diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-04 02:13:28 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-10-04 02:13:28 +0300 |
| commit | 1a4a2bc460721bc8f91e4c1294d39b38e5af132f (patch) | |
| tree | fe646d05f6e17f05601e0a32cc796bec718ab6e7 | |
| parent | 110a9e42b68719f584879c5c5c727bbae90d15f9 (diff) | |
| parent | 1ef55be16ed69538f89e0a6508be5e62fdc9851c (diff) | |
| download | linux-1a4a2bc460721bc8f91e4c1294d39b38e5af132f.tar.xz | |
Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull low-level x86 updates from Ingo Molnar:
"In this cycle this topic tree has become one of those 'super topics'
that accumulated a lot of changes:
- Add CONFIG_VMAP_STACK=y support to the core kernel and enable it on
x86 - preceded by an array of changes. v4.8 saw preparatory changes
in this area already - this is the rest of the work. Includes the
thread stack caching performance optimization. (Andy Lutomirski)
- switch_to() cleanups and all around enhancements. (Brian Gerst)
- A large number of dumpstack infrastructure enhancements and an
unwinder abstraction. The secret long term plan is safe(r) live
patching plus maybe another attempt at debuginfo based unwinding -
but all these current bits are standalone enhancements in a frame
pointer based debug environment as well. (Josh Poimboeuf)
- More __ro_after_init and const annotations. (Kees Cook)
- Enable KASLR for the vmemmap memory region. (Thomas Garnier)"
[ The virtually mapped stack changes are pretty fundamental, and not
x86-specific per se, even if they are only used on x86 right now. ]
* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
x86/asm: Get rid of __read_cr4_safe()
thread_info: Use unsigned long for flags
x86/alternatives: Add stack frame dependency to alternative_call_2()
x86/dumpstack: Fix show_stack() task pointer regression
x86/dumpstack: Remove dump_trace() and related callbacks
x86/dumpstack: Convert show_trace_log_lvl() to use the new unwinder
oprofile/x86: Convert x86_backtrace() to use the new unwinder
x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder
perf/x86: Convert perf_callchain_kernel() to use the new unwinder
x86/unwind: Add new unwind interface and implementations
x86/dumpstack: Remove NULL task pointer convention
fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y
sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK
lib/syscall: Pin the task stack in collect_syscall()
x86/process: Pin the target stack in get_wchan()
x86/dumpstack: Pin the target stack when dumping it
kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function
sched/core: Add try_get_task_stack() and put_task_stack()
x86/entry/64: Fix a minor comment rebase error
iommu/amd: Don't put completion-wait semaphore on stack
...
114 files changed, 1722 insertions, 1108 deletions
diff --git a/Documentation/trace/ftrace-design.txt b/Documentation/trace/ftrace-design.txt index dd5f916b351d..a273dd0bbaaa 100644 --- a/Documentation/trace/ftrace-design.txt +++ b/Documentation/trace/ftrace-design.txt @@ -203,6 +203,17 @@ along to ftrace_push_return_trace() instead of a stub value of 0. Similarly, when you call ftrace_return_to_handler(), pass it the frame pointer. +HAVE_FUNCTION_GRAPH_RET_ADDR_PTR +-------------------------------- + +An arch may pass in a pointer to the return address on the stack. This +prevents potential stack unwinding issues where the unwinder gets out of +sync with ret_stack and the wrong addresses are reported by +ftrace_graph_ret_addr(). + +Adding support for it is easy: just define the macro in asm/ftrace.h and +pass the return address pointer as the 'retp' argument to +ftrace_push_return_trace(). HAVE_FTRACE_NMI_ENTER --------------------- diff --git a/arch/Kconfig b/arch/Kconfig index fd6e9712af81..180ea33164dc 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -696,4 +696,38 @@ config ARCH_NO_COHERENT_DMA_MMAP config CPU_NO_EFFICIENT_FFS def_bool n +config HAVE_ARCH_VMAP_STACK + def_bool n + help + An arch should select this symbol if it can support kernel stacks + in vmalloc space. This means: + + - vmalloc space must be large enough to hold many kernel stacks. + This may rule out many 32-bit architectures. + + - Stacks in vmalloc space need to work reliably. For example, if + vmap page tables are created on demand, either this mechanism + needs to work while the stack points to a virtual address with + unpopulated page tables or arch code (switch_to() and switch_mm(), + most likely) needs to ensure that the stack's page table entries + are populated before running on a possibly unpopulated stack. + + - If the stack overflows into a guard page, something reasonable + should happen. The definition of "reasonable" is flexible, but + instantly rebooting without logging anything would be unfriendly. + +config VMAP_STACK + default y + bool "Use a virtually-mapped stack" + depends on HAVE_ARCH_VMAP_STACK && !KASAN + ---help--- + Enable this if you want the use virtually-mapped kernel stacks + with guard pages. This causes kernel stack overflows to be + caught immediately rather than causing difficult-to-diagnose + corruption. + + This is presently incompatible with KASAN because KASAN expects + the stack to map directly to the KASAN shadow map using a formula + that is incorrect if the stack is in vmalloc space. + source "kernel/gcov/Kconfig" diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 709ee1d6d4df..3f1759411d51 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -218,7 +218,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, } err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer); + frame_pointer, NULL); if (err == -EBUSY) { *parent = old; return; diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 0f03a8fe2314..aef02d2af3b5 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -219,7 +219,7 @@ ENDPROC(ftrace_graph_caller) * * Run ftrace_return_to_handler() before going back to parent. * @fp is checked against the value passed by ftrace_graph_caller() - * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled. + * only when HAVE_FUNCTION_GRAPH_FP_TEST is enabled. */ ENTRY(return_to_handler) save_return_regs diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index ebecf9aa33d1..40ad08ac569a 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -138,7 +138,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, return; err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer); + frame_pointer, NULL); if (err == -EBUSY) return; else diff --git a/arch/blackfin/kernel/ftrace-entry.S b/arch/blackfin/kernel/ftrace-entry.S index 28d059540424..3b8bdcbb7da3 100644 --- a/arch/blackfin/kernel/ftrace-entry.S +++ b/arch/blackfin/kernel/ftrace-entry.S @@ -169,7 +169,7 @@ ENTRY(_ftrace_graph_caller) r0 = sp; /* unsigned long *parent */ r1 = [sp]; /* unsigned long self_addr */ # endif -# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +# ifdef HAVE_FUNCTION_GRAPH_FP_TEST r2 = fp; /* unsigned long frame_pointer */ # endif r0 += 16; /* skip the 4 local regs on stack */ @@ -190,7 +190,7 @@ ENTRY(_return_to_handler) [--sp] = r1; /* get original return address */ -# ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +# ifdef HAVE_FUNCTION_GRAPH_FP_TEST r0 = fp; /* Blackfin is sane, so omit this */ # endif call _ftrace_return_to_handler; diff --git a/arch/blackfin/kernel/ftrace.c b/arch/blackfin/kernel/ftrace.c index 095de0fa044d..8dad7589b843 100644 --- a/arch/blackfin/kernel/ftrace.c +++ b/arch/blackfin/kernel/ftrace.c @@ -107,7 +107,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, return; if (ftrace_push_return_trace(*parent, self_addr, &trace.depth, - frame_pointer) == -EBUSY) + frame_pointer, NULL) == -EBUSY) return; trace.func = self_addr; diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 29bd59790d6c..c7026429816b 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -56,7 +56,7 @@ struct thread_info { #define alloc_thread_stack_node(tsk, node) ((unsigned long *) 0) #define task_thread_info(tsk) ((struct thread_info *) 0) #endif -#define free_thread_stack(ti) /* nothing */ +#define free_thread_stack(tsk) /* nothing */ #define task_stack_page(tsk) ((void *)(tsk)) #define __HAVE_THREAD_FUNCTIONS diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c index fc7b48a52cd5..d57563c58a26 100644 --- a/arch/microblaze/kernel/ftrace.c +++ b/arch/microblaze/kernel/ftrace.c @@ -63,7 +63,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0); + err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL); if (err == -EBUSY) { *parent = old; return; diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 937c54bc8ccc..30a3b75e88eb 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -382,8 +382,8 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, if (unlikely(faulted)) goto out; - if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp) - == -EBUSY) { + if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp, + NULL) == -EBUSY) { *parent_ra_addr = old_parent_ra; return; } diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index a828a0adf52c..5a5506a35395 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -48,7 +48,7 @@ static void __hot prepare_ftrace_return(unsigned long *parent, return; if (ftrace_push_return_trace(old, self_addr, &trace.depth, - 0 ) == -EBUSY) + 0, NULL) == -EBUSY) return; /* activate parisc_return_to_handler() as return point */ diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c index cc52d9795f88..a95639b8d4ac 100644 --- a/arch/powerpc/kernel/ftrace.c +++ b/arch/powerpc/kernel/ftrace.c @@ -593,7 +593,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) if (!ftrace_graph_entry(&trace)) goto out; - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0, + NULL) == -EBUSY) goto out; parent = return_hooker; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 0f7bfeba6da6..60a8a4e207ed 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -209,7 +209,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) /* Only trace if the calling function expects to. */ if (!ftrace_graph_entry(&trace)) goto out; - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0) == -EBUSY) + if (ftrace_push_return_trace(parent, ip, &trace.depth, 0, + NULL) == -EBUSY) goto out; parent = (unsigned long) return_to_handler; out: diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 38993e09ef03..95eccd49672f 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -382,7 +382,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0); + err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL); if (err == -EBUSY) { __raw_writel(old, parent); return; diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 59b09600dd32..f5d60f14a0bc 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -56,7 +56,6 @@ config SPARC64 def_bool 64BIT select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_KRETPROBES select HAVE_KPROBES select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h index 3192a8e42fd6..62755a339a59 100644 --- a/arch/sparc/include/asm/ftrace.h +++ b/arch/sparc/include/asm/ftrace.h @@ -9,6 +9,10 @@ void _mcount(void); #endif +#endif /* CONFIG_MCOUNT */ + +#if defined(CONFIG_SPARC64) && !defined(CC_USE_FENTRY) +#define HAVE_FUNCTION_GRAPH_FP_TEST #endif #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 0a2d2ddff543..6bcff698069b 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -131,7 +131,7 @@ unsigned long prepare_ftrace_return(unsigned long parent, return parent + 8UL; if (ftrace_push_return_trace(parent, self_addr, &trace.depth, - frame_pointer) == -EBUSY) + frame_pointer, NULL) == -EBUSY) return parent + 8UL; trace.func = self_addr; diff --git a/arch/tile/kernel/ftrace.c b/arch/tile/kernel/ftrace.c index 4a572088b270..b827a418b155 100644 --- a/arch/tile/kernel/ftrace.c +++ b/arch/tile/kernel/ftrace.c @@ -184,7 +184,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, *parent = return_hooker; err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer); + frame_pointer, NULL); if (err == -EBUSY) { *parent = old; return; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0cc8811af4e0..ac5944fa6da2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -93,6 +93,7 @@ config X86 select HAVE_ARCH_TRANSPARENT_HUGEPAGE select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_EBPF_JIT if X86_64 + select HAVE_ARCH_VMAP_STACK if X86_64 select HAVE_CC_STACKPROTECTOR select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL @@ -109,7 +110,6 @@ config X86 select HAVE_EXIT_THREAD select HAVE_FENTRY if X86_64 select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FUNCTION_GRAPH_FP_TEST select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -157,6 +157,7 @@ config X86 select SPARSE_IRQ select SRCU select SYSCTL_EXCEPTION_TRACE + select THREAD_INFO_IN_TASK select USER_STACKTRACE_SUPPORT select VIRT_TO_BUS select X86_DEV_DMA_OPS if X86_64 diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 1433f6b4607d..bdd9cc59d20f 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -31,13 +31,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> -static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs) -{ - unsigned long top_of_stack = - (unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING; - return (struct thread_info *)(top_of_stack - THREAD_SIZE); -} - #ifdef CONFIG_CONTEXT_TRACKING /* Called on entry from user mode with IRQs off. */ __visible inline void enter_from_user_mode(void) @@ -71,7 +64,7 @@ static long syscall_trace_enter(struct pt_regs *regs) { u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); unsigned long ret = 0; bool emulated = false; u32 work; @@ -173,18 +166,17 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) /* Disable IRQs and retry */ local_irq_disable(); - cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags); + cached_flags = READ_ONCE(current_thread_info()->flags); if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS)) break; - } } /* Called with IRQs disabled. */ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); u32 cached_flags; if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled())) @@ -209,7 +201,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) * special case only applies after poking regs and before the * very next return to user mode. */ - ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); + current->thread.status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif user_enter_irqoff(); @@ -247,7 +239,7 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) */ __visible inline void syscall_return_slowpath(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); u32 cached_flags = READ_ONCE(ti->flags); CT_WARN_ON(ct_state() != CONTEXT_KERNEL); @@ -270,7 +262,7 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) #ifdef CONFIG_X86_64 __visible void do_syscall_64(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); unsigned long nr = regs->orig_ax; enter_from_user_mode(); @@ -303,11 +295,11 @@ __visible void do_syscall_64(struct pt_regs *regs) */ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) { - struct thread_info *ti = pt_regs_to_thread_info(regs); + struct thread_info *ti = current_thread_info(); unsigned int nr = (unsigned int)regs->orig_ax; #ifdef CONFIG_IA32_EMULATION - ti->status |= TS_COMPAT; + current->thread.status |= TS_COMPAT; #endif if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) { diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 0b56666e6039..b75a8bcd2d23 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -204,34 +204,70 @@ POP_GS_EX .endm +/* + * %eax: prev task + * %edx: next task + */ +ENTRY(__switch_to_asm) + /* + * Save callee-saved registers + * This must match the order in struct inactive_task_frame + */ + pushl %ebp + pushl %ebx + pushl %edi + pushl %esi + + /* switch stack */ + movl %esp, TASK_threadsp(%eax) + movl TASK_threadsp(%edx), %esp + +#ifdef CONFIG_CC_STACKPROTECTOR + movl TASK_stack_canary(%edx), %ebx + movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset +#endif + + /* restore callee-saved registers */ + popl %esi + popl %edi + popl %ebx + popl %ebp + + jmp __switch_to +END(__switch_to_asm) + +/* + * A newly forked process directly context switches into this address. + * + * eax: prev task we switched from + * ebx: kernel thread func (NULL for user thread) + * edi: kernel thread arg + */ ENTRY(ret_from_fork) pushl %eax call schedule_tail popl %eax + testl %ebx, %ebx + jnz 1f /* kernel threads are uncommon */ + +2: /* When we fork, we trace the syscall return in the child, too. */ movl %esp, %eax call syscall_return_slowpath jmp restore_all -END(ret_from_fork) - -ENTRY(ret_from_kernel_thread) - pushl %eax - call schedule_tail - popl %eax - movl PT_EBP(%esp), %eax - call *PT_EBX(%esp) - movl $0, PT_EAX(%esp) + /* kernel thread */ +1: movl %edi, %eax + call *%ebx /* - * Kernel threads return to userspace as if returning from a syscall. - * We should check whether anything actually uses this path and, if so, - * consider switching it over to ret_from_fork. + * A kernel thread is allowed to return here after successfully + * calling do_execve(). Exit to userspace to complete the execve() + * syscall. */ - movl %esp, %eax - call syscall_return_slowpath - jmp restore_all -ENDPROC(ret_from_kernel_thread) + movl $0, PT_EAX(%esp) + jmp 2b +END(ret_from_fork) /* * Return to user mode is not as complex as all this looks, diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 02fff3ebfb87..fee1d95902b5 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -179,7 +179,8 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) * If we need to do entry work or if we guess we'll need to do * exit work, go straight to the slow path. */ - testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + movq PER_CPU_VAR(current_task), %r11 + testl $_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) jnz entry_SYSCALL64_slow_path entry_SYSCALL_64_fastpath: @@ -217,7 +218,8 @@ entry_SYSCALL_64_fastpath: */ DISABLE_INTERRUPTS(CLBR_NONE) TRACE_IRQS_OFF - testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + movq PER_CPU_VAR(current_task), %r11 + testl $_TIF_ALLWORK_MASK, TASK_TI_flags(%r11) jnz 1f LOCKDEP_SYS_EXIT @@ -351,8 +353,7 @@ ENTRY(stub_ptregs_64) jmp entry_SYSCALL64_slow_path 1: - /* Called from C */ - jmp *%rax /* called from C */ + jmp *%rax /* Called from C */ END(stub_ptregs_64) .macro ptregs_stub func @@ -369,41 +370,73 @@ END(ptregs_\func) #include <asm/syscalls_64.h> /* + * %rdi: prev task + * %rsi: next task + */ +ENTRY(__switch_to_asm) + /* + * Save callee-saved registers + * This must match the order in inactive_task_frame + */ + pushq %rbp + pushq %rbx + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 + + /* switch stack */ + movq %rsp, TASK_threadsp(%rdi) + movq TASK_threadsp(%rsi), %rsp + +#ifdef CONFIG_CC_STACKPROTECTOR + movq TASK_stack_canary(%rsi), %rbx + movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset +#endif + + /* restore callee-saved registers */ + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbx + popq %rbp + + jmp __switch_to +END(__switch_to_asm) + +/* * A newly forked process directly context switches into this address. * - * rdi: prev task we switched from + * rax: prev task we switched from + * rbx: kernel thread func (NULL for user thread) + * r12: kernel thread arg */ ENTRY(ret_from_fork) - LOCK ; btr $TIF_FORK, TI_flags(%r8) - + movq %rax, %rdi call schedule_tail /* rdi: 'prev' task parameter */ - testb $3, CS(%rsp) /* from kernel_thread? */ - jnz 1f + testq %rbx, %rbx /* from kernel_thread? */ + jnz 1f /* kernel threads are uncommon */ - /* - * We came from kernel_thread. This code path is quite twisted, and - * someone should clean it up. - * - * copy_thread_tls stashes the function pointer in RBX and the - * parameter to be passed in RBP. The called function is permitted - * to call do_execve and thereby jump to user mode. - */ - movq RBP(%rsp), %rdi - call *RBX(%rsp) - movl $0, RAX(%rsp) - - /* - * Fall through as though we're exiting a syscall. This makes a - * twisted sort of sense if we just called do_execve. - */ - -1: +2: movq %rsp, %rdi call syscall_return_slowpath /* returns with IRQs disabled */ TRACE_IRQS_ON /* user mode is traced as IRQS on */ SWAPGS jmp restore_regs_and_iret + +1: + /* kernel thread */ + movq %r12, %rdi + call *%rbx + /* + * A kernel thread is allowed to return here after successfully + * calling do_execve(). Exit to userspace to complete the execve() + * syscall. + */ + movq $0, RAX(%rsp) + jmp 2b END(ret_from_fork) /* @@ -555,27 +588,69 @@ native_irq_return_iret: #ifdef CONFIG_X86_ESPFIX64 native_irq_return_ldt: - pushq %rax - pushq %rdi + /* + * We are running with user GSBASE. All GPRs contain their user + * values. We have a percpu ESPFIX stack that is eight slots + * long (see ESPFIX_STACK_SIZE). espfix_waddr points to the bottom + * of the ESPFIX stack. + * + * We clobber RAX and RDI in this code. We stash RDI on the + * normal stack and RAX on the ESPFIX stack. + * + * The ESPFIX stack layout we set up looks like this: + * + * --- top of ESPFIX stack --- + * SS + * RSP + * RFLAGS + * CS + * RIP <-- RSP points here when we're done + * RAX <-- espfix_waddr points here + * --- bottom of ESPFIX stack --- + */ + + pushq %rdi /* Stash user RDI */ SWAPGS movq PER_CPU_VAR(espfix_waddr), %rdi - movq %rax, (0*8)(%rdi) /* RAX */ - movq (2*8)(%rsp), %rax /* RIP */ + movq %rax, (0*8)(%rdi) /* user RAX */ + movq (1*8)(%rsp), %rax /* user RIP */ movq %rax, (1*8)(%rdi) - movq (3*8)(%rsp), %rax /* CS */ + movq (2*8)(%rsp), %rax /* user CS */ movq %rax, (2*8)(%rdi) - movq (4*8)(%rsp), %rax /* RFLAGS */ + movq (3*8)(%rsp), %rax /* user RFLAGS */ movq %rax, (3*8)(%rdi) - movq (6*8)(%rsp), %rax /* SS */ + movq (5*8)(%rsp), %rax /* user SS */ movq %rax, (5*8)(%rdi) - movq (5*8)(%rsp), %rax /* RSP */ + movq (4*8)(%rsp), %rax /* user RSP */ movq %rax, (4*8)(%rdi) - andl $0xffff0000, %eax - popq %rdi + /* Now RAX == RSP. */ + + andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */ + popq %rdi /* Restore user RDI */ + + /* + * espfix_stack[31:16] == 0. The page tables are set up such that + * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of + * espfix_waddr for any X. That is, there are 65536 RO aliases of + * the same page. Set up RSP so that RSP[31:16] contains the + * respective 16 bits of the /userspace/ RSP and RSP nonetheless + * still points to an RO alias of the ESPFIX stack. + */ orq PER_CPU_VAR(espfix_stack), %rax SWAPGS movq %rax, %rsp - popq %rax + + /* + * At this point, we cannot write to the stack any more, but we can + * still read. + */ + popq %rax /* Restore user RAX */ + + /* + * RSP now points to an ordinary IRET frame, except that the page + * is read-only and RSP[31:16] are preloaded with the userspace + * values. We can now IRET back to userspace. + */ jmp native_irq_return_iret #endif END(common_interrupt) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 18a1acf86c90..d31735f37ed7 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -37,6 +37,7 @@ #include <asm/timer.h> #include <asm/desc.h> #include <asm/ldt.h> +#include <asm/unwind.h> #include "perf_event.h" @@ -2267,39 +2268,26 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(data); } -/* - * callchain support - */ - -static int backtrace_stack(void *data, char *name) -{ - return 0; -} - -static int backtrace_address(void *data, unsigned long addr, int reliable) -{ - struct perf_callchain_entry_ctx *entry = data; - - return perf_callchain_store(entry, addr); -} - -static const struct stacktrace_ops backtrace_ops = { - .stack = backtrace_stack, - .address = backtrace_address, - .walk_stack = print_context_stack_bp, -}; - void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct unwind_state state; + unsigned long addr; + if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ return; } - perf_callchain_store(entry, regs->ip); + if (perf_callchain_store(entry, regs->ip)) + return; - dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry); + for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr || perf_callchain_store(entry, addr)) + return; + } } static inline int 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 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); diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index a4820d4df617..eccd0ac6bc38 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 */ @@ -13,6 +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; 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/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); diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 4cd8db05301f..ce932812f142 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 60aac60ba25f..0f400c0e4979 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/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) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 63def9537a2d..984a7bf17f6a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -389,9 +389,9 @@ struct thread_struct { unsigned short fsindex; unsigned short gsindex; #endif -#ifdef CONFIG_X86_32 - unsigned long ip; -#endif + + u32 status; /* thread synchronous flags */ + #ifdef CONFIG_X86_64 unsigned long fsbase; unsigned long gsbase; @@ -438,6 +438,15 @@ 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 */ static inline void native_set_iopl_mask(unsigned mask) @@ -724,8 +733,6 @@ 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" @@ -776,17 +783,13 @@ 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); diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index b2988c0ed829..230e1903acf0 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -44,9 +44,9 @@ 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; +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 { 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/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 0944218af9e2..37f2e0b377ad 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -8,86 +8,86 @@ #include <linux/uaccess.h> #include <linux/ptrace.h> +#include <asm/switch_to.h> + +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, +}; -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, - unsigned long *end, - 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); - -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); - -/* 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); - walk_stack_t walk_stack; +struct stack_info { + enum stack_type type; + unsigned long *begin, *end, *next_sp; }; -void dump_trace(struct task_struct *tsk, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data); +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; #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 == current) + return __builtin_frame_address(0); - /* bp is the last reg pushed by switch_to */ - return *(unsigned long *)task->thread.sp; + 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 == 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, - 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; @@ -106,7 +106,7 @@ 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; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 8f321a1b03a1..5cb436acd463 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -2,130 +2,66 @@ #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); -#ifdef CONFIG_X86_32 +/* 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 +} + +asmlinkage void ret_from_fork(void); + +/* 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_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; \ - \ - 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) \ + prepare_switch_to(prev, 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) \ - 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/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 8b7c8d8e0852..2aaca53c0974 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -52,21 +52,6 @@ struct task_struct; #include <asm/cpufeature.h> #include <linux/atomic.h> -struct thread_info { - struct task_struct *task; /* main task structure */ - __u32 flags; /* low level flags */ - __u32 status; /* thread synchronous 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__ */ @@ -95,7 +80,6 @@ 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 +103,6 @@ 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) @@ -160,11 +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; @@ -226,60 +204,19 @@ 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 -/* - * 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 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. */ 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 */ 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 <linux/sched.h> +#include <linux/ftrace.h> +#include <asm/ptrace.h> +#include <asm/stacktrace.h> + +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 */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0503f5bfb18d..45257cf84370 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -125,6 +125,12 @@ obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o +ifdef CONFIG_FRAME_POINTER +obj-y += unwind_frame.o +else +obj-y += unwind_guess.o +endif + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index adb3eaf8fe2a..48587335ede8 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -99,7 +99,7 @@ int x86_acpi_suspend_lowlevel(void) saved_magic = 0x12345678; #else /* CONFIG_64BIT */ #ifdef CONFIG_SMP - stack_start = (unsigned long)temp_stack + sizeof(temp_stack); + initial_stack = (unsigned long)temp_stack + sizeof(temp_stack); early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 5b2ae106bd4a..8862da76ef6f 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -25,7 +25,7 @@ static struct apic apic_physflat; static struct apic apic_flat; -struct apic __read_mostly *apic = &apic_flat; +struct apic *apic __ro_after_init = &apic_flat; EXPORT_SYMBOL_GPL(apic); static int flat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) @@ -154,7 +154,7 @@ static int flat_probe(void) return 1; } -static struct apic apic_flat = { +static struct apic apic_flat __ro_after_init = { .name = "flat", .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, @@ -248,7 +248,7 @@ static int physflat_probe(void) return 0; } -static struct apic apic_physflat = { +static struct apic apic_physflat __ro_after_init = { .name = "physical flat", .probe = physflat_probe, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index c05688b2deff..b109e4389c92 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -108,7 +108,7 @@ static void noop_apic_write(u32 reg, u32 v) WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_APIC) && !disable_apic); } -struct apic apic_noop = { +struct apic apic_noop __ro_after_init = { .name = "noop", .probe = noop_probe, .acpi_madt_oem_check = NULL, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 06dbaa458bfe..56012010332c 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -142,7 +142,7 @@ static int probe_bigsmp(void) return dmi_bigsmp; } -static struct apic apic_bigsmp = { +static struct apic apic_bigsmp __ro_after_init = { .name = "bigsmp", .probe = probe_bigsmp, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index ade25320df96..015bbf30e3e3 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -269,7 +269,7 @@ static void hpet_msi_write_msg(struct irq_data *data, struct msi_msg *msg) hpet_msi_write(irq_data_get_irq_handler_data(data), msg); } -static struct irq_chip hpet_msi_controller = { +static struct irq_chip hpet_msi_controller __ro_after_init = { .name = "HPET-MSI", .irq_unmask = hpet_msi_unmask, .irq_mask = hpet_msi_mask, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 563096267ca2..c48264e202fd 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -72,7 +72,7 @@ static int probe_default(void) return 1; } -static struct apic apic_default = { +static struct apic apic_default __ro_after_init = { .name = "default", .probe = probe_default, @@ -126,7 +126,7 @@ static struct apic apic_default = { apic_driver(apic_default); -struct apic *apic = &apic_default; +struct apic *apic __ro_after_init = &apic_default; EXPORT_SYMBOL_GPL(apic); static int cmdline_apic __initdata; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 54f35d988025..200af5ae9662 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -227,7 +227,7 @@ static void cluster_vector_allocation_domain(int cpu, struct cpumask *retmask, cpumask_and(retmask, mask, per_cpu(cpus_in_cluster, cpu)); } -static struct apic apic_x2apic_cluster = { +static struct apic apic_x2apic_cluster __ro_after_init = { .name = "cluster x2apic", .probe = x2apic_cluster_probe, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 4f13f54f1b1f..ff111f05a314 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -98,7 +98,7 @@ static int x2apic_phys_probe(void) return apic == &apic_x2apic_phys; } -static struct apic apic_x2apic_phys = { +static struct apic apic_x2apic_phys __ro_after_init = { .name = "physical x2apic", .probe = x2apic_phys_probe, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index cb0673c1e940..b9f6157d4271 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -560,7 +560,7 @@ static int uv_probe(void) return apic == &apic_x2apic_uv_x; } -static struct apic __refdata apic_x2apic_uv_x = { +static struct apic apic_x2apic_uv_x __ro_after_init = { .name = "UV large system", .probe = uv_probe, diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 2bd5c6ff7ee7..c62e015b126c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -29,10 +29,13 @@ void common(void) { BLANK(); - OFFSET(TI_flags, thread_info, flags); - OFFSET(TI_status, thread_info, status); + OFFSET(TASK_threadsp, task_struct, thread.sp); +#ifdef CONFIG_CC_STACKPROTECTOR + OFFSET(TASK_stack_canary, task_struct, stack_canary); +#endif BLANK(); + OFFSET(TASK_TI_flags, task_struct, thread_info.flags); OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); BLANK(); diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index ecdc1d217dc0..880aa093268d 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -57,6 +57,11 @@ void foo(void) /* Size of SYSENTER_stack */ DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack)); +#ifdef CONFIG_CC_STACKPROTECTOR + BLANK(); + OFFSET(stack_canary_offset, stack_canary, canary); +#endif + #if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE) BLANK(); OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d875f97d4e0b..210927ee2e74 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -56,6 +56,11 @@ int main(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); BLANK(); +#ifdef CONFIG_CC_STACKPROTECTOR + DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary)); + BLANK(); +#endif + DEFINE(__NR_syscall_max, sizeof(syscalls_64) - 1); DEFINE(NR_syscalls, sizeof(syscalls_64)); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index bcc9ccc220c9..9bd910a7dd0a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1264,9 +1264,14 @@ static __init int setup_disablecpuid(char *arg) __setup("clearcpuid=", setup_disablecpuid); #ifdef CONFIG_X86_64 -struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table }; -struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, - (unsigned long) debug_idt_table }; +struct desc_ptr idt_descr __ro_after_init = { + .size = NR_VECTORS * 16 - 1, + .address = (unsigned long) idt_table, +}; +const struct desc_ptr debug_idt_descr = { + .size = NR_VECTORS * 16 - 1, + .address = (unsigned long) debug_idt_table, +}; DEFINE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __aligned(PAGE_SIZE) __visible; @@ -1280,7 +1285,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = EXPORT_PER_CPU_SYMBOL(current_task); DEFINE_PER_CPU(char *, irq_stack_ptr) = - init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; + init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE; DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; @@ -1304,11 +1309,6 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks /* May not be marked __init: used by software suspend */ void syscall_init(void) { - /* - * LSTAR and STAR live in a bit strange symbiosis. - * They both write to the same internal register. STAR allows to - * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. - */ wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 28f1b54b7fad..24e87e74990d 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -72,14 +72,14 @@ static DEFINE_MUTEX(mtrr_mutex); u64 size_or_mask, size_and_mask; static bool mtrr_aps_delayed_init; -static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM]; +static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM] __ro_after_init; const struct mtrr_ops *mtrr_if; static void set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); -void set_mtrr_ops(const struct mtrr_ops *ops) +void __init set_mtrr_ops(const struct mtrr_ops *ops) { if (ops->vendor && ops->vendor < X86_VENDOR_NUM) mtrr_ops[ops->vendor] = ops; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 6c7ced07d16d..ad8bd763efa5 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -54,7 +54,7 @@ void fill_mtrr_var_range(unsigned int index, bool get_mtrr_state(void); void mtrr_bp_pat_init(void); -extern void set_mtrr_ops(const struct mtrr_ops *ops); +extern void __init set_mtrr_ops(const struct mtrr_ops *ops); extern u64 size_or_mask, size_and_mask; extern const struct mtrr_ops *mtrr_if; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 92e8f0a7159c..9b7cf5c28f5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -17,7 +17,7 @@ #include <linux/sysfs.h> #include <asm/stacktrace.h> - +#include <asm/unwind.h> int panic_on_unrecovered_nmi; int panic_on_io_nmi; @@ -25,11 +25,29 @@ unsigned int code_bytes = 64; int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE; static int die_counter; +bool in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info) +{ + unsigned long *begin = task_stack_page(task); + unsigned long *end = task_stack_page(task) + THREAD_SIZE; + + if (stack < begin || stack >= end) + return false; + + info->type = STACK_TYPE_TASK; + info->begin = begin; + info->end = end; + info->next_sp = NULL; + + return true; +} + static void printk_stack_address(unsigned long address, int reliable, - void *data) + char *log_lvl) { + touch_nmi_watchdog(); printk("%s [<%p>] %s%pB\n", - (char *)data, (void *)address, reliable ? "" : "? ", + log_lvl, (void *)address, reliable ? "" : "? ", (void *)address); } @@ -38,176 +56,120 @@ void printk_address(unsigned long address) pr_cont(" [<%p>] %pS\n", (void *)address, (void *)address); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void -print_ftrace_graph_addr(unsigned long addr, void *data, - const struct stacktrace_ops *ops, - struct task_struct *task, int *graph) +void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, char *log_lvl) { - unsigned long ret_addr; - int index; - - if (addr != (unsigned long)return_to_handler) - return; - - index = task->curr_ret_stack; - - if (!task->ret_stack || index < *graph) - return; - - index -= *graph; - ret_addr = task->ret_stack[index].ret; - - ops->address(data, ret_addr, 1); + struct unwind_state state; + struct stack_info stack_info = {0}; + unsigned long visit_mask = 0; + int graph_idx = 0; - (*graph)++; -} -#else -static inline void -print_ftrace_graph_addr(unsigned long addr, void *data, - const struct stacktrace_ops *ops, - struct task_struct *task, int *graph) -{ } -#endif - -/* - * x86-64 can have up to three kernel stacks: - * process stack - * interrupt stack - * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack - */ - -static inline int valid_stack_ptr(struct task_struct *task, - void *p, unsigned int size, void *end) -{ - void *t = task_stack_page(task); - if (end) { - if (p < end && p >= (end-THREAD_SIZE)) - return 1; - else - return 0; - } - return p >= t && p < t + THREAD_SIZE - size; -} + printk("%sCall Trace:\n", log_lvl); -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_frame *frame = (struct stack_frame *)bp; + unwind_start(&state, task, regs, stack); /* - * If we overflowed the stack into a guard page, jump back to the - * bottom of the usable stack. + * Iterate through the stacks, starting with the current stack pointer. + * Each stack has a pointer to the next one. + * + * x86-64 can have several stacks: + * - task stack + * - interrupt stack + * - HW exception stacks (double fault, nmi, debug, mce) + * + * x86-32 can have up to three stacks: + * - task stack + * - softirq stack + * - hardirq stack */ - if ((unsigned long)task_stack_page(task) - (unsigned long)stack < - PAGE_SIZE) - stack = (unsigned long *)task_stack_page(task); - - while (valid_stack_ptr(task, stack, sizeof(*stack), end)) { - unsigned long addr; - - addr = *stack; - if (__kernel_text_address(addr)) { - if ((unsigned long) stack == bp + sizeof(long)) { - ops->address(data, addr, 1); - frame = frame->next_frame; - bp = (unsigned long) frame; - } else { - ops->address(data, addr, 0); - } - print_ftrace_graph_addr(addr, data, ops, task, graph); - } - stack++; - } - return bp; -} -EXPORT_SYMBOL_GPL(print_context_stack); - -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_frame *frame = (struct stack_frame *)bp; - unsigned long *ret_addr = &frame->return_address; + for (; stack; stack = stack_info.next_sp) { + const char *str_begin, *str_end; - while (valid_stack_ptr(task, ret_addr, sizeof(*ret_addr), end)) { - unsigned long addr = *ret_addr; + /* + * 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 (!__kernel_text_address(addr)) + if (get_stack_info(stack, task, &stack_info, &visit_mask)) break; - if (ops->address(data, addr, 1)) - break; - frame = frame->next_frame; - ret_addr = &frame->return_address; - print_ftrace_graph_addr(addr, data, ops, task, graph); - } - - return (unsigned long)frame; -} -EXPORT_SYMBOL_GPL(print_context_stack_bp); - -static int print_trace_stack(void *data, char *name) -{ - printk("%s <%s> ", (char *)data, name); - return 0; -} - -/* - * Print one address/symbol entries per line. - */ -static int print_trace_address(void *data, unsigned long addr, int reliable) -{ - touch_nmi_watchdog(); - printk_stack_address(addr, reliable, data); - return 0; -} - -static const struct stacktrace_ops print_trace_ops = { - .stack = print_trace_stack, - .address = print_trace_address, - .walk_stack = print_context_stack, -}; - -void -show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, char *log_lvl) -{ - printk("%sCall Trace:\n", log_lvl); - dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl); -} + stack_type_str(stack_info.type, &str_begin, &str_end); + if (str_begin) + printk("%s <%s> ", log_lvl, str_begin); + + /* + * Scan the stack, printing any text addresses we find. At the + * same time, follow proper stack frames with the unwinder. + * + * Addresses found during the scan which are not reported by + * the unwinder are considered to be additional clues which are + * sometimes useful for debugging and are prefixed with '?'. + * This also serves as a failsafe option in case the unwinder + * goes off in the weeds. + */ + for (; stack < stack_info.end; stack++) { + unsigned long real_addr; + int reliable = 0; + unsigned long addr = *stack; + unsigned long *ret_addr_p = + unwind_get_return_address_ptr(&state); + + if (!__kernel_text_address(addr)) + continue; + + if (stack == ret_addr_p) + reliable = 1; + + /* + * When function graph tracing is enabled for a + * function, its return address on the stack is + * replaced with the address of an ftrace handler + * (return_to_handler). In that case, before printing + * the "real" address, we want to print the handler + * address as an "unreliable" hint that function graph + * tracing was involved. + */ + real_addr = ftrace_graph_ret_addr(task, &graph_idx, + addr, stack); + if (real_addr != addr) + printk_stack_address(addr, 0, log_lvl); + printk_stack_address(real_addr, reliable, log_lvl); + + if (!reliable) + continue; + + /* + * Get the next frame from the unwinder. No need to + * check for an error: if anything goes wrong, the rest + * of the addresses will just be printed as unreliable. + */ + unwind_next_frame(&state); + } -void show_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp) -{ - show_trace_log_lvl(task, regs, stack, bp, ""); + if (str_end) + printk("%s <%s> ", log_lvl, str_end); + } } void show_stack(struct task_struct *task, unsigned long *sp) { - unsigned long bp = 0; - unsigned long stack; + task = task ? : current; /* * Stack frames below this one aren't interesting. Don't show them * if we're printing for %current. */ - if (!sp && (!task || task == current)) { - sp = &stack; - bp = stack_frame(current, NULL); - } + if (!sp && task == current) + sp = get_stack_pointer(current, NULL); - show_stack_log_lvl(task, NULL, sp, bp, ""); + show_stack_log_lvl(task, NULL, sp, ""); } void show_stack_regs(struct pt_regs *regs) { - show_stack_log_lvl(current, regs, (unsigned long *)regs->sp, regs->bp, ""); + show_stack_log_lvl(current, regs, NULL, ""); } static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 09675712eba8..06eb322b5f9f 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -16,93 +16,121 @@ #include <asm/stacktrace.h> -static void *is_irq_stack(void *p, void *irq) +void stack_type_str(enum stack_type type, const char **begin, const char **end) { - if (p < irq || p >= (irq + THREAD_SIZE)) - return NULL; - return irq + THREAD_SIZE; + switch (type) { + case STACK_TYPE_IRQ: + case STACK_TYPE_SOFTIRQ: + *begin = "IRQ"; + *end = "EOI"; + break; + default: + *begin = NULL; + *end = NULL; + } } - -static void *is_hardirq_stack(unsigned long *stack, int cpu) +static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info) { - void *irq = per_cpu(hardirq_stack, cpu); + unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack); + unsigned long *end = begin + (THREAD_SIZE / sizeof(long)); - return is_irq_stack(stack, irq); -} + /* + * This is a software stack, so 'end' can be a valid stack pointer. + * It just means the stack is empty. + */ + if (stack < begin || stack > end) + return false; -static void *is_softirq_stack(unsigned long *stack, int cpu) -{ - void *irq = per_cpu(softirq_stack, cpu); + info->type = STACK_TYPE_IRQ; + info->begin = begin; + info->end = end; - return is_irq_stack(stack, irq); + /* + * See irq_32.c -- the next stack pointer is stored at the beginning of + * the stack. + */ + info->next_sp = (unsigned long *)*begin; + + return true; } -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) +static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) { - const unsigned cpu = get_cpu(); - int graph = 0; - u32 *prev_esp; + unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack); + unsigned long *end = begin + (THREAD_SIZE / sizeof(long)); - if (!task) - task = current; + /* + * This is a software stack, so 'end' can be a valid stack pointer. + * It just means the stack is empty. + */ + if (stack < begin || stack > end) + return false; - if (!stack) { - unsigned long dummy; + info->type = STACK_TYPE_SOFTIRQ; + info->begin = begin; + info->end = end; - stack = &dummy; - if (task != current) - stack = (unsigned long *)task->thread.sp; - } + /* + * The next stack pointer is stored at the beginning of the stack. + * See irq_32.c. + */ + info->next_sp = (unsigned long *)*begin; - if (!bp) - bp = stack_frame(task, regs); + return true; +} - for (;;) { - void *end_stack; +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask) +{ + if (!stack) + goto unknown; - end_stack = is_hardirq_stack(stack, cpu); - if (!end_stack) - end_stack = is_softirq_stack(stack, cpu); + task = task ? : current; - bp = ops->walk_stack(task, stack, bp, ops, data, - end_stack, &graph); + if (in_task_stack(stack, task, info)) + goto recursion_check; - /* Stop if not on irq stack */ - if (!end_stack) - break; + if (task != current) + goto unknown; - /* The previous esp is saved on the bottom of the stack */ - prev_esp = (u32 *)(end_stack - THREAD_SIZE); - stack = (unsigned long *)*prev_esp; - if (!stack) - break; + if (in_hardirq_stack(stack, info)) + goto recursion_check; - if (ops->stack(data, "IRQ") < 0) - break; - touch_nmi_watchdog(); + if (in_softirq_stack(stack, info)) + goto recursion_check; + + goto unknown; + +recursion_check: + /* + * Make sure we don't iterate through any given stack more than once. + * If it comes up a second time then there's something wrong going on: + * just break out and report an unknown stack type. + */ + if (visit_mask) { + if (*visit_mask & (1UL << info->type)) + goto unknown; + *visit_mask |= 1UL << info->type; } - put_cpu(); + + return 0; + +unknown: + info->type = STACK_TYPE_UNKNOWN; + return -EINVAL; } -EXPORT_SYMBOL(dump_trace); -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) { unsigned long *stack; int i; - if (sp == NULL) { - if (regs) - sp = (unsigned long *)regs->sp; - else if (task) - sp = (unsigned long *)task->thread.sp; - else - sp = (unsigned long *)&sp; - } + if (!try_get_task_stack(task)) + return; + + sp = sp ? : get_stack_pointer(task, regs); stack = sp; for (i = 0; i < kstack_depth_to_print; i++) { @@ -117,7 +145,9 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, touch_nmi_watchdog(); } pr_cont("\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); + + put_task_stack(task); } @@ -139,7 +169,7 @@ void show_regs(struct pt_regs *regs) u8 *ip; pr_emerg("Stack:\n"); - show_stack_log_lvl(NULL, regs, ®s->sp, 0, KERN_EMERG); + show_stack_log_lvl(current, regs, NULL, KERN_EMERG); pr_emerg("Code:"); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 9ee4520ce83c..36cf1a498227 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -16,261 +16,145 @@ #include <asm/stacktrace.h> +static char *exception_stack_names[N_EXCEPTION_STACKS] = { + [ DOUBLEFAULT_STACK-1 ] = "#DF", + [ NMI_STACK-1 ] = "NMI", + [ DEBUG_STACK-1 ] = "#DB", + [ MCE_STACK-1 ] = "#MC", +}; -#define N_EXCEPTION_STACKS_END \ - (N_EXCEPTION_STACKS + DEBUG_STKSZ/EXCEPTION_STKSZ - 2) - -static char x86_stack_ids[][8] = { - [ DEBUG_STACK-1 ] = "#DB", - [ NMI_STACK-1 ] = "NMI", - [ DOUBLEFAULT_STACK-1 ] = "#DF", - [ MCE_STACK-1 ] = "#MC", -#if DEBUG_STKSZ > EXCEPTION_STKSZ - [ N_EXCEPTION_STACKS ... - N_EXCEPTION_STACKS_END ] = "#DB[?]" -#endif +static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = { + [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, + [DEBUG_STACK - 1] = DEBUG_STKSZ }; -static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack, - unsigned *usedp, char **idp) +void stack_type_str(enum stack_type type, const char **begin, const char **end) { - unsigned k; - - /* - * Iterate over all exception stacks, and figure out whether - * 'stack' is in one of them: - */ - for (k = 0; k < N_EXCEPTION_STACKS; k++) { - unsigned long end = per_cpu(orig_ist, cpu).ist[k]; - /* - * Is 'stack' above this exception frame's end? - * If yes then skip to the next frame. - */ - if (stack >= end) - continue; - /* - * Is 'stack' above this exception frame's start address? - * If yes then we found the right frame. - */ - if (stack >= end - EXCEPTION_STKSZ) { - /* - * Make sure we only iterate through an exception - * stack once. If it comes up for the second time - * then there's something wrong going on - just - * break out and return NULL: - */ - if (*usedp & (1U << k)) - break; - *usedp |= 1U << k; - *idp = x86_stack_ids[k]; - return (unsigned long *)end; - } - /* - * If this is a debug stack, and if it has a larger size than - * the usual exception stacks, then 'stack' might still - * be within the lower portion of the debug stack: - */ -#if DEBUG_STKSZ > EXCEPTION_STKSZ - if (k == DEBUG_STACK - 1 && stack >= end - DEBUG_STKSZ) { - unsigned j = N_EXCEPTION_STACKS - 1; - - /* - * Black magic. A large debug stack is composed of - * multiple exception stack entries, which we - * iterate through now. Dont look: - */ - do { - ++j; - end -= EXCEPTION_STKSZ; - x86_stack_ids[j][4] = '1' + - (j - N_EXCEPTION_STACKS); - } while (stack < end - EXCEPTION_STKSZ); - if (*usedp & (1U << j)) - break; - *usedp |= 1U << j; - *idp = x86_stack_ids[j]; - return (unsigned long *)end; - } -#endif + BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); + + switch (type) { + case STACK_TYPE_IRQ: + *begin = "IRQ"; + *end = "EOI"; + break; + case STACK_TYPE_EXCEPTION ... STACK_TYPE_EXCEPTION_LAST: + *begin = exception_stack_names[type - STACK_TYPE_EXCEPTION]; + *end = "EOE"; + break; + default: + *begin = NULL; + *end = NULL; } - return NULL; } -static inline int -in_irq_stack(unsigned long *stack, unsigned long *irq_stack, - unsigned long *irq_stack_end) +static bool in_exception_stack(unsigned long *stack, struct stack_info *info) { - return (stack >= irq_stack && stack < irq_stack_end); -} - -static const unsigned long irq_stack_size = - (IRQ_STACK_SIZE - 64) / sizeof(unsigned long); - -enum stack_type { - STACK_IS_UNKNOWN, - STACK_IS_NORMAL, - STACK_IS_EXCEPTION, - STACK_IS_IRQ, -}; - -static enum stack_type -analyze_stack(int cpu, struct task_struct *task, unsigned long *stack, - unsigned long **stack_end, unsigned long *irq_stack, - unsigned *used, char **id) -{ - unsigned long addr; + unsigned long *begin, *end; + struct pt_regs *regs; + unsigned k; - addr = ((unsigned long)stack & (~(THREAD_SIZE - 1))); - if ((unsigned long)task_stack_page(task) == addr) - return STACK_IS_NORMAL; + BUILD_BUG_ON(N_EXCEPTION_STACKS != 4); - *stack_end = in_exception_stack(cpu, (unsigned long)stack, - used, id); - if (*stack_end) - return STACK_IS_EXCEPTION; + for (k = 0; k < N_EXCEPTION_STACKS; k++) { + end = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k]; + begin = end - (exception_stack_sizes[k] / sizeof(long)); + regs = (struct pt_regs *)end - 1; - if (!irq_stack) - return STACK_IS_NORMAL; + if (stack < begin || stack >= end) + continue; - *stack_end = irq_stack; - irq_stack = irq_stack - irq_stack_size; + info->type = STACK_TYPE_EXCEPTION + k; + info->begin = begin; + info->end = end; + info->next_sp = (unsigned long *)regs->sp; - if (in_irq_stack(stack, irq_stack, *stack_end)) - return STACK_IS_IRQ; + return true; + } - return STACK_IS_UNKNOWN; + return false; } -/* - * x86-64 can have up to three kernel stacks: - * process stack - * interrupt stack - * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack - */ - -void dump_trace(struct task_struct *task, struct pt_regs *regs, - unsigned long *stack, unsigned long bp, - const struct stacktrace_ops *ops, void *data) +static bool in_irq_stack(unsigned long *stack, struct stack_info *info) { - const unsigned cpu = get_cpu(); - unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu); - unsigned long dummy; - unsigned used = 0; - int graph = 0; - int done = 0; - - if (!task) - task = current; - - if (!stack) { - if (regs) - stack = (unsigned long *)regs->sp; - else if (task != current) - stack = (unsigned long *)task->thread.sp; - else - stack = &dummy; - } + unsigned long *end = (unsigned long *)this_cpu_read(irq_stack_ptr); + unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long)); - if (!bp) - bp = stack_frame(task, regs); /* - * Print function call entries in all stacks, starting at the - * current stack address. If the stacks consist of nested - * exceptions + * This is a software stack, so 'end' can be a valid stack pointer. + * It just means the stack is empty. */ - while (!done) { - unsigned long *stack_end; - enum stack_type stype; - char *id; + if (stack < begin || stack > end) + return false; - stype = analyze_stack(cpu, task, stack, &stack_end, - irq_stack, &used, &id); + info->type = STACK_TYPE_IRQ; + info->begin = begin; + info->end = end; - /* Default finish unless specified to continue */ - done = 1; + /* + * The next stack pointer is the first thing pushed by the entry code + * after switching to the irq stack. + */ + info->next_sp = (unsigned long *)*(end - 1); - switch (stype) { + return true; +} - /* Break out early if we are on the thread stack */ - case STACK_IS_NORMAL: - break; +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask) +{ + if (!stack) + goto unknown; - case STACK_IS_EXCEPTION: + task = task ? : current; - if (ops->stack(data, id) < 0) - break; + if (in_task_stack(stack, task, info)) + goto recursion_check; - bp = ops->walk_stack(task, stack, bp, ops, - data, stack_end, &graph); - ops->stack(data, "<EOE>"); - /* - * We link to the next stack via the - * second-to-last pointer (index -2 to end) in the - * exception stack: - */ - stack = (unsigned long *) stack_end[-2]; - done = 0; - break; + if (task != current) + goto unknown; - case STACK_IS_IRQ: + if (in_exception_stack(stack, info)) + goto recursion_check; - if (ops->stack(data, "IRQ") < 0) - break; - bp = ops->walk_stack(task, stack, bp, - ops, data, stack_end, &graph); - /* - * We link to the next stack (which would be - * the process stack normally) the last - * pointer (index -1 to end) in the IRQ stack: - */ - stack = (unsigned long *) (stack_end[-1]); - irq_stack = NULL; - ops->stack(data, "EOI"); - done = 0; - break; + if (in_irq_stack(stack, info)) + goto recursion_check; - case STACK_IS_UNKNOWN: - ops->stack(data, "UNK"); - break; - } - } + goto unknown; +recursion_check: /* - * This handles the process stack: + * Make sure we don't iterate through any given stack more than once. + * If it comes up a second time then there's something wrong going on: + * just break out and report an unknown stack type. */ - bp = ops->walk_stack(task, stack, bp, ops, data, NULL, &graph); - put_cpu(); + if (visit_mask) { + if (*visit_mask & (1UL << info->type)) + goto unknown; + *visit_mask |= 1UL << info->type; + } + + return 0; + +unknown: + info->type = STACK_TYPE_UNKNOWN; + return -EINVAL; } -EXPORT_SYMBOL(dump_trace); -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) { unsigned long *irq_stack_end; unsigned long *irq_stack; unsigned long *stack; - int cpu; int i; - preempt_disable(); - cpu = smp_processor_id(); + if (!try_get_task_stack(task)) + return; - irq_stack_end = (unsigned long *)(per_cpu(irq_stack_ptr, cpu)); - irq_stack = (unsigned long *)(per_cpu(irq_stack_ptr, cpu) - IRQ_STACK_SIZE); + irq_stack_end = (unsigned long *)this_cpu_read(irq_stack_ptr); + irq_stack = irq_stack_end - (IRQ_STACK_SIZE / sizeof(long)); - /* - * Debugging aid: "show_stack(NULL, NULL);" prints the - * back trace for this cpu: - */ - if (sp == NULL) { - if (regs) - sp = (unsigned long *)regs->sp; - else if (task) - sp = (unsigned long *)task->thread.sp; - else - sp = (unsigned long *)&sp; - } + sp = sp ? : get_stack_pointer(task, regs); stack = sp; for (i = 0; i < kstack_depth_to_print; i++) { @@ -299,18 +183,17 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, stack++; touch_nmi_watchdog(); } - preempt_enable(); pr_cont("\n"); - show_trace_log_lvl(task, regs, sp, bp, log_lvl); + show_trace_log_lvl(task, regs, sp, log_lvl); + + put_task_stack(task); } void show_regs(struct pt_regs *regs) { int i; - unsigned long sp; - sp = regs->sp; show_regs_print_info(KERN_DEFAULT); __show_regs(regs, 1); @@ -325,8 +208,7 @@ void show_regs(struct pt_regs *regs) u8 *ip; printk(KERN_DEFAULT "Stack:\n"); - show_stack_log_lvl(NULL, regs, (unsigned long *)sp, - 0, KERN_DEFAULT); + show_stack_log_lvl(current, regs, NULL, KERN_DEFAULT); printk(KERN_DEFAULT "Code: "); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 93982aebb398..2f2b8c7ccb85 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -317,7 +317,6 @@ static void __init fpu__init_system_ctx_switch(void) on_boot_cpu = 0; WARN_ON_FPU(current->thread.fpu.fpstate_active); - current_thread_info()->status = 0; if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) eagerfpu = ENABLE; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index d036cfb4495d..8639bb2ae058 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -1029,7 +1029,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, } if (ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer) == -EBUSY) { + frame_pointer, parent) == -EBUSY) { *parent = old; return; } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 6f8902b0d151..5f401262f12d 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -94,7 +94,7 @@ RESERVE_BRK(pagetables, INIT_MAP_SIZE) */ __HEAD ENTRY(startup_32) - movl pa(stack_start),%ecx + movl pa(initial_stack),%ecx /* test KEEP_SEGMENTS flag to see if the bootloader is asking us to not reload segments */ @@ -286,7 +286,7 @@ num_subarch_entries = (. - subarch_entries) / 4 * start_secondary(). */ ENTRY(start_cpu0) - movl stack_start, %ecx + movl initial_stack, %ecx movl %ecx, %esp jmp *(initial_code) ENDPROC(start_cpu0) @@ -307,7 +307,7 @@ ENTRY(startup_32_smp) movl %eax,%es movl %eax,%fs movl %eax,%gs - movl pa(stack_start),%ecx + movl pa(initial_stack),%ecx movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp @@ -703,7 +703,7 @@ ENTRY(initial_page_table) .data .balign 4 -ENTRY(stack_start) +ENTRY(initial_stack) .long init_thread_union+THREAD_SIZE __INITRODATA diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 9f8efc9f0075..c98a559c346e 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -66,7 +66,7 @@ startup_64: */ /* - * Setup stack for verify_cpu(). "-8" because stack_start is defined + * Setup stack for verify_cpu(). "-8" because initial_stack is defined * this way, see below. Our best guess is a NULL ptr for stack * termination heuristics and we don't want to break anything which * might depend on it (kgdb, ...). @@ -226,7 +226,7 @@ ENTRY(secondary_startup_64) movq %rax, %cr0 /* Setup a boot time stack */ - movq stack_start(%rip), %rsp + movq initial_stack(%rip), %rsp /* zero EFLAGS after setting rsp */ pushq $0 @@ -310,7 +310,7 @@ ENDPROC(secondary_startup_64) * start_secondary(). */ ENTRY(start_cpu0) - movq stack_start(%rip),%rsp + movq initial_stack(%rip),%rsp movq initial_code(%rip),%rax pushq $0 # fake return address to stop unwinder pushq $__KERNEL_CS # set correct cs @@ -319,17 +319,15 @@ ENTRY(start_cpu0) ENDPROC(start_cpu0) #endif - /* SMP bootup changes these two */ + /* Both SMP bootup and ACPI suspend change these variables */ __REFDATA .balign 8 GLOBAL(initial_code) .quad x86_64_start_kernel GLOBAL(initial_gs) .quad INIT_PER_CPU_VAR(irq_stack_union) - - GLOBAL(stack_start) + GLOBAL(initial_stack) .quad init_thread_union+THREAD_SIZE-8 - .word 0 __FINITDATA bad_address: diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 4a7903714065..9ebd0b0e73d9 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -40,8 +40,7 @@ static inline void stack_overflow_check(struct pt_regs *regs) if (user_mode(regs)) return; - if (regs->sp >= curbase + sizeof(struct thread_info) + - sizeof(struct pt_regs) + STACK_TOP_MARGIN && + if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN && regs->sp <= curbase + THREAD_SIZE) return; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 04cde527d728..8e36f249646e 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -50,6 +50,7 @@ #include <asm/apicdef.h> #include <asm/apic.h> #include <asm/nmi.h> +#include <asm/switch_to.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { @@ -166,21 +167,19 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_DX] = 0; gdb_regs[GDB_SI] = 0; gdb_regs[GDB_DI] = 0; - gdb_regs[GDB_BP] = *(unsigned long *)p->thread.sp; + gdb_regs[GDB_BP] = ((struct inactive_task_frame *)p->thread.sp)->bp; #ifdef CONFIG_X86_32 gdb_regs[GDB_DS] = __KERNEL_DS; gdb_regs[GDB_ES] = __KERNEL_DS; gdb_regs[GDB_PS] = 0; gdb_regs[GDB_CS] = __KERNEL_CS; - gdb_regs[GDB_PC] = p->thread.ip; gdb_regs[GDB_SS] = __KERNEL_DS; gdb_regs[GDB_FS] = 0xFFFF; gdb_regs[GDB_GS] = 0xFFFF; #else - gdb_regs32[GDB_PS] = *(unsigned long *)(p->thread.sp + 8); + gdb_regs32[GDB_PS] = 0; gdb_regs32[GDB_CS] = __KERNEL_CS; gdb_regs32[GDB_SS] = __KERNEL_DS; - gdb_regs[GDB_PC] = 0; gdb_regs[GDB_R8] = 0; gdb_regs[GDB_R9] = 0; gdb_regs[GDB_R10] = 0; @@ -190,6 +189,7 @@ void sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *p) gdb_regs[GDB_R14] = 0; gdb_regs[GDB_R15] = 0; #endif + gdb_regs[GDB_PC] = 0; gdb_regs[GDB_SP] = p->thread.sp; } diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index c2bedaea11f7..4afc67f5facc 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -184,7 +184,7 @@ out: static struct kobj_attribute type_attr = __ATTR_RO(type); -static struct bin_attribute data_attr = { +static struct bin_attribute data_attr __ro_after_init = { .attr = { .name = "data", .mode = S_IRUGO, diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 3692249a70f1..60b9949f1e65 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -29,7 +29,7 @@ #include <asm/x86_init.h> #include <asm/reboot.h> -static int kvmclock = 1; +static int kvmclock __ro_after_init = 1; static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME; static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK; static cycle_t kvm_sched_clock_offset; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 1acfd76e3e26..bbf3d5933eaa 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -332,7 +332,6 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .read_cr0 = native_read_cr0, .write_cr0 = native_write_cr0, .read_cr4 = native_read_cr4, - .read_cr4_safe = native_read_cr4_safe, .write_cr4 = native_write_cr4, #ifdef CONFIG_X86_64 .read_cr8 = native_read_cr8, @@ -389,7 +388,7 @@ NOKPROBE_SYMBOL(native_load_idt); #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) #endif -struct pv_mmu_ops pv_mmu_ops = { +struct pv_mmu_ops pv_mmu_ops __ro_after_init = { .read_cr2 = native_read_cr2, .write_cr2 = native_write_cr2, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 62c0b0ea2ce4..4002b475171c 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -32,6 +32,7 @@ #include <asm/tlbflush.h> #include <asm/mce.h> #include <asm/vm86.h> +#include <asm/switch_to.h> /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, @@ -513,6 +514,17 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) } /* + * Return saved PC of a blocked thread. + * What is this good for? it will be always the scheduler or ret_from_fork. + */ +unsigned long thread_saved_pc(struct task_struct *tsk) +{ + struct inactive_task_frame *frame = + (struct inactive_task_frame *) READ_ONCE(tsk->thread.sp); + return READ_ONCE_NOCHECK(frame->ret_addr); +} + +/* * Called from fs/proc with a reference on @p to find the function * which called into schedule(). This needs to be done carefully * because the task might wake up and we might look at a stack @@ -520,15 +532,18 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) */ unsigned long get_wchan(struct task_struct *p) { - unsigned long start, bottom, top, sp, fp, ip; + unsigned long start, bottom, top, sp, fp, ip, ret = 0; int count = 0; if (!p || p == current || p->state == TASK_RUNNING) return 0; + if (!try_get_task_stack(p)) + return 0; + start = (unsigned long)task_stack_page(p); if (!start) - return 0; + goto out; /* * Layout of the stack page: @@ -537,9 +552,7 @@ unsigned long get_wchan(struct task_struct *p) * PADDING * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING * stack - * ----------- bottom = start + sizeof(thread_info) - * thread_info - * ----------- start + * ----------- bottom = start * * The tasks stack pointer points at the location where the * framepointer is stored. The data on the stack is: @@ -550,20 +563,25 @@ unsigned long get_wchan(struct task_struct *p) */ top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; top -= 2 * sizeof(unsigned long); - bottom = start + sizeof(struct thread_info); + bottom = start; sp = READ_ONCE(p->thread.sp); if (sp < bottom || sp > top) - return 0; + goto out; - fp = READ_ONCE_NOCHECK(*(unsigned long *)sp); + fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp); do { if (fp < bottom || fp > top) - return 0; + goto out; ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long))); - if (!in_sched_functions(ip)) - return ip; + if (!in_sched_functions(ip)) { + ret = ip; + goto out; + } fp = READ_ONCE_NOCHECK(*(unsigned long *)fp); } while (count++ < 16 && p->state != TASK_RUNNING); - return 0; + +out: + put_task_stack(p); + return ret; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index d86be29c38c7..bd7be8efdc4c 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -55,17 +55,6 @@ #include <asm/switch_to.h> #include <asm/vm86.h> -asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); -asmlinkage void ret_from_kernel_thread(void) __asm__("ret_from_kernel_thread"); - -/* - * Return saved PC of a blocked thread. - */ -unsigned long thread_saved_pc(struct task_struct *tsk) -{ - return ((unsigned long *)tsk->thread.sp)[3]; -} - void __show_regs(struct pt_regs *regs, int all) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; @@ -101,7 +90,7 @@ void __show_regs(struct pt_regs *regs, int all) cr0 = read_cr0(); cr2 = read_cr2(); cr3 = read_cr3(); - cr4 = __read_cr4_safe(); + cr4 = __read_cr4(); printk(KERN_DEFAULT "CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4); @@ -133,35 +122,31 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, unsigned long arg, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); + struct fork_frame *fork_frame = container_of(childregs, struct fork_frame, regs); + struct inactive_task_frame *frame = &fork_frame->frame; struct task_struct *tsk; int err; - p->thread.sp = (unsigned long) childregs; + frame->bp = 0; + frame->ret_addr = (unsigned long) ret_from_fork; + p->thread.sp = (unsigned long) fork_frame; p->thread.sp0 = (unsigned long) (childregs+1); memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - p->thread.ip = (unsigned long) ret_from_kernel_thread; - task_user_gs(p) = __KERNEL_STACK_CANARY; - childregs->ds = __USER_DS; - childregs->es = __USER_DS; - childregs->fs = __KERNEL_PERCPU; - childregs->bx = sp; /* function */ - childregs->bp = arg; - childregs->orig_ax = -1; - childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; + frame->bx = sp; /* function */ + frame->di = arg; p->thread.io_bitmap_ptr = NULL; return 0; } + frame->bx = 0; *childregs = *current_pt_regs(); childregs->ax = 0; if (sp) childregs->sp = sp; - p->thread.ip = (unsigned long) ret_from_fork; task_user_gs(p) = get_user_gs(current_pt_regs()); p->thread.io_bitmap_ptr = NULL; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 63236d8f84bf..de9acaf2d371 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -50,8 +50,6 @@ #include <asm/switch_to.h> #include <asm/xen/hypervisor.h> -asmlinkage extern void ret_from_fork(void); - __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ @@ -141,12 +139,17 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, { int err; struct pt_regs *childregs; + struct fork_frame *fork_frame; + struct inactive_task_frame *frame; struct task_struct *me = current; p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE; childregs = task_pt_regs(p); - p->thread.sp = (unsigned long) childregs; - set_tsk_thread_flag(p, TIF_FORK); + fork_frame = container_of(childregs, struct fork_frame, regs); + frame = &fork_frame->frame; + frame->bp = 0; + frame->ret_addr = (unsigned long) ret_from_fork; + p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap_ptr = NULL; savesegment(gs, p->thread.gsindex); @@ -160,15 +163,11 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp, if (unlikely(p->flags & PF_KTHREAD)) { /* kernel thread */ memset(childregs, 0, sizeof(struct pt_regs)); - childregs->sp = (unsigned long)childregs; - childregs->ss = __KERNEL_DS; - childregs->bx = sp; /* function */ - childregs->bp = arg; - childregs->orig_ax = -1; - childregs->cs = __KERNEL_CS | get_kernel_rpl(); - childregs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; + frame->bx = sp; /* function */ + frame->r12 = arg; return 0; } + frame->bx = 0; *childregs = *current_pt_regs(); childregs->ax = 0; @@ -511,7 +510,7 @@ void set_personality_ia32(bool x32) current->personality &= ~READ_IMPLIES_EXEC; /* in_compat_syscall() uses the presence of the x32 syscall bit flag to determine compat status */ - current_thread_info()->status &= ~TS_COMPAT; + current->thread.status &= ~TS_COMPAT; } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); @@ -519,7 +518,7 @@ void set_personality_ia32(bool x32) current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ - current_thread_info()->status |= TS_COMPAT; + current->thread.status |= TS_COMPAT; } } EXPORT_SYMBOL_GPL(set_personality_ia32); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index f79576a541ff..ce94c38cf4d6 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -173,8 +173,8 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs) return sp; prev_esp = (u32 *)(context); - if (prev_esp) - return (unsigned long)prev_esp; + if (*prev_esp) + return (unsigned long)*prev_esp; return (unsigned long)regs; } @@ -934,7 +934,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value) */ regs->orig_ax = value; if (syscall_get_nr(child, regs) >= 0) - task_thread_info(child)->status |= TS_I386_REGS_POKED; + child->thread.status |= TS_I386_REGS_POKED; break; case offsetof(struct user32, regs.eflags): @@ -1250,7 +1250,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, #ifdef CONFIG_X86_64 -static struct user_regset x86_64_regsets[] __read_mostly = { +static struct user_regset x86_64_regsets[] __ro_after_init = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, .n = sizeof(struct user_regs_struct) / sizeof(long), @@ -1291,7 +1291,7 @@ static const struct user_regset_view user_x86_64_view = { #endif /* CONFIG_X86_64 */ #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION -static struct user_regset x86_32_regsets[] __read_mostly = { +static struct user_regset x86_32_regsets[] __ro_after_init = { [REGSET_GENERAL] = { .core_note_type = NT_PRSTATUS, .n = sizeof(struct user_regs_struct32) / sizeof(u32), @@ -1344,7 +1344,7 @@ static const struct user_regset_view user_x86_32_view = { */ u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -void update_regset_xstate_info(unsigned int size, u64 xstate_mask) +void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) { #ifdef CONFIG_X86_64 x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 63bf27d972b7..e244c19a2451 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -705,7 +705,7 @@ static void native_machine_power_off(void) tboot_shutdown(TB_SHUTDOWN_HALT); } -struct machine_ops machine_ops = { +struct machine_ops machine_ops __ro_after_init = { .power_off = native_machine_power_off, .shutdown = native_machine_shutdown, .emergency_restart = native_machine_emergency_restart, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 2c4bc85dfe90..eeb094ea794a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -210,9 +210,9 @@ EXPORT_SYMBOL(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) -__visible unsigned long mmu_cr4_features; +__visible unsigned long mmu_cr4_features __ro_after_init; #else -__visible unsigned long mmu_cr4_features = X86_CR4_PAE; +__visible unsigned long mmu_cr4_features __ro_after_init = X86_CR4_PAE; #endif /* Boot loader ID and version as integers, for the benefit of proc_dointvec */ @@ -1137,7 +1137,7 @@ void __init setup_arch(char **cmdline_p) * auditing all the early-boot CR4 manipulation would be needed to * rule it out. */ - mmu_cr4_features = __read_cr4_safe(); + mmu_cr4_features = __read_cr4(); memblock_set_current_limit(get_max_mapped()); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 7a40e068302d..2bbd27f89802 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -33,7 +33,7 @@ EXPORT_PER_CPU_SYMBOL(cpu_number); DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET; EXPORT_PER_CPU_SYMBOL(this_cpu_off); -unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = { +unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = { [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET, }; EXPORT_SYMBOL(__per_cpu_offset); @@ -246,7 +246,7 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_X86_64 per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack_union.irq_stack, cpu) + - IRQ_STACK_SIZE - 64; + IRQ_STACK_SIZE; #endif #ifdef CONFIG_NUMA per_cpu(x86_cpu_to_node_map, cpu) = diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 04cb3212db2d..da20ecb5397a 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -783,7 +783,7 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * than the tracee. */ #ifdef CONFIG_IA32_EMULATION - if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED)) + if (current->thread.status & (TS_COMPAT|TS_I386_REGS_POKED)) return __NR_ia32_restart_syscall; #endif #ifdef CONFIG_X86_X32_ABI diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 54e2f1a968a4..7249dcf2cbcb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -943,7 +943,6 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) per_cpu(cpu_current_top_of_stack, cpu) = (unsigned long)task_stack_page(idle) + THREAD_SIZE; #else - clear_tsk_thread_flag(idle, TIF_FORK); initial_gs = per_cpu_offset(cpu); #endif } @@ -970,7 +969,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu); initial_code = (unsigned long)start_secondary; - stack_start = idle->thread.sp; + initial_stack = idle->thread.sp; /* * Enable the espfix hack for this CPU diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 4738f5e0f2ab..0653788026e2 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -8,80 +8,69 @@ #include <linux/export.h> #include <linux/uaccess.h> #include <asm/stacktrace.h> +#include <asm/unwind.h> -static int save_stack_stack(void *data, char *name) +static int save_stack_address(struct stack_trace *trace, unsigned long addr, + bool nosched) { - return 0; -} - -static int -__save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched) -{ - struct stack_trace *trace = data; -#ifdef CONFIG_FRAME_POINTER - if (!reliable) - return 0; -#endif if (nosched && in_sched_functions(addr)) return 0; + if (trace->skip > 0) { trace->skip--; return 0; } - if (trace->nr_entries < trace->max_entries) { - trace->entries[trace->nr_entries++] = addr; - return 0; - } else { - return -1; /* no more room, stop walking the stack */ - } -} -static int save_stack_address(void *data, unsigned long addr, int reliable) -{ - return __save_stack_address(data, addr, reliable, false); + if (trace->nr_entries >= trace->max_entries) + return -1; + + trace->entries[trace->nr_entries++] = addr; + return 0; } -static int -save_stack_address_nosched(void *data, unsigned long addr, int reliable) +static void __save_stack_trace(struct stack_trace *trace, + struct task_struct *task, struct pt_regs *regs, + bool nosched) { - return __save_stack_address(data, addr, reliable, true); -} + struct unwind_state state; + unsigned long addr; -static const struct stacktrace_ops save_stack_ops = { - .stack = save_stack_stack, - .address = save_stack_address, - .walk_stack = print_context_stack, -}; + if (regs) + save_stack_address(trace, regs->ip, nosched); -static const struct stacktrace_ops save_stack_ops_nosched = { - .stack = save_stack_stack, - .address = save_stack_address_nosched, - .walk_stack = print_context_stack, -}; + for (unwind_start(&state, task, regs, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr || save_stack_address(trace, addr, nosched)) + break; + } + + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} /* * Save stack-backtrace addresses into a stack_trace buffer. */ void save_stack_trace(struct stack_trace *trace) { - dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; + __save_stack_trace(trace, current, NULL, false); } EXPORT_SYMBOL_GPL(save_stack_trace); void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) { - dump_trace(current, regs, NULL, 0, &save_stack_ops, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; + __save_stack_trace(trace, current, regs, false); } void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) { - dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace); - if (trace->nr_entries < trace->max_entries) - trace->entries[trace->nr_entries++] = ULONG_MAX; + if (!try_get_task_stack(tsk)) + return; + + __save_stack_trace(trace, tsk, NULL, true); + + put_task_stack(tsk); } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index b70ca12dd389..bd4e3d4d3625 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -292,12 +292,30 @@ DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check) +#ifdef CONFIG_VMAP_STACK +__visible void __noreturn handle_stack_overflow(const char *message, + struct pt_regs *regs, + unsigned long fault_address) +{ + printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n", + (void *)fault_address, current->stack, + (char *)current->stack + THREAD_SIZE - 1); + die(message, regs, 0); + + /* Be absolutely certain we don't return. */ + panic(message); +} +#endif + #ifdef CONFIG_X86_64 /* Runs on IST stack */ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) { static const char str[] = "double fault"; struct task_struct *tsk = current; +#ifdef CONFIG_VMAP_STACK + unsigned long cr2; +#endif #ifdef CONFIG_X86_ESPFIX64 extern unsigned char native_irq_return_iret[]; @@ -332,6 +350,49 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_DF; +#ifdef CONFIG_VMAP_STACK + /* + * If we overflow the stack into a guard page, the CPU will fail + * to deliver #PF and will send #DF instead. Similarly, if we + * take any non-IST exception while too close to the bottom of + * the stack, the processor will get a page fault while + * delivering the exception and will generate a double fault. + * + * According to the SDM (footnote in 6.15 under "Interrupt 14 - + * Page-Fault Exception (#PF): + * + * Processors update CR2 whenever a page fault is detected. If a + * second page fault occurs while an earlier page fault is being + * deliv- ered, the faulting linear address of the second fault will + * overwrite the contents of CR2 (replacing the previous + * address). These updates to CR2 occur even if the page fault + * results in a double fault or occurs during the delivery of a + * double fault. + * + * The logic below has a small possibility of incorrectly diagnosing + * some errors as stack overflows. For example, if the IDT or GDT + * gets corrupted such that #GP delivery fails due to a bad descriptor + * causing #GP and we hit this condition while CR2 coincidentally + * points to the stack guard page, we'll think we overflowed the + * stack. Given that we're going to panic one way or another + * if this happens, this isn't necessarily worth fixing. + * + * If necessary, we could improve the test by only diagnosing + * a stack overflow if the saved RSP points within 47 bytes of + * the bottom of the stack: if RSP == tsk_stack + 48 and we + * take an exception, the stack is already aligned and there + * will be enough room SS, RSP, RFLAGS, CS, RIP, and a + * possible error code, so a stack overflow would *not* double + * fault. With any less space left, exception delivery could + * fail, and, as a practical matter, we've overflowed the + * stack even if the actual trigger for the double fault was + * something else. + */ + cr2 = read_cr2(); + if ((unsigned long)task_stack_page(tsk) - 1 - cr2 < PAGE_SIZE) + handle_stack_overflow("kernel stack overflow (double-fault)", regs, cr2); +#endif + #ifdef CONFIG_DOUBLEFAULT df_debug(regs, error_code); #endif diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c new file mode 100644 index 000000000000..a2456d4d286a --- /dev/null +++ b/arch/x86/kernel/unwind_frame.c @@ -0,0 +1,93 @@ +#include <linux/sched.h> +#include <asm/ptrace.h> +#include <asm/bitops.h> +#include <asm/stacktrace.h> +#include <asm/unwind.h> + +#define FRAME_HEADER_SIZE (sizeof(long) * 2) + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + unsigned long addr; + unsigned long *addr_p = unwind_get_return_address_ptr(state); + + if (unwind_done(state)) + return 0; + + addr = ftrace_graph_ret_addr(state->task, &state->graph_idx, *addr_p, + addr_p); + + return __kernel_text_address(addr) ? addr : 0; +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +static bool update_stack_state(struct unwind_state *state, void *addr, + size_t len) +{ + struct stack_info *info = &state->stack_info; + + /* + * If addr isn't on the current stack, switch to the next one. + * + * We may have to traverse multiple stacks to deal with the possibility + * that 'info->next_sp' could point to an empty stack and 'addr' could + * be on a subsequent stack. + */ + while (!on_stack(info, addr, len)) + if (get_stack_info(info->next_sp, state->task, info, + &state->stack_mask)) + return false; + + return true; +} + +bool unwind_next_frame(struct unwind_state *state) +{ + unsigned long *next_bp; + + if (unwind_done(state)) + return false; + + next_bp = (unsigned long *)*state->bp; + + /* make sure the next frame's data is accessible */ + if (!update_stack_state(state, next_bp, FRAME_HEADER_SIZE)) + return false; + + /* move to the next frame */ + state->bp = next_bp; + return true; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + memset(state, 0, sizeof(*state)); + state->task = task; + + /* don't even attempt to start from user mode regs */ + if (regs && user_mode(regs)) { + state->stack_info.type = STACK_TYPE_UNKNOWN; + return; + } + + /* set up the starting stack frame */ + state->bp = get_frame_pointer(task, regs); + + /* initialize stack info and make sure the frame data is accessible */ + get_stack_info(state->bp, state->task, &state->stack_info, + &state->stack_mask); + update_stack_state(state, state->bp, FRAME_HEADER_SIZE); + + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + while (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + state->bp < first_frame)) + unwind_next_frame(state); +} +EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c new file mode 100644 index 000000000000..b5a834c93065 --- /dev/null +++ b/arch/x86/kernel/unwind_guess.c @@ -0,0 +1,43 @@ +#include <linux/sched.h> +#include <linux/ftrace.h> +#include <asm/ptrace.h> +#include <asm/bitops.h> +#include <asm/stacktrace.h> +#include <asm/unwind.h> + +bool unwind_next_frame(struct unwind_state *state) +{ + struct stack_info *info = &state->stack_info; + + if (unwind_done(state)) + return false; + + do { + for (state->sp++; state->sp < info->end; state->sp++) + if (__kernel_text_address(*state->sp)) + return true; + + state->sp = info->next_sp; + + } while (!get_stack_info(state->sp, state->task, info, + &state->stack_mask)); + + return false; +} +EXPORT_SYMBOL_GPL(unwind_next_frame); + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + memset(state, 0, sizeof(*state)); + + state->task = task; + state->sp = first_frame; + + get_stack_info(first_frame, state->task, &state->stack_info, + &state->stack_mask); + + if (!__kernel_text_address(*first_frame)) + unwind_next_frame(state); +} +EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 76c5e52436c4..0bd9f1287f39 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -91,7 +91,7 @@ struct x86_cpuinit_ops x86_cpuinit = { static void default_nmi_init(void) { }; static int default_i8042_detect(void) { return 1; }; -struct x86_platform_ops x86_platform = { +struct x86_platform_ops x86_platform __ro_after_init = { .calibrate_cpu = native_calibrate_cpu, .calibrate_tsc = native_calibrate_tsc, .get_wallclock = mach_get_cmos_time, @@ -108,7 +108,7 @@ struct x86_platform_ops x86_platform = { EXPORT_SYMBOL_GPL(x86_platform); #if defined(CONFIG_PCI_MSI) -struct x86_msi_ops x86_msi = { +struct x86_msi_ops x86_msi __ro_after_init = { .setup_msi_irqs = native_setup_msi_irqs, .teardown_msi_irq = native_teardown_msi_irq, .teardown_msi_irqs = default_teardown_msi_irqs, @@ -137,7 +137,7 @@ void arch_restore_msi_irqs(struct pci_dev *dev) } #endif -struct x86_io_apic_ops x86_io_apic_ops = { +struct x86_io_apic_ops x86_io_apic_ops __ro_after_init = { .read = native_io_apic_read, .disable = native_disable_io_apic, }; diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index af523d84d102..1e6b84b96ea6 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -4961,7 +4961,7 @@ static inline void avic_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -static struct kvm_x86_ops svm_x86_ops = { +static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 5cede40e2552..121fdf6e9ed0 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -11177,7 +11177,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEATURE_CONTROL_LMCE; } -static struct kvm_x86_ops vmx_x86_ops = { +static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios, .hardware_setup = hardware_setup, diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index dc8023060456..0b92fce3e6c0 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -753,6 +753,38 @@ no_context(struct pt_regs *regs, unsigned long error_code, return; } +#ifdef CONFIG_VMAP_STACK + /* + * Stack overflow? During boot, we can fault near the initial + * stack in the direct map, but that's not an overflow -- check + * that we're in vmalloc space to avoid this. + */ + if (is_vmalloc_addr((void *)address) && + (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) || + address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) { + register void *__sp asm("rsp"); + unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *); + /* + * We're likely to be running with very little stack space + * left. It's plausible that we'd hit this condition but + * double-fault even before we get this far, in which case + * we're fine: the double-fault handler will deal with it. + * + * We don't want to make it all the way into the oops code + * and then double-fault, though, because we're likely to + * break the console driver and lose most of the stack dump. + */ + asm volatile ("movq %[stack], %%rsp\n\t" + "call handle_stack_overflow\n\t" + "1: jmp 1b" + : "+r" (__sp) + : "D" ("kernel stack overflow (page fault)"), + "S" (regs), "d" (address), + [stack] "rm" (stack)); + unreachable(); + } +#endif + /* * 32-bit: * diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index bda8d5eef04d..ddd2661c4502 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -40,17 +40,26 @@ * You need to add an if/def entry if you introduce a new memory region * compatible with KASLR. Your entry must be in logical order with memory * layout. For example, ESPFIX is before EFI because its virtual address is - * before. You also need to add a BUILD_BUG_ON in kernel_randomize_memory to + * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to * ensure that this order is correct and won't be changed. */ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; -static const unsigned long vaddr_end = VMEMMAP_START; + +#if defined(CONFIG_X86_ESPFIX64) +static const unsigned long vaddr_end = ESPFIX_BASE_ADDR; +#elif defined(CONFIG_EFI) +static const unsigned long vaddr_end = EFI_VA_START; +#else +static const unsigned long vaddr_end = __START_KERNEL_map; +#endif /* Default values */ unsigned long page_offset_base = __PAGE_OFFSET_BASE; EXPORT_SYMBOL(page_offset_base); unsigned long vmalloc_base = __VMALLOC_BASE; EXPORT_SYMBOL(vmalloc_base); +unsigned long vmemmap_base = __VMEMMAP_BASE; +EXPORT_SYMBOL(vmemmap_base); /* * Memory regions randomized by KASLR (except modules that use a separate logic @@ -63,6 +72,7 @@ static __initdata struct kaslr_memory_region { } kaslr_regions[] = { { &page_offset_base, 64/* Maximum */ }, { &vmalloc_base, VMALLOC_SIZE_TB }, + { &vmemmap_base, 1 }, }; /* Get size in bytes used by the memory region */ @@ -89,6 +99,18 @@ void __init kernel_randomize_memory(void) struct rnd_state rand_state; unsigned long remain_entropy; + /* + * All these BUILD_BUG_ON checks ensures the memory layout is + * consistent with the vaddr_start/vaddr_end variables. + */ + BUILD_BUG_ON(vaddr_start >= vaddr_end); + BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) && + vaddr_end >= EFI_VA_START); + BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) || + config_enabled(CONFIG_EFI)) && + vaddr_end >= __START_KERNEL_map); + BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + if (!kaslr_memory_enabled()) return; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 4dbe65622810..a7655f6caf7d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -77,10 +77,25 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, unsigned cpu = smp_processor_id(); if (likely(prev != next)) { + if (IS_ENABLED(CONFIG_VMAP_STACK)) { + /* + * If our current stack is in vmalloc space and isn't + * mapped in the new pgd, we'll double-fault. Forcibly + * map it. + */ + unsigned int stack_pgd_index = pgd_index(current_stack_pointer()); + + pgd_t *pgd = next->pgd + stack_pgd_index; + + if (unlikely(pgd_none(*pgd))) + set_pgd(pgd, init_mm.pgd[stack_pgd_index]); + } + #ifdef CONFIG_SMP this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); this_cpu_write(cpu_tlbstate.active_mm, next); #endif + cpumask_set_cpu(cpu, mm_cpumask(next)); /* diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c index cb31a4440e58..a2488b6e27d6 100644 --- a/arch/x86/oprofile/backtrace.c +++ b/arch/x86/oprofile/backtrace.c @@ -16,27 +16,7 @@ #include <asm/ptrace.h> #include <asm/stacktrace.h> - -static int backtrace_stack(void *data, char *name) -{ - /* Yes, we want all stacks */ - return 0; -} - -static int backtrace_address(void *data, unsigned long addr, int reliable) -{ - unsigned int *depth = data; - - if ((*depth)--) - oprofile_add_trace(addr); - return 0; -} - -static struct stacktrace_ops backtrace_ops = { - .stack = backtrace_stack, - .address = backtrace_address, - .walk_stack = print_context_stack, -}; +#include <asm/unwind.h> #ifdef CONFIG_COMPAT static struct stack_frame_ia32 * @@ -113,10 +93,29 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth) struct stack_frame *head = (struct stack_frame *)frame_pointer(regs); if (!user_mode(regs)) { - unsigned long stack = kernel_stack_pointer(regs); - if (depth) - dump_trace(NULL, regs, (unsigned long *)stack, 0, - &backtrace_ops, &depth); + struct unwind_state state; + unsigned long addr; + + if (!depth) + return; + + oprofile_add_trace(regs->ip); + + if (!--depth) + return; + + for (unwind_start(&state, current, regs, NULL); + !unwind_done(&state); unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr) + break; + + oprofile_add_trace(addr); + + if (!--depth) + break; + } + return; } diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 9770e55e768f..1d97cea3b3a4 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -120,9 +120,12 @@ static unsigned long __init bios32_service(unsigned long service) static struct { unsigned long address; unsigned short segment; -} pci_indirect = { 0, __KERNEL_CS }; +} pci_indirect __ro_after_init = { + .address = 0, + .segment = __KERNEL_CS, +}; -static int pci_bios_present; +static int pci_bios_present __ro_after_init; static int __init check_pcibios(void) { diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index b12c26e2e309..53cace2ec0e2 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -130,7 +130,7 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); ctxt->cr3 = read_cr3(); - ctxt->cr4 = __read_cr4_safe(); + ctxt->cr4 = __read_cr4(); #ifdef CONFIG_X86_64 ctxt->cr8 = read_cr8(); #endif diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index a7ef7b131e25..5766ead6fdb9 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -194,7 +194,7 @@ int peek_user(struct task_struct *child, long addr, long data) static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { - int err, n, cpu = ((struct thread_info *) child->stack)->cpu; + int err, n, cpu = task_cpu(child); struct user_i387_struct fpregs; err = save_i387_registers(userspace_pid[cpu], @@ -211,7 +211,7 @@ static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *c static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { - int n, cpu = ((struct thread_info *) child->stack)->cpu; + int n, cpu = task_cpu(child); struct user_i387_struct fpregs; n = copy_from_user(&fpregs, buf, sizeof(fpregs)); @@ -224,7 +224,7 @@ static int set_fpregs(struct user_i387_struct __user *buf, struct task_struct *c static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { - int err, n, cpu = ((struct thread_info *) child->stack)->cpu; + int err, n, cpu = task_cpu(child); struct user_fxsr_struct fpregs; err = save_fpx_registers(userspace_pid[cpu], (unsigned long *) &fpregs); @@ -240,7 +240,7 @@ static int get_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct * static int set_fpxregs(struct user_fxsr_struct __user *buf, struct task_struct *child) { - int n, cpu = ((struct thread_info *) child->stack)->cpu; + int n, cpu = task_cpu(child); struct user_fxsr_struct fpregs; n = copy_from_user(&fpregs, buf, sizeof(fpregs)); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index bc9aaba01a22..f1d2182e071f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1237,7 +1237,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_cr0 = xen_write_cr0, .read_cr4 = native_read_cr4, - .read_cr4_safe = native_read_cr4_safe, .write_cr4 = xen_write_cr4, #ifdef CONFIG_X86_64 diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 96de97a46079..4025291ea0ae 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -940,15 +940,13 @@ static void build_inv_irt(struct iommu_cmd *cmd, u16 devid) * Writes the command to the IOMMUs command buffer and informs the * hardware about the new command. */ -static int iommu_queue_command_sync(struct amd_iommu *iommu, - struct iommu_cmd *cmd, - bool sync) +static int __iommu_queue_command_sync(struct amd_iommu *iommu, + struct iommu_cmd *cmd, + bool sync) { u32 left, tail, head, next_tail; - unsigned long flags; again: - spin_lock_irqsave(&iommu->lock, flags); head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); @@ -957,15 +955,14 @@ again: if (left <= 2) { struct iommu_cmd sync_cmd; - volatile u64 sem = 0; int ret; - build_completion_wait(&sync_cmd, (u64)&sem); - copy_cmd_to_buffer(iommu, &sync_cmd, tail); + iommu->cmd_sem = 0; - spin_unlock_irqrestore(&iommu->lock, flags); + build_completion_wait(&sync_cmd, (u64)&iommu->cmd_sem); + copy_cmd_to_buffer(iommu, &sync_cmd, tail); - if ((ret = wait_on_sem(&sem)) != 0) + if ((ret = wait_on_sem(&iommu->cmd_sem)) != 0) return ret; goto again; @@ -976,9 +973,21 @@ again: /* We need to sync now to make sure all commands are processed */ iommu->need_sync = sync; + return 0; +} + +static int iommu_queue_command_sync(struct amd_iommu *iommu, + struct iommu_cmd *cmd, + bool sync) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&iommu->lock, flags); + ret = __iommu_queue_command_sync(iommu, cmd, sync); spin_unlock_irqrestore(&iommu->lock, flags); - return 0; + return ret; } static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) @@ -993,19 +1002,29 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) static int iommu_completion_wait(struct amd_iommu *iommu) { struct iommu_cmd cmd; - volatile u64 sem = 0; + unsigned long flags; int ret; if (!iommu->need_sync) return 0; - build_completion_wait(&cmd, (u64)&sem); - ret = iommu_queue_command_sync(iommu, &cmd, false); + build_completion_wait(&cmd, (u64)&iommu->cmd_sem); + + spin_lock_irqsave(&iommu->lock, flags); + + iommu->cmd_sem = 0; + + ret = __iommu_queue_command_sync(iommu, &cmd, false); if (ret) - return ret; + goto out_unlock; + + ret = wait_on_sem(&iommu->cmd_sem); - return wait_on_sem(&sem); +out_unlock: + spin_unlock_irqrestore(&iommu->lock, flags); + + return ret; } static int iommu_flush_dte(struct amd_iommu *iommu, u16 devid) diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index caf5e3822715..9652848e3155 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -524,6 +524,8 @@ struct amd_iommu { struct irq_domain *ir_domain; struct irq_domain *msi_domain; #endif + + volatile u64 __aligned(8) cmd_sem; }; #define ACPIHID_UID_LEN 256 diff --git a/fs/proc/base.c b/fs/proc/base.c index ac0df4dde823..3b792ab3c0dc 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -483,7 +483,7 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, save_stack_trace_tsk(task, &trace); for (i = 0; i < trace.nr_entries; i++) { - seq_printf(m, "[<%pK>] %pS\n", + seq_printf(m, "[<%pK>] %pB\n", (void *)entries[i], (void *)entries[i]); } unlock_trace(task); diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 7d565afe35d2..6f93ac46e7f0 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -795,7 +795,12 @@ struct ftrace_ret_stack { unsigned long func; unsigned long long calltime; unsigned long long subtime; +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST unsigned long fp; +#endif +#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + unsigned long *retp; +#endif }; /* @@ -807,7 +812,10 @@ extern void return_to_handler(void); extern int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer); + unsigned long frame_pointer, unsigned long *retp); + +unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, + unsigned long ret, unsigned long *retp); /* * Sometimes we don't want to trace a function with the function @@ -870,6 +878,13 @@ static inline int task_curr_ret_stack(struct task_struct *tsk) return -1; } +static inline unsigned long +ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, + unsigned long *retp) +{ + return ret; +} + static inline void pause_graph_tracing(void) { } static inline void unpause_graph_tracing(void) { } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index f8834f820ec2..325f649d77ff 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -15,6 +15,8 @@ #include <net/net_namespace.h> #include <linux/sched/rt.h> +#include <asm/thread_info.h> + #ifdef CONFIG_SMP # define INIT_PUSHABLE_TASKS(tsk) \ .pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), @@ -183,12 +185,21 @@ extern struct task_group root_task_group; # define INIT_KASAN(tsk) #endif +#ifdef CONFIG_THREAD_INFO_IN_TASK +# define INIT_TASK_TI(tsk) \ + .thread_info = INIT_THREAD_INFO(tsk), \ + .stack_refcount = ATOMIC_INIT(1), +#else +# define INIT_TASK_TI(tsk) +#endif + /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) */ #define INIT_TASK(tsk) \ { \ + INIT_TASK_TI(tsk) \ .state = 0, \ .stack = init_stack, \ .usage = ATOMIC_INIT(2), \ diff --git a/include/linux/sched.h b/include/linux/sched.h index f76d75fc9eaf..7543a476178b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1471,6 +1471,13 @@ struct tlbflush_unmap_batch { }; struct task_struct { +#ifdef CONFIG_THREAD_INFO_IN_TASK + /* + * For reasons of header soup (see current_thread_info()), this + * must be the first element of task_struct. + */ + struct thread_info thread_info; +#endif volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */ void *stack; atomic_t usage; @@ -1480,6 +1487,9 @@ struct task_struct { #ifdef CONFIG_SMP struct llist_node wake_entry; int on_cpu; +#ifdef CONFIG_THREAD_INFO_IN_TASK + unsigned int cpu; /* current CPU */ +#endif unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -1936,6 +1946,13 @@ struct task_struct { #ifdef CONFIG_MMU struct task_struct *oom_reaper_list; #endif +#ifdef CONFIG_VMAP_STACK + struct vm_struct *stack_vm_area; +#endif +#ifdef CONFIG_THREAD_INFO_IN_TASK + /* A live task holds one reference. */ + atomic_t stack_refcount; +#endif /* CPU-specific state of this task */ struct thread_struct thread; /* @@ -1952,6 +1969,18 @@ extern int arch_task_struct_size __read_mostly; # define arch_task_struct_size (sizeof(struct task_struct)) #endif +#ifdef CONFIG_VMAP_STACK +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return t->stack_vm_area; +} +#else +static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) +{ + return NULL; +} +#endif + /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) @@ -2586,7 +2615,9 @@ extern void ia64_set_curr_task(int cpu, struct task_struct *p); void yield(void); union thread_union { +#ifndef CONFIG_THREAD_INFO_IN_TASK struct thread_info thread_info; +#endif unsigned long stack[THREAD_SIZE/sizeof(long)]; }; @@ -3074,10 +3105,34 @@ static inline void threadgroup_change_end(struct task_struct *tsk) cgroup_threadgroup_change_end(tsk); } -#ifndef __HAVE_THREAD_FUNCTIONS +#ifdef CONFIG_THREAD_INFO_IN_TASK + +static inline struct thread_info *task_thread_info(struct task_struct *task) +{ + return &task->thread_info; +} + +/* + * When accessing the stack of a non-current task that might exit, use + * try_get_task_stack() instead. task_stack_page will return a pointer + * that could get freed out from under you. + */ +static inline void *task_stack_page(const struct task_struct *task) +{ + return task->stack; +} + +#define setup_thread_stack(new,old) do { } while(0) + +static inline unsigned long *end_of_stack(const struct task_struct *task) +{ + return task->stack; +} + +#elif !defined(__HAVE_THREAD_FUNCTIONS) #define task_thread_info(task) ((struct thread_info *)(task)->stack) -#define task_stack_page(task) ((task)->stack) +#define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { @@ -3104,6 +3159,24 @@ static inline unsigned long *end_of_stack(struct task_struct *p) } #endif + +#ifdef CONFIG_THREAD_INFO_IN_TASK +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return atomic_inc_not_zero(&tsk->stack_refcount) ? + task_stack_page(tsk) : NULL; +} + +extern void put_task_stack(struct task_struct *tsk); +#else +static inline void *try_get_task_stack(struct task_struct *tsk) +{ + return task_stack_page(tsk); +} + +static inline void put_task_stack(struct task_struct *tsk) {} +#endif + #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) @@ -3390,7 +3463,11 @@ static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) static inline unsigned int task_cpu(const struct task_struct *p) { +#ifdef CONFIG_THREAD_INFO_IN_TASK + return p->cpu; +#else return task_thread_info(p)->cpu; +#endif } static inline int task_node(const struct task_struct *p) diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 2b5b10eed74f..45f004e9cc59 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -13,6 +13,21 @@ struct timespec; struct compat_timespec; +#ifdef CONFIG_THREAD_INFO_IN_TASK +struct thread_info { + unsigned long flags; /* low level flags */ +}; + +#define INIT_THREAD_INFO(tsk) \ +{ \ + .flags = 0, \ +} +#endif + +#ifdef CONFIG_THREAD_INFO_IN_TASK +#define current_thread_info() ((struct thread_info *)current) +#endif + /* * System call restart block. */ diff --git a/init/Kconfig b/init/Kconfig index cac3f096050d..3b9a47fe843b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -26,6 +26,16 @@ config IRQ_WORK config BUILDTIME_EXTABLE_SORT bool +config THREAD_INFO_IN_TASK + bool + help + Select this to move thread_info off the stack into task_struct. To + make this work, an arch will need to remove all thread_info fields + except flags and fix any runtime bugs. + + One subtle change that will be needed is to use try_get_task_stack() + and put_task_stack() in save_thread_stack_tsk() and get_wchan(). + menu "General setup" config BROKEN diff --git a/init/init_task.c b/init/init_task.c index ba0a7f362d9e..11f83be1fa79 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -22,5 +22,8 @@ EXPORT_SYMBOL(init_task); * Initial thread structure. Alignment of this is handled by a special * linker map entry. */ -union thread_union init_thread_union __init_task_data = - { INIT_THREAD_INFO(init_task) }; +union thread_union init_thread_union __init_task_data = { +#ifndef CONFIG_THREAD_INFO_IN_TASK + INIT_THREAD_INFO(init_task) +#endif +}; diff --git a/kernel/fork.c b/kernel/fork.c index beb31725f7e2..c060c7e7c247 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -158,19 +158,83 @@ void __weak arch_release_thread_stack(unsigned long *stack) * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ -# if THREAD_SIZE >= PAGE_SIZE -static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, - int node) +# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK) + +#ifdef CONFIG_VMAP_STACK +/* + * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB + * flush. Try to minimize the number of calls by caching stacks. + */ +#define NR_CACHED_STACKS 2 +static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); +#endif + +static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) { +#ifdef CONFIG_VMAP_STACK + void *stack; + int i; + + local_irq_disable(); + for (i = 0; i < NR_CACHED_STACKS; i++) { + struct vm_struct *s = this_cpu_read(cached_stacks[i]); + + if (!s) + continue; + this_cpu_write(cached_stacks[i], NULL); + + tsk->stack_vm_area = s; + local_irq_enable(); + return s->addr; + } + local_irq_enable(); + + stack = __vmalloc_node_range(THREAD_SIZE, THREAD_SIZE, + VMALLOC_START, VMALLOC_END, + THREADINFO_GFP | __GFP_HIGHMEM, + PAGE_KERNEL, + 0, node, __builtin_return_address(0)); + + /* + * We can't call find_vm_area() in interrupt context, and + * free_thread_stack() can be called in interrupt context, + * so cache the vm_struct. + */ + if (stack) + tsk->stack_vm_area = find_vm_area(stack); + return stack; +#else struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); return page ? page_address(page) : NULL; +#endif } -static inline void free_thread_stack(unsigned long *stack) +static inline void free_thread_stack(struct task_struct *tsk) { - __free_pages(virt_to_page(stack), THREAD_SIZE_ORDER); +#ifdef CONFIG_VMAP_STACK + if (task_stack_vm_area(tsk)) { + unsigned long flags; + int i; + + local_irq_save(flags); + for (i = 0; i < NR_CACHED_STACKS; i++) { + if (this_cpu_read(cached_stacks[i])) + continue; + + this_cpu_write(cached_stacks[i], tsk->stack_vm_area); + local_irq_restore(flags); + return; + } + local_irq_restore(flags); + + vfree(tsk->stack); + return; + } +#endif + + __free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER); } # else static struct kmem_cache *thread_stack_cache; @@ -181,9 +245,9 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, return kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); } -static void free_thread_stack(unsigned long *stack) +static void free_thread_stack(struct task_struct *tsk) { - kmem_cache_free(thread_stack_cache, stack); + kmem_cache_free(thread_stack_cache, tsk->stack); } void thread_stack_cache_init(void) @@ -213,24 +277,76 @@ struct kmem_cache *vm_area_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; -static void account_kernel_stack(unsigned long *stack, int account) +static void account_kernel_stack(struct task_struct *tsk, int account) { - /* All stack pages are in the same zone and belong to the same memcg. */ - struct page *first_page = virt_to_page(stack); + void *stack = task_stack_page(tsk); + struct vm_struct *vm = task_stack_vm_area(tsk); + + BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0); + + if (vm) { + int i; - mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, - THREAD_SIZE / 1024 * account); + BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE); - memcg_kmem_update_page_stat( - first_page, MEMCG_KERNEL_STACK_KB, - account * (THREAD_SIZE / 1024)); + for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { + mod_zone_page_state(page_zone(vm->pages[i]), + NR_KERNEL_STACK_KB, + PAGE_SIZE / 1024 * account); + } + + /* All stack pages belong to the same memcg. */ + memcg_kmem_update_page_stat(vm->pages[0], MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); + } else { + /* + * All stack pages are in the same zone and belong to the + * same memcg. + */ + struct page *first_page = virt_to_page(stack); + + mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB, + THREAD_SIZE / 1024 * account); + + memcg_kmem_update_page_stat(first_page, MEMCG_KERNEL_STACK_KB, + account * (THREAD_SIZE / 1024)); + } } -void free_task(struct task_struct *tsk) +static void release_task_stack(struct task_struct *tsk) { - account_kernel_stack(tsk->stack, -1); + account_kernel_stack(tsk, -1); arch_release_thread_stack(tsk->stack); - free_thread_stack(tsk->stack); + free_thread_stack(tsk); + tsk->stack = NULL; +#ifdef CONFIG_VMAP_STACK + tsk->stack_vm_area = NULL; +#endif +} + +#ifdef CONFIG_THREAD_INFO_IN_TASK +void put_task_stack(struct task_struct *tsk) +{ + if (atomic_dec_and_test(&tsk->stack_refcount)) + release_task_stack(tsk); +} +#endif + +void free_task(struct task_struct *tsk) +{ +#ifndef CONFIG_THREAD_INFO_IN_TASK + /* + * The task is finally done with both the stack and thread_info, + * so free both. + */ + release_task_stack(tsk); +#else + /* + * If the task had a separate stack allocation, it should be gone + * by now. + */ + WARN_ON_ONCE(atomic_read(&tsk->stack_refcount) != 0); +#endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); put_seccomp_filter(tsk); @@ -342,6 +458,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; unsigned long *stack; + struct vm_struct *stack_vm_area; int err; if (node == NUMA_NO_NODE) @@ -354,11 +471,26 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) if (!stack) goto free_tsk; + stack_vm_area = task_stack_vm_area(tsk); + err = arch_dup_task_struct(tsk, orig); + + /* + * arch_dup_task_struct() clobbers the stack-related fields. Make + * sure they're properly initialized before using any stack-related + * functions again. + */ + tsk->stack = stack; +#ifdef CONFIG_VMAP_STACK + tsk->stack_vm_area = stack_vm_area; +#endif +#ifdef CONFIG_THREAD_INFO_IN_TASK + atomic_set(&tsk->stack_refcount, 1); +#endif + if (err) goto free_stack; - tsk->stack = stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under @@ -390,14 +522,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - account_kernel_stack(stack, 1); + account_kernel_stack(tsk, 1); kcov_task_init(tsk); return tsk; free_stack: - free_thread_stack(stack); + free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; @@ -1715,6 +1847,7 @@ bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); exit_creds(p); bad_fork_free: + put_task_stack(p); free_task(p); fork_out: return ERR_PTR(retval); diff --git a/kernel/kthread.c b/kernel/kthread.c index 9ff173dca1ae..4ab4c3766a80 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -64,7 +64,7 @@ static inline struct kthread *to_kthread(struct task_struct *k) static struct kthread *to_live_kthread(struct task_struct *k) { struct completion *vfork = ACCESS_ONCE(k->vfork_done); - if (likely(vfork)) + if (likely(vfork) && try_get_task_stack(k)) return __to_kthread(vfork); return NULL; } @@ -425,8 +425,10 @@ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_live_kthread(k); - if (kthread) + if (kthread) { __kthread_unpark(k, kthread); + put_task_stack(k); + } } EXPORT_SYMBOL_GPL(kthread_unpark); @@ -455,6 +457,7 @@ int kthread_park(struct task_struct *k) wait_for_completion(&kthread->parked); } } + put_task_stack(k); ret = 0; } return ret; @@ -490,6 +493,7 @@ int kthread_stop(struct task_struct *k) __kthread_unpark(k, kthread); wake_up_process(k); wait_for_completion(&kthread->exited); + put_task_stack(k); } ret = k->exit_code; put_task_struct(k); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fac6492f0b98..94732d1ab00a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2781,6 +2781,10 @@ static struct rq *finish_task_switch(struct task_struct *prev) * task and put them back on the free list. */ kprobe_flush_task(prev); + + /* Task is done with its stack. */ + put_task_stack(prev); + put_task_struct(prev); } @@ -3403,7 +3407,6 @@ static void __sched notrace __schedule(bool preempt) balance_callback(rq); } -STACK_FRAME_NON_STANDARD(__schedule); /* switch_to() */ void __noreturn do_task_dead(void) { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 58df5590d028..055f935d4421 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1021,7 +1021,11 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) * per-task data have been completed by this moment. */ smp_wmb(); +#ifdef CONFIG_THREAD_INFO_IN_TASK + p->cpu = cpu; +#else task_thread_info(p)->cpu = cpu; +#endif p->wake_cpu = cpu; #endif } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index f4b86e8ca1e7..ba3326785ca4 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -24,11 +24,6 @@ config HAVE_FUNCTION_GRAPH_TRACER help See Documentation/trace/ftrace-design.txt -config HAVE_FUNCTION_GRAPH_FP_TEST - bool - help - See Documentation/trace/ftrace-design.txt - config HAVE_DYNAMIC_FTRACE bool help diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 7363ccf79512..0cbe38a844fa 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -119,7 +119,7 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, /* Add a function return address to the trace stack on thread info.*/ int ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer) + unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; int index; @@ -171,7 +171,12 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, current->ret_stack[index].func = func; current->ret_stack[index].calltime = calltime; current->ret_stack[index].subtime = 0; +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST current->ret_stack[index].fp = frame_pointer; +#endif +#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR + current->ret_stack[index].retp = retp; +#endif *depth = current->curr_ret_stack; return 0; @@ -204,7 +209,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, return; } -#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY) +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST /* * The arch may choose to record the frame pointer used * and check it here to make sure that it is what we expect it @@ -279,6 +284,64 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) return ret; } +/** + * ftrace_graph_ret_addr - convert a potentially modified stack return address + * to its original value + * + * This function can be called by stack unwinding code to convert a found stack + * return address ('ret') to its original value, in case the function graph + * tracer has modified it to be 'return_to_handler'. If the address hasn't + * been modified, the unchanged value of 'ret' is returned. + * + * 'idx' is a state variable which should be initialized by the caller to zero + * before the first call. + * + * 'retp' is a pointer to the return address on the stack. It's ignored if + * the arch doesn't have HAVE_FUNCTION_GRAPH_RET_ADDR_PTR defined. + */ +#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR +unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, + unsigned long ret, unsigned long *retp) +{ + int index = task->curr_ret_stack; + int i; + + if (ret != (unsigned long)return_to_handler) + return ret; + + if (index < -1) + index += FTRACE_NOTRACE_DEPTH; + + if (index < 0) + return ret; + + for (i = 0; i <= index; i++) + if (task->ret_stack[i].retp == retp) + return task->ret_stack[i].ret; + + return ret; +} +#else /* !HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ +unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, + unsigned long ret, unsigned long *retp) +{ + int task_idx; + + if (ret != (unsigned long)return_to_handler) + return ret; + + task_idx = task->curr_ret_stack; + + if (!task->ret_stack || task_idx < *idx) + return ret; + + task_idx -= *idx; + (*idx)++; + + return task->ret_stack[task_idx].ret; +} +#endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ + int __trace_graph_entry(struct trace_array *tr, struct ftrace_graph_ent *trace, unsigned long flags, diff --git a/lib/dma-debug.c b/lib/dma-debug.c index fcfa1939ac41..06f02f6aecd2 100644 --- a/lib/dma-debug.c +++ b/lib/dma-debug.c @@ -22,6 +22,7 @@ #include <linux/stacktrace.h> #include <linux/dma-debug.h> #include <linux/spinlock.h> +#include <linux/vmalloc.h> #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/export.h> @@ -1164,11 +1165,32 @@ static void check_unmap(struct dma_debug_entry *ref) put_hash_bucket(bucket, &flags); } -static void check_for_stack(struct device *dev, void *addr) +static void check_for_stack(struct device *dev, + struct page *page, size_t offset) { - if (object_is_on_stack(addr)) - err_printk(dev, NULL, "DMA-API: device driver maps memory from " - "stack [addr=%p]\n", addr); + void *addr; + struct vm_struct *stack_vm_area = task_stack_vm_area(current); + + if (!stack_vm_area) { + /* Stack is direct-mapped. */ + if (PageHighMem(page)) + return; + addr = page_address(page) + offset; + if (object_is_on_stack(addr)) + err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr); + } else { + /* Stack is vmalloced. */ + int i; + + for (i = 0; i < stack_vm_area->nr_pages; i++) { + if (page != stack_vm_area->pages[i]) + continue; + + addr = (u8 *)current->stack + i * PAGE_SIZE + offset; + err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr); + break; + } + } } static inline bool overlap(void *addr, unsigned long len, void *start, void *end) @@ -1291,10 +1313,11 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, if (map_single) entry->type = dma_debug_single; + check_for_stack(dev, page, offset); + if (!PageHighMem(page)) { void *addr = page_address(page) + offset; - check_for_stack(dev, addr); check_for_illegal_area(dev, addr, size); } @@ -1386,8 +1409,9 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg, entry->sg_call_ents = nents; entry->sg_mapped_ents = mapped_ents; + check_for_stack(dev, sg_page(s), s->offset); + if (!PageHighMem(sg_page(s))) { - check_for_stack(dev, sg_virt(s)); check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s)); } diff --git a/lib/syscall.c b/lib/syscall.c index e30e03932480..63239e097b13 100644 --- a/lib/syscall.c +++ b/lib/syscall.c @@ -7,9 +7,19 @@ static int collect_syscall(struct task_struct *target, long *callno, unsigned long args[6], unsigned int maxargs, unsigned long *sp, unsigned long *pc) { - struct pt_regs *regs = task_pt_regs(target); - if (unlikely(!regs)) + struct pt_regs *regs; + + if (!try_get_task_stack(target)) { + /* Task has no stack, so the task isn't in a syscall. */ + *callno = -1; + return 0; + } + + regs = task_pt_regs(target); + if (unlikely(!regs)) { + put_task_stack(target); return -EAGAIN; + } *sp = user_stack_pointer(regs); *pc = instruction_pointer(regs); @@ -18,6 +28,7 @@ static int collect_syscall(struct task_struct *target, long *callno, if (*callno != -1L && maxargs > 0) syscall_get_arguments(target, regs, 0, maxargs, args); + put_task_stack(target); return 0; } diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c index 421456784bc6..b037ce9cf116 100644 --- a/tools/testing/selftests/x86/ptrace_syscall.c +++ b/tools/testing/selftests/x86/ptrace_syscall.c @@ -147,7 +147,7 @@ static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *)) if (args.nr != getpid() || args.arg0 != 10 || args.arg1 != 11 || args.arg2 != 12 || args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) { - printf("[FAIL]\tgetpid() failed to preseve regs\n"); + printf("[FAIL]\tgetpid() failed to preserve regs\n"); nerrs++; } else { printf("[OK]\tgetpid() preserves regs\n"); @@ -162,7 +162,7 @@ static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *)) if (args.nr != 0 || args.arg0 != getpid() || args.arg1 != SIGUSR1 || args.arg2 != 12 || args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) { - printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preseve regs\n"); + printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preserve regs\n"); nerrs++; } else { printf("[OK]\tkill(getpid(), SIGUSR1) preserves regs\n"); diff --git a/tools/testing/selftests/x86/sigreturn.c b/tools/testing/selftests/x86/sigreturn.c index 8a577e7070c6..246145b84a12 100644 --- a/tools/testing/selftests/x86/sigreturn.c +++ b/tools/testing/selftests/x86/sigreturn.c @@ -106,7 +106,7 @@ asm (".pushsection .text\n\t" ".type int3, @function\n\t" ".align 4096\n\t" "int3:\n\t" - "mov %ss,%eax\n\t" + "mov %ss,%ecx\n\t" "int3\n\t" ".size int3, . - int3\n\t" ".align 4096, 0xcc\n\t" @@ -306,7 +306,7 @@ static volatile sig_atomic_t sig_corrupt_final_ss; #ifdef __x86_64__ # define REG_IP REG_RIP # define REG_SP REG_RSP -# define REG_AX REG_RAX +# define REG_CX REG_RCX struct selectors { unsigned short cs, gs, fs, ss; @@ -326,7 +326,7 @@ static unsigned short *csptr(ucontext_t *ctx) #else # define REG_IP REG_EIP # define REG_SP REG_ESP -# define REG_AX REG_EAX +# define REG_CX REG_ECX static greg_t *ssptr(ucontext_t *ctx) { @@ -457,10 +457,10 @@ static void sigusr1(int sig, siginfo_t *info, void *ctx_void) ctx->uc_mcontext.gregs[REG_IP] = sig_cs == code16_sel ? 0 : (unsigned long)&int3; ctx->uc_mcontext.gregs[REG_SP] = (unsigned long)0x8badf00d5aadc0deULL; - ctx->uc_mcontext.gregs[REG_AX] = 0; + ctx->uc_mcontext.gregs[REG_CX] = 0; memcpy(&requested_regs, &ctx->uc_mcontext.gregs, sizeof(gregset_t)); - requested_regs[REG_AX] = *ssptr(ctx); /* The asm code does this. */ + requested_regs[REG_CX] = *ssptr(ctx); /* The asm code does this. */ return; } @@ -482,7 +482,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void) unsigned short ss; asm ("mov %%ss,%0" : "=r" (ss)); - greg_t asm_ss = ctx->uc_mcontext.gregs[REG_AX]; + greg_t asm_ss = ctx->uc_mcontext.gregs[REG_CX]; if (asm_ss != sig_ss && sig == SIGTRAP) { /* Sanity check failure. */ printf("[FAIL]\tSIGTRAP: ss = %hx, frame ss = %hx, ax = %llx\n", @@ -654,8 +654,8 @@ static int test_valid_sigreturn(int cs_bits, bool use_16bit_ss, int force_ss) #endif /* Sanity check on the kernel */ - if (i == REG_AX && requested_regs[i] != resulting_regs[i]) { - printf("[FAIL]\tAX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n", + if (i == REG_CX && requested_regs[i] != resulting_regs[i]) { + printf("[FAIL]\tCX (saved SP) mismatch: requested 0x%llx; got 0x%llx\n", (unsigned long long)requested_regs[i], (unsigned long long)resulting_regs[i]); nerrs++; |