summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig17
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/entry/common.c34
-rw-r--r--arch/x86/entry/vdso/vdso2c.c2
-rw-r--r--arch/x86/entry/vdso/vdso32/sigreturn.S2
-rw-r--r--arch/x86/entry/vdso/vma.c15
-rw-r--r--arch/x86/include/asm/elf.h2
-rw-r--r--arch/x86/include/asm/idtentry.h3
-rw-r--r--arch/x86/include/asm/thread_info.h13
-rw-r--r--arch/x86/include/asm/vdso.h2
-rw-r--r--arch/x86/kernel/cpu/mce/core.c6
-rw-r--r--arch/x86/kernel/nmi.c6
-rw-r--r--arch/x86/kernel/signal.c4
-rw-r--r--arch/x86/kernel/signal_compat.c2
-rw-r--r--arch/x86/kernel/traps.c13
15 files changed, 60 insertions, 62 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index ba4e966484ab..7a3371d28508 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
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 52e36adb5112..88a4fa909766 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -163,6 +163,7 @@ 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
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/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/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 <asm/irq_stack.h>
-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/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index a12b9644193b..0d751d5da702 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 */
};
@@ -74,15 +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 */
@@ -91,6 +88,7 @@ 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 */
@@ -98,18 +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)
@@ -118,13 +111,13 @@ 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)
#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() */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index b5d23470f56b..98aa103eb4ab 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -29,6 +29,8 @@ 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
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 6af6a3c0698f..13d3f1cbda17 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1974,7 +1974,7 @@ 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));
@@ -1986,7 +1986,7 @@ 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.
@@ -1997,7 +1997,7 @@ 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/signal.c b/arch/x86/kernel/signal.c
index be0d7d4152ec..ea794a083c44 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;
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index ddfd919be46c..a5330ff498f0 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);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7798d862983f..fb55981f2a0d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -409,7 +409,7 @@ 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);
@@ -658,12 +658,13 @@ 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);
}
}
@@ -858,7 +859,7 @@ 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();
/*
@@ -915,7 +916,7 @@ 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);
}
@@ -933,7 +934,7 @@ 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
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-22 21:48:58 +0000