 7c7900f89770d7fba96100d8a9e18043a1af3973 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 16 Sep 2016 14:18:12 -0500 Subject: x86/unwind: Add new unwind interface and implementations The x86 stack dump code is a bit of a mess. dump_trace() uses callbacks, and each user of it seems to have slightly different requirements, so there are several slightly different callbacks floating around. Also there are some upcoming features which will need more changes to the stack dump code, including the printing of stack pt_regs, reliable stack detection for live patching, and a DWARF unwinder. Each of those features would at least need more callbacks and/or callback interfaces, resulting in a much bigger mess than what we have today. Before doing all that, we should try to clean things up and replace dump_trace() with something cleaner and more flexible. The new unwinder is a simple state machine which was heavily inspired by a suggestion from Andy Lutomirski: https://lkml.kernel.org/r/CALCETrUbNTqaM2LRyXGRx=kVLRPeY5A3Pc6k4TtQxF320rUT=w@mail.gmail.com It's also similar to the libunwind API: http://www.nongnu.org/libunwind/man/libunwind(3).html Some if its advantages: - Simplicity: no more callback sprawl and less code duplication. - Flexibility: it allows the caller to stop and inspect the stack state at each step in the unwinding process. - Modularity: the unwinder code, console stack dump code, and stack metadata analysis code are all better separated so that changing one of them shouldn't have much of an impact on any of the others. Two implementations are added which conform to the new unwind interface: - The frame pointer unwinder which is used for CONFIG_FRAME_POINTER=y. - The "guess" unwinder which is used for CONFIG_FRAME_POINTER=n. This isn't an "unwinder" per se. All it does is scan the stack for kernel text addresses. But with no frame pointers, guesses are better than nothing in most cases. Suggested-by: Andy Lutomirski Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/6dc2f909c47533d213d0505f0a113e64585bec82.1474045023.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/unwind.h | 73 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 arch/x86/include/asm/unwind.h (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h new file mode 100644 index 000000000000..c4b6d1cafa46 --- /dev/null +++ b/arch/x86/include/asm/unwind.h @@ -0,0 +1,73 @@ +#ifndef _ASM_X86_UNWIND_H +#define _ASM_X86_UNWIND_H + +#include +#include +#include +#include + +struct unwind_state { + struct stack_info stack_info; + unsigned long stack_mask; + struct task_struct *task; + int graph_idx; +#ifdef CONFIG_FRAME_POINTER + unsigned long *bp; +#else + unsigned long *sp; +#endif +}; + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame); + +bool unwind_next_frame(struct unwind_state *state); + +static inline bool unwind_done(struct unwind_state *state) +{ + return state->stack_info.type == STACK_TYPE_UNKNOWN; +} + +static inline +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + first_frame = first_frame ? : get_stack_pointer(task, regs); + + __unwind_start(state, task, regs, first_frame); +} + +#ifdef CONFIG_FRAME_POINTER + +static inline +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + if (unwind_done(state)) + return NULL; + + return state->bp + 1; +} + +unsigned long unwind_get_return_address(struct unwind_state *state); + +#else /* !CONFIG_FRAME_POINTER */ + +static inline +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state) +{ + return NULL; +} + +static inline +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + if (unwind_done(state)) + return 0; + + return ftrace_graph_ret_addr(state->task, &state->graph_idx, + *state->sp, state->sp); +} + +#endif /* CONFIG_FRAME_POINTER */ + +#endif /* _ASM_X86_UNWIND_H */ -- cgit From e18bcccd1a4ecb41e99678e002ef833586185bf1 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 16 Sep 2016 14:18:16 -0500 Subject: x86/dumpstack: Convert show_trace_log_lvl() to use the new unwinder Convert show_trace_log_lvl() to use the new unwinder. dump_trace() has been deprecated. show_trace_log_lvl() is special compared to other users of the unwinder. It's the only place where both reliable *and* unreliable addresses are needed. With frame pointers enabled, most callers of the unwinder don't want to know about unreliable addresses. But in this case, when we're dumping the stack to the console because something presumably went wrong, the unreliable addresses are useful: - They show stale data on the stack which can provide useful clues. - If something goes wrong with the unwinder, or if frame pointers are corrupt or missing, all the stack addresses still get shown. So in order to show all addresses on the stack, and at the same time figure out which addresses are reliable, we have to do the scanning and the unwinding in parallel. The scanning is done with the help of get_stack_info() to traverse the stacks. The unwinding is done separately by the new unwinder. In theory we could simplify show_trace_log_lvl() by instead pushing some of this logic into the unwind code. But then we would need some kind of "fake" frame logic in the unwinder which would add a lot of complexity and wouldn't be worth it in order to support only one user. Another benefit of this approach is that once we have a DWARF unwinder, we should be able to just plug it in with minimal impact to this code. Another change here is that callers of show_trace_log_lvl() don't need to provide the 'bp' argument. The unwinder already finds the relevant frame pointer by unwinding until it reaches the first frame after the provided stack pointer. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/703b5998604c712a1f801874b43f35d6dac52ede.1474045023.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index ed2be1b5ada8..c9ccf0676ca6 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -119,13 +119,11 @@ get_stack_pointer(struct task_struct *task, struct pt_regs *regs) return (unsigned long *)task->thread.sp; } -extern void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl); +void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, char *log_lvl); -extern void -show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *sp, unsigned long bp, char *log_lvl); +void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, char *log_lvl); extern unsigned int code_bytes; -- cgit From c8fe4609827aedc9c4b45de80e7cdc8ccfa8541b Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 16 Sep 2016 14:18:17 -0500 Subject: x86/dumpstack: Remove dump_trace() and related callbacks All previous users of dump_trace() have been converted to use the new unwind interfaces, so we can remove it and the related print_context_stack() and print_context_stack_bp() callback functions. Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Byungchul Park Cc: Denys Vlasenko Cc: Frederic Weisbecker Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Nilay Vaish Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/5b97da3572b40b5a4d8e185cf2429308d0987a13.1474045023.git.jpoimboe@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/stacktrace.h | 36 ------------------------------------ 1 file changed, 36 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index c9ccf0676ca6..37f2e0b377ad 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -45,42 +45,6 @@ static inline bool on_stack(struct stack_info *info, void *addr, size_t len) extern int kstack_depth_to_print; -struct thread_info; -struct stacktrace_ops; - -typedef unsigned long (*walk_stack_t)(struct task_struct *task, - unsigned long *stack, - unsigned long bp, - const struct stacktrace_ops *ops, - void *data, - struct stack_info *info, - int *graph); - -extern unsigned long -print_context_stack(struct task_struct *task, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - struct stack_info *info, int *graph); - -extern unsigned long -print_context_stack_bp(struct task_struct *task, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data, - struct stack_info *info, int *graph); - -/* Generic stack tracer with callbacks */ - -struct stacktrace_ops { - int (*address)(void *data, unsigned long address, int reliable); - /* On negative return stop dumping */ - int (*stack)(void *data, const char *name); - walk_stack_t walk_stack; -}; - -void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data); - #ifdef CONFIG_X86_32 #define STACKSLOTS_PER_LINE 8 #else -- cgit From 317c2ce77d8ab73c24f4fb9c75e5bb441fbe3e30 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 23 Sep 2016 16:49:39 -0500 Subject: x86/alternatives: Add stack frame dependency to alternative_call_2() Linus reported the following objtool warning: kernel/signal.o: warning: objtool: .altinstr_replacement+0x54: call without frame pointer save/setup The warning is valid. It's caused by the fact that gcc placed the call instruction in alternative_call_2()'s inline asm before the frame pointer setup, which breaks frame pointer convention and can result in a bad stack trace. Force a stack frame to be created before the call instruction by listing the stack pointer as an output operand in the inline asm statement. Reported-and-tested-by: Linus Torvalds Signed-off-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160923214939.j5o7c67nhepzmh3t@treble Signed-off-by: Ingo Molnar --- arch/x86/include/asm/alternative.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index e77a6443104f..1b020381ab38 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -217,10 +217,14 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2, \ output, input...) \ +{ \ + register void *__sp asm(_ASM_SP); \ asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\ "call %P[new2]", feature2) \ - : output : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ - [new2] "i" (newfunc2), ## input) + : output, "+r" (__sp) \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ + [new2] "i" (newfunc2), ## input); \ +} /* * use this macro(s) if you need more than one output parameter -- cgit From 1ef55be16ed69538f89e0a6508be5e62fdc9851c Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Thu, 29 Sep 2016 12:48:12 -0700 Subject: x86/asm: Get rid of __read_cr4_safe() We use __read_cr4() vs __read_cr4_safe() inconsistently. On CR4-less CPUs, all CR4 bits are effectively clear, so we can make the code simpler and more robust by making __read_cr4() always fix up faults on 32-bit kernels. This may fix some bugs on old 486-like CPUs, but I don't have any easy way to test that. Signed-off-by: Andy Lutomirski Cc: Brian Gerst Cc: Borislav Petkov Cc: david@saggiorato.net Link: http://lkml.kernel.org/r/ea647033d357d9ce2ad2bbde5a631045f5052fb6.1475178370.git.luto@kernel.org Signed-off-by: Thomas Gleixner --- arch/x86/include/asm/paravirt.h | 4 ---- arch/x86/include/asm/paravirt_types.h | 1 - arch/x86/include/asm/special_insns.h | 22 +++++++--------------- arch/x86/include/asm/tlbflush.h | 2 +- 4 files changed, 8 insertions(+), 21 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 2970d22d7766..91b6f4eed3fd 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -80,10 +80,6 @@ static inline unsigned long __read_cr4(void) { return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4); } -static inline unsigned long __read_cr4_safe(void) -{ - return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe); -} static inline void __write_cr4(unsigned long x) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 7fa9e7740ba3..fcf243f077ac 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -108,7 +108,6 @@ struct pv_cpu_ops { unsigned long (*read_cr0)(void); void (*write_cr0)(unsigned long); - unsigned long (*read_cr4_safe)(void); unsigned long (*read_cr4)(void); void (*write_cr4)(unsigned long); diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 587d7914ea4b..19a2224f9e16 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -59,22 +59,19 @@ static inline void native_write_cr3(unsigned long val) static inline unsigned long native_read_cr4(void) { unsigned long val; - asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); - return val; -} - -static inline unsigned long native_read_cr4_safe(void) -{ - unsigned long val; - /* This could fault if %cr4 does not exist. In x86_64, a cr4 always - * exists, so it will never fail. */ #ifdef CONFIG_X86_32 + /* + * This could fault if CR4 does not exist. Non-existent CR4 + * is functionally equivalent to CR4 == 0. Keep it simple and pretend + * that CR4 == 0 on CPUs that don't have CR4. + */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val), "=m" (__force_order) : "0" (0)); #else - val = native_read_cr4(); + /* CR4 always exists on x86_64. */ + asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); #endif return val; } @@ -182,11 +179,6 @@ static inline unsigned long __read_cr4(void) return native_read_cr4(); } -static inline unsigned long __read_cr4_safe(void) -{ - return native_read_cr4_safe(); -} - static inline void __write_cr4(unsigned long x) { native_write_cr4(x); diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index dee8a70382ba..6fa85944af83 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -81,7 +81,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); /* Initialize cr4 shadow for this CPU. */ static inline void cr4_init_shadow(void) { - this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe()); + this_cpu_write(cpu_tlbstate.cr4, __read_cr4()); } /* Set in this cpu's CR4. */ -- cgit