From 12db8b690010ccfadf9d0b49a1e1798e47dbbe1a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:28 -0600 Subject: entry: Add support for TIF_NOTIFY_SIGNAL Add TIF_NOTIFY_SIGNAL handling in the generic entry code, which if set, will return true if signal_pending() is used in a wait loop. That causes an exit of the loop so that notify_signal tracehooks can be run. If the wait loop is currently inside a system call, the system call is restarted once task_work has been processed. In preparation for only having arch_do_signal() handle syscall restarts if _TIF_SIGPENDING isn't set, rename it to arch_do_signal_or_restart(). Pass in a boolean that tells the architecture specific signal handler if it should attempt to get a signal, or just process a potential syscall restart. For !CONFIG_GENERIC_ENTRY archs, add the TIF_NOTIFY_SIGNAL handling to get_signal(). This is done to minimize the needed architecture changes to support this feature. Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Reviewed-by: Oleg Nesterov Link: https://lore.kernel.org/r/20201026203230.386348-3-axboe@kernel.dk --- arch/x86/kernel/signal.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index d5fa494c2304..ec3b9c6e5a4c 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -804,11 +804,11 @@ static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs) * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. */ -void arch_do_signal(struct pt_regs *regs) +void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal) { struct ksignal ksig; - if (get_signal(&ksig)) { + if (has_signal && get_signal(&ksig)) { /* Whee! Actually deliver the signal. */ handle_signal(&ksig, regs); return; -- cgit From c8d5ed67936fddbe2ae845fc80397718006322d7 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Oct 2020 14:32:29 -0600 Subject: x86: Wire up TIF_NOTIFY_SIGNAL The generic entry code has support for TIF_NOTIFY_SIGNAL already. Just provide the TIF bit. [ tglx: Adopted to other TIF changes in x86 ] Signed-off-by: Jens Axboe Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201026203230.386348-4-axboe@kernel.dk --- arch/x86/include/asm/thread_info.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index a12b9644193b..06a171037558 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -91,6 +91,7 @@ struct thread_info { #define TIF_NEED_FPU_LOAD 14 /* load FPU on return to userspace */ #define TIF_NOCPUID 15 /* CPUID is not accessible in userland */ #define TIF_NOTSC 16 /* TSC is not accessible in userland */ +#define TIF_NOTIFY_SIGNAL 17 /* signal notifications exist */ #define TIF_SLD 18 /* Restore split lock detection on context switch */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ #define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ @@ -118,6 +119,7 @@ struct thread_info { #define _TIF_NEED_FPU_LOAD (1 << TIF_NEED_FPU_LOAD) #define _TIF_NOCPUID (1 << TIF_NOCPUID) #define _TIF_NOTSC (1 << TIF_NOTSC) +#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL) #define _TIF_SLD (1 << TIF_SLD) #define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) -- cgit From b6be002bcd1dd1dedb926abf3c90c794eacb77dc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 2 Nov 2020 12:53:16 -0800 Subject: x86/entry: Move nmi entry/exit into common code Lockdep state handling on NMI enter and exit is nothing specific to X86. It's not any different on other architectures. Also the extra state type is not necessary, irqentry_state_t can carry the necessary information as well. Move it to common code and extend irqentry_state_t to carry lockdep state. [ Ira: Make exit_rcu and lockdep a union as they are mutually exclusive between the IRQ and NMI exceptions, and add kernel documentation for struct irqentry_state_t ] Signed-off-by: Thomas Gleixner Signed-off-by: Ira Weiny Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20201102205320.1458656-7-ira.weiny@intel.com --- arch/x86/entry/common.c | 34 ---------------------------------- arch/x86/include/asm/idtentry.h | 3 --- arch/x86/kernel/cpu/mce/core.c | 6 +++--- arch/x86/kernel/nmi.c | 6 +++--- arch/x86/kernel/traps.c | 13 +++++++------ 5 files changed, 13 insertions(+), 49 deletions(-) (limited to 'arch') diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 870efeec8bda..18d8f17f755c 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -209,40 +209,6 @@ SYSCALL_DEFINE0(ni_syscall) return -ENOSYS; } -noinstr bool idtentry_enter_nmi(struct pt_regs *regs) -{ - bool irq_state = lockdep_hardirqs_enabled(); - - __nmi_enter(); - lockdep_hardirqs_off(CALLER_ADDR0); - lockdep_hardirq_enter(); - rcu_nmi_enter(); - - instrumentation_begin(); - trace_hardirqs_off_finish(); - ftrace_nmi_enter(); - instrumentation_end(); - - return irq_state; -} - -noinstr void idtentry_exit_nmi(struct pt_regs *regs, bool restore) -{ - instrumentation_begin(); - ftrace_nmi_exit(); - if (restore) { - trace_hardirqs_on_prepare(); - lockdep_hardirqs_on_prepare(CALLER_ADDR0); - } - instrumentation_end(); - - rcu_nmi_exit(); - lockdep_hardirq_exit(); - if (restore) - lockdep_hardirqs_on(CALLER_ADDR0); - __nmi_exit(); -} - #ifdef CONFIG_XEN_PV #ifndef CONFIG_PREEMPTION /* diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index b2442eb0ac2f..247a60a47331 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -11,9 +11,6 @@ #include -bool idtentry_enter_nmi(struct pt_regs *regs); -void idtentry_exit_nmi(struct pt_regs *regs, bool irq_state); - /** * DECLARE_IDTENTRY - Declare functions for simple IDT entry points * No error code pushed by hardware diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 4102b866e7c0..f5c860b1a50b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1983,7 +1983,7 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { - bool irq_state; + irqentry_state_t irq_state; WARN_ON_ONCE(user_mode(regs)); @@ -1995,7 +1995,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) mce_check_crashing_cpu()) return; - irq_state = idtentry_enter_nmi(regs); + irq_state = irqentry_nmi_enter(regs); /* * The call targets are marked noinstr, but objtool can't figure * that out because it's an indirect call. Annotate it. @@ -2006,7 +2006,7 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) if (regs->flags & X86_EFLAGS_IF) trace_hardirqs_on_prepare(); instrumentation_end(); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); } static __always_inline void exc_machine_check_user(struct pt_regs *regs) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4bc77aaf1303..bf250a339655 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -475,7 +475,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { - bool irq_state; + irqentry_state_t irq_state; /* * Re-enable NMIs right here when running as an SEV-ES guest. This might @@ -502,14 +502,14 @@ nmi_restart: this_cpu_write(nmi_dr7, local_db_save()); - irq_state = idtentry_enter_nmi(regs); + irq_state = irqentry_nmi_enter(regs); inc_irq_stat(__nmi_count); if (!ignore_nmis) default_do_nmi(regs); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); local_db_restore(this_cpu_read(nmi_dr7)); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index e19df6cde35d..e1b78829d909 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -405,7 +405,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault) } #endif - idtentry_enter_nmi(regs); + irqentry_nmi_enter(regs); instrumentation_begin(); notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -651,12 +651,13 @@ DEFINE_IDTENTRY_RAW(exc_int3) instrumentation_end(); irqentry_exit_to_user_mode(regs); } else { - bool irq_state = idtentry_enter_nmi(regs); + irqentry_state_t irq_state = irqentry_nmi_enter(regs); + instrumentation_begin(); if (!do_int3(regs)) die("int3", regs, 0); instrumentation_end(); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); } } @@ -851,7 +852,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, * includes the entry stack is excluded for everything. */ unsigned long dr7 = local_db_save(); - bool irq_state = idtentry_enter_nmi(regs); + irqentry_state_t irq_state = irqentry_nmi_enter(regs); instrumentation_begin(); /* @@ -908,7 +909,7 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, regs->flags &= ~X86_EFLAGS_TF; out: instrumentation_end(); - idtentry_exit_nmi(regs, irq_state); + irqentry_nmi_exit(regs, irq_state); local_db_restore(dr7); } @@ -926,7 +927,7 @@ static __always_inline void exc_debug_user(struct pt_regs *regs, /* * NB: We can't easily clear DR7 here because - * idtentry_exit_to_usermode() can invoke ptrace, schedule, access + * irqentry_exit_to_usermode() can invoke ptrace, schedule, access * user memory, etc. This means that a recursive #DB is possible. If * this happens, that #DB will hit exc_debug_kernel() and clear DR7. * Since we're not on the IST stack right now, everything will be -- cgit From b4581a52caff79eab1ea6caaaa4e08526ce2782b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 16 Nov 2020 12:41:57 -0500 Subject: x86: Expose syscall_work field in thread_info This field will be used by SYSCALL_WORK flags, migrated from TI flags. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20201116174206.2639648-2-krisman@collabora.com --- arch/x86/include/asm/thread_info.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 06a171037558..0da5d58d7c79 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -55,6 +55,7 @@ struct task_struct; struct thread_info { unsigned long flags; /* low level flags */ + unsigned long syscall_work; /* SYSCALL_WORK_ flags */ u32 status; /* thread synchronous flags */ }; -- cgit From 51af3f23063946344330a77a7d1dece6fc6bb5d8 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 16 Nov 2020 12:42:06 -0500 Subject: x86: Reclaim unused x86 TI flags Reclaim TI flags that were migrated to syscall_work flags. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Link: https://lore.kernel.org/r/20201116174206.2639648-11-krisman@collabora.com --- arch/x86/include/asm/thread_info.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'arch') diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 0da5d58d7c79..0d751d5da702 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -75,15 +75,11 @@ struct thread_info { * - these are process state flags that various assembly files * may need to access */ -#define TIF_SYSCALL_TRACE 0 /* syscall trace active */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ #define TIF_SSBD 5 /* Speculative store bypass disable */ -#define TIF_SYSCALL_EMU 6 /* syscall emulation active */ -#define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ -#define TIF_SECCOMP 8 /* secure computing */ #define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ #define TIF_SPEC_FORCE_UPDATE 10 /* Force speculation MSR update in context switch */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ @@ -100,18 +96,13 @@ struct thread_info { #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ #define TIF_LAZY_MMU_UPDATES 27 /* task is updating the mmu lazily */ -#define TIF_SYSCALL_TRACEPOINT 28 /* syscall tracepoint instrumentation */ #define TIF_ADDR32 29 /* 32-bit address space on 64 bits */ -#define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_SINGLESTEP (1 << TIF_SINGLESTEP) #define _TIF_SSBD (1 << TIF_SSBD) -#define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) -#define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) -#define _TIF_SECCOMP (1 << TIF_SECCOMP) #define _TIF_SPEC_IB (1 << TIF_SPEC_IB) #define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) @@ -127,7 +118,6 @@ struct thread_info { #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) #define _TIF_LAZY_MMU_UPDATES (1 << TIF_LAZY_MMU_UPDATES) -#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT) #define _TIF_ADDR32 (1 << TIF_ADDR32) /* flags to check in __switch_to() */ -- cgit From 83c2da2e605c73aafcc02df04b2dbf1ccbfc24c0 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 17 Nov 2020 16:16:33 +0100 Subject: context_tracking: Introduce HAVE_CONTEXT_TRACKING_OFFSTACK Historically, context tracking had to deal with fragile entry code path, ie: before user_exit() is called and after user_enter() is called, in case some of those spots would call schedule() or use RCU. On such cases, the site had to be protected between exception_enter() and exception_exit() that save the context tracking state in the task stack. Such sleepable fragile code path had many different origins: tracing, exceptions, early or late calls to context tracking on syscalls... Aside of that not being pretty, saving the context tracking state on the task stack forces us to run context tracking on all CPUs, including housekeepers, and prevents us to completely shutdown nohz_full at runtime on a CPU in the future as context tracking and its overhead would still need to run system wide. Now thanks to the extensive efforts to sanitize x86 entry code, those conditions have been removed and we can now get rid of these workarounds in this architecture. Create a Kconfig feature to express this achievement. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201117151637.259084-2-frederic@kernel.org --- arch/Kconfig | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'arch') diff --git a/arch/Kconfig b/arch/Kconfig index 56b6ccc0e32d..090ef3566c56 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -618,6 +618,23 @@ config HAVE_CONTEXT_TRACKING protected inside rcu_irq_enter/rcu_irq_exit() but preemption or signal handling on irq exit still need to be protected. +config HAVE_CONTEXT_TRACKING_OFFSTACK + bool + help + Architecture neither relies on exception_enter()/exception_exit() + nor on schedule_user(). Also preempt_schedule_notrace() and + preempt_schedule_irq() can't be called in a preemptible section + while context tracking is CONTEXT_USER. This feature reflects a sane + entry implementation where the following requirements are met on + critical entry code, ie: before user_exit() or after user_enter(): + + - Critical entry code isn't preemptible (or better yet: + not interruptible). + - No use of RCU read side critical sections, unless rcu_nmi_enter() + got called. + - No use of instrumentation, unless instrumentation_begin() got + called. + config HAVE_TIF_NOHZ bool help -- cgit From d1f250e2205eca9f1264f8e2d3a41fcf38f92d91 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 17 Nov 2020 16:16:37 +0100 Subject: x86: Support HAVE_CONTEXT_TRACKING_OFFSTACK A lot of ground work has been performed on x86 entry code. Fragile path between user_enter() and user_exit() have IRQs disabled. Uses of RCU and intrumentation in these fragile areas have been explicitly annotated and protected. This architecture doesn't need exception_enter()/exception_exit() anymore and has therefore earned CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK. Signed-off-by: Frederic Weisbecker Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20201117151637.259084-6-frederic@kernel.org --- arch/x86/Kconfig | 1 + 1 file changed, 1 insertion(+) (limited to 'arch') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f6946b81f74a..d793361839b5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -162,6 +162,7 @@ config X86 select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_CONTEXT_TRACKING if X86_64 + select HAVE_CONTEXT_TRACKING_OFFSTACK if HAVE_CONTEXT_TRACKING select HAVE_C_RECORDMCOUNT select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS -- cgit From c5c878125ad5aca199dfc10b1af4010165aaa596 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 27 Nov 2020 14:32:32 -0500 Subject: x86: vdso: Expose sigreturn address on vdso to the kernel Syscall user redirection requires the signal trampoline code to not be captured, in order to support returning with a locked selector while avoiding recursion back into the signal handler. For ia-32, which has the trampoline in the vDSO, expose the entry points to the kernel, such that it can avoid dispatching syscalls from that region to userspace. Suggested-by: Andy Lutomirski Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Reviewed-by: Kees Cook Reviewed-by: Andy Lutomirski Acked-by: Andy Lutomirski Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20201127193238.821364-2-krisman@collabora.com --- arch/x86/entry/vdso/vdso2c.c | 2 ++ arch/x86/entry/vdso/vdso32/sigreturn.S | 2 ++ arch/x86/entry/vdso/vma.c | 15 +++++++++++++++ arch/x86/include/asm/elf.h | 2 ++ arch/x86/include/asm/vdso.h | 2 ++ 5 files changed, 23 insertions(+) (limited to 'arch') diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 7380908045c7..2d0f3d8bcc25 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -101,6 +101,8 @@ struct vdso_sym required_syms[] = { {"__kernel_sigreturn", true}, {"__kernel_rt_sigreturn", true}, {"int80_landing_pad", true}, + {"vdso32_rt_sigreturn_landing_pad", true}, + {"vdso32_sigreturn_landing_pad", true}, }; __attribute__((format(printf, 1, 2))) __attribute__((noreturn)) diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S index c3233ee98a6b..1bd068f72d4c 100644 --- a/arch/x86/entry/vdso/vdso32/sigreturn.S +++ b/arch/x86/entry/vdso/vdso32/sigreturn.S @@ -18,6 +18,7 @@ __kernel_sigreturn: movl $__NR_sigreturn, %eax SYSCALL_ENTER_KERNEL .LEND_sigreturn: +SYM_INNER_LABEL(vdso32_sigreturn_landing_pad, SYM_L_GLOBAL) nop .size __kernel_sigreturn,.-.LSTART_sigreturn @@ -29,6 +30,7 @@ __kernel_rt_sigreturn: movl $__NR_rt_sigreturn, %eax SYSCALL_ENTER_KERNEL .LEND_rt_sigreturn: +SYM_INNER_LABEL(vdso32_rt_sigreturn_landing_pad, SYM_L_GLOBAL) nop .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn .previous diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 50e5d3a2e70a..de60cd37070b 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -436,6 +436,21 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) } #endif +bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs) +{ +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) + const struct vdso_image *image = current->mm->context.vdso_image; + unsigned long vdso = (unsigned long) current->mm->context.vdso; + + if (in_ia32_syscall() && image == &vdso_image_32) { + if (regs->ip == vdso + image->sym_vdso32_sigreturn_landing_pad || + regs->ip == vdso + image->sym_vdso32_rt_sigreturn_landing_pad) + return true; + } +#endif + return false; +} + #ifdef CONFIG_X86_64 static __init int vdso_setup(char *s) { diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 44a9b9940535..66bdfe838d61 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -388,6 +388,8 @@ extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, compat_arch_setup_additional_pages(bprm, interpreter, \ (ex->e_machine == EM_X86_64)) +extern bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs); + /* Do not change the values. See get_align_mask() */ enum align_flags { ALIGN_VA_32 = BIT(0), diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index bbcdc7b8f963..589f489dd375 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -27,6 +27,8 @@ struct vdso_image { long sym___kernel_rt_sigreturn; long sym___kernel_vsyscall; long sym_int80_landing_pad; + long sym_vdso32_sigreturn_landing_pad; + long sym_vdso32_rt_sigreturn_landing_pad; }; #ifdef CONFIG_X86_64 -- cgit From 1d7637d89cfce54a4f4a41c2325288c2f47470e8 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Fri, 27 Nov 2020 14:32:33 -0500 Subject: signal: Expose SYS_USER_DISPATCH si_code type SYS_USER_DISPATCH will be triggered when a syscall is sent to userspace by the Syscall User Dispatch mechanism. This adjusts eventual BUILD_BUG_ON around the tree. Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Thomas Gleixner Reviewed-by: Andy Lutomirski Acked-by: Kees Cook Acked-by: Christian Brauner Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20201127193238.821364-3-krisman@collabora.com --- arch/x86/kernel/signal_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index a7f3e12cfbdb..d7b51870f16b 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -31,7 +31,7 @@ static inline void signal_compat_build_tests(void) BUILD_BUG_ON(NSIGBUS != 5); BUILD_BUG_ON(NSIGTRAP != 5); BUILD_BUG_ON(NSIGCHLD != 6); - BUILD_BUG_ON(NSIGSYS != 1); + BUILD_BUG_ON(NSIGSYS != 2); /* This is part of the ABI and can never change in size: */ BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128); -- cgit