diff options
111 files changed, 2727 insertions, 2414 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d41812aba393..dde744682e63 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -181,7 +181,6 @@ config X86 select HAVE_HW_BREAKPOINT select HAVE_IDE select HAVE_IOREMAP_PROT - select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64 select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 85eb381259c2..b7a5790d8d63 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -3,7 +3,13 @@ # Makefile for the x86 low level entry code # -OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y +KASAN_SANITIZE := n +UBSAN_SANITIZE := n +KCOV_INSTRUMENT := n + +CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong +CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong +CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 1c7f13bb6728..4208c1e3f601 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -341,30 +341,13 @@ For 32-bit we have the following conventions - kernel is built with #endif .endm -#endif /* CONFIG_X86_64 */ +#else /* CONFIG_X86_64 */ +# undef UNWIND_HINT_IRET_REGS +# define UNWIND_HINT_IRET_REGS +#endif /* !CONFIG_X86_64 */ .macro STACKLEAK_ERASE #ifdef CONFIG_GCC_PLUGIN_STACKLEAK call stackleak_erase #endif .endm - -/* - * This does 'call enter_from_user_mode' unless we can avoid it based on - * kernel config or using the static jump infrastructure. - */ -.macro CALL_enter_from_user_mode -#ifdef CONFIG_CONTEXT_TRACKING -#ifdef CONFIG_JUMP_LABEL - STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_key, def=0 -#endif - call enter_from_user_mode -.Lafter_call_\@: -#endif -.endm - -#ifdef CONFIG_PARAVIRT_XXL -#define GET_CR2_INTO(reg) GET_CR2_INTO_AX ; _ASM_MOV %_ASM_AX, reg -#else -#define GET_CR2_INTO(reg) _ASM_MOV %cr2, reg -#endif diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 76735ec813e6..bd3f14175193 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -27,6 +27,11 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> +#ifdef CONFIG_XEN_PV +#include <xen/xen-ops.h> +#include <xen/events.h> +#endif + #include <asm/desc.h> #include <asm/traps.h> #include <asm/vdso.h> @@ -35,21 +40,67 @@ #include <asm/nospec-branch.h> #include <asm/io_bitmap.h> #include <asm/syscall.h> +#include <asm/irq_stack.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> #ifdef CONFIG_CONTEXT_TRACKING -/* Called on entry from user mode with IRQs off. */ -__visible inline void enter_from_user_mode(void) +/** + * enter_from_user_mode - Establish state when coming from user mode + * + * Syscall entry disables interrupts, but user mode is traced as interrupts + * enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + */ +static noinstr void enter_from_user_mode(void) { - CT_WARN_ON(ct_state() != CONTEXT_USER); + enum ctx_state state = ct_state(); + + lockdep_hardirqs_off(CALLER_ADDR0); user_exit_irqoff(); + + instrumentation_begin(); + CT_WARN_ON(state != CONTEXT_USER); + trace_hardirqs_off_finish(); + instrumentation_end(); } #else -static inline void enter_from_user_mode(void) {} +static __always_inline void enter_from_user_mode(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} #endif +/** + * exit_to_user_mode - Fixup state when exiting to user mode + * + * Syscall exit enables interrupts, but the kernel state is interrupts + * disabled when this is invoked. Also tell RCU about it. + * + * 1) Trace interrupts on state + * 2) Invoke context tracking if enabled to adjust RCU state + * 3) Clear CPU buffers if CPU is affected by MDS and the migitation is on. + * 4) Tell lockdep that interrupts are enabled + */ +static __always_inline void exit_to_user_mode(void) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + instrumentation_end(); + + user_enter_irqoff(); + mds_user_clear_cpu_buffers(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch) { #ifdef CONFIG_X86_64 @@ -179,8 +230,7 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) } } -/* Called with IRQs disabled. */ -__visible inline void prepare_exit_to_usermode(struct pt_regs *regs) +static void __prepare_exit_to_usermode(struct pt_regs *regs) { struct thread_info *ti = current_thread_info(); u32 cached_flags; @@ -219,10 +269,14 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs) */ ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED); #endif +} - user_enter_irqoff(); - - mds_user_clear_cpu_buffers(); +__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs) +{ + instrumentation_begin(); + __prepare_exit_to_usermode(regs); + instrumentation_end(); + exit_to_user_mode(); } #define SYSCALL_EXIT_WORK_FLAGS \ @@ -251,11 +305,7 @@ static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags) tracehook_report_syscall_exit(regs, step); } -/* - * Called with IRQs on and fully valid regs. Returns with IRQs off in a - * state such that we can immediately switch to user mode. - */ -__visible inline void syscall_return_slowpath(struct pt_regs *regs) +static void __syscall_return_slowpath(struct pt_regs *regs) { struct thread_info *ti = current_thread_info(); u32 cached_flags = READ_ONCE(ti->flags); @@ -276,15 +326,29 @@ __visible inline void syscall_return_slowpath(struct pt_regs *regs) syscall_slow_exit_work(regs, cached_flags); local_irq_disable(); - prepare_exit_to_usermode(regs); + __prepare_exit_to_usermode(regs); +} + +/* + * Called with IRQs on and fully valid regs. Returns with IRQs off in a + * state such that we can immediately switch to user mode. + */ +__visible noinstr void syscall_return_slowpath(struct pt_regs *regs) +{ + instrumentation_begin(); + __syscall_return_slowpath(regs); + instrumentation_end(); + exit_to_user_mode(); } #ifdef CONFIG_X86_64 -__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) +__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) { struct thread_info *ti; enter_from_user_mode(); + instrumentation_begin(); + local_irq_enable(); ti = current_thread_info(); if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) @@ -301,8 +365,10 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) regs->ax = x32_sys_call_table[nr](regs); #endif } + __syscall_return_slowpath(regs); - syscall_return_slowpath(regs); + instrumentation_end(); + exit_to_user_mode(); } #endif @@ -313,7 +379,7 @@ __visible void do_syscall_64(unsigned long nr, struct pt_regs *regs) * extremely hot in workloads that use it, and it's usually called from * do_fast_syscall_32, so forcibly inline it to improve performance. */ -static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs) +static void do_syscall_32_irqs_on(struct pt_regs *regs) { struct thread_info *ti = current_thread_info(); unsigned int nr = (unsigned int)regs->orig_ax; @@ -337,27 +403,62 @@ static __always_inline |