summaryrefslogtreecommitdiff
path: root/arch/x86/entry
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/entry')
-rw-r--r--arch/x86/entry/common.c264
-rw-r--r--arch/x86/entry/entry_32.S185
-rw-r--r--arch/x86/entry/entry_64.S28
-rw-r--r--arch/x86/entry/entry_64_compat.S547
-rw-r--r--arch/x86/entry/syscall_32.c9
-rw-r--r--arch/x86/entry/syscall_64.c4
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl13
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl1
-rw-r--r--arch/x86/entry/vdso/Makefile39
-rw-r--r--arch/x86/entry/vdso/vdso2c.c2
-rw-r--r--arch/x86/entry/vdso/vdso32-setup.c28
-rw-r--r--arch/x86/entry/vdso/vdso32/int80.S56
-rw-r--r--arch/x86/entry/vdso/vdso32/syscall.S75
-rw-r--r--arch/x86/entry/vdso/vdso32/sysenter.S116
-rw-r--r--arch/x86/entry/vdso/vdso32/system_call.S89
-rw-r--r--arch/x86/entry/vdso/vdso32/vclock_gettime.c2
-rw-r--r--arch/x86/entry/vdso/vma.c13
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c9
18 files changed, 561 insertions, 919 deletions
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 80dcc9261..03663740c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -24,10 +24,19 @@
#include <asm/desc.h>
#include <asm/traps.h>
+#include <asm/vdso.h>
+#include <asm/uaccess.h>
#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 void enter_from_user_mode(void)
@@ -66,13 +75,14 @@ static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
*/
unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
{
+ struct thread_info *ti = pt_regs_to_thread_info(regs);
unsigned long ret = 0;
u32 work;
- BUG_ON(regs != task_pt_regs(current));
+ if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+ BUG_ON(regs != task_pt_regs(current));
- work = ACCESS_ONCE(current_thread_info()->flags) &
- _TIF_WORK_SYSCALL_ENTRY;
+ work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
#ifdef CONFIG_CONTEXT_TRACKING
/*
@@ -154,11 +164,12 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
unsigned long phase1_result)
{
+ struct thread_info *ti = pt_regs_to_thread_info(regs);
long ret = 0;
- u32 work = ACCESS_ONCE(current_thread_info()->flags) &
- _TIF_WORK_SYSCALL_ENTRY;
+ u32 work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
- BUG_ON(regs != task_pt_regs(current));
+ if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+ BUG_ON(regs != task_pt_regs(current));
/*
* If we stepped into a sysenter/syscall insn, it trapped in
@@ -207,19 +218,12 @@ long syscall_trace_enter(struct pt_regs *regs)
return syscall_trace_enter_phase2(regs, arch, phase1_result);
}
-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);
-}
+#define EXIT_TO_USERMODE_LOOP_FLAGS \
+ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+ _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
-/* Called with IRQs disabled. */
-__visible void prepare_exit_to_usermode(struct pt_regs *regs)
+static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
{
- if (WARN_ON(!irqs_disabled()))
- local_irq_disable();
-
/*
* In order to return to user mode, we need to have IRQs off with
* none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY,
@@ -229,14 +233,6 @@ __visible void prepare_exit_to_usermode(struct pt_regs *regs)
* work to clear some of the flags can sleep.
*/
while (true) {
- u32 cached_flags =
- READ_ONCE(pt_regs_to_thread_info(regs)->flags);
-
- if (!(cached_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME |
- _TIF_UPROBE | _TIF_NEED_RESCHED |
- _TIF_USER_RETURN_NOTIFY)))
- break;
-
/* We have work to do. */
local_irq_enable();
@@ -260,50 +256,81 @@ __visible void prepare_exit_to_usermode(struct pt_regs *regs)
/* Disable IRQs and retry */
local_irq_disable();
+
+ cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->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)
+{
+ u32 cached_flags;
+
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
+ local_irq_disable();
+
+ lockdep_sys_exit();
+
+ cached_flags =
+ READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+
+ if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+ exit_to_usermode_loop(regs, cached_flags);
user_enter();
}
+#define SYSCALL_EXIT_WORK_FLAGS \
+ (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
+ _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
+
+static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
+{
+ bool step;
+
+ audit_syscall_exit(regs);
+
+ if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
+ trace_sys_exit(regs, regs->ax);
+
+ /*
+ * If TIF_SYSCALL_EMU is set, we only get here because of
+ * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
+ * We already reported this syscall instruction in
+ * syscall_trace_enter().
+ */
+ step = unlikely(
+ (cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
+ == _TIF_SINGLESTEP);
+ if (step || cached_flags & _TIF_SYSCALL_TRACE)
+ 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 void syscall_return_slowpath(struct pt_regs *regs)
+__visible inline void syscall_return_slowpath(struct pt_regs *regs)
{
struct thread_info *ti = pt_regs_to_thread_info(regs);
u32 cached_flags = READ_ONCE(ti->flags);
- bool step;
CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
- if (WARN(irqs_disabled(), "syscall %ld left IRQs disabled",
- regs->orig_ax))
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
+ WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
local_irq_enable();
/*
* First do one-time work. If these work items are enabled, we
* want to run them exactly once per syscall exit with IRQs on.
*/
- if (cached_flags & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |
- _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)) {
- audit_syscall_exit(regs);
-
- if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
- trace_sys_exit(regs, regs->ax);
-
- /*
- * If TIF_SYSCALL_EMU is set, we only get here because of
- * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
- * We already reported this syscall instruction in
- * syscall_trace_enter().
- */
- step = unlikely(
- (cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
- == _TIF_SINGLESTEP);
- if (step || cached_flags & _TIF_SYSCALL_TRACE)
- tracehook_report_syscall_exit(regs, step);
- }
+ if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
+ syscall_slow_exit_work(regs, cached_flags);
#ifdef CONFIG_COMPAT
/*
@@ -316,3 +343,144 @@ __visible void syscall_return_slowpath(struct pt_regs *regs)
local_irq_disable();
prepare_exit_to_usermode(regs);
}
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+/*
+ * Does a 32-bit syscall. Called with IRQs on and does all entry and
+ * exit work and returns with IRQs off. This function is extremely hot
+ * in workloads that use it, and it's usually called from
+ * do_fast_syscall_32, so forcibly inline it to improve performance.
+ */
+#ifdef CONFIG_X86_32
+/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */
+__visible
+#else
+/* 64-bit kernels use do_syscall_32_irqs_off() instead. */
+static
+#endif
+__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+{
+ struct thread_info *ti = pt_regs_to_thread_info(regs);
+ unsigned int nr = (unsigned int)regs->orig_ax;
+
+#ifdef CONFIG_IA32_EMULATION
+ ti->status |= TS_COMPAT;
+#endif
+
+ if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
+ /*
+ * Subtlety here: if ptrace pokes something larger than
+ * 2^32-1 into orig_ax, this truncates it. This may or
+ * may not be necessary, but it matches the old asm
+ * behavior.
+ */
+ nr = syscall_trace_enter(regs);
+ }
+
+ if (likely(nr < IA32_NR_syscalls)) {
+ /*
+ * It's possible that a 32-bit syscall implementation
+ * takes a 64-bit parameter but nonetheless assumes that
+ * the high bits are zero. Make sure we zero-extend all
+ * of the args.
+ */
+ regs->ax = ia32_sys_call_table[nr](
+ (unsigned int)regs->bx, (unsigned int)regs->cx,
+ (unsigned int)regs->dx, (unsigned int)regs->si,
+ (unsigned int)regs->di, (unsigned int)regs->bp);
+ }
+
+ syscall_return_slowpath(regs);
+}
+
+#ifdef CONFIG_X86_64
+/* Handles INT80 on 64-bit kernels */
+__visible void do_syscall_32_irqs_off(struct pt_regs *regs)
+{
+ local_irq_enable();
+ do_syscall_32_irqs_on(regs);
+}
+#endif
+
+/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
+__visible long do_fast_syscall_32(struct pt_regs *regs)
+{
+ /*
+ * Called using the internal vDSO SYSENTER/SYSCALL32 calling
+ * convention. Adjust regs so it looks like we entered using int80.
+ */
+
+ unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
+ vdso_image_32.sym_int80_landing_pad;
+
+ /*
+ * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
+ * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
+ * Fix it up.
+ */
+ regs->ip = landing_pad;
+
+ /*
+ * Fetch EBP from where the vDSO stashed it.
+ *
+ * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
+ */
+ local_irq_enable();
+ if (
+#ifdef CONFIG_X86_64
+ /*
+ * Micro-optimization: the pointer we're following is explicitly
+ * 32 bits, so it can't be out of range.
+ */
+ __get_user(*(u32 *)&regs->bp,
+ (u32 __user __force *)(unsigned long)(u32)regs->sp)
+#else
+ get_user(*(u32 *)&regs->bp,
+ (u32 __user __force *)(unsigned long)(u32)regs->sp)
+#endif
+ ) {
+
+ /* User code screwed up. */
+ local_irq_disable();
+ regs->ax = -EFAULT;
+#ifdef CONFIG_CONTEXT_TRACKING
+ enter_from_user_mode();
+#endif
+ prepare_exit_to_usermode(regs);
+ return 0; /* Keep it simple: use IRET. */
+ }
+
+ /* Now this is just like a normal syscall. */
+ do_syscall_32_irqs_on(regs);
+
+#ifdef CONFIG_X86_64
+ /*
+ * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
+ * SYSRETL is available on all 64-bit CPUs, so we don't need to
+ * bother with SYSEXIT.
+ *
+ * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
+ * because the ECX fixup above will ensure that this is essentially
+ * never the case.
+ */
+ return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
+ regs->ip == landing_pad &&
+ (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
+#else
+ /*
+ * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
+ *
+ * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
+ * because the ECX fixup above will ensure that this is essentially
+ * never the case.
+ *
+ * We don't allow syscalls at all from VM86 mode, but we still
+ * need to check VM, because we might be returning from sys_vm86.
+ */
+ return static_cpu_has(X86_FEATURE_SEP) &&
+ regs->cs == __USER_CS && regs->ss == __USER_DS &&
+ regs->ip == landing_pad &&
+ (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
+#endif
+}
+#endif
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b2909bf8c..f3b6d54e0 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -3,7 +3,7 @@
*
* entry_32.S contains the system-call and low-level fault and trap handling routines.
*
- * Stack layout in 'syscall_exit':
+ * Stack layout while running C code:
* ptrace needs to have all registers on the stack.
* If the order here is changed, it needs to be
* updated in fork.c:copy_process(), signal.c:do_signal(),
@@ -153,13 +153,13 @@
#endif /* CONFIG_X86_32_LAZY_GS */
-.macro SAVE_ALL
+.macro SAVE_ALL pt_regs_ax=%eax
cld
PUSH_GS
pushl %fs
pushl %es
pushl %ds
- pushl %eax
+ pushl \pt_regs_ax
pushl %ebp
pushl %edi
pushl %esi
@@ -211,7 +211,11 @@ ENTRY(ret_from_fork)
popl %eax
pushl $0x0202 # Reset kernel eflags
popfl
- jmp syscall_exit
+
+ /* 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)
@@ -224,7 +228,15 @@ ENTRY(ret_from_kernel_thread)
movl PT_EBP(%esp), %eax
call *PT_EBX(%esp)
movl $0, PT_EAX(%esp)
- jmp syscall_exit
+
+ /*
+ * 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.
+ */
+ movl %esp, %eax
+ call syscall_return_slowpath
+ jmp restore_all
ENDPROC(ret_from_kernel_thread)
/*
@@ -255,7 +267,6 @@ ret_from_intr:
jb resume_kernel # not returning to v8086 or userspace
ENTRY(resume_userspace)
- LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
movl %esp, %eax
@@ -276,76 +287,48 @@ need_resched:
END(resume_kernel)
#endif
-/*
- * SYSENTER_RETURN points to after the SYSENTER instruction
- * in the vsyscall page. See vsyscall-sysentry.S, which defines
- * the symbol.
- */
-
# SYSENTER call handler stub
ENTRY(entry_SYSENTER_32)
movl TSS_sysenter_sp0(%esp), %esp
sysenter_past_esp:
+ pushl $__USER_DS /* pt_regs->ss */
+ pushl %ebp /* pt_regs->sp (stashed in bp) */
+ pushfl /* pt_regs->flags (except IF = 0) */
+ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */
+ pushl $__USER_CS /* pt_regs->cs */
+ pushl $0 /* pt_regs->ip = 0 (placeholder) */
+ pushl %eax /* pt_regs->orig_ax */
+ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+
/*
- * Interrupts are disabled here, but we can't trace it until
- * enough kernel state to call TRACE_IRQS_OFF can be called - but
- * we immediately enable interrupts at that point anyway.
- */
- pushl $__USER_DS
- pushl %ebp
- pushfl
- orl $X86_EFLAGS_IF, (%esp)
- pushl $__USER_CS
- /*
- * Push current_thread_info()->sysenter_return to the stack.
- * A tiny bit of offset fixup is necessary: TI_sysenter_return
- * is relative to thread_info, which is at the bottom of the
- * kernel stack page. 4*4 means the 4 words pushed above;
- * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
- * and THREAD_SIZE takes us to the bottom.
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
*/
- pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
-
- pushl %eax
- SAVE_ALL
- ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
- cmpl $__PAGE_OFFSET-3, %ebp
- jae syscall_fault
- ASM_STAC
-1: movl (%ebp), %ebp
- ASM_CLAC
- movl %ebp, PT_EBP(%esp)
- _ASM_EXTABLE(1b, syscall_fault)
-
- GET_THREAD_INFO(%ebp)
-
- testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
- jnz syscall_trace_entry
-sysenter_do_call:
- cmpl $(NR_syscalls), %eax
- jae sysenter_badsys
- call *sys_call_table(, %eax, 4)
-sysenter_after_call:
- movl %eax, PT_EAX(%esp)
- LOCKDEP_SYS_EXIT
- DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
- movl TI_flags(%ebp), %ecx
- testl $_TIF_ALLWORK_MASK, %ecx
- jnz syscall_exit_work_irqs_off
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
- movl PT_EIP(%esp), %edx
- movl PT_OLDESP(%esp), %ecx
- xorl %ebp, %ebp
- TRACE_IRQS_ON
+
+ movl %esp, %eax
+ call do_fast_syscall_32
+ /* XEN PV guests always use IRET path */
+ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+
+/* Opportunistic SYSEXIT */
+ TRACE_IRQS_ON /* User mode traces as IRQs on. */
+ movl PT_EIP(%esp), %edx /* pt_regs->ip */
+ movl PT_OLDESP(%esp), %ecx /* pt_regs->sp */
1: mov PT_FS(%esp), %fs
PTGS_TO_GS
+ popl %ebx /* pt_regs->bx */
+ addl $2*4, %esp /* skip pt_regs->cx and pt_regs->dx */
+ popl %esi /* pt_regs->si */
+ popl %edi /* pt_regs->di */
+ popl %ebp /* pt_regs->bp */
+ popl %eax /* pt_regs->ax */
+
+ /*
+ * Return back to the vDSO, which will pop ecx and edx.
+ * Don't bother with DS and ES (they already contain __USER_DS).
+ */
ENABLE_INTERRUPTS_SYSEXIT
.pushsection .fixup, "ax"
@@ -359,21 +342,18 @@ ENDPROC(entry_SYSENTER_32)
# system call handler stub
ENTRY(entry_INT80_32)
ASM_CLAC
- pushl %eax # save orig_eax
- SAVE_ALL
- GET_THREAD_INFO(%ebp)
- # system call tracing in operation / emulation
- testl $_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
- jnz syscall_trace_entry
- cmpl $(NR_syscalls), %eax
- jae syscall_badsys
-syscall_call:
- call *sys_call_table(, %eax, 4)
-syscall_after_call:
- movl %eax, PT_EAX(%esp) # store the return value
-syscall_exit:
- LOCKDEP_SYS_EXIT
- jmp syscall_exit_work
+ pushl %eax /* pt_regs->orig_ax */
+ SAVE_ALL pt_regs_ax=$-ENOSYS /* save rest */
+
+ /*
+ * User mode is traced as though IRQs are on. Unlike the 64-bit
+ * case, INT80 is a trap gate on 32-bit kernels, so interrupts
+ * are already on (unless user code is messing around with iopl).
+ */
+
+ movl %esp, %eax
+ call do_syscall_32_irqs_on
+.Lsyscall_32_done:
restore_all:
TRACE_IRQS_IRET
@@ -450,47 +430,6 @@ ldt_ss:
#endif
ENDPROC(entry_INT80_32)
- # perform syscall exit tracing
- ALIGN
-syscall_trace_entry:
- movl $-ENOSYS, PT_EAX(%esp)
- movl %esp, %eax
- call syscall_trace_enter
- /* What it returned is what we'll actually use. */
- cmpl $(NR_syscalls), %eax
- jnae syscall_call
- jmp syscall_exit
-END(syscall_trace_entry)
-
- # perform syscall exit tracing
- ALIGN
-syscall_exit_work_irqs_off:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_ANY)
-
-syscall_exit_work:
- movl %esp, %eax
- call syscall_return_slowpath
- jmp restore_all
-END(syscall_exit_work)
-
-syscall_fault:
- ASM_CLAC
- GET_THREAD_INFO(%ebp)
- movl $-EFAULT, PT_EAX(%esp)
- jmp resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
- movl $-ENOSYS, %eax
- jmp syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
- movl $-ENOSYS, %eax
- jmp sysenter_after_call
-END(sysenter_badsys)
-
.macro FIXUP_ESPFIX_STACK
/*
* Switch back for ESPFIX stack to the normal zerobased stack
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 055a01de7..a55697d19 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -391,20 +391,16 @@ GLOBAL(stub_execveat)
jmp return_from_execve
END(stub_execveat)
-#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_X32_ABI)
.align 8
GLOBAL(stub_x32_execve)
-GLOBAL(stub32_execve)
call compat_sys_execve
jmp return_from_execve
-END(stub32_execve)
END(stub_x32_execve)
.align 8
GLOBAL(stub_x32_execveat)
-GLOBAL(stub32_execveat)
call compat_sys_execveat
jmp return_from_execve
-END(stub32_execveat)
END(stub_x32_execveat)
#endif
@@ -513,6 +509,17 @@ END(irq_entries_start)
* tracking that we're in kernel mode.
*/
SWAPGS
+
+ /*
+ * We need to tell lockdep that IRQs are off. We can't do this until
+ * we fix gsbase, and we should do it before enter_from_user_mode
+ * (which can take locks). Since TRACE_IRQS_OFF idempotent,
+ * the simplest way to handle it is to just call it twice if
+ * we enter from user mode. There's no reason to optimize this since
+ * TRACE_IRQS_OFF is a no-op if lockdep is off.
+ */
+ TRACE_IRQS_OFF
+
#ifdef CONFIG_CONTEXT_TRACKING
call enter_from_user_mode
#endif
@@ -557,7 +564,6 @@ ret_from_intr:
jz retint_kernel
/* Interrupt came from user space */
- LOCKDEP_SYS_EXIT_IRQ
GLOBAL(retint_user)
mov %rsp,%rdi
call prepare_exit_to_usermode
@@ -587,7 +593,7 @@ retint_kernel:
* At this label, code paths which return to kernel and to user,
* which come from interrupts/exception and from syscalls, merge.
*/
-restore_regs_and_iret:
+GLOBAL(restore_regs_and_iret)
RESTORE_EXTRA_REGS
restore_c_regs_and_iret:
RESTORE_C_REGS
@@ -1054,12 +1060,18 @@ ENTRY(error_entry)
SWAPGS
.Lerror_entry_from_usermode_after_swapgs:
+ /*
+ * We need to tell lockdep that IRQs are off. We can't do this until
+ * we fix gsbase, and we should do it before enter_from_user_mode
+ * (which can take locks).
+ */
+ TRACE_IRQS_OFF
#ifdef CONFIG_CONTEXT_TRACKING
call enter_from_user_mode
#endif
+ ret
.Lerror_entry_done:
-
TRACE_IRQS_OFF
ret
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index a9360d40f..6a1ae3751 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -16,16 +16,6 @@
#include <linux/linkage.h>
#include <linux/err.h>
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE 0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-# define sysexit_audit ia32_ret_from_sys_call_irqs_off
-# define sysretl_audit ia32_ret_from_sys_call_irqs_off
-#endif
-
.section .entry.text, "ax"
#ifdef CONFIG_PARAVIRT
@@ -58,219 +48,88 @@ ENDPROC(native_usergs_sysret32)
* with the int 0x80 path.
*/
ENTRY(entry_SYSENTER_compat)
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
+ /* Interrupts are off on entry. */
SWAPGS_UNSAFE_STACK
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
- /* Zero-extending 32-bit regs, do not remove */
- movl %ebp, %ebp
+ /*
+ * User tracing code (ptrace or signal handlers) might assume that
+ * the saved RAX contains a 32-bit number when we're invoking a 32-bit
+ * syscall. Just in case the high bits are nonzero, zero-extend
+ * the syscall number. (This could almost certainly be deleted
+ * with no ill effects.)
+ */
movl %eax, %eax
- movl ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
-
/* Construct struct pt_regs on stack */
pushq $__USER32_DS /* pt_regs->ss */
- pushq %rbp /* pt_regs->sp */
- pushfq /* pt_regs->flags */
+ pushq %rbp /* pt_regs->sp (stashed in bp) */
+
+ /*
+ * Push flags. This is nasty. First, interrupts are currently
+ * off, but we need pt_regs->flags to have IF set. Second, even
+ * if TF was set when SYSENTER started, it's clear by now. We fix
+ * that later using TIF_SINGLESTEP.
+ */
+ pushfq /* pt_regs->flags (except IF = 0) */
+ orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */
+ ASM_CLAC /* Clear AC after saving FLAGS */
+
pushq $__USER32_CS /* pt_regs->cs */
- pushq %r10 /* pt_regs->ip = thread_info->sysenter_return */
+ xorq %r8,%r8
+ pushq %r8 /* pt_regs->ip = 0 (placeholder) */
pushq %rax /* pt_regs->orig_ax */
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r9 = 0 */
+ pushq %r8 /* pt_regs->r10 = 0 */
+ pushq %r8 /* pt_regs->r11 = 0 */
+ pushq %rbx /* pt_regs->rbx */
+ pushq %rbp /* pt_regs->rbp (will be overwritten) */
+ pushq %r8 /* pt_regs->r12 = 0 */
+ pushq %r8 /* pt_regs->r13 = 0 */
+ pushq %r8 /* pt_regs->r14 = 0 */
+ pushq %r8 /* pt_regs->r15 = 0 */
cld
- sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
-
- /*
- * no need to do an access_ok check here because rbp has been
- * 32-bit zero extended
- */
- ASM_STAC
-1: movl (%rbp), %ebp
- _ASM_EXTABLE(1b, ia32_badarg)
- ASM_CLAC
/*
* Sysenter doesn't filter flags, so we need to clear NT
* ourselves. To save a few cycles, we can check whether
* NT was set instead of doing an unconditional popfq.
+ * This needs to happen before enabling interrupts so that
+ * we don't get preempted with NT set.
+ *
+ * NB.: sysenter_fix_flags is a label with the code under it moved
+ * out-of-line as an optimization: NT is unlikely to be set in the
+ * majority of the cases and instead of polluting the I$ unnecessarily,
+ * we're keeping that code behind a branch which will predict as
+ * not-taken and therefore its instructions won't be fetched.
*/
testl $X86_EFLAGS_NT, EFLAGS(%rsp)
jnz sysenter_fix_flags
sysenter_flags_fixed:
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysenter_tracesys
-
-sysenter_do_call:
- /* 32-bit syscall -> 64-bit C ABI argument conversion */
- movl %edi, %r8d /* arg5 */
- movl %ebp, %r9d /* arg6 */
- xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
- movl %ebx, %edi /* arg1 */
- movl %edx, %edx /* arg3 (zero extension) */
-sysenter_dispatch:
- cmpq $(IA32_NR_syscalls-1), %rax
- ja 1f
- call *ia32_sys_call_table(, %rax, 8)
- movq %rax, RAX(%rsp)
-1:
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysexit_audit
-sysexit_from_sys_call:
- /*
- * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
- * NMI between STI and SYSEXIT has poorly specified behavior,
- * and and NMI followed by an IRQ with usergs is fatal. So
- * we just pretend we're using SYSEXIT but we really use
- * SYSRETL instead.
- *
- * This code path is still called 'sysexit' because it pairs
- * with 'sysenter' and it uses the SYSENTER calling convention.
- */
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RIP(%rsp), %ecx /* User %eip */
- movq RAX(%rsp), %rax
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- xorl %edx, %edx /* Do not leak kernel information */
- xorq %r8, %r8
- xorq %r9, %r9
- xorq %r10, %r10
- movl EFLAGS(%rsp), %r11d /* User eflags */
- TRACE_IRQS_ON
-
- /*
- * SYSRETL works even on Intel CPUs. Use it in preference to SYSEXIT,
- * since it avoids a dicey window with interrupts enabled.
- */
- movl RSP(%rsp), %esp
-
- /*
- * USERGS_SYSRET32 does:
- * gsbase = user's gs base
- * eip = ecx
- * rflags = r11
- * cs = __USER32_CS
- * ss = __USER_DS
- *
- * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
- *
- * pop %ebp
- * pop %edx
- * pop %ecx
- *
- * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
- * avoid info leaks. R11 ends up with VDSO32_SYSENTER_RETURN's
- * address (already known to user code), and R12-R15 are
- * callee-saved and therefore don't contain any interesting
- * kernel data.
- */
- USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
- .macro auditsys_entry_common
- /*
- * At this point, registers hold syscall args in the 32-bit syscall ABI:
- * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
- *
- * We want to pass them to __audit_syscall_entry(), which is a 64-bit
- * C function with 5 parameters, so shuffle them to match what
- * the function expects: RDI,RSI,RDX,RCX,R8.
- */
- movl %esi, %r8d /* arg5 (R8 ) <= 4th syscall arg (ESI) */
- xchg %ecx, %edx /* arg4 (RCX) <= 3rd syscall arg (EDX) */
- /* arg3 (RDX) <= 2nd syscall arg (ECX) */
- movl %ebx, %esi /* arg2 (RSI) <= 1st syscall arg (EBX) */
- movl %eax, %edi /* arg1 (RDI) <= syscall number (EAX) */
- call __audit_syscall_entry
-
/*
- * We are going to jump back to the syscall dispatch code.
- * Prepare syscall args as required by the 64-bit C ABI.
- * Registers clobbered by __audit_syscall_entry() are
- * loaded from pt_regs on stack:
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
*/
- movl ORIG_RAX(%rsp), %eax /* syscall number */
- movl %ebx, %edi /* arg1 */
- movl RCX(%rsp), %esi /* arg2 */
- movl RDX(%rsp), %edx /* arg3 */
- movl RSI(%rsp), %ecx /* arg4 */
- movl RDI(%rsp), %r8d /* arg5 */
- .endm
-
- .macro auditsys_exit exit
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
- testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_ret_from_sys_call
- movl %eax, %esi /* second arg, syscall return value */
- cmpl $-MAX_ERRNO, %eax /* is it an error ? */
- jbe 1f
- movslq %eax, %rsi /* if error sign extend to 64 bits */
-1: setbe %al /* 1 if error, 0 if not */
- movzbl %al, %edi /* zero-extend that into %edi */
- call __audit_syscall_exit
- movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
- DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- testl %edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz \exit
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- jmp int_ret_from_sys_call_irqs_off
- .endm
-sysenter_auditsys:
- auditsys_entry_common
- movl %ebp, %r9d /* reload 6th syscall arg */
- jmp sysenter_dispatch
-
-sysexit_audit:
- auditsys_exit sysexit_from_sys_call
-#endif
+ movq %rsp, %rdi
+ call do_fast_syscall_32
+ /* XEN PV guests always use IRET path */
+ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+ jmp sysret32_from_system_call
sysenter_fix_flags:
- pushq $(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+ pushq $X86_EFLAGS_FIXED
popfq
jmp sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz sysenter_auditsys
-#endif
- SAVE_EXTRA_REGS
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- movq %rsp, %rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
-
- /* Reload arg registers from stack. (see sysenter_tracesys) */
- movl RCX(%rsp), %ecx
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl %eax, %eax /* zero extension */
-
- RESTORE_EXTRA_REGS
- jmp sysenter_do_call
ENDPROC(entry_SYSENTER_compat)
/*
@@ -298,21 +157,14 @@ ENDPROC(entry_SYSENTER_compat)
* edi arg5
* esp user stack
* 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
*/
ENTRY(entry_SYSCALL_compat)
- /*
- * Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
- */
+ /* Interrupts are off on entry. */
SWAPGS_UNSAFE_STACK
+
+ /* Stash user ESP and switch to the kernel stack. */
movl %esp, %r8d
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
- ENABLE_INTERRUPTS(CLBR_NONE)
/* Zero-extending 32-bit regs, do not remove */
movl %eax, %eax
@@ -327,162 +179,68 @@ ENTRY(entry_SYSCALL_compat)
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %rdx /* pt_regs->dx */
- pushq %rbp /* pt_regs->cx */
- movl %ebp, %ecx
+ pushq %rbp /* pt_regs->cx (stashed in bp) */
pushq $-ENOSYS /* pt_regs->ax */
- sub $(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
+ xorq %r8,%r8
+ pushq %r8 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r9 = 0 */
+ pushq %r8 /* pt_regs->r10 = 0 */
+ pushq %r8 /* pt_regs->r11 = 0 */
+ pushq %rbx /* pt_regs->rbx */
+ pushq %rbp /* pt_regs->rbp (will be overwritten) */
+ pushq %r8 /* pt_regs->r12 = 0 */
+ pushq %r8 /* pt_regs->r13 = 0 */
+ pushq %r8 /* pt_regs->r14 = 0 */
+ pushq %r8 /* pt_regs->r15 = 0 */
/*
- * No need to do an access_ok check here because r8 has been
- * 32-bit zero extended:
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
*/
- ASM_STAC
-1: movl (%r8), %r9d
- _ASM_EXTABLE(1b, ia32_badarg)
- ASM_CLAC
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz cstar_tracesys
-
-cstar_do_call:
- /* 32-bit syscall -> 64-bit C ABI argument conversion */
- movl %edi, %r8d /* arg5 */
- /* r9 already loaded */ /* arg6 */
- xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
- movl %ebx, %edi /* arg1 */
- movl %edx, %edx /* arg3 (zero extension) */
-
-cstar_dispatch:
- cmpq $(IA32_NR_syscalls-1), %rax
- ja 1f
-
- call *ia32_sys_call_table(, %rax, 8)
- movq %rax, RAX(%rsp)
-1:
- DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz sysretl_audit
-sysretl_from_sys_call:
- andl $~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl RIP(%rsp), %ecx
- movl EFLAGS(%rsp), %r11d
- movq RAX(%rsp), %rax
- xorq %r10, %r10
- xorq %r9, %r9
- xorq %r8, %r8
- TRACE_IRQS_ON
- movl RSP(%rsp), %esp
- /*
- * 64-bit->32-bit SYSRET restores eip from ecx,
- * eflags from r11 (but RF and VM bits are forced to 0),
- * cs and ss are loaded from MSRs.
- * (Note: 32-bit->32-bit SYSRET is different: since r11
- * does not exist, it merely sets eflags.IF=1).
+ movq %rsp, %rdi
+ call do_fast_syscall_32
+ /* XEN PV guests always use IRET path */
+ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \
+ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV
+
+ /* Opportunistic SYSRET */
+sysret32_from_system_call:
+ TRACE_IRQS_ON /* User mode traces as IRQs on. */
+ movq RBX(%rsp), %rbx /* pt_regs->rbx */
+ movq RBP(%rsp), %rbp /* pt_regs->rbp */
+ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */
+ movq RIP(%rsp), %rcx /* pt_regs->ip (in rcx) */
+ addq $RAX, %rsp /* Skip r8-r15 */
+ popq %rax /* pt_regs->rax */
+ popq %rdx /* Skip pt_regs->cx */
+ popq %rdx /* pt_regs->dx */
+ popq %rsi /* pt_regs->si */
+ popq %rdi /* pt_regs->di */
+
+ /*
+ * USERGS_SYSRET32 does:
+ * GSBASE = user's GS base
+ * EIP = ECX
+ * RFLAGS = R11
+ * CS = __USER32_CS
+ * SS = __USER_DS
+ *
+ * ECX will not match pt_regs->cx, but we're returning to a vDSO
+ * trampoline that will fix up RCX, so this is okay.
*
- * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
- * descriptor is not reinitialized. This means that we must
- * avoid SYSRET with SS == NULL, which could happen if we schedule,
- * exit the kernel, and re-enter using an interrupt vector. (All
- * interrupt entries on x86_64 set SS to NULL.) We prevent that
- * from happening by reloading SS in __switch_to.
- */
- USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
- movl %r9d, R9(%rsp) /* register to be clobbered by call */
- auditsys_entry_common
- movl R9(%rsp), %r9d /* reload 6th syscall arg */
- jmp cstar_dispatch
-
-sysretl_audit:
- auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
- testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jz cstar_auditsys
-#endif
- xchgl %r9d, %ebp
- SAVE_EXTRA_REGS
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %r9, R9(%rsp)
- movq %rax, R8(%rsp)
- movq %rsp, %rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
- movl R9(%rsp), %r9d
-
- /* Reload arg registers from stack. (see sysenter_tracesys) */
- movl RCX(%rsp), %ecx
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl %eax, %eax /* zero extension */
-
- RESTORE_EXTRA_REGS
- xchgl %ebp, %r9d
- jmp cstar_do_call
+ * R12-R15 are callee-saved, so they contain whatever was in them
+ * when the system call started, which is already known to user
+ * code. We zero R8-R10 to avoid info leaks.
+ */
+ xorq %r8, %r8
+ xorq %r9, %r9
+ xorq %r10, %r10
+ movq RSP-ORIG_RAX(%rsp), %rsp
+ USERGS_SYSRET32
END(entry_SYSCALL_compat)
-ia32_badarg:
- /*
- * So far, we've entered kernel mode, set AC, turned on IRQs, and
- * saved C regs except r8-r11. We haven't done any of the other
- * standard entry work, though. We want to bail, but we shouldn't
- * treat this as a syscall entry since we don't even know what the
- * args are. Instead, treat this as a non-syscall entry, finish
- * the entry work, and immediately exit after setting AX = -EFAULT.
- *
- * We're really just being polite here. Killing the task outright
- * would be a reasonable action, too. Given that the only valid
- * way to have gotten here is through the vDSO, and we already know
- * that the stack pointer is bad, the task isn't going to survive
- * for long no matter what we do.
- */
-
- ASM_CLAC /* undo STAC */
- movq $-EFAULT, RAX(%rsp) /* return -EFAULT if possible */
-
- /* Fill in the rest of pt_regs */
- xorl %eax, %eax
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- SAVE_EXTRA_REGS
-
- /* Turn IRQs back off. */
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
-
- /* Now finish entering normal kernel mode. */
-#ifdef CONFIG_CONTEXT_TRACKING
- call enter_from_user_mode
-#endif
-
- /* And exit again. */
- jmp retint_user
-
-ia32_ret_from_sys_call_irqs_off:
- TRACE_IRQS_ON
- ENABLE_INTERRUPTS(CLBR_NONE)
-
-ia32_ret_from_sys_call:
- xorl %eax, %eax /* Do not leak kernel information */
- movq %rax, R11(%rsp)
- movq %rax, R10(%rsp)
- movq %rax, R9(%rsp)
- movq %rax, R8(%rsp)
- jmp int_ret_from_sys_call
-
/*
* Emulated IA32 system calls via int 0x80.
*
@@ -507,14 +265,17 @@ ia32_ret_from_sys_call:
ENTRY(entry_INT80_compat)
/*
* Interrupts are off on entry.
- * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
- * it is too small to ever cause noticeable irq latency.
*/
PARAVIRT_ADJUST_EXCEPTION_FRAME
SWAPGS
- ENABLE_INTERRUPTS(CLBR_NONE)
- /* Zero-extending 32-bit regs, do not remove */
+ /*
+ * User tracing code (ptrace or signal handlers) might assume that
+ * the saved RAX contains a 32-bit number when we're invoking a 32-bit
+ * syscall. Just in case the high bits are nonzero, zero-extend
+ * the syscall number. (This could almost certainly be deleted
+ * with no ill effects.)
+ */
movl %eax, %eax
/* Construct struct pt_regs on stack (iret frame is already on stack) */
@@ -524,67 +285,37 @@ ENTRY(entry_INT80_compat)
pushq %rdx /* pt_regs->dx */
pushq %rcx /* pt_regs->cx */
pushq $-ENOSYS /* pt_regs->ax */
- pushq $0 /* pt_regs->r8 */
- pushq $0 /* pt_regs->r9 */
- pushq $0 /* pt_regs->r10 */
- pushq $0 /* pt_regs->r11 */
+ xorq %r8,%r8
+ pushq %r8 /* pt_regs->r8 = 0 */
+ pushq %r8 /* pt_regs->r9 = 0 */
+ pushq %r8 /* pt_regs->r10 = 0 */
+ pushq %r8 /* pt_regs->r11 = 0 */
+ pushq %rbx /* pt_regs->rbx */
+ pushq %rbp /* pt_regs->rbp */
+ pushq %r12 /* pt_regs->r12 */
+ pushq %r13 /* pt_regs->r13 */
+ pushq %r14 /* pt_regs->r14 */
+ pushq %r15 /* pt_regs->r15 */
cld
- sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
-
- orl $TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
- testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
- jnz ia32_tracesys
-
-ia32_do_call:
- /* 32-bit syscall -> 64-bit C ABI argument conversion */
- movl %edi, %r8d /* arg5 */
- movl %ebp, %r9d /* arg6 */
- xchg %ecx, %esi /* rsi:arg2, rcx:arg4 */
- movl %ebx, %edi /* arg1 */
- movl %edx, %edx /* arg3 (zero extension) */
- cmpq $(IA32_NR_syscalls-1), %rax
- ja 1f
- call *ia32_sys_call_table(, %rax, 8)
- movq %rax, RAX(%rsp)
-1:
- jmp int_ret_from_sys_call
-
-ia32_tracesys:
- SAVE_EXTRA_REGS
- movq %rsp, %rdi /* &pt_regs -> arg1 */
- call syscall_trace_enter
/*
- * Reload arg registers from stack in case ptrace changed them.
- * Don't reload %eax because syscall_trace_enter() returned
- * the %rax value we should see. But do truncate it to 32 bits.
- * If it's -1 to make us punt the syscall, then (u32)-1 is still
- * an appropriately invalid value.
+ * User mode is traced as though IRQs are on, and the interrupt
+ * gate turned them off.
*/
- movl RCX(%rsp), %ecx
- movl RDX(%rsp), %edx
- movl RSI(%rsp), %esi
- movl RDI(%rsp), %edi
- movl %eax, %eax /* zero extension */
- RESTORE_EXTRA_REGS
- jmp ia32_do_call
-END(entry_INT80_compat)
+ TRACE_IRQS_OFF
- .macro PTREGSCALL label, func
- ALIGN
-GLOBAL(\label)
- leaq \func(%rip), %rax
- jmp ia32_ptregs_common
- .endm
+ movq %rsp, %rdi
+ call do_syscall_32_irqs_off
+.Lsyscall_32_done:
- PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
- PTREGSCALL stub32_sigreturn, sys32_sigreturn
- PTREGSCALL stub32_fork, sys_fork
- PTREGSCALL stub32_vfork, sys_vfork
+ /* Go back to user mode. */
+ TRACE_IRQS_ON
+ SWAPGS
+ jmp restore_regs_and_iret
+END(entry_INT80_compat)
ALIGN
GLOBAL(stub32_clone)
- leaq sys_clone(%rip), %rax
/*
* The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
* The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
@@ -593,12 +324,4 @@ GLOBAL(stub32_clone)
* so we need to swap arguments here before calling it:
*/
xchg %r8, %rcx
- jmp ia32_ptregs_common
-
- ALIGN
-ia32_ptregs_common:
- SAVE_EXTRA_REGS 8
- call *%rax
- RESTORE_EXTRA_REGS 8
- ret
-END(ia32_ptregs_common)
+ jmp sys_clone
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8ea34f94e..9a6649857 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -4,24 +4,21 @@
#include <linux/sys.h>
#include <linux/cache.h>
#include <asm/asm-offsets.h>
+#include <asm/syscall.h>
#ifdef CONFIG_IA32_EMULATION
#define SYM(sym, compat) compat
#else
#define SYM(sym, compat) sym
-#define ia32_sys_call_table sys_call_table
-#define __NR_syscall_compat_max __NR_syscall_max
#endif
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
#include <asm/syscalls_32.h>
#undef __SYSCALL_I386
#define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
-typedef asmlinkage void (*sys_call_ptr_t)(void);
-
-extern asmlinkage void sys_ni_syscall(void);
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
/*
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index 4ac730b37..41283d22b 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -14,13 +14,13 @@
# define __SYSCALL_X32(nr, sym, compat) /* nothing */
#endif
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
+#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
#include <asm/syscalls_64.h>
#undef __SYSCALL_64
#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
-extern void sys_ni_syscall(void);
+extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
/*
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 7663c455b..f17705e13 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -8,7 +8,7 @@
#
0 i386 restart_syscall sys_restart_syscall
1 i386 exit sys_exit
-2 i386 fork sys_fork stub32_fork
+2 i386 fork sys_fork sys_fork
3 i386 read sys_read
4 i386 write sys_write
5 i386 open sys_open compat_sys_open
@@ -17,7 +17,7 @@
8 i386 creat sys_creat
9 i386 link sys_link
10 i386 unlink sys_unlink
-11 i386 execve sys_execve stub32_execve
+11 i386 execve sys_execve compat_sys_execve
12 i386 chdir sys_chdir
13 i386 time sys_time compat_sys_time
14 i386 mknod sys_mknod
@@ -125,7 +125,7 @@
116 i386 sysinfo sys_sysinfo compat_sys_sysinfo
117 i386 ipc sys_ipc compat_sys_ipc
118 i386 fsync sys_fsync
-119 i386 sigreturn sys_sigreturn stub32_sigreturn
+119 i386 sigreturn sys_sigreturn sys32_sigreturn
120 i386 clone sys_clone stub32_clone
121 i386 setdomainname sys_setdomainname
122 i386 uname sys_newuname
@@ -179,7 +179,7 @@
170 i386 setresgid sys_setresgid16
171 i386 getresgid sys_getresgid16
172 i386 prctl sys_prctl
-173 i386 rt_sigreturn sys_rt_sigreturn stub32_rt_sigreturn
+173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn
174 i386 rt_sigaction sys_rt_sigaction compat_sys_rt_sigaction
175 i386 rt_sigprocmask sys_rt_sigprocmask
176 i386 rt_sigpending sys_rt_sigpending compat_sys_rt_sigpending
@@ -196,7 +196,7 @@
187 i386 sendfile sys_sendfile compat_sys_sendfile
188 i386 getpmsg
189 i386 putpmsg
-190 i386 vfork sys_vfork stub32_vfork
+190 i386 vfork sys_vfork sys_vfork
191 i386 ugetrlimit sys_getrlimit compat_sys_getrlimit
192 i386 mmap2 sys_mmap_pgoff
193 i386 truncate64 sys_truncate64 sys32_truncate64
@@ -364,7 +364,7 @@
355 i386 getrandom sys_getrandom
356 i386 memfd_create sys_memfd_create
357 i386 bpf sys_bpf
-358 i386 execveat sys_execveat stub32_execveat
+358 i386 execveat sys_execveat compat_sys_execveat
359 i386 socket sys_socket
360 i386 socketpair sys_socketpair
361 i386 bind sys_bind
@@ -382,3 +382,4 @@
373 i386 shutdown sys_shutdown
374 i386 userfaultfd sys_userfaultfd
375 i386 membarrier sys_membarrier
+376 i386 mlock2 sys_mlock2
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 278842fdf..314a90bfc 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -331,6 +331,7 @@
322 64 execveat stub_execveat
323 common userfaultfd sys_userfaultfd
324 common membarrier sys_membarrier
+325 common mlock2 sys_mlock2
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index a3d0767a6..265c0ed68 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -19,9 +19,7 @@ obj-y += vma.o
# vDSO images to build
vdso_img-$(VDSO64-y) += 64
vdso_img-$(VDSOX32-y) += x32
-vdso_img-$(VDSO32-y) += 32-int80
-vdso_img-$(CONFIG_IA32_EMULATION) += 32-syscall
-vdso_img-$(VDSO32-y) += 32-sysenter
+vdso_img-$(VDSO32-y) += 32
obj-$(VDSO32-y) += vdso32-setup.o
@@ -69,7 +67,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
$(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
-fno-omit-frame-pointer -foptimize-sibling-calls \
- -DDISABLE_BRANCH_PROFILING
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
$(vobjs): KBUILD_CFLAGS += $(CFL)
@@ -122,15 +120,6 @@ $(obj)/%.so: $(obj)/%.so.dbg
$(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
$(call if_changed,vdso)
-#
-# Build multiple 32-bit vDSO images to choose from at boot time.
-#
-vdso32.so-$(VDSO32-y) += int80
-vdso32.so-$(CONFIG_IA32_EMULATION) += syscall
-vdso32.so-$(VDSO32-y) += sysenter
-
-vdso32-images = $(vdso32.so-y:%=vdso32-%.so)
-
CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
@@ -139,14 +128,12 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
targets += vdso32/vdso32.lds
-targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
+targets += vdso32/note.o vdso32/vclock_gettime.o vdso32/system_call.o
targets += vdso32/vclock_gettime.o
-$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
-
-KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
-$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
-$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
+KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO
+$(obj)/vdso32.so.dbg: KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
+$(obj)/vdso32.so.dbg: asflags-$(CONFIG_X86_64) += -m32
KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
@@ -157,13 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
-$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
- $(obj)/vdso32/vdso32.lds \
- $(obj)/vdso32/vclock_gettime.o \
- $(obj)/vdso32/note.o \
- $(obj)/vdso32/%.o
+$(obj)/vdso32.so.dbg: FORCE \
+ $(obj)/vdso32/vdso32.lds \
+ $(obj)/vdso32/vclock_gettime.o \
+ $(obj)/vdso32/note.o \
+ $(obj)/vdso32/system_call.o
$(call if_changed,vdso)
#
@@ -206,4 +193,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
PHONY += vdso_install $(vdso_img_insttargets)
vdso_install: $(vdso_img_insttargets) FORCE
-clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so*
+clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so*
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
index 8627db24a..785d9922b 100644
--- a/arch/x86/entry/vdso/vdso2c.c
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -98,10 +98,10 @@ struct vdso_sym required_syms[] = {
"VDSO_FAKE_SECTION_TABLE_END", false
},
{"VDSO32_NOTE_MASK", true},
- {"VDSO32_SYSENTER_RETURN", true},
{"__kernel_vsyscall", true},
{"__kernel_sigreturn", true},
{"__kernel_rt_sigreturn", true},
+ {"int80_landing_pad", true},
};
__attribute__((format(printf, 1, 2))) __attribute__((noreturn))
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index e904c2705..08a317a9a 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -48,35 +48,9 @@ __setup("vdso32=", vdso32_setup);
__setup_param("vdso=", vdso_setup, vdso32_setup, 0);
#endif
-#ifdef CONFIG_X86_64
-
-#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32))
-#define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32))
-
-#else /* CONFIG_X86_32 */
-
-#define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP))
-#define vdso32_syscall() (0)
-
-#endif /* CONFIG_X86_64 */
-
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
-const struct vdso_image *selected_vdso32;
-#endif
-
int __init sysenter_setup(void)
{
-#ifdef CONFIG_COMPAT
- if (vdso32_syscall())
- selected_vdso32 = &vdso_image_32_syscall;
- else
-#endif
- if (vdso32_sysenter())
- selected_vdso32 = &vdso_image_32_sysenter;
- else
- selected_vdso32 = &vdso_image_32_int80;
-
- init_vdso_image(selected_vdso32);
+ init_vdso_image(&vdso_image_32);
return 0;
}
diff --git a/arch/x86/entry/vdso/vdso32/int80.S b/arch/x86/entry/vdso/vdso32/int80.S
deleted file mode 100644
index b15b7c01a..000000000
--- a/arch/x86/entry/vdso/vdso32/int80.S
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Code for the vDSO. This version uses the old int $0x80 method.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
- .text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
- int $0x80
- ret
-.LEND_vsyscall:
- .size __kernel_vsyscall,.-.LSTART_vsyscall
- .previous
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI:
- .long .LENDCIEDLSI-.LSTARTCIEDLSI
-.LSTARTCIEDLSI:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zR" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0x0c /* DW_CFA_def_cfa */
- .uleb128 4
- .uleb128 4
- .byte 0x88 /* DW_CFA_offset, column 0x8 */
- .uleb128 1
- .align 4
-.LENDCIEDLSI:
- .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
-.LSTARTFDEDLSI:
- .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
- .long .LSTART_vsyscall-. /* PC-relative start address */
- .long .LEND_vsyscall-.LSTART_vsyscall
- .uleb128 0
- .align 4
-.LENDFDEDLSI:
- .previous
-
- /*
- * Pad out the segment to match the size of the sysenter.S version.
- */
-VDSO32_vsyscall_eh_frame_size = 0x40
- .section .data,"aw",@progbits
- .space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0
- .previous
diff --git a/arch/x86/entry/vdso/vdso32/syscall.S b/arch/x86/entry/vdso/vdso32/syscall.S
deleted file mode 100644
index 6b286bb52..000000000
--- a/arch/x86/entry/vdso/vdso32/syscall.S
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * Code for the vDSO. This version uses the syscall instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#define SYSCALL_ENTER_KERNEL syscall
-#include "sigreturn.S"
-
-#include <asm/segment.h>
-
- .text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
- push %ebp
-.Lpush_ebp:
- movl %ecx, %ebp
- syscall
- movl %ebp, %ecx
- popl %ebp
-.Lpop_ebp:
- ret
-.LEND_vsyscall:
- .size __kernel_vsyscall,.-.LSTART_vsyscall
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAME:
- .long .LENDCIE-.LSTARTCIE
-.LSTARTCIE:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zR" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0x0c /* DW_CFA_def_cfa */
- .uleb128 4
- .uleb128 4
- .byte 0x88 /* DW_CFA_offset, column 0x8 */
- .uleb128 1
- .align 4
-.LENDCIE:
-
- .long .LENDFDE1-.LSTARTFDE1 /* Length FDE */
-.LSTARTFDE1:
- .long .LSTARTFDE1-.LSTARTFRAME /* CIE pointer */
- .long .LSTART_vsyscall-. /* PC-relative start address */
- .long .LEND_vsyscall-.LSTART_vsyscall
- .uleb128 0 /* Augmentation length */
- /* What follows are the instructions for the table generation.
- We have to record all changes of the stack pointer. */
- .byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .uleb128 8
- .byte 0x85, 0x02 /* DW_CFA_offset %ebp -8 */
- .byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */
- .byte 0xc5 /* DW_CFA_restore %ebp */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .uleb128 4
- .align 4
-.LENDFDE1:
- .previous
-
- /*
- * Pad out the segment to match the size of the sysenter.S version.
- */
-VDSO32_vsyscall_eh_frame_size = 0x40
- .section .data,"aw",@progbits
- .space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0
- .previous
diff --git a/arch/x86/entry/vdso/vdso32/sysenter.S b/arch/x86/entry/vdso/vdso32/sysenter.S
deleted file mode 100644
index e354bceee..000000000
--- a/arch/x86/entry/vdso/vdso32/sysenter.S
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * Code for the vDSO. This version uses the sysenter instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
-/*
- * The caller puts arg2 in %ecx, which gets pushed. The kernel will use
- * %ecx itself for arg2. The pushing is because the sysexit instruction
- * (found in entry.S) requires that we clobber %ecx with the desired %esp.
- * User code might expect that %ecx is unclobbered though, as it would be
- * for returning via the iret instruction, so we must push and pop.
- *
- * The caller puts arg3 in %edx, which the sysexit instruction requires
- * for %eip. Thus, exactly as for arg2, we must push and pop.
- *
- * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
- * instruction clobbers %esp, the user's %esp won't even survive entry
- * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
- * arg6 from the stack.
- *
- * You can not use this vsyscall for the clone() syscall because the
- * three words on the parent stack do not get copied to the child.
- */
- .text
- .globl __kernel_vsyscall
- .type __kernel_vsyscall,@function
- ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
- push %ecx
-.Lpush_ecx:
- push %edx
-.Lpush_edx:
- push %ebp
-.Lenter_kernel:
- movl %esp,%ebp
- sysenter
-
- /* 7: align return point with nop's to make disassembly easier */
- .space 7,0x90
-
- /* 14: System call restart point is here! (SYSENTER_RETURN-2) */
- int $0x80
- /* 16: System call normal return point is here! */
-VDSO32_SYSENTER_RETURN: /* Symbol used by sysenter.c via vdso32-syms.h */
- pop %ebp
-.Lpop_ebp:
- pop %edx
-.Lpop_edx:
- pop %ecx
-.Lpop_ecx:
- ret
-.LEND_vsyscall:
- .size __kernel_vsyscall,.-.LSTART_vsyscall
- .previous
-
- .section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI:
- .long .LENDCIEDLSI-.LSTARTCIEDLSI
-.LSTARTCIEDLSI:
- .long 0 /* CIE ID */
- .byte 1 /* Version number */
- .string "zR" /* NUL-terminated augmentation string */
- .uleb128 1 /* Code alignment factor */
- .sleb128 -4 /* Data alignment factor */
- .byte 8 /* Return address register column */
- .uleb128 1 /* Augmentation value length */
- .byte 0x1b /* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
- .byte 0x0c /* DW_CFA_def_cfa */
- .uleb128 4
- .uleb128 4
- .byte 0x88 /* DW_CFA_offset, column 0x8 */
- .uleb128 1
- .align 4
-.LENDCIEDLSI:
- .long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
-.LSTARTFDEDLSI:
- .long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
- .long .LSTART_vsyscall-. /* PC-relative start address */
- .long .LEND_vsyscall-.LSTART_vsyscall
- .uleb128 0
- /* What follows are the instructions for the table generation.
- We have to record all changes of the stack pointer. */
- .byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x08 /* RA at offset 8 now */
- .byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x0c /* RA at offset 12 now */
- .byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x10 /* RA at offset 16 now */
- .byte 0x85, 0x04 /* DW_CFA_offset %ebp -16 */
- /* Finally the epilogue. */
- .byte 0x40 + (.Lpop_ebp-.Lenter_kernel) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x0c /* RA at offset 12 now */
- .byte 0xc5 /* DW_CFA_restore %ebp */
- .byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x08 /* RA at offset 8 now */
- .byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */
- .byte 0x0e /* DW_CFA_def_cfa_offset */
- .byte 0x04 /* RA at offset 4 now */
- .align 4
-.LENDFDEDLSI:
- .previous
-
- /*
- * Emit a symbol with the size of this .eh_frame data,
- * to verify it matches the other versions.
- */
-VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI)
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
new file mode 100644
index 000000000..3a1d92970
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -0,0 +1,89 @@
+/*
+ * AT_SYSINFO entry point
+*/
+
+#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+
+/*
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#include "sigreturn.S"
+
+ .text
+ .globl __kernel_vsyscall
+ .type __kernel_vsyscall,@function
+ ALIGN
+__kernel_vsyscall:
+ CFI_STARTPROC
+ /*
+ * Reshuffle regs so that all of any of the entry instructions
+ * will preserve enough state.
+ *
+ * A really nice entry sequence would be:
+ * pushl %edx
+ * pushl %ecx
+ * movl %esp, %ecx
+ *
+ * Unfortunately, naughty Android versions between July and December
+ * 2015 actually hardcode the traditional Linux SYSENTER entry
+ * sequence. That is severely broken for a number of reasons (ask
+ * anyone with an AMD CPU, for example). Nonetheless, we try to keep
+ * it working approximately as well as it ever worked.
+ *
+ * This link may eludicate some of the history:
+ * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7
+ * personally, I find it hard to understand what's going on there.
+ *
+ * Note to future user developers: DO NOT USE SYSENTER IN YOUR CODE.
+ * Execute an indirect call to the address in the AT_SYSINFO auxv
+ * entry. That is the ONLY correct way to make a fast 32-bit system
+ * call on Linux. (Open-coding int $0x80 is also fine, but it's
+ * slow.)
+ */
+ pushl %ecx
+ CFI_ADJUST_CFA_OFFSET 4
+ CFI_REL_OFFSET ecx, 0
+ pushl %edx
+ CFI_ADJUST_CFA_OFFSET 4
+ CFI_REL_OFFSET edx, 0
+ pushl %ebp
+ CFI_ADJUST_CFA_OFFSET 4
+ CFI_REL_OFFSET ebp, 0
+
+ #define SYSENTER_SEQUENCE "movl %esp, %ebp; sysenter"
+ #define SYSCALL_SEQUENCE "movl %ecx, %ebp; syscall"
+
+#ifdef CONFIG_X86_64
+ /* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */
+ ALTERNATIVE_2 "", SYSENTER_SEQUENCE, X86_FEATURE_SYSENTER32, \
+ SYSCALL_SEQUENCE, X86_FEATURE_SYSCALL32
+#else
+ ALTERNATIVE "", SYSENTER_SEQUENCE, X86_FEATURE_SEP
+#endif
+
+ /* Enter using int $0x80 */
+ int $0x80
+GLOBAL(int80_landing_pad)
+
+ /*
+ * Restore EDX and ECX in case they were clobbered. EBP is not
+ * clobbered (the kernel restores it), but it's cleaner and
+ * probably faster to pop it than to adjust ESP using addl.
+ */
+ popl %ebp
+ CFI_RESTORE ebp
+ CFI_ADJUST_CFA_OFFSET -4
+ popl %edx
+ CFI_RESTORE edx
+ CFI_ADJUST_CFA_OFFSET -4
+ popl %ecx
+ CFI_RESTORE ecx
+ CFI_ADJUST_CFA_OFFSET -4
+ ret
+ CFI_ENDPROC
+
+ .size __kernel_vsyscall,.-__kernel_vsyscall
+ .previous
diff --git a/arch/x86/entry/vdso/vdso32/vclock_gettime.c b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
index 175cc72c0..87a86e017 100644
--- a/arch/x86/entry/vdso/vdso32/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
@@ -14,11 +14,13 @@
*/
#undef CONFIG_64BIT
#undef CONFIG_X86_64
+#undef CONFIG_PGTABLE_LEVELS
#undef CONFIG_ILLEGAL_POINTER_VALUE
#undef CONFIG_SPARSEMEM_VMEMMAP
#undef CONFIG_NR_CPUS
#define CONFIG_X86_32 1
+#define CONFIG_PGTABLE_LEVELS 2
#define CONFIG_PAGE_OFFSET 0
#define CONFIG_ILLEGAL_POINTER_VALUE 0
#define CONFIG_NR_CPUS 1
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 434543145..64df47148 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -180,21 +180,10 @@ up_fail:
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static int load_vdso32(void)
{
- int ret;
-
if (vdso32_enabled != 1) /* Other values all mean "disabled" */
return 0;
- ret = map_vdso(selected_vdso32, false);
- if (ret)
- return ret;
-
- if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN)
- current_thread_info()->sysenter_return =
- current->mm->context.vdso +
- selected_vdso32->sym_VDSO32_SYSENTER_RETURN;
-
- return 0;
+ return map_vdso(&vdso_image_32, false);
}
#endif
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index b160c0c6b..174c25499 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -38,7 +38,14 @@
#define CREATE_TRACE_POINTS
#include "vsyscall_trace.h"
-static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
+#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE)
+ NATIVE;
+#elif defined(CONFIG_LEGACY_VSYSCALL_NONE)
+ NONE;
+#else
+ EMULATE;
+#endif
static int __init vsyscall_setup(char *str)
{