summaryrefslogtreecommitdiffstats
path: root/arch/x86/entry
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/entry')
-rw-r--r--arch/x86/entry/Makefile17
-rw-r--r--arch/x86/entry/calling.h350
-rw-r--r--arch/x86/entry/common.c432
-rw-r--r--arch/x86/entry/entry_32.S1514
-rw-r--r--arch/x86/entry/entry_64.S1751
-rw-r--r--arch/x86/entry/entry_64_compat.S414
-rw-r--r--arch/x86/entry/syscall_32.c34
-rw-r--r--arch/x86/entry/syscall_64.c25
-rw-r--r--arch/x86/entry/syscalls/Makefile70
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl400
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl388
-rw-r--r--arch/x86/entry/syscalls/syscallhdr.sh28
-rw-r--r--arch/x86/entry/syscalls/syscalltbl.sh81
-rw-r--r--arch/x86/entry/thunk_32.S43
-rw-r--r--arch/x86/entry/thunk_64.S73
-rw-r--r--arch/x86/entry/vdso/.gitignore7
-rw-r--r--arch/x86/entry/vdso/Makefile205
-rwxr-xr-xarch/x86/entry/vdso/checkundef.sh10
-rw-r--r--arch/x86/entry/vdso/vclock_gettime.c341
-rw-r--r--arch/x86/entry/vdso/vdso-layout.lds.S120
-rw-r--r--arch/x86/entry/vdso/vdso-note.S15
-rw-r--r--arch/x86/entry/vdso/vdso.lds.S30
-rw-r--r--arch/x86/entry/vdso/vdso2c.c260
-rw-r--r--arch/x86/entry/vdso/vdso2c.h175
-rw-r--r--arch/x86/entry/vdso/vdso32-setup.c102
-rw-r--r--arch/x86/entry/vdso/vdso32/.gitignore1
-rw-r--r--arch/x86/entry/vdso/vdso32/note.S48
-rw-r--r--arch/x86/entry/vdso/vdso32/sigreturn.S138
-rw-r--r--arch/x86/entry/vdso/vdso32/system_call.S85
-rw-r--r--arch/x86/entry/vdso/vdso32/vclock_gettime.c31
-rw-r--r--arch/x86/entry/vdso/vdso32/vdso32.lds.S38
-rw-r--r--arch/x86/entry/vdso/vdsox32.lds.S26
-rw-r--r--arch/x86/entry/vdso/vgetcpu.c28
-rw-r--r--arch/x86/entry/vdso/vma.c383
-rw-r--r--arch/x86/entry/vsyscall/Makefile7
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c375
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_emu_64.S37
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_gtod.c78
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_trace.h30
39 files changed, 8190 insertions, 0 deletions
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
new file mode 100644
index 000000000..06fc70cf5
--- /dev/null
+++ b/arch/x86/entry/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the x86 low level entry code
+#
+
+OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y
+
+CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,)
+obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+obj-y += common.o
+
+obj-y += vdso/
+obj-y += vsyscall/
+
+obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o
+
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
new file mode 100644
index 000000000..993dd06c8
--- /dev/null
+++ b/arch/x86/entry/calling.h
@@ -0,0 +1,350 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/jump_label.h>
+#include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
+
+/*
+
+ x86 function call convention, 64-bit:
+ -------------------------------------
+ arguments | callee-saved | extra caller-saved | return
+ [callee-clobbered] | | [callee-clobbered] |
+ ---------------------------------------------------------------------------
+ rdi rsi rdx rcx r8-9 | rbx rbp [*] r12-15 | r10-11 | rax, rdx [**]
+
+ ( rsp is obviously invariant across normal function calls. (gcc can 'merge'
+ functions when it sees tail-call optimization possibilities) rflags is
+ clobbered. Leftover arguments are passed over the stack frame.)
+
+ [*] In the frame-pointers case rbp is fixed to the stack frame.
+
+ [**] for struct return values wider than 64 bits the return convention is a
+ bit more complex: up to 128 bits width we return small structures
+ straight in rax, rdx. For structures larger than that (3 words or
+ larger) the caller puts a pointer to an on-stack return struct
+ [allocated in the caller's stack frame] into the first argument - i.e.
+ into rdi. All other arguments shift up by one in this case.
+ Fortunately this case is rare in the kernel.
+
+For 32-bit we have the following conventions - kernel is built with
+-mregparm=3 and -freg-struct-return:
+
+ x86 function calling convention, 32-bit:
+ ----------------------------------------
+ arguments | callee-saved | extra caller-saved | return
+ [callee-clobbered] | | [callee-clobbered] |
+ -------------------------------------------------------------------------
+ eax edx ecx | ebx edi esi ebp [*] | <none> | eax, edx [**]
+
+ ( here too esp is obviously invariant across normal function calls. eflags
+ is clobbered. Leftover arguments are passed over the stack frame. )
+
+ [*] In the frame-pointers case ebp is fixed to the stack frame.
+
+ [**] We build with -freg-struct-return, which on 32-bit means similar
+ semantics as on 64-bit: edx can be used for a second return value
+ (i.e. covering integer and structure sizes up to 64 bits) - after that
+ it gets more complex and more expensive: 3-word or larger struct returns
+ get done in the caller's frame and the pointer to the return struct goes
+ into regparm0, i.e. eax - the other arguments shift up and the
+ function's register parameters degenerate to regparm=2 in essence.
+
+*/
+
+#ifdef CONFIG_X86_64
+
+/*
+ * 64-bit system call stack frame layout defines and helpers,
+ * for assembly code:
+ */
+
+/* The layout forms the "struct pt_regs" on the stack: */
+/*
+ * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
+ * unless syscall needs a complete, fully filled "struct pt_regs".
+ */
+#define R15 0*8
+#define R14 1*8
+#define R13 2*8
+#define R12 3*8
+#define RBP 4*8
+#define RBX 5*8
+/* These regs are callee-clobbered. Always saved on kernel entry. */
+#define R11 6*8
+#define R10 7*8
+#define R9 8*8
+#define R8 9*8
+#define RAX 10*8
+#define RCX 11*8
+#define RDX 12*8
+#define RSI 13*8
+#define RDI 14*8
+/*
+ * On syscall entry, this is syscall#. On CPU exception, this is error code.
+ * On hw interrupt, it's IRQ number:
+ */
+#define ORIG_RAX 15*8
+/* Return frame for iretq */
+#define RIP 16*8
+#define CS 17*8
+#define EFLAGS 18*8
+#define RSP 19*8
+#define SS 20*8
+
+#define SIZEOF_PTREGS 21*8
+
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
+ .if \save_ret
+ pushq %rsi /* pt_regs->si */
+ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */
+ movq %rdi, 8(%rsp) /* pt_regs->di (overwriting original return address) */
+ .else
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ .endif
+ pushq \rdx /* pt_regs->dx */
+ pushq %rcx /* pt_regs->cx */
+ pushq \rax /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 */
+ pushq %r9 /* pt_regs->r9 */
+ pushq %r10 /* pt_regs->r10 */
+ pushq %r11 /* pt_regs->r11 */
+ 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 */
+ UNWIND_HINT_REGS
+
+ .if \save_ret
+ pushq %rsi /* return address on top of stack */
+ .endif
+
+ /*
+ * Sanitize registers of values that a speculation attack might
+ * otherwise want to exploit. The lower registers are likely clobbered
+ * well before they could be put to use in a speculative execution
+ * gadget.
+ */
+ xorl %edx, %edx /* nospec dx */
+ xorl %ecx, %ecx /* nospec cx */
+ xorl %r8d, %r8d /* nospec r8 */
+ xorl %r9d, %r9d /* nospec r9 */
+ xorl %r10d, %r10d /* nospec r10 */
+ xorl %r11d, %r11d /* nospec r11 */
+ xorl %ebx, %ebx /* nospec rbx */
+ xorl %ebp, %ebp /* nospec rbp */
+ xorl %r12d, %r12d /* nospec r12 */
+ xorl %r13d, %r13d /* nospec r13 */
+ xorl %r14d, %r14d /* nospec r14 */
+ xorl %r15d, %r15d /* nospec r15 */
+
+.endm
+
+.macro POP_REGS pop_rdi=1 skip_r11rcx=0
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbp
+ popq %rbx
+ .if \skip_r11rcx
+ popq %rsi
+ .else
+ popq %r11
+ .endif
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ .if \skip_r11rcx
+ popq %rsi
+ .else
+ popq %rcx
+ .endif
+ popq %rdx
+ popq %rsi
+ .if \pop_rdi
+ popq %rdi
+ .endif
+.endm
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_USER_PGTABLE_BIT PAGE_SHIFT
+#define PTI_USER_PGTABLE_MASK (1 << PTI_USER_PGTABLE_BIT)
+#define PTI_USER_PCID_BIT X86_CR3_PTI_PCID_USER_BIT
+#define PTI_USER_PCID_MASK (1 << PTI_USER_PCID_BIT)
+#define PTI_USER_PGTABLE_AND_PCID_MASK (PTI_USER_PCID_MASK | PTI_USER_PGTABLE_MASK)
+
+.macro SET_NOFLUSH_BIT reg:req
+ bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+ ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+ /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+ andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+ ADJUST_KERNEL_CR3 \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask \
+ PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * Test if the ASID needs a flush.
+ */
+ movq \scratch_reg, \scratch_reg2
+ andq $(0x7FF), \scratch_reg /* mask ASID */
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ /* Flush needed, clear the bit */
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ movq \scratch_reg2, \scratch_reg
+ jmp .Lwrcr3_pcid_\@
+
+.Lnoflush_\@:
+ movq \scratch_reg2, \scratch_reg
+ SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_pcid_\@:
+ /* Flip the ASID to the user version */
+ orq $(PTI_USER_PCID_MASK), \scratch_reg
+
+.Lwrcr3_\@:
+ /* Flip the PGD to the user version */
+ orq $(PTI_USER_PGTABLE_MASK), \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+ pushq %rax
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+ popq %rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+ movq %cr3, \scratch_reg
+ movq \scratch_reg, \save_reg
+ /*
+ * Test the user pagetable bit. If set, then the user page tables
+ * are active. If clear CR3 already has the kernel page table
+ * active.
+ */
+ bt $PTI_USER_PGTABLE_BIT, \scratch_reg
+ jnc .Ldone_\@
+
+ ADJUST_KERNEL_CR3 \scratch_reg
+ movq \scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * KERNEL pages can always resume with NOFLUSH as we do
+ * explicit flushes.
+ */
+ bt $PTI_USER_PGTABLE_BIT, \save_reg
+ jnc .Lnoflush_\@
+
+ /*
+ * Check if there's a pending flush for the user ASID we're
+ * about to set.
+ */
+ movq \save_reg, \scratch_reg
+ andq $(0x7FF), \scratch_reg
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jmp .Lwrcr3_\@
+
+.Lnoflush_\@:
+ SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+ /*
+ * The CR3 write could be avoided when not changing its value,
+ * but would require a CR3 read *and* a scratch register.
+ */
+ movq \save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
+/*
+ * Mitigate Spectre v1 for conditional swapgs code paths.
+ *
+ * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to
+ * prevent a speculative swapgs when coming from kernel space.
+ *
+ * FENCE_SWAPGS_KERNEL_ENTRY is used in the kernel entry non-swapgs code path,
+ * to prevent the swapgs from getting speculatively skipped when coming from
+ * user space.
+ */
+.macro FENCE_SWAPGS_USER_ENTRY
+ ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_USER
+.endm
+.macro FENCE_SWAPGS_KERNEL_ENTRY
+ ALTERNATIVE "", "lfence", X86_FEATURE_FENCE_SWAPGS_KERNEL
+.endm
+
+#endif /* CONFIG_X86_64 */
+
+/*
+ * This does 'call enter_from_user_mode' unless we can avoid it based on
+ * kernel config or using the static jump infrastructure.
+ */
+.macro CALL_enter_from_user_mode
+#ifdef CONFIG_CONTEXT_TRACKING
+#ifdef CONFIG_JUMP_LABEL
+ STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0
+#endif
+ call enter_from_user_mode
+.Lafter_call_\@:
+#endif
+.endm
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
new file mode 100644
index 000000000..8353348dd
--- /dev/null
+++ b/arch/x86/entry/common.c
@@ -0,0 +1,432 @@
+/*
+ * common.c - C code for kernel entry and exit
+ * Copyright (c) 2015 Andrew Lutomirski
+ * GPL v2
+ *
+ * Based on asm and ptrace code by many authors. The code here originated
+ * in ptrace.c and signal.c.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/ptrace.h>
+#include <linux/tracehook.h>
+#include <linux/audit.h>
+#include <linux/seccomp.h>
+#include <linux/signal.h>
+#include <linux/export.h>
+#include <linux/context_tracking.h>
+#include <linux/user-return-notifier.h>
+#include <linux/nospec.h>
+#include <linux/uprobes.h>
+#include <linux/livepatch.h>
+#include <linux/syscalls.h>
+
+#include <asm/desc.h>
+#include <asm/traps.h>
+#include <asm/vdso.h>
+#include <linux/uaccess.h>
+#include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+#ifdef CONFIG_CONTEXT_TRACKING
+/* Called on entry from user mode with IRQs off. */
+__visible inline void enter_from_user_mode(void)
+{
+ CT_WARN_ON(ct_state() != CONTEXT_USER);
+ user_exit_irqoff();
+}
+#else
+static inline void enter_from_user_mode(void) {}
+#endif
+
+static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
+{
+#ifdef CONFIG_X86_64
+ if (arch == AUDIT_ARCH_X86_64) {
+ audit_syscall_entry(regs->orig_ax, regs->di,
+ regs->si, regs->dx, regs->r10);
+ } else
+#endif
+ {
+ audit_syscall_entry(regs->orig_ax, regs->bx,
+ regs->cx, regs->dx, regs->si);
+ }
+}
+
+/*
+ * Returns the syscall nr to run (which should match regs->orig_ax) or -1
+ * to skip the syscall.
+ */
+static long syscall_trace_enter(struct pt_regs *regs)
+{
+ u32 arch = in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
+
+ struct thread_info *ti = current_thread_info();
+ unsigned long ret = 0;
+ bool emulated = false;
+ u32 work;
+
+ if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+ BUG_ON(regs != task_pt_regs(current));
+
+ work = READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
+
+ if (unlikely(work & _TIF_SYSCALL_EMU))
+ emulated = true;
+
+ if ((emulated || (work & _TIF_SYSCALL_TRACE)) &&
+ tracehook_report_syscall_entry(regs))
+ return -1L;
+
+ if (emulated)
+ return -1L;
+
+#ifdef CONFIG_SECCOMP
+ /*
+ * Do seccomp after ptrace, to catch any tracer changes.
+ */
+ if (work & _TIF_SECCOMP) {
+ struct seccomp_data sd;
+
+ sd.arch = arch;
+ sd.nr = regs->orig_ax;
+ sd.instruction_pointer = regs->ip;
+#ifdef CONFIG_X86_64
+ if (arch == AUDIT_ARCH_X86_64) {
+ sd.args[0] = regs->di;
+ sd.args[1] = regs->si;
+ sd.args[2] = regs->dx;
+ sd.args[3] = regs->r10;
+ sd.args[4] = regs->r8;
+ sd.args[5] = regs->r9;
+ } else
+#endif
+ {
+ sd.args[0] = regs->bx;
+ sd.args[1] = regs->cx;
+ sd.args[2] = regs->dx;
+ sd.args[3] = regs->si;
+ sd.args[4] = regs->di;
+ sd.args[5] = regs->bp;
+ }
+
+ ret = __secure_computing(&sd);
+ if (ret == -1)
+ return ret;
+ }
+#endif
+
+ if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+ trace_sys_enter(regs, regs->orig_ax);
+
+ do_audit_syscall_entry(regs, arch);
+
+ return ret ?: regs->orig_ax;
+}
+
+#define EXIT_TO_USERMODE_LOOP_FLAGS \
+ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+ _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
+
+static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
+{
+ /*
+ * In order to return to user mode, we need to have IRQs off with
+ * none of EXIT_TO_USERMODE_LOOP_FLAGS set. Several of these flags
+ * can be set at any time on preemptable kernels if we have IRQs on,
+ * so we need to loop. Disabling preemption wouldn't help: doing the
+ * work to clear some of the flags can sleep.
+ */
+ while (true) {
+ /* We have work to do. */
+ local_irq_enable();
+
+ if (cached_flags & _TIF_NEED_RESCHED)
+ schedule();
+
+ if (cached_flags & _TIF_UPROBE)
+ uprobe_notify_resume(regs);
+
+ if (cached_flags & _TIF_PATCH_PENDING)
+ klp_update_patch_state(current);
+
+ /* deal with pending signal delivery */
+ if (cached_flags & _TIF_SIGPENDING)
+ do_signal(regs);
+
+ if (cached_flags & _TIF_NOTIFY_RESUME) {
+ clear_thread_flag(TIF_NOTIFY_RESUME);
+ tracehook_notify_resume(regs);
+ rseq_handle_notify_resume(NULL, regs);
+ }
+
+ if (cached_flags & _TIF_USER_RETURN_NOTIFY)
+ fire_user_return_notifiers();
+
+ /* Disable IRQs and retry */
+ local_irq_disable();
+
+ cached_flags = READ_ONCE(current_thread_info()->flags);
+
+ if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+ break;
+ }
+}
+
+/* Called with IRQs disabled. */
+__visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
+{
+ struct thread_info *ti = current_thread_info();
+ u32 cached_flags;
+
+ addr_limit_user_check();
+
+ lockdep_assert_irqs_disabled();
+ lockdep_sys_exit();
+
+ cached_flags = READ_ONCE(ti->flags);
+
+ if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+ exit_to_usermode_loop(regs, cached_flags);
+
+#ifdef CONFIG_COMPAT
+ /*
+ * Compat syscalls set TS_COMPAT. Make sure we clear it before
+ * returning to user mode. We need to clear it *after* signal
+ * handling, because syscall restart has a fixup for compat
+ * syscalls. The fixup is exercised by the ptrace_syscall_32
+ * selftest.
+ *
+ * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer
+ * special case only applies after poking regs and before the
+ * very next return to user mode.
+ */
+ ti->status &= ~(TS_COMPAT|TS_I386_REGS_POKED);
+#endif
+
+ user_enter_irqoff();
+
+ mds_user_clear_cpu_buffers();
+}
+
+#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 inline void syscall_return_slowpath(struct pt_regs *regs)
+{
+ struct thread_info *ti = current_thread_info();
+ u32 cached_flags = READ_ONCE(ti->flags);
+
+ CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
+
+ if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
+ WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
+ local_irq_enable();
+
+ rseq_syscall(regs);
+
+ /*
+ * 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 (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
+ syscall_slow_exit_work(regs, cached_flags);
+
+ local_irq_disable();
+ prepare_exit_to_usermode(regs);
+}
+
+#ifdef CONFIG_X86_64
+__visible void do_syscall_64(unsigned long nr, struct pt_regs *regs)
+{
+ struct thread_info *ti;
+
+ enter_from_user_mode();
+ local_irq_enable();
+ ti = current_thread_info();
+ if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY)
+ nr = syscall_trace_enter(regs);
+
+ /*
+ * NB: Native and x32 syscalls are dispatched from the same
+ * table. The only functional difference is the x32 bit in
+ * regs->orig_ax, which changes the behavior of some syscalls.
+ */
+ nr &= __SYSCALL_MASK;
+ if (likely(nr < NR_syscalls)) {
+ nr = array_index_nospec(nr, NR_syscalls);
+ regs->ax = sys_call_table[nr](regs);
+ }
+
+ syscall_return_slowpath(regs);
+}
+#endif
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+/*
+ * Does a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. 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.
+ */
+static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+{
+ struct thread_info *ti = current_thread_info();
+ unsigned int nr = (unsigned int)regs->orig_ax;
+
+#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)) {
+ nr = array_index_nospec(nr, IA32_NR_syscalls);
+#ifdef CONFIG_IA32_EMULATION
+ regs->ax = ia32_sys_call_table[nr](regs);
+#else
+ /*
+ * 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);
+#endif /* CONFIG_IA32_EMULATION */
+ }
+
+ syscall_return_slowpath(regs);
+}
+
+/* Handles int $0x80 */
+__visible void do_int80_syscall_32(struct pt_regs *regs)
+{
+ enter_from_user_mode();
+ local_irq_enable();
+ do_syscall_32_irqs_on(regs);
+}
+
+/* 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;
+
+ enter_from_user_mode();
+
+ local_irq_enable();
+
+ /* Fetch EBP from where the vDSO stashed it. */
+ 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;
+ 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
new file mode 100644
index 000000000..37d9016d4
--- /dev/null
+++ b/arch/x86/entry/entry_32.S
@@ -0,0 +1,1514 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1991,1992 Linus Torvalds
+ *
+ * entry_32.S contains the system-call and low-level fault and trap handling routines.
+ *
+ * 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(),
+ * ptrace.c and ptrace.h
+ *
+ * 0(%esp) - %ebx
+ * 4(%esp) - %ecx
+ * 8(%esp) - %edx
+ * C(%esp) - %esi
+ * 10(%esp) - %edi
+ * 14(%esp) - %ebp
+ * 18(%esp) - %eax
+ * 1C(%esp) - %ds
+ * 20(%esp) - %es
+ * 24(%esp) - %fs
+ * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS
+ * 2C(%esp) - orig_eax
+ * 30(%esp) - %eip
+ * 34(%esp) - %cs
+ * 38(%esp) - %eflags
+ * 3C(%esp) - %oldesp
+ * 40(%esp) - %oldss
+ */
+
+#include <linux/linkage.h>
+#include <linux/err.h>
+#include <asm/thread_info.h>
+#include <asm/irqflags.h>
+#include <asm/errno.h>
+#include <asm/segment.h>
+#include <asm/smp.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+#include <asm/irq_vectors.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <asm/frame.h>
+#include <asm/nospec-branch.h>
+
+ .section .entry.text, "ax"
+
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization. The following will never clobber any registers:
+ * INTERRUPT_RETURN (aka. "iret")
+ * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
+
+#ifdef CONFIG_PREEMPT
+# define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
+#else
+# define preempt_stop(clobbers)
+# define resume_kernel restore_all_kernel
+#endif
+
+.macro TRACE_IRQS_IRET
+#ifdef CONFIG_TRACE_IRQFLAGS
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off?
+ jz 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+#define PTI_SWITCH_MASK (1 << PAGE_SHIFT)
+
+/*
+ * User gs save/restore
+ *
+ * %gs is used for userland TLS and kernel only uses it for stack
+ * canary which is required to be at %gs:20 by gcc. Read the comment
+ * at the top of stackprotector.h for more info.
+ *
+ * Local labels 98 and 99 are used.
+ */
+#ifdef CONFIG_X86_32_LAZY_GS
+
+ /* unfortunately push/pop can't be no-op */
+.macro PUSH_GS
+ pushl $0
+.endm
+.macro POP_GS pop=0
+ addl $(4 + \pop), %esp
+.endm
+.macro POP_GS_EX
+.endm
+
+ /* all the rest are no-op */
+.macro PTGS_TO_GS
+.endm
+.macro PTGS_TO_GS_EX
+.endm
+.macro GS_TO_REG reg
+.endm
+.macro REG_TO_PTGS reg
+.endm
+.macro SET_KERNEL_GS reg
+.endm
+
+#else /* CONFIG_X86_32_LAZY_GS */
+
+.macro PUSH_GS
+ pushl %gs
+.endm
+
+.macro POP_GS pop=0
+98: popl %gs
+ .if \pop <> 0
+ add $\pop, %esp
+ .endif
+.endm
+.macro POP_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, (%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro PTGS_TO_GS
+98: mov PT_GS(%esp), %gs
+.endm
+.macro PTGS_TO_GS_EX
+.pushsection .fixup, "ax"
+99: movl $0, PT_GS(%esp)
+ jmp 98b
+.popsection
+ _ASM_EXTABLE(98b, 99b)
+.endm
+
+.macro GS_TO_REG reg
+ movl %gs, \reg
+.endm
+.macro REG_TO_PTGS reg
+ movl \reg, PT_GS(%esp)
+.endm
+.macro SET_KERNEL_GS reg
+ movl $(__KERNEL_STACK_CANARY), \reg
+ movl \reg, %gs
+.endm
+
+#endif /* CONFIG_X86_32_LAZY_GS */
+
+/* Unconditionally switch to user cr3 */
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+ movl %cr3, \scratch_reg
+ orl $PTI_SWITCH_MASK, \scratch_reg
+ movl \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro BUG_IF_WRONG_CR3 no_user_check=0
+#ifdef CONFIG_DEBUG_ENTRY
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ .if \no_user_check == 0
+ /* coming from usermode? */
+ testl $SEGMENT_RPL_MASK, PT_CS(%esp)
+ jz .Lend_\@
+ .endif
+ /* On user-cr3? */
+ movl %cr3, %eax
+ testl $PTI_SWITCH_MASK, %eax
+ jnz .Lend_\@
+ /* From userspace with kernel cr3 - BUG */
+ ud2
+.Lend_\@:
+#endif
+.endm
+
+/*
+ * Switch to kernel cr3 if not already loaded and return current cr3 in
+ * \scratch_reg
+ */
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ movl %cr3, \scratch_reg
+ /* Test if we are already on kernel CR3 */
+ testl $PTI_SWITCH_MASK, \scratch_reg
+ jz .Lend_\@
+ andl $(~PTI_SWITCH_MASK), \scratch_reg
+ movl \scratch_reg, %cr3
+ /* Return original CR3 in \scratch_reg */
+ orl $PTI_SWITCH_MASK, \scratch_reg
+.Lend_\@:
+.endm
+
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
+ cld
+ PUSH_GS
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl \pt_regs_ax
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ movl $(__USER_DS), %edx
+ movl %edx, %ds
+ movl %edx, %es
+ movl $(__KERNEL_PERCPU), %edx
+ movl %edx, %fs
+ SET_KERNEL_GS %edx
+
+ /* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+ SWITCH_TO_KERNEL_STACK
+.endif
+
+.endm
+
+.macro SAVE_ALL_NMI cr3_reg:req
+ SAVE_ALL
+
+ BUG_IF_WRONG_CR3
+
+ /*
+ * Now switch the CR3 when PTI is enabled.
+ *
+ * We can enter with either user or kernel cr3, the code will
+ * store the old cr3 in \cr3_reg and switches to the kernel cr3
+ * if necessary.
+ */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
+
+.Lend_\@:
+.endm
+
+.macro RESTORE_INT_REGS
+ popl %ebx
+ popl %ecx
+ popl %edx
+ popl %esi
+ popl %edi
+ popl %ebp
+ popl %eax
+.endm
+
+.macro RESTORE_REGS pop=0
+ RESTORE_INT_REGS
+1: popl %ds
+2: popl %es
+3: popl %fs
+ POP_GS \pop
+.pushsection .fixup, "ax"
+4: movl $0, (%esp)
+ jmp 1b
+5: movl $0, (%esp)
+ jmp 2b
+6: movl $0, (%esp)
+ jmp 3b
+.popsection
+ _ASM_EXTABLE(1b, 4b)
+ _ASM_EXTABLE(2b, 5b)
+ _ASM_EXTABLE(3b, 6b)
+ POP_GS_EX
+.endm
+
+.macro RESTORE_ALL_NMI cr3_reg:req pop=0
+ /*
+ * Now switch the CR3 when PTI is enabled.
+ *
+ * We enter with kernel cr3 and switch the cr3 to the value
+ * stored on \cr3_reg, which is either a user or a kernel cr3.
+ */
+ ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
+
+ testl $PTI_SWITCH_MASK, \cr3_reg
+ jz .Lswitched_\@
+
+ /* User cr3 in \cr3_reg - write it to hardware cr3 */
+ movl \cr3_reg, %cr3
+
+.Lswitched_\@:
+
+ BUG_IF_WRONG_CR3
+
+ RESTORE_REGS pop=\pop
+.endm
+
+.macro CHECK_AND_APPLY_ESPFIX
+#ifdef CONFIG_X86_ESPFIX32
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+
+ ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX
+
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS
+ /*
+ * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+ * are returning to the kernel.
+ * See comments in process.c:copy_thread() for details.
+ */
+ movb PT_OLDSS(%esp), %ah
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+ cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
+ jne .Lend_\@ # returning to user-space with LDT SS
+
+ /*
+ * Setup and switch to ESPFIX stack
+ *
+ * We're returning to userspace with a 16 bit stack. The CPU will not
+ * restore the high word of ESP for us on executing iret... This is an
+ * "official" bug of all the x86-compatible CPUs, which we can work
+ * around to make dosemu and wine happy. We do this by preloading the
+ * high word of ESP with the high word of the userspace ESP while
+ * compensating for the offset by changing to the ESPFIX segment with
+ * a base address that matches for the difference.
+ */
+ mov %esp, %edx /* load kernel esp */
+ mov PT_OLDESP(%esp), %eax /* load userspace esp */
+ mov %dx, %ax /* eax: new kernel esp */
+ sub %eax, %edx /* offset (low word is 0) */
+ shr $16, %edx
+ mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */
+ mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */
+ pushl $__ESPFIX_SS
+ pushl %eax /* new kernel esp */
+ /*
+ * Disable interrupts, but do not irqtrace this section: we
+ * will soon execute iret and the tracer was already set to
+ * the irqstate after the IRET:
+ */
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ lss (%esp), %esp /* switch to espfix segment */
+.Lend_\@:
+#endif /* CONFIG_X86_ESPFIX32 */
+.endm
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+
+#define CS_FROM_ENTRY_STACK (1 << 31)
+#define CS_FROM_USER_CR3 (1 << 30)
+
+.macro SWITCH_TO_KERNEL_STACK
+
+ ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+ BUG_IF_WRONG_CR3
+
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+
+ /*
+ * %eax now contains the entry cr3 and we carry it forward in
+ * that register for the time this macro runs
+ */
+
+ /*
+ * The high bits of the CS dword (__csh) are used for
+ * CS_FROM_ENTRY_STACK and CS_FROM_USER_CR3. Clear them in case
+ * hardware didn't do this for us.
+ */
+ andl $(0x0000ffff), PT_CS(%esp)
+
+ /* Are we on the entry stack? Bail out if not! */
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %esp, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
+ jae .Lend_\@
+
+ /* Load stack pointer into %esi and %edi */
+ movl %esp, %esi
+ movl %esi, %edi
+
+ /* Move %edi to the top of the entry stack */
+ andl $(MASK_entry_stack), %edi
+ addl $(SIZEOF_entry_stack), %edi
+
+ /* Load top of task-stack into %edi */
+ movl TSS_entry2task_stack(%edi), %edi
+
+ /* Special case - entry from kernel mode via entry stack */
+#ifdef CONFIG_VM86
+ movl PT_EFLAGS(%esp), %ecx # mix EFLAGS and CS
+ movb PT_CS(%esp), %cl
+ andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx
+#else
+ movl PT_CS(%esp), %ecx
+ andl $SEGMENT_RPL_MASK, %ecx
+#endif
+ cmpl $USER_RPL, %ecx
+ jb .Lentry_from_kernel_\@
+
+ /* Bytes to copy */
+ movl $PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+ testl $X86_EFLAGS_VM, PT_EFLAGS(%esi)
+ jz .Lcopy_pt_regs_\@
+
+ /*
+ * Stack-frame contains 4 additional segment registers when
+ * coming from VM86 mode
+ */
+ addl $(4 * 4), %ecx
+
+#endif
+.Lcopy_pt_regs_\@:
+
+ /* Allocate frame on task-stack */
+ subl %ecx, %edi
+
+ /* Switch to task-stack */
+ movl %edi, %esp
+
+ /*
+ * We are now on the task-stack and can safely copy over the
+ * stack-frame
+ */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+ jmp .Lend_\@
+
+.Lentry_from_kernel_\@:
+
+ /*
+ * This handles the case when we enter the kernel from
+ * kernel-mode and %esp points to the entry-stack. When this
+ * happens we need to switch to the task-stack to run C code,
+ * but switch back to the entry-stack again when we approach
+ * iret and return to the interrupted code-path. This usually
+ * happens when we hit an exception while restoring user-space
+ * segment registers on the way back to user-space or when the
+ * sysenter handler runs with eflags.tf set.
+ *
+ * When we switch to the task-stack here, we can't trust the
+ * contents of the entry-stack anymore, as the exception handler
+ * might be scheduled out or moved to another CPU. Therefore we
+ * copy the complete entry-stack to the task-stack and set a
+ * marker in the iret-frame (bit 31 of the CS dword) to detect
+ * what we've done on the iret path.
+ *
+ * On the iret path we copy everything back and switch to the
+ * entry-stack, so that the interrupted kernel code-path
+ * continues on the same stack it was interrupted with.
+ *
+ * Be aware that an NMI can happen anytime in this code.
+ *
+ * %esi: Entry-Stack pointer (same as %esp)
+ * %edi: Top of the task stack
+ * %eax: CR3 on kernel entry
+ */
+
+ /* Calculate number of bytes on the entry stack in %ecx */
+ movl %esi, %ecx
+
+ /* %ecx to the top of entry-stack */
+ andl $(MASK_entry_stack), %ecx
+ addl $(SIZEOF_entry_stack), %ecx
+
+ /* Number of bytes on the entry stack to %ecx */
+ sub %esi, %ecx
+
+ /* Mark stackframe as coming from entry stack */
+ orl $CS_FROM_ENTRY_STACK, PT_CS(%esp)
+
+ /*
+ * Test the cr3 used to enter the kernel and add a marker
+ * so that we can switch back to it before iret.
+ */
+ testl $PTI_SWITCH_MASK, %eax
+ jz .Lcopy_pt_regs_\@
+ orl $CS_FROM_USER_CR3, PT_CS(%esp)
+
+ /*
+ * %esi and %edi are unchanged, %ecx contains the number of
+ * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
+ * the stack-frame on task-stack and copy everything over
+ */
+ jmp .Lcopy_pt_regs_\@
+
+.Lend_\@:
+.endm
+
+/*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsl'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+ ALTERNATIVE "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+ /* Bytes to copy */
+ movl $PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+ testl $(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+ jz .Lcopy_pt_regs_\@
+
+ /* Additional 4 registers to copy when returning to VM86 mode */
+ addl $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+ /* Initialize source and destination for movsl */
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+ subl %ecx, %edi
+ movl %esp, %esi
+
+ /* Save future stack pointer in %ebx */
+ movl %edi, %ebx
+
+ /* Copy over the stack-frame */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+ /*
+ * Switch to entry-stack - needs to happen after everything is
+ * copied because the NMI handler will overwrite the task-stack
+ * when on entry-stack
+ */
+ movl %ebx, %esp
+
+.Lend_\@:
+.endm
+
+/*
+ * This macro handles the case when we return to kernel-mode on the iret
+ * path and have to switch back to the entry stack and/or user-cr3
+ *
+ * See the comments below the .Lentry_from_kernel_\@ label in the
+ * SWITCH_TO_KERNEL_STACK macro for more details.
+ */
+.macro PARANOID_EXIT_TO_KERNEL_MODE
+
+ /*
+ * Test if we entered the kernel with the entry-stack. Most
+ * likely we did not, because this code only runs on the
+ * return-to-kernel path.
+ */
+ testl $CS_FROM_ENTRY_STACK, PT_CS(%esp)
+ jz .Lend_\@
+
+ /* Unlikely slow-path */
+
+ /* Clear marker from stack-frame */
+ andl $(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
+
+ /* Copy the remaining task-stack contents to entry-stack */
+ movl %esp, %esi
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+
+ /* Bytes on the task-stack to ecx */
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
+ subl %esi, %ecx
+
+ /* Allocate stack-frame on entry-stack */
+ subl %ecx, %edi
+
+ /*
+ * Save future stack-pointer, we must not switch until the
+ * copy is done, otherwise the NMI handler could destroy the
+ * contents of the task-stack we are about to copy.
+ */
+ movl %edi, %ebx
+
+ /* Do the copy */
+ shrl $2, %ecx
+ cld
+ rep movsl
+
+ /* Safe to switch to entry-stack now */
+ movl %ebx, %esp
+
+ /*
+ * We came from entry-stack and need to check if we also need to
+ * switch back to user cr3.
+ */
+ testl $CS_FROM_USER_CR3, PT_CS(%esp)
+ jz .Lend_\@
+
+ /* Clear marker from stack-frame */
+ andl $(~CS_FROM_USER_CR3), PT_CS(%esp)
+
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+.Lend_\@:
+.endm
+/*
+ * %eax: prev task
+ * %edx: next task
+ */
+ENTRY(__switch_to_asm)
+ /*
+ * Save callee-saved registers
+ * This must match the order in struct inactive_task_frame
+ */
+ pushl %ebp
+ pushl %ebx
+ pushl %edi
+ pushl %esi
+ pushfl
+
+ /* switch stack */
+ movl %esp, TASK_threadsp(%eax)
+ movl TASK_threadsp(%edx), %esp
+
+#ifdef CONFIG_STACKPROTECTOR
+ movl TASK_stack_canary(%edx), %ebx
+ movl %ebx, PER_CPU_VAR(stack_canary)+stack_canary_offset
+#endif
+
+#ifdef CONFIG_RETPOLINE
+ /*
+ * When switching from a shallower to a deeper call stack
+ * the RSB may either underflow or use entries populated
+ * with userspace addresses. On CPUs where those concerns
+ * exist, overwrite the RSB with entries which capture
+ * speculative execution to prevent attack.
+ */
+ FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
+ /* restore callee-saved registers */
+ popfl
+ popl %esi
+ popl %edi
+ popl %ebx
+ popl %ebp
+
+ jmp __switch_to
+END(__switch_to_asm)
+
+/*
+ * The unwinder expects the last frame on the stack to always be at the same
+ * offset from the end of the page, which allows it to validate the stack.
+ * Calling schedule_tail() directly would break that convention because its an
+ * asmlinkage function so its argument has to be pushed on the stack. This
+ * wrapper creates a proper "end of stack" frame header before the call.
+ */
+ENTRY(schedule_tail_wrapper)
+ FRAME_BEGIN
+
+ pushl %eax
+ call schedule_tail
+ popl %eax
+
+ FRAME_END
+ ret
+ENDPROC(schedule_tail_wrapper)
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * eax: prev task we switched from
+ * ebx: kernel thread func (NULL for user thread)
+ * edi: kernel thread arg
+ */
+ENTRY(ret_from_fork)
+ call schedule_tail_wrapper
+
+ testl %ebx, %ebx
+ jnz 1f /* kernel threads are uncommon */
+
+2:
+ /* When we fork, we trace the syscall return in the child, too. */
+ movl %esp, %eax
+ call syscall_return_slowpath
+ jmp restore_all
+
+ /* kernel thread */
+1: movl %edi, %eax
+ CALL_NOSPEC %ebx
+ /*
+ * A kernel thread is allowed to return here after successfully
+ * calling do_execve(). Exit to userspace to complete the execve()
+ * syscall.
+ */
+ movl $0, PT_EAX(%esp)
+ jmp 2b
+END(ret_from_fork)
+
+/*
+ * Return to user mode is not as complex as all this looks,
+ * but we want the default path for a system call return to
+ * go as quickly as possible which is why some of this is
+ * less clear than it otherwise should be.
+ */
+
+ # userspace resumption stub bypassing syscall exit tracing
+ ALIGN
+ret_from_exception:
+ preempt_stop(CLBR_ANY)
+ret_from_intr:
+#ifdef CONFIG_VM86
+ movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS
+ movb PT_CS(%esp), %al
+ andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax
+#else
+ /*
+ * We can be coming here from child spawned by kernel_thread().
+ */
+ movl PT_CS(%esp), %eax
+ andl $SEGMENT_RPL_MASK, %eax
+#endif
+ cmpl $USER_RPL, %eax
+ jb resume_kernel # not returning to v8086 or userspace
+
+ENTRY(resume_userspace)
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ movl %esp, %eax
+ call prepare_exit_to_usermode
+ jmp restore_all
+END(ret_from_exception)
+
+#ifdef CONFIG_PREEMPT
+ENTRY(resume_kernel)
+ DISABLE_INTERRUPTS(CLBR_ANY)
+.Lneed_resched:
+ cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz restore_all_kernel
+ testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
+ jz restore_all_kernel
+ call preempt_schedule_irq
+ jmp .Lneed_resched
+END(resume_kernel)
+#endif
+
+GLOBAL(__begin_SYSENTER_singlestep_region)
+/*
+ * All code from here through __end_SYSENTER_singlestep_region is subject
+ * to being single-stepped if a user program sets TF and executes SYSENTER.
+ * There is absolutely nothing that we can do to prevent this from happening
+ * (thanks Intel!). To keep our handling of this situation as simple as
+ * possible, we handle TF just like AC and NT, except that our #DB handler
+ * will ignore all of the single-step traps generated in this range.
+ */
+
+#ifdef CONFIG_XEN
+/*
+ * Xen doesn't set %esp to be precisely what the normal SYSENTER
+ * entry point expects, so fix it up before using the normal path.
+ */
+ENTRY(xen_sysenter_target)
+ addl $5*4, %esp /* remove xen-provided frame */
+ jmp .Lsysenter_past_esp
+#endif
+
+/*
+ * 32-bit SYSENTER entry.
+ *
+ * 32-bit system calls through the vDSO's __kernel_vsyscall enter here
+ * if X86_FEATURE_SEP is available. This is the preferred system call
+ * entry on 32-bit systems.
+ *
+ * The SYSENTER instruction, in principle, should *only* occur in the
+ * vDSO. In practice, a small number of Android devices were shipped
+ * with a copy of Bionic that inlined a SYSENTER instruction. This
+ * never happened in any of Google's Bionic versions -- it only happened
+ * in a narrow range of Intel-provided versions.
+ *
+ * SYSENTER loads SS, ESP, CS, and EIP from previously programmed MSRs.
+ * IF and VM in RFLAGS are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old EIP (!!!), ESP, or EFLAGS.
+ *
+ * To avoid losing track of EFLAGS.VM (and thus potentially corrupting
+ * user and/or vm86 state), we explicitly disable the SYSENTER
+ * instruction in vm86 mode by reprogramming the MSRs.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp user stack
+ * 0(%ebp) arg6
+ */
+ENTRY(entry_SYSENTER_32)
+ /*
+ * On entry-stack with all userspace-regs live - save and
+ * restore eflags and %eax to use it as scratch-reg for the cr3
+ * switch.
+ */
+ pushfl
+ pushl %eax
+ BUG_IF_WRONG_CR3 no_user_check=1
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+ popl %eax
+ popfl
+
+ /* Stack empty again, switch to task stack */
+ movl TSS_entry2task_stack(%esp), %esp
+
+.Lsysenter_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, stack already switched */
+
+ /*
+ * SYSENTER doesn't filter flags, so we need to clear NT, AC
+ * and TF ourselves. To save a few cycles, we can check whether
+ * either 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.
+ *
+ * If TF is set, we will single-step all the way to here -- do_debug
+ * will ignore all the traps. (Yes, this is slow, but so is
+ * single-stepping in general. This allows us to avoid having
+ * a more complicated code to handle the case where a user program
+ * forces us to single-step through the SYSENTER entry code.)
+ *
+ * NB.: .Lsysenter_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|X86_EFLAGS_AC|X86_EFLAGS_TF, PT_EFLAGS(%esp)
+ jnz .Lsysenter_fix_flags
+.Lsysenter_flags_fixed:
+
+ /*
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
+ */
+ TRACE_IRQS_OFF
+
+ 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. */
+
+ /*
+ * Setup entry stack - we keep the pointer in %eax and do the
+ * switch after almost all user-state is restored.
+ */
+
+ /* Load entry stack pointer and allocate frame for eflags/eax */
+ movl PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax
+ subl $(2*4), %eax
+
+ /* Copy eflags and eax to entry stack */
+ movl PT_EFLAGS(%esp), %edi
+ movl PT_EAX(%esp), %esi
+ movl %edi, (%eax)
+ movl %esi, 4(%eax)
+
+ /* Restore user registers and segments */
+ 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 */
+
+ /* Switch to entry stack */
+ movl %eax, %esp
+
+ /* Now ready to switch the cr3 */
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+ /*
+ * Restore all flags except IF. (We restore IF separately because
+ * STI gives a one-instruction window in which we won't be interrupted,
+ * whereas POPF does not.)
+ */
+ btrl $X86_EFLAGS_IF_BIT, (%esp)
+ BUG_IF_WRONG_CR3 no_user_check=1
+ popfl
+ popl %eax
+
+ /*
+ * Return back to the vDSO, which will pop ecx and edx.
+ * Don't bother with DS and ES (they already contain __USER_DS).
+ */
+ sti
+ sysexit
+
+.pushsection .fixup, "ax"
+2: movl $0, PT_FS(%esp)
+ jmp 1b
+.popsection
+ _ASM_EXTABLE(1b, 2b)
+ PTGS_TO_GS_EX
+
+.Lsysenter_fix_flags:
+ pushl $X86_EFLAGS_FIXED
+ popfl
+ jmp .Lsysenter_flags_fixed
+GLOBAL(__end_SYSENTER_singlestep_region)
+ENDPROC(entry_SYSENTER_32)
+
+/*
+ * 32-bit legacy system call entry.
+ *
+ * 32-bit x86 Linux system calls traditionally used the INT $0x80
+ * instruction. INT $0x80 lands here.
+ *
+ * This entry point can be used by any 32-bit perform system calls.
+ * Instances of INT $0x80 can be found inline in various programs and
+ * libraries. It is also used by the vDSO's __kernel_vsyscall
+ * fallback for hardware that doesn't support a faster entry method.
+ * Restarted 32-bit system calls also fall back to INT $0x80
+ * regardless of what instruction was originally used to do the system
+ * call. (64-bit programs can use INT $0x80 as well, but they can
+ * only run on 64-bit kernels and therefore land in
+ * entry_INT80_compat.)
+ *
+ * This is considered a slow path. It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp arg6
+ */
+ENTRY(entry_INT80_32)
+ ASM_CLAC
+ pushl %eax /* pt_regs->orig_ax */
+
+ SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1 /* save rest */
+
+ /*
+ * User mode is traced as though IRQs are on, and the interrupt gate
+ * turned them off.
+ */
+ TRACE_IRQS_OFF
+
+ movl %esp, %eax
+ call do_int80_syscall_32
+.Lsyscall_32_done:
+
+restore_all:
+ TRACE_IRQS_IRET
+ SWITCH_TO_ENTRY_STACK
+.Lrestore_all_notrace:
+ CHECK_AND_APPLY_ESPFIX
+.Lrestore_nocheck:
+ /* Switch back to user CR3 */
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+ BUG_IF_WRONG_CR3
+
+ /* Restore user state */
+ RESTORE_REGS pop=4 # skip orig_eax/error_code
+.Lirq_return:
+ /*
+ * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
+ * when returning from IPI handler and when returning from
+ * scheduler to user-space.
+ */
+ INTERRUPT_RETURN
+
+restore_all_kernel:
+ TRACE_IRQS_IRET
+ PARANOID_EXIT_TO_KERNEL_MODE
+ BUG_IF_WRONG_CR3
+ RESTORE_REGS 4
+ jmp .Lirq_return
+
+.section .fixup, "ax"
+ENTRY(iret_exc )
+ pushl $0 # no error code
+ pushl $do_iret_error
+
+#ifdef CONFIG_DEBUG_ENTRY
+ /*
+ * The stack-frame here is the one that iret faulted on, so its a
+ * return-to-user frame. We are on kernel-cr3 because we come here from
+ * the fixup code. This confuses the CR3 checker, so switch to user-cr3
+ * as the checker expects it.
+ */
+ pushl %eax
+ SWITCH_TO_USER_CR3 scratch_reg=%eax
+ popl %eax
+#endif
+
+ jmp common_exception
+.previous
+ _ASM_EXTABLE(.Lirq_return, iret_exc)
+ENDPROC(entry_INT80_32)
+
+.macro FIXUP_ESPFIX_STACK
+/*
+ * Switch back for ESPFIX stack to the normal zerobased stack
+ *
+ * We can't call C functions using the ESPFIX stack. This code reads
+ * the high word of the segment base from the GDT and swiches to the
+ * normal stack and adjusts ESP with the matching offset.
+ */
+#ifdef CONFIG_X86_ESPFIX32
+ /* fixup the stack */
+ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
+ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
+ shl $16, %eax
+ addl %esp, %eax /* the adjusted stack pointer */
+ pushl $__KERNEL_DS
+ pushl %eax
+ lss (%esp), %esp /* switch to the normal stack segment */
+#endif
+.endm
+.macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
+ movl %ss, %eax
+ /* see if on espfix stack */
+ cmpw $__ESPFIX_SS, %ax
+ jne 27f
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ /* switch to normal stack */
+ FIXUP_ESPFIX_STACK
+27:
+#endif
+.endm
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ pushl $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_interrupt
+ .align 8
+ .endr
+END(irq_entries_start)
+
+#ifdef CONFIG_X86_LOCAL_APIC
+ .align 8
+ENTRY(spurious_entries_start)
+ vector=FIRST_SYSTEM_VECTOR
+ .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
+ pushl $(~vector+0x80) /* Note: always in signed byte range */
+ vector=vector+1
+ jmp common_spurious
+ .align 8
+ .endr
+END(spurious_entries_start)
+
+common_spurious:
+ ASM_CLAC
+ addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
+ SAVE_ALL switch_stacks=1
+ ENCODE_FRAME_POINTER
+ TRACE_IRQS_OFF
+ movl %esp, %eax
+ call smp_spurious_interrupt
+ jmp ret_from_intr
+ENDPROC(common_spurious)
+#endif
+
+/*
+ * the CPU automatically disables interrupts when executing an IRQ vector,
+ * so IRQ-flags tracing has to follow that:
+ */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ ASM_CLAC
+ addl $-0x80, (%esp) /* Adjust vector into the [-256, -1] range */
+
+ SAVE_ALL switch_stacks=1
+ ENCODE_FRAME_POINTER
+ TRACE_IRQS_OFF
+ movl %esp, %eax
+ call do_IRQ
+ jmp ret_from_intr
+ENDPROC(common_interrupt)
+
+#define BUILD_INTERRUPT3(name, nr, fn) \
+ENTRY(name) \
+ ASM_CLAC; \
+ pushl $~(nr); \
+ SAVE_ALL switch_stacks=1; \
+ ENCODE_FRAME_POINTER; \
+ TRACE_IRQS_OFF \
+ movl %esp, %eax; \
+ call fn; \
+ jmp ret_from_intr; \
+ENDPROC(name)
+
+#define BUILD_INTERRUPT(name, nr) \
+ BUILD_INTERRUPT3(name, nr, smp_##name); \
+
+/* The include is where all of the SMP etc. interrupts come from */
+#include <asm/entry_arch.h>
+
+ENTRY(coprocessor_error)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_error
+ jmp common_exception
+END(coprocessor_error)
+
+ENTRY(simd_coprocessor_error)
+ ASM_CLAC
+ pushl $0
+#ifdef CONFIG_X86_INVD_BUG
+ /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */
+ ALTERNATIVE "pushl $do_general_protection", \
+ "pushl $do_simd_coprocessor_error", \
+ X86_FEATURE_XMM
+#else
+ pushl $do_simd_coprocessor_error
+#endif
+ jmp common_exception
+END(simd_coprocessor_error)
+
+ENTRY(device_not_available)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ pushl $do_device_not_available
+ jmp common_exception
+END(device_not_available)
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+ iret
+ _ASM_EXTABLE(native_iret, iret_exc)
+END(native_iret)
+#endif
+
+ENTRY(overflow)
+ ASM_CLAC
+ pushl $0
+ pushl $do_overflow
+ jmp common_exception
+END(overflow)
+
+ENTRY(bounds)
+ ASM_CLAC
+ pushl $0
+ pushl $do_bounds
+ jmp common_exception
+END(bounds)
+
+ENTRY(invalid_op)
+ ASM_CLAC
+ pushl $0
+ pushl $do_invalid_op
+ jmp common_exception
+END(invalid_op)
+
+ENTRY(coprocessor_segment_overrun)
+ ASM_CLAC
+ pushl $0
+ pushl $do_coprocessor_segment_overrun
+ jmp common_exception
+END(coprocessor_segment_overrun)
+
+ENTRY(invalid_TSS)
+ ASM_CLAC
+ pushl $do_invalid_TSS
+ jmp common_exception
+END(invalid_TSS)
+
+ENTRY(segment_not_present)
+ ASM_CLAC
+ pushl $do_segment_not_present
+ jmp common_exception
+END(segment_not_present)
+
+ENTRY(stack_segment)
+ ASM_CLAC
+ pushl $do_stack_segment
+ jmp common_exception
+END(stack_segment)
+
+ENTRY(alignment_check)
+ ASM_CLAC
+ pushl $do_alignment_check
+ jmp common_exception
+END(alignment_check)
+
+ENTRY(divide_error)
+ ASM_CLAC
+ pushl $0 # no error code
+ pushl $do_divide_error
+ jmp common_exception
+END(divide_error)
+
+#ifdef CONFIG_X86_MCE
+ENTRY(machine_check)
+ ASM_CLAC
+ pushl $0
+ pushl machine_check_vector
+ jmp common_exception
+END(machine_check)
+#endif
+
+ENTRY(spurious_interrupt_bug)
+ ASM_CLAC
+ pushl $0
+ pushl $do_spurious_interrupt_bug
+ jmp common_exception
+END(spurious_interrupt_bug)
+
+#ifdef CONFIG_XEN
+ENTRY(xen_hypervisor_callback)
+ pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ ENCODE_FRAME_POINTER
+ TRACE_IRQS_OFF
+
+ /*
+ * Check to see if we got the event in the critical
+ * region in xen_iret_direct, after we've reenabled
+ * events and checked for pending events. This simulates
+ * iret instruction's behaviour where it delivers a
+ * pending interrupt when enabling interrupts:
+ */
+ movl PT_EIP(%esp), %eax
+ cmpl $xen_iret_start_crit, %eax
+ jb 1f
+ cmpl $xen_iret_end_crit, %eax
+ jae 1f
+
+ jmp xen_iret_crit_fixup
+
+ENTRY(xen_do_upcall)
+1: mov %esp, %eax
+ call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp ret_from_intr
+ENDPROC(xen_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we fix up by reattempting the load, and zeroing the segment
+ * register if the load fails.
+ * Category 2 we fix up by jumping to do_iret_error. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by maintaining a status value in EAX.
+ */
+ENTRY(xen_failsafe_callback)
+ pushl %eax
+ movl $1, %eax
+1: mov 4(%esp), %ds
+2: mov 8(%esp), %es
+3: mov 12(%esp), %fs
+4: mov 16(%esp), %gs
+ /* EAX == 0 => Category 1 (Bad segment)
+ EAX != 0 => Category 2 (Bad IRET) */
+ testl %eax, %eax
+ popl %eax
+ lea 16(%esp), %esp
+ jz 5f
+ jmp iret_exc
+5: pushl $-1 /* orig_ax = -1 => not a system call */
+ SAVE_ALL
+ ENCODE_FRAME_POINTER
+ jmp ret_from_exception
+
+.section .fixup, "ax"
+6: xorl %eax, %eax
+ movl %eax, 4(%esp)
+ jmp 1b
+7: xorl %eax, %eax
+ movl %eax, 8(%esp)
+ jmp 2b
+8: xorl %eax, %eax
+ movl %eax, 12(%esp)
+ jmp 3b
+9: xorl %eax, %eax
+ movl %eax, 16(%esp)
+ jmp 4b
+.previous
+ _ASM_EXTABLE(1b, 6b)
+ _ASM_EXTABLE(2b, 7b)
+ _ASM_EXTABLE(3b, 8b)
+ _ASM_EXTABLE(4b, 9b)
+ENDPROC(xen_failsafe_callback)
+
+BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ xen_evtchn_do_upcall)
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+
+BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR,
+ hyperv_vector_handler)
+
+BUILD_INTERRUPT3(hyperv_reenlightenment_vector, HYPERV_REENLIGHTENMENT_VECTOR,
+ hyperv_reenlightenment_intr)
+
+BUILD_INTERRUPT3(hv_stimer0_callback_vector, HYPERV_STIMER0_VECTOR,
+ hv_stimer0_vector_handler)
+
+#endif /* CONFIG_HYPERV */
+
+ENTRY(page_fault)
+ ASM_CLAC
+ pushl $do_page_fault
+ ALIGN
+ jmp common_exception
+END(page_fault)
+
+common_exception:
+ /* the function address is in %gs's slot on the stack */
+ pushl %fs
+ pushl %es
+ pushl %ds
+ pushl %eax
+ movl $(__USER_DS), %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl $(__KERNEL_PERCPU), %eax
+ movl %eax, %fs
+ pushl %ebp
+ pushl %edi
+ pushl %esi
+ pushl %edx
+ pushl %ecx
+ pushl %ebx
+ SWITCH_TO_KERNEL_STACK
+ ENCODE_FRAME_POINTER
+ cld
+ UNWIND_ESPFIX_STACK
+ GS_TO_REG %ecx
+ movl PT_GS(%esp), %edi # get the function address
+ movl PT_ORIG_EAX(%esp), %edx # get the error code
+ movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart
+ REG_TO_PTGS %ecx
+ SET_KERNEL_GS %ecx
+ TRACE_IRQS_OFF
+ movl %esp, %eax # pt_regs pointer
+ CALL_NOSPEC %edi
+ jmp ret_from_exception
+END(common_exception)
+
+ENTRY(debug)
+ /*
+ * Entry from sysenter is now handled in common_exception
+ */
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+ pushl $do_debug
+ jmp common_exception
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen on the first instruction of
+ * entry_SYSENTER_32 (just like #DB), but it can also interrupt the beginning
+ * of the #DB handler even if that #DB in turn hit before entry_SYSENTER_32
+ * switched stacks. We handle both conditions by simply checking whether we
+ * interrupted kernel code running on the SYSENTER stack.
+ */
+ENTRY(nmi)
+ ASM_CLAC
+
+#ifdef CONFIG_X86_ESPFIX32
+ pushl %eax
+ movl %ss, %eax
+ cmpw $__ESPFIX_SS, %ax
+ popl %eax
+ je .Lnmi_espfix_stack
+#endif
+
+ pushl %eax # pt_regs->orig_ax
+ SAVE_ALL_NMI cr3_reg=%edi
+ ENCODE_FRAME_POINTER
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+
+ /* Are we currently on the SYSENTER stack? */
+ movl PER_CPU_VAR(cpu_entry_area), %ecx
+ addl $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+ subl %eax, %ecx /* ecx = (end of entry_stack) - esp */
+ cmpl $SIZEOF_entry_stack, %ecx
+ jb .Lnmi_from_sysenter_stack
+
+ /* Not on SYSENTER stack. */
+ call do_nmi
+ jmp .Lnmi_return
+
+.Lnmi_from_sysenter_stack:
+ /*
+ * We're on the SYSENTER stack. Switch off. No one (not even debug)
+ * is using the thread stack right now, so it's safe for us to use it.
+ */
+ movl %esp, %ebx
+ movl PER_CPU_VAR(cpu_current_top_of_stack), %esp
+ call do_nmi
+ movl %ebx, %esp
+
+.Lnmi_return:
+ CHECK_AND_APPLY_ESPFIX
+ RESTORE_ALL_NMI cr3_reg=%edi pop=4
+ jmp .Lirq_return
+
+#ifdef CONFIG_X86_ESPFIX32
+.Lnmi_espfix_stack:
+ /*
+ * create the pointer to lss back
+ */
+ pushl %ss
+ pushl %esp
+ addl $4, (%esp)
+ /* copy the iret frame of 12 bytes */
+ .rept 3
+ pushl 16(%esp)
+ .endr
+ pushl %eax
+ SAVE_ALL_NMI cr3_reg=%edi
+ ENCODE_FRAME_POINTER
+ FIXUP_ESPFIX_STACK # %eax == %esp
+ xorl %edx, %edx # zero error code
+ call do_nmi
+ RESTORE_ALL_NMI cr3_reg=%edi
+ lss 12+4(%esp), %esp # back to espfix stack
+ jmp .Lirq_return
+#endif
+END(nmi)
+
+ENTRY(int3)
+ ASM_CLAC
+ pushl $-1 # mark this as an int
+
+ SAVE_ALL switch_stacks=1
+ ENCODE_FRAME_POINTER
+ TRACE_IRQS_OFF
+ xorl %edx, %edx # zero error code
+ movl %esp, %eax # pt_regs pointer
+ call do_int3
+ jmp ret_from_exception
+END(int3)
+
+ENTRY(general_protection)
+ ASM_CLAC
+ pushl $do_general_protection
+ jmp common_exception
+END(general_protection)
+
+#ifdef CONFIG_KVM_GUEST
+ENTRY(async_page_fault)
+ ASM_CLAC
+ pushl $do_async_page_fault
+ jmp common_exception
+END(async_page_fault)
+#endif
+
+ENTRY(rewind_stack_do_exit)
+ /* Prevent any naive code from trying to unwind to our caller. */
+ xorl %ebp, %ebp
+
+ movl PER_CPU_VAR(cpu_current_top_of_stack), %esi
+ leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp
+
+ call do_exit
+1: jmp 1b
+END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
new file mode 100644
index 000000000..dfe26f3cf
--- /dev/null
+++ b/arch/x86/entry/entry_64.S
@@ -0,0 +1,1751 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * linux/arch/x86_64/entry.S
+ *
+ * Copyright (C) 1991, 1992 Linus Torvalds
+ * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
+ * Copyright (C) 2000 Pavel Machek <pavel@suse.cz>
+ *
+ * entry.S contains the system-call and fault low-level handling routines.
+ *
+ * Some of this is documented in Documentation/x86/entry_64.txt
+ *
+ * A note on terminology:
+ * - iret frame: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
+ *
+ * Some macro usage:
+ * - ENTRY/END: Define functions in the symbol table.
+ * - TRACE_IRQ_*: Trace hardirq state for lock debugging.
+ * - idtentry: Define exception entry points.
+ */
+#include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/cache.h>
+#include <asm/errno.h>
+#include <asm/asm-offsets.h>
+#include <asm/msr.h>
+#include <asm/unistd.h>
+#include <asm/thread_info.h>
+#include <asm/hw_irq.h>
+#include <asm/page_types.h>
+#include <asm/irqflags.h>
+#include <asm/paravirt.h>
+#include <asm/percpu.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <asm/pgtable_types.h>
+#include <asm/export.h>
+#include <asm/frame.h>
+#include <asm/nospec-branch.h>
+#include <linux/err.h>
+
+#include "calling.h"
+
+.code64
+.section .entry.text, "ax"
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret64)
+ UNWIND_HINT_EMPTY
+ swapgs
+ sysretq
+END(native_usergs_sysret64)
+#endif /* CONFIG_PARAVIRT */
+
+.macro TRACE_IRQS_FLAGS flags:req
+#ifdef CONFIG_TRACE_IRQFLAGS
+ btl $9, \flags /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON
+1:
+#endif
+.endm
+
+.macro TRACE_IRQS_IRETQ
+ TRACE_IRQS_FLAGS EFLAGS(%rsp)
+.endm
+
+/*
+ * When dynamic function tracer is enabled it will add a breakpoint
+ * to all locations that it is about to modify, sync CPUs, update
+ * all the code, sync CPUs, then remove the breakpoints. In this time
+ * if lockdep is enabled, it might jump back into the debug handler
+ * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF).
+ *
+ * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to
+ * make sure the stack pointer does not get reset back to the top
+ * of the debug stack, and instead just reuses the current stack.
+ */
+#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS)
+
+.macro TRACE_IRQS_OFF_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_OFF
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_ON_DEBUG
+ call debug_stack_set_zero
+ TRACE_IRQS_ON
+ call debug_stack_reset
+.endm
+
+.macro TRACE_IRQS_IRETQ_DEBUG
+ btl $9, EFLAGS(%rsp) /* interrupts off? */
+ jnc 1f
+ TRACE_IRQS_ON_DEBUG
+1:
+.endm
+
+#else
+# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF
+# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON
+# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ
+#endif
+
+/*
+ * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
+ *
+ * This is the only entry point used for 64-bit system calls. The
+ * hardware interface is reasonably well designed and the register to
+ * argument mapping Linux uses fits well with the registers that are
+ * available when SYSCALL is used.
+ *
+ * SYSCALL instructions can be found inlined in libc implementations as
+ * well as some other programs and libraries. There are also a handful
+ * of SYSCALL instructions in the vDSO used, for example, as a
+ * clock_gettimeofday fallback.
+ *
+ * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
+ * then loads new ss, cs, and rip from previously programmed MSRs.
+ * rflags gets masked by a value from another MSR (so CLD and CLAC
+ * are not needed). SYSCALL does not save anything on the stack
+ * and does not change rsp.
+ *
+ * Registers on entry:
+ * rax system call number
+ * rcx return address
+ * r11 saved rflags (note: r11 is callee-clobbered register in C ABI)
+ * rdi arg0
+ * rsi arg1
+ * rdx arg2
+ * r10 arg3 (needs to be moved to rcx to conform to C ABI)
+ * r8 arg4
+ * r9 arg5
+ * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
+ *
+ * Only called from user space.
+ *
+ * When user can change pt_regs->foo always force IRET. That is because
+ * it deals with uncanonical addresses better. SYSRET has trouble
+ * with them due to bugs in both AMD and Intel CPUs.
+ */
+
+ .pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline. This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address). So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline. We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+ _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH CPU_ENTRY_AREA_entry_stack + \
+ SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+ UNWIND_HINT_EMPTY
+ swapgs
+
+ /* Stash the user RSP. */
+ movq %rsp, RSP_SCRATCH
+
+ /* Note: using %rsp as a scratch reg. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+ /* Load the top of the task stack into RSP */
+ movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+ /* Start building the simulated IRET frame. */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq RSP_SCRATCH /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+
+ /*
+ * x86 lacks a near absolute jump, and we can't jump to the real
+ * entry text with a relative jump. We could push the target
+ * address and then use retq, but this destroys the pipeline on
+ * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead,
+ * spill RDI and restore it in a second-stage trampoline.
+ */
+ pushq %rdi
+ movq $entry_SYSCALL_64_stage2, %rdi
+ JMP_NOSPEC %rdi
+END(entry_SYSCALL_64_trampoline)
+
+ .popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+ UNWIND_HINT_EMPTY
+ popq %rdi
+ jmp entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
+ENTRY(entry_SYSCALL_64)
+ UNWIND_HINT_EMPTY
+ /*
+ * 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.
+ */
+
+ swapgs
+ /*
+ * This path is only taken when PAGE_TABLE_ISOLATION is disabled so it
+ * is not required to switch CR3.
+ */
+ movq %rsp, PER_CPU_VAR(rsp_scratch)
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+GLOBAL(entry_SYSCALL_64_after_hwframe)
+ pushq %rax /* pt_regs->orig_ax */
+
+ PUSH_AND_CLEAR_REGS rax=$-ENOSYS
+
+ TRACE_IRQS_OFF
+
+ /* IRQs are off. */
+ movq %rax, %rdi
+ movq %rsp, %rsi
+ call do_syscall_64 /* returns with IRQs disabled */
+
+ TRACE_IRQS_IRETQ /* we're about to change IF */
+
+ /*
+ * Try to use SYSRET instead of IRET if we're returning to
+ * a completely clean 64-bit userspace context. If we're not,
+ * go to the slow exit path.
+ */
+ movq RCX(%rsp), %rcx
+ movq RIP(%rsp), %r11
+
+ cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */
+ jne swapgs_restore_regs_and_return_to_usermode
+
+ /*
+ * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+ * in kernel space. This essentially lets the user take over
+ * the kernel, since userspace controls RSP.
+ *
+ * If width of "canonical tail" ever becomes variable, this will need
+ * to be updated to remain correct on both old and new CPUs.
+ *
+ * Change top bits to match most significant bit (47th or 56th bit
+ * depending on paging mode) in the address.
+ */
+#ifdef CONFIG_X86_5LEVEL
+ ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
+ "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
+#else
+ shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+ sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+#endif
+
+ /* If this changed %rcx, it was not canonical */
+ cmpq %rcx, %r11
+ jne swapgs_restore_regs_and_return_to_usermode
+
+ cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
+ jne swapgs_restore_regs_and_return_to_usermode
+
+ movq R11(%rsp), %r11
+ cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
+ jne swapgs_restore_regs_and_return_to_usermode
+
+ /*
+ * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
+ * restore RF properly. If the slowpath sets it for whatever reason, we
+ * need to restore it correctly.
+ *
+ * SYSRET can restore TF, but unlike IRET, restoring TF results in a
+ * trap from userspace immediately after SYSRET. This would cause an
+ * infinite loop whenever #DB happens with register state that satisfies
+ * the opportunistic SYSRET conditions. For example, single-stepping
+ * this user code:
+ *
+ * movq $stuck_here, %rcx
+ * pushfq
+ * popq %r11
+ * stuck_here:
+ *
+ * would never get past 'stuck_here'.
+ */
+ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
+ jnz swapgs_restore_regs_and_return_to_usermode
+
+ /* nothing to check for RSP */
+
+ cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
+ jne swapgs_restore_regs_and_return_to_usermode
+
+ /*
+ * We win! This label is here just for ease of understanding
+ * perf profiles. Nothing jumps here.
+ */
+syscall_return_via_sysret:
+ /* rcx and r11 are already restored (see code above) */
+ POP_REGS pop_rdi=0 skip_r11rcx=1
+
+ /*
+ * Now all regs are restored except RSP and RDI.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+ UNWIND_HINT_EMPTY
+
+ pushq RSP-RDI(%rdi) /* RSP */
+ pushq (%rdi) /* RDI */
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
+ popq %rdi
+ popq %rsp
+ USERGS_SYSRET64
+END(entry_SYSCALL_64)
+
+/*
+ * %rdi: prev task
+ * %rsi: next task
+ */
+ENTRY(__switch_to_asm)
+ UNWIND_HINT_FUNC
+ /*
+ * Save callee-saved registers
+ * This must match the order in inactive_task_frame
+ */
+ pushq %rbp
+ pushq %rbx
+ pushq %r12
+ pushq %r13
+ pushq %r14
+ pushq %r15
+ pushfq
+
+ /* switch stack */
+ movq %rsp, TASK_threadsp(%rdi)
+ movq TASK_threadsp(%rsi), %rsp
+
+#ifdef CONFIG_STACKPROTECTOR
+ movq TASK_stack_canary(%rsi), %rbx
+ movq %rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+#endif
+
+#ifdef CONFIG_RETPOLINE
+ /*
+ * When switching from a shallower to a deeper call stack
+ * the RSB may either underflow or use entries populated
+ * with userspace addresses. On CPUs where those concerns
+ * exist, overwrite the RSB with entries which capture
+ * speculative execution to prevent attack.
+ */
+ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+#endif
+
+ /* restore callee-saved registers */
+ popfq
+ popq %r15
+ popq %r14
+ popq %r13
+ popq %r12
+ popq %rbx
+ popq %rbp
+
+ jmp __switch_to
+END(__switch_to_asm)
+
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * rax: prev task we switched from
+ * rbx: kernel thread func (NULL for user thread)
+ * r12: kernel thread arg
+ */
+ENTRY(ret_from_fork)
+ UNWIND_HINT_EMPTY
+ movq %rax, %rdi
+ call schedule_tail /* rdi: 'prev' task parameter */
+
+ testq %rbx, %rbx /* from kernel_thread? */
+ jnz 1f /* kernel threads are uncommon */
+
+2:
+ UNWIND_HINT_REGS
+ movq %rsp, %rdi
+ call syscall_return_slowpath /* returns with IRQs disabled */
+ TRACE_IRQS_ON /* user mode is traced as IRQS on */
+ jmp swapgs_restore_regs_and_return_to_usermode
+
+1:
+ /* kernel thread */
+ UNWIND_HINT_EMPTY
+ movq %r12, %rdi
+ CALL_NOSPEC %rbx
+ /*
+ * A kernel thread is allowed to return here after successfully
+ * calling do_execve(). Exit to userspace to complete the execve()
+ * syscall.
+ */
+ movq $0, RAX(%rsp)
+ jmp 2b
+END(ret_from_fork)
+
+/*
+ * Build the entry stubs with some assembler magic.
+ * We pack 1 stub into every 8-byte block.
+ */
+ .align 8
+ENTRY(irq_entries_start)
+ vector=FIRST_EXTERNAL_VECTOR
+ .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ UNWIND_HINT_IRET_REGS
+ pushq $(~vector+0x80) /* Note: always in signed byte range */
+ jmp common_interrupt
+ .align 8
+ vector=vector+1
+ .endr
+END(irq_entries_start)
+
+ .align 8
+ENTRY(spurious_entries_start)
+ vector=FIRST_SYSTEM_VECTOR
+ .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
+ UNWIND_HINT_IRET_REGS
+ pushq $(~vector+0x80) /* Note: always in signed byte range */
+ jmp common_spurious
+ .align 8
+ vector=vector+1
+ .endr
+END(spurious_entries_start)
+
+.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
+#ifdef CONFIG_DEBUG_ENTRY
+ pushq %rax
+ SAVE_FLAGS(CLBR_RAX)
+ testl $X86_EFLAGS_IF, %eax
+ jz .Lokay_\@
+ ud2
+.Lokay_\@:
+ popq %rax
+#endif
+.endm
+
+/*
+ * Enters the IRQ stack if we're not already using it. NMI-safe. Clobbers
+ * flags and puts old RSP into old_rsp, and leaves all other GPRs alone.
+ * Requires kernel GSBASE.
+ *
+ * The invariant is that, if irq_count != -1, then the IRQ stack is in use.
+ */
+.macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
+ DEBUG_ENTRY_ASSERT_IRQS_OFF
+
+ .if \save_ret
+ /*
+ * If save_ret is set, the original stack contains one additional
+ * entry -- the return address. Therefore, move the address one
+ * entry below %rsp to \old_rsp.
+ */
+ leaq 8(%rsp), \old_rsp
+ .else
+ movq %rsp, \old_rsp
+ .endif
+
+ .if \regs
+ UNWIND_HINT_REGS base=\old_rsp
+ .endif
+
+ incl PER_CPU_VAR(irq_count)
+ jnz .Lirq_stack_push_old_rsp_\@
+
+ /*
+ * Right now, if we just incremented irq_count to zero, we've
+ * claimed the IRQ stack but we haven't switched to it yet.
+ *
+ * If anything is added that can interrupt us here without using IST,
+ * it must be *extremely* careful to limit its stack usage. This
+ * could include kprobes and a hypothetical future IST-less #DB
+ * handler.
+ *
+ * The OOPS unwinder relies on the word at the top of the IRQ
+ * stack linking back to the previous RSP for the entire time we're
+ * on the IRQ stack. For this to work reliably, we need to write
+ * it before we actually move ourselves to the IRQ stack.
+ */
+
+ movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8)
+ movq PER_CPU_VAR(irq_stack_ptr), %rsp
+
+#ifdef CONFIG_DEBUG_ENTRY
+ /*
+ * If the first movq above becomes wrong due to IRQ stack layout
+ * changes, the only way we'll notice is if we try to unwind right
+ * here. Assert that we set up the stack right to catch this type
+ * of bug quickly.
+ */
+ cmpq -8(%rsp), \old_rsp
+ je .Lirq_stack_okay\@
+ ud2
+ .Lirq_stack_okay\@:
+#endif
+
+.Lirq_stack_push_old_rsp_\@:
+ pushq \old_rsp
+
+ .if \regs
+ UNWIND_HINT_REGS indirect=1
+ .endif
+
+ .if \save_ret
+ /*
+ * Push the return address to the stack. This return address can
+ * be found at the "real" original RSP, which was offset by 8 at
+ * the beginning of this macro.
+ */
+ pushq -8(\old_rsp)
+ .endif
+.endm
+
+/*
+ * Undoes ENTER_IRQ_STACK.
+ */
+.macro LEAVE_IRQ_STACK regs=1
+ DEBUG_ENTRY_ASSERT_IRQS_OFF
+ /* We need to be off the IRQ stack before decrementing irq_count. */
+ popq %rsp
+
+ .if \regs
+ UNWIND_HINT_REGS
+ .endif
+
+ /*
+ * As in ENTER_IRQ_STACK, irq_count == 0, we are still claiming
+ * the irq stack but we're not on it.
+ */
+
+ decl PER_CPU_VAR(irq_count)
+.endm
+
+/*
+ * Interrupt entry helper function.
+ *
+ * Entry runs with interrupts off. Stack layout at entry:
+ * +----------------------------------------------------+
+ * | regs->ss |
+ * | regs->rsp |
+ * | regs->eflags |
+ * | regs->cs |
+ * | regs->ip |
+ * +----------------------------------------------------+
+ * | regs->orig_ax = ~(interrupt number) |
+ * +----------------------------------------------------+
+ * | return address |
+ * +----------------------------------------------------+
+ */
+ENTRY(interrupt_entry)
+ UNWIND_HINT_IRET_REGS offset=16
+ ASM_CLAC
+ cld
+
+ testb $3, CS-ORIG_RAX+8(%rsp)
+ jz 1f
+ SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
+ /*
+ * Switch to the thread stack. The IRET frame and orig_ax are
+ * on the stack, as well as the return address. RDI..R12 are
+ * not (yet) on the stack and space has not (yet) been
+ * allocated for them.
+ */
+ pushq %rdi
+
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /*
+ * We have RDI, return address, and orig_ax on the stack on
+ * top of the IRET frame. That means offset=24
+ */
+ UNWIND_HINT_IRET_REGS base=%rdi offset=24
+
+ pushq 7*8(%rdi) /* regs->ss */
+ pushq 6*8(%rdi) /* regs->rsp */
+ pushq 5*8(%rdi) /* regs->eflags */
+ pushq 4*8(%rdi) /* regs->cs */
+ pushq 3*8(%rdi) /* regs->ip */
+ UNWIND_HINT_IRET_REGS
+ pushq 2*8(%rdi) /* regs->orig_ax */
+ pushq 8(%rdi) /* return address */
+
+ movq (%rdi), %rdi
+ jmp 2f
+1:
+ FENCE_SWAPGS_KERNEL_ENTRY
+2:
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
+
+ testb $3, CS+8(%rsp)
+ jz 1f
+
+ /*
+ * IRQ from user mode.
+ *
+ * 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 is 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
+
+ CALL_enter_from_user_mode
+
+1:
+ ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
+ /* We entered an interrupt context - irqs are off: */
+ TRACE_IRQS_OFF
+
+ ret
+END(interrupt_entry)
+_ASM_NOKPROBE(interrupt_entry)
+
+
+/* Interrupt entry/exit. */
+
+/*
+ * The interrupt stubs push (~vector+0x80) onto the stack and
+ * then jump to common_spurious/interrupt.
+ */
+common_spurious:
+ addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call smp_spurious_interrupt /* rdi points to pt_regs */
+ jmp ret_from_intr
+END(common_spurious)
+_ASM_NOKPROBE(common_spurious)
+
+/* common_interrupt is a hotpath. Align it */
+ .p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
+ addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call do_IRQ /* rdi points to pt_regs */
+ /* 0(%rsp): old RSP */
+ret_from_intr:
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+
+ LEAVE_IRQ_STACK
+
+ testb $3, CS(%rsp)
+ jz retint_kernel
+
+ /* Interrupt came from user space */
+GLOBAL(retint_user)
+ mov %rsp,%rdi
+ call prepare_exit_to_usermode
+ TRACE_IRQS_IRETQ
+
+GLOBAL(swapgs_restore_regs_and_return_to_usermode)
+#ifdef CONFIG_DEBUG_ENTRY
+ /* Assert that pt_regs indicates user mode. */
+ testb $3, CS(%rsp)
+ jnz 1f
+ ud2
+1:
+#endif
+ POP_REGS pop_rdi=0
+
+ /*
+ * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+ UNWIND_HINT_EMPTY
+
+ /* Copy the IRET frame to the trampoline stack. */
+ pushq 6*8(%rdi) /* SS */
+ pushq 5*8(%rdi) /* RSP */
+ pushq 4*8(%rdi) /* EFLAGS */
+ pushq 3*8(%rdi) /* CS */
+ pushq 2*8(%rdi) /* RIP */
+
+ /* Push user RDI on the trampoline stack. */
+ pushq (%rdi)
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
+ /* Restore RDI. */
+ popq %rdi
+ SWAPGS
+ INTERRUPT_RETURN
+
+
+/* Returning to kernel space */
+retint_kernel:
+#ifdef CONFIG_PREEMPT
+ /* Interrupts are off */
+ /* Check if we need preemption */
+ btl $9, EFLAGS(%rsp) /* were interrupts off? */
+ jnc 1f
+0: cmpl $0, PER_CPU_VAR(__preempt_count)
+ jnz 1f
+ call preempt_schedule_irq
+ jmp 0b
+1:
+#endif
+ /*
+ * The iretq could re-enable interrupts:
+ */
+ TRACE_IRQS_IRETQ
+
+GLOBAL(restore_regs_and_return_to_kernel)
+#ifdef CONFIG_DEBUG_ENTRY
+ /* Assert that pt_regs indicates kernel mode. */
+ testb $3, CS(%rsp)
+ jz 1f
+ ud2
+1:
+#endif
+ POP_REGS
+ addq $8, %rsp /* skip regs->orig_ax */
+ /*
+ * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
+ * when returning from IPI handler.
+ */
+ INTERRUPT_RETURN
+
+ENTRY(native_iret)
+ UNWIND_HINT_IRET_REGS
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4, (SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
+#endif
+
+.global native_irq_return_iret
+native_irq_return_iret:
+ /*
+ * This may fault. Non-paranoid faults on return to userspace are
+ * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
+ * Double-faults due to espfix64 are handled in do_double_fault.
+ * Other faults here are fatal.
+ */
+ iretq
+
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ /*
+ * We are running with user GSBASE. All GPRs contain their user
+ * values. We have a percpu ESPFIX stack that is eight slots
+ * long (see ESPFIX_STACK_SIZE). espfix_waddr points to the bottom
+ * of the ESPFIX stack.
+ *
+ * We clobber RAX and RDI in this code. We stash RDI on the
+ * normal stack and RAX on the ESPFIX stack.
+ *
+ * The ESPFIX stack layout we set up looks like this:
+ *
+ * --- top of ESPFIX stack ---
+ * SS
+ * RSP
+ * RFLAGS
+ * CS
+ * RIP <-- RSP points here when we're done
+ * RAX <-- espfix_waddr points here
+ * --- bottom of ESPFIX stack ---
+ */
+
+ pushq %rdi /* Stash user RDI */
+ SWAPGS /* to kernel GS */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
+
+ movq PER_CPU_VAR(espfix_waddr), %rdi
+ movq %rax, (0*8)(%rdi) /* user RAX */
+ movq (1*8)(%rsp), %rax /* user RIP */
+ movq %rax, (1*8)(%rdi)
+ movq (2*8)(%rsp), %rax /* user CS */
+ movq %rax, (2*8)(%rdi)
+ movq (3*8)(%rsp), %rax /* user RFLAGS */
+ movq %rax, (3*8)(%rdi)
+ movq (5*8)(%rsp), %rax /* user SS */
+ movq %rax, (5*8)(%rdi)
+ movq (4*8)(%rsp), %rax /* user RSP */
+ movq %rax, (4*8)(%rdi)
+ /* Now RAX == RSP. */
+
+ andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */
+
+ /*
+ * espfix_stack[31:16] == 0. The page tables are set up such that
+ * (espfix_stack | (X & 0xffff0000)) points to a read-only alias of
+ * espfix_waddr for any X. That is, there are 65536 RO aliases of
+ * the same page. Set up RSP so that RSP[31:16] contains the
+ * respective 16 bits of the /userspace/ RSP and RSP nonetheless
+ * still points to an RO alias of the ESPFIX stack.
+ */
+ orq PER_CPU_VAR(espfix_stack), %rax
+
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+ SWAPGS /* to user GS */
+ popq %rdi /* Restore user RDI */
+
+ movq %rax, %rsp
+ UNWIND_HINT_IRET_REGS offset=8
+
+ /*
+ * At this point, we cannot write to the stack any more, but we can
+ * still read.
+ */
+ popq %rax /* Restore user RAX */
+
+ /*
+ * RSP now points to an ordinary IRET frame, except that the page
+ * is read-only and RSP[31:16] are preloaded with the userspace
+ * values. We can now IRET back to userspace.
+ */
+ jmp native_irq_return_iret
+#endif
+END(common_interrupt)
+_ASM_NOKPROBE(common_interrupt)
+
+/*
+ * APIC interrupts.
+ */
+.macro apicinterrupt3 num sym do_sym
+ENTRY(\sym)
+ UNWIND_HINT_IRET_REGS
+ pushq $~(\num)
+.Lcommon_\sym:
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call \do_sym /* rdi points to pt_regs */
+ jmp ret_from_intr
+END(\sym)
+_ASM_NOKPROBE(\sym)
+.endm
+
+/* Make sure APIC interrupt handlers end up in the irqentry section: */
+#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
+#define POP_SECTION_IRQENTRY .popsection
+
+.macro apicinterrupt num sym do_sym
+PUSH_SECTION_IRQENTRY
+apicinterrupt3 \num \sym \do_sym
+POP_SECTION_IRQENTRY
+.endm
+
+#ifdef CONFIG_SMP
+apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
+apicinterrupt3 REBOOT_VECTOR reboot_interrupt smp_reboot_interrupt
+#endif
+
+#ifdef CONFIG_X86_UV
+apicinterrupt3 UV_BAU_MESSAGE uv_bau_message_intr1 uv_bau_message_interrupt
+#endif
+
+apicinterrupt LOCAL_TIMER_VECTOR apic_timer_interrupt smp_apic_timer_interrupt
+apicinterrupt X86_PLATFORM_IPI_VECTOR x86_platform_ipi smp_x86_platform_ipi
+
+#ifdef CONFIG_HAVE_KVM
+apicinterrupt3 POSTED_INTR_VECTOR kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+apicinterrupt3 POSTED_INTR_WAKEUP_VECTOR kvm_posted_intr_wakeup_ipi smp_kvm_posted_intr_wakeup_ipi
+apicinterrupt3 POSTED_INTR_NESTED_VECTOR kvm_posted_intr_nested_ipi smp_kvm_posted_intr_nested_ipi
+#endif
+
+#ifdef CONFIG_X86_MCE_THRESHOLD
+apicinterrupt THRESHOLD_APIC_VECTOR threshold_interrupt smp_threshold_interrupt
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+apicinterrupt DEFERRED_ERROR_VECTOR deferred_error_interrupt smp_deferred_error_interrupt
+#endif
+
+#ifdef CONFIG_X86_THERMAL_VECTOR
+apicinterrupt THERMAL_APIC_VECTOR thermal_interrupt smp_thermal_interrupt
+#endif
+
+#ifdef CONFIG_SMP
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR call_function_single_interrupt smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR call_function_interrupt smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR reschedule_interrupt smp_reschedule_interrupt
+#endif
+
+apicinterrupt ERROR_APIC_VECTOR error_interrupt smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR spurious_interrupt smp_spurious_interrupt
+
+#ifdef CONFIG_IRQ_WORK
+apicinterrupt IRQ_WORK_VECTOR irq_work_interrupt smp_irq_work_interrupt
+#endif
+
+/*
+ * Exception entry points.
+ */
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 create_gap=0
+ENTRY(\sym)
+ UNWIND_HINT_IRET_REGS offset=\has_error_code*8
+
+ /* Sanity check */
+ .if \shift_ist != -1 && \paranoid == 0
+ .error "using shift_ist requires paranoid=1"
+ .endif
+
+ ASM_CLAC
+
+ .if \has_error_code == 0
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
+ .endif
+
+ .if \paranoid == 1
+ testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */
+ jnz .Lfrom_usermode_switch_stack_\@
+ .endif
+
+ .if \create_gap == 1
+ /*
+ * If coming from kernel space, create a 6-word gap to allow the
+ * int3 handler to emulate a call instruction.
+ */
+ testb $3, CS-ORIG_RAX(%rsp)
+ jnz .Lfrom_usermode_no_gap_\@
+ .rept 6
+ pushq 5*8(%rsp)
+ .endr
+ UNWIND_HINT_IRET_REGS offset=8
+.Lfrom_usermode_no_gap_\@:
+ .endif
+
+ .if \paranoid
+ call paranoid_entry
+ .else
+ call error_entry
+ .endif
+ UNWIND_HINT_REGS
+ /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
+
+ .if \paranoid
+ .if \shift_ist != -1
+ TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */
+ .else
+ TRACE_IRQS_OFF
+ .endif
+ .endif
+
+ movq %rsp, %rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi, %esi /* no error code */
+ .endif
+
+ .if \shift_ist != -1
+ subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ .endif
+
+ call \do_sym
+
+ .if \shift_ist != -1
+ addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+ .endif
+
+ /* these procedures expect "no swapgs" flag in ebx */
+ .if \paranoid
+ jmp paranoid_exit
+ .else
+ jmp error_exit
+ .endif
+
+ .if \paranoid == 1
+ /*
+ * Entry from userspace. Switch stacks and treat it
+ * as a normal entry. This means that paranoid handlers
+ * run in real process context if user_mode(regs).
+ */
+.Lfrom_usermode_switch_stack_\@:
+ call error_entry
+
+ movq %rsp, %rdi /* pt_regs pointer */
+
+ .if \has_error_code
+ movq ORIG_RAX(%rsp), %rsi /* get error code */
+ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */
+ .else
+ xorl %esi, %esi /* no error code */
+ .endif
+
+ call \do_sym
+
+ jmp error_exit
+ .endif
+_ASM_NOKPROBE(\sym)
+END(\sym)
+.endm
+
+idtentry divide_error do_divide_error has_error_code=0
+idtentry overflow do_overflow has_error_code=0
+idtentry bounds do_bounds has_error_code=0
+idtentry invalid_op do_invalid_op has_error_code=0
+idtentry device_not_available do_device_not_available has_error_code=0
+idtentry double_fault do_double_fault has_error_code=1 paranoid=2
+idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
+idtentry invalid_TSS do_invalid_TSS has_error_code=1
+idtentry segment_not_present do_segment_not_present has_error_code=1
+idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0
+idtentry coprocessor_error do_coprocessor_error has_error_code=0
+idtentry alignment_check do_alignment_check has_error_code=1
+idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0
+
+
+ /*
+ * Reload gs selector with exception handling
+ * edi: new selector
+ */
+ENTRY(native_load_gs_index)
+ FRAME_BEGIN
+ pushfq
+ DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
+ TRACE_IRQS_OFF
+ SWAPGS
+.Lgs_change:
+ movl %edi, %gs
+2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
+ SWAPGS
+ TRACE_IRQS_FLAGS (%rsp)
+ popfq
+ FRAME_END
+ ret
+ENDPROC(native_load_gs_index)
+EXPORT_SYMBOL(native_load_gs_index)
+
+ _ASM_EXTABLE(.Lgs_change, bad_gs)
+ .section .fixup, "ax"
+ /* running with kernelgs */
+bad_gs:
+ SWAPGS /* switch back to user gs */
+.macro ZAP_GS
+ /* This can't be a string because the preprocessor needs to see it. */
+ movl $__USER_DS, %eax
+ movl %eax, %gs
+.endm
+ ALTERNATIVE "", "ZAP_GS", X86_BUG_NULL_SEG
+ xorl %eax, %eax
+ movl %eax, %gs
+ jmp 2b
+ .previous
+
+/* Call softirq on interrupt stack. Interrupts are off. */
+ENTRY(do_softirq_own_stack)
+ pushq %rbp
+ mov %rsp, %rbp
+ ENTER_IRQ_STACK regs=0 old_rsp=%r11
+ call __do_softirq
+ LEAVE_IRQ_STACK regs=0
+ leaveq
+ ret
+ENDPROC(do_softirq_own_stack)
+
+#ifdef CONFIG_XEN
+idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
+
+/*
+ * A note on the "critical region" in our callback handler.
+ * We want to avoid stacking callback handlers due to events occurring
+ * during handling of the last event. To do this, we keep events disabled
+ * until we've done all processing. HOWEVER, we must enable events before
+ * popping the stack frame (can't be done atomically) and so it would still
+ * be possible to get enough handler activations to overflow the stack.
+ * Although unlikely, bugs of that kind are hard to track down, so we'd
+ * like to avoid the possibility.
+ * So, on entry to the handler we detect whether we interrupted an
+ * existing activation in its critical region -- if so, we pop the current
+ * activation and restart the handler using the previous one.
+ */
+ENTRY(xen_do_hypervisor_callback) /* do_hypervisor_callback(struct *pt_regs) */
+
+/*
+ * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
+ * see the correct pointer to the pt_regs
+ */
+ UNWIND_HINT_FUNC
+ movq %rdi, %rsp /* we don't return, adjust the stack frame */
+ UNWIND_HINT_REGS
+
+ ENTER_IRQ_STACK old_rsp=%r10
+ call xen_evtchn_do_upcall
+ LEAVE_IRQ_STACK
+
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
+ jmp error_exit
+END(xen_do_hypervisor_callback)
+
+/*
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ * 1. Fault while reloading DS, ES, FS or GS
+ * 2. Fault while executing IRET
+ * Category 1 we do not need to fix up as Xen has already reloaded all segment
+ * registers that could be reloaded and zeroed the others.
+ * Category 2 we fix up by killing the current process. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by comparing each saved segment register
+ * with its current contents: any discrepancy means we in category 1.
+ */
+ENTRY(xen_failsafe_callback)
+ UNWIND_HINT_EMPTY
+ movl %ds, %ecx
+ cmpw %cx, 0x10(%rsp)
+ jne 1f
+ movl %es, %ecx
+ cmpw %cx, 0x18(%rsp)
+ jne 1f
+ movl %fs, %ecx
+ cmpw %cx, 0x20(%rsp)
+ jne 1f
+ movl %gs, %ecx
+ cmpw %cx, 0x28(%rsp)
+ jne 1f
+ /* All segments match their saved values => Category 2 (Bad IRET). */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ pushq $0 /* RIP */
+ UNWIND_HINT_IRET_REGS offset=8
+ jmp general_protection
+1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
+ movq (%rsp), %rcx
+ movq 8(%rsp), %r11
+ addq $0x30, %rsp
+ UNWIND_HINT_IRET_REGS
+ pushq $-1 /* orig_ax = -1 => not a system call */
+ PUSH_AND_CLEAR_REGS
+ ENCODE_FRAME_POINTER
+ jmp error_exit
+END(xen_failsafe_callback)
+
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
+ xen_hvm_callback_vector xen_evtchn_do_upcall
+
+#endif /* CONFIG_XEN */
+
+#if IS_ENABLED(CONFIG_HYPERV)
+apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
+ hyperv_callback_vector hyperv_vector_handler
+
+apicinterrupt3 HYPERV_REENLIGHTENMENT_VECTOR \
+ hyperv_reenlightenment_vector hyperv_reenlightenment_intr
+
+apicinterrupt3 HYPERV_STIMER0_VECTOR \
+ hv_stimer0_callback_vector hv_stimer0_vector_handler
+#endif /* CONFIG_HYPERV */
+
+idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
+idtentry int3 do_int3 has_error_code=0 create_gap=1
+idtentry stack_segment do_stack_segment has_error_code=1
+
+#ifdef CONFIG_XEN
+idtentry xennmi do_nmi has_error_code=0
+idtentry xendebug do_debug has_error_code=0
+#endif
+
+idtentry general_protection do_general_protection has_error_code=1
+idtentry page_fault do_page_fault has_error_code=1
+
+#ifdef CONFIG_KVM_GUEST
+idtentry async_page_fault do_async_page_fault has_error_code=1
+#endif
+
+#ifdef CONFIG_X86_MCE
+idtentry machine_check do_mce has_error_code=0 paranoid=1
+#endif
+
+/*
+ * Save all registers in pt_regs, and switch gs if needed.
+ * Use slow, but surefire "are we in kernel?" check.
+ * Return: ebx=0: need swapgs on exit, ebx=1: otherwise
+ */
+ENTRY(paranoid_entry)
+ UNWIND_HINT_FUNC
+ cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
+ movl $1, %ebx
+ movl $MSR_GS_BASE, %ecx
+ rdmsr
+ testl %edx, %edx
+ js 1f /* negative -> in kernel */
+ SWAPGS
+ xorl %ebx, %ebx
+
+1:
+ /*
+ * Always stash CR3 in %r14. This value will be restored,
+ * verbatim, at exit. Needed if paranoid_entry interrupted
+ * another entry that already switched to the user CR3 value
+ * but has not yet returned to userspace.
+ *
+ * This is also why CS (stashed in the "iret frame" by the
+ * hardware at entry) can not be used: this may be a return
+ * to kernel code, but with a user CR3 value.
+ */
+ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+ /*
+ * The above SAVE_AND_SWITCH_TO_KERNEL_CR3 macro doesn't do an
+ * unconditional CR3 write, even in the PTI case. So do an lfence
+ * to prevent GS speculation, regardless of whether PTI is enabled.
+ */
+ FENCE_SWAPGS_KERNEL_ENTRY
+
+ ret
+END(paranoid_entry)
+
+/*
+ * "Paranoid" exit path from exception stack. This is invoked
+ * only on return from non-NMI IST interrupts that came
+ * from kernel space.
+ *
+ * We may be returning to very strange contexts (e.g. very early
+ * in syscall entry), so checking for preemption here would
+ * be complicated. Fortunately, we there's no good reason
+ * to try to handle preemption here.
+ *
+ * On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
+ */
+ENTRY(paranoid_exit)
+ UNWIND_HINT_REGS
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF_DEBUG
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz .Lparanoid_exit_no_swapgs
+ TRACE_IRQS_IRETQ
+ /* Always restore stashed CR3 value (see paranoid_entry) */
+ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
+ SWAPGS_UNSAFE_STACK
+ jmp .Lparanoid_exit_restore
+.Lparanoid_exit_no_swapgs:
+ TRACE_IRQS_IRETQ_DEBUG
+ /* Always restore stashed CR3 value (see paranoid_entry) */
+ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
+.Lparanoid_exit_restore:
+ jmp restore_regs_and_return_to_kernel
+END(paranoid_exit)
+
+/*
+ * Save all registers in pt_regs, and switch GS if needed.
+ */
+ENTRY(error_entry)
+ UNWIND_HINT_FUNC
+ cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
+ testb $3, CS+8(%rsp)
+ jz .Lerror_kernelspace
+
+ /*
+ * We entered from user mode or we're pretending to have entered
+ * from user mode due to an IRET fault.
+ */
+ SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
+ /* We have user CR3. Change to kernel CR3. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
+
+.Lerror_entry_from_usermode_after_swapgs:
+ /* Put us onto the real thread stack. */
+ popq %r12 /* save return addr in %12 */
+ movq %rsp, %rdi /* arg0 = pt_regs pointer */
+ call sync_regs
+ movq %rax, %rsp /* switch stack */
+ ENCODE_FRAME_POINTER
+ pushq %r12
+
+ /*
+ * 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
+ CALL_enter_from_user_mode
+ ret
+
+.Lerror_entry_done_lfence:
+ FENCE_SWAPGS_KERNEL_ENTRY
+.Lerror_entry_done:
+ TRACE_IRQS_OFF
+ ret
+
+ /*
+ * There are two places in the kernel that can potentially fault with
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
+ */
+.Lerror_kernelspace:
+ leaq native_irq_return_iret(%rip), %rcx
+ cmpq %rcx, RIP+8(%rsp)
+ je .Lerror_bad_iret
+ movl %ecx, %eax /* zero extend */
+ cmpq %rax, RIP+8(%rsp)
+ je .Lbstep_iret
+ cmpq $.Lgs_change, RIP+8(%rsp)
+ jne .Lerror_entry_done_lfence
+
+ /*
+ * hack: .Lgs_change can fail with user gsbase. If this happens, fix up
+ * gsbase and proceed. We'll fix up the exception and land in
+ * .Lgs_change's error handler with kernel gsbase.
+ */
+ SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
+ jmp .Lerror_entry_done
+
+.Lbstep_iret:
+ /* Fix truncated RIP */
+ movq %rcx, RIP+8(%rsp)
+ /* fall through */
+
+.Lerror_bad_iret:
+ /*
+ * We came from an IRET to user mode, so we have user
+ * gsbase and CR3. Switch to kernel gsbase and CR3:
+ */
+ SWAPGS
+ FENCE_SWAPGS_USER_ENTRY
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
+
+ /*
+ * Pretend that the exception came from user mode: set up pt_regs
+ * as if we faulted immediately after IRET.
+ */
+ mov %rsp, %rdi
+ call fixup_bad_iret
+ mov %rax, %rsp
+ jmp .Lerror_entry_from_usermode_after_swapgs
+END(error_entry)
+
+ENTRY(error_exit)
+ UNWIND_HINT_REGS
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ TRACE_IRQS_OFF
+ testb $3, CS(%rsp)
+ jz retint_kernel
+ jmp retint_user
+END(error_exit)
+
+/*
+ * Runs on exception stack. Xen PV does not go through this path at all,
+ * so we can use real assembly here.
+ *
+ * Registers:
+ * %r14: Used to save/restore the CR3 of the interrupted context
+ * when PAGE_TABLE_ISOLATION is in use. Do not clobber.
+ */
+ENTRY(nmi)
+ UNWIND_HINT_IRET_REGS
+
+ /*
+ * We allow breakpoints in NMIs. If a breakpoint occurs, then
+ * the iretq it performs will take us out of NMI context.
+ * This means that we can have nested NMIs where the next
+ * NMI is using the top of the stack of the previous NMI. We
+ * can't let it execute because the nested NMI will corrupt the
+ * stack of the previous NMI. NMI handlers are not re-entrant
+ * anyway.
+ *
+ * To handle this case we do the following:
+ * Check the a special location on the stack that contains
+ * a variable that is set when NMIs are executing.
+ * The interrupted task's stack is also checked to see if it
+ * is an NMI stack.
+ * If the variable is not set and the stack is not the NMI
+ * stack then:
+ * o Set the special variable on the stack
+ * o Copy the interrupt frame into an "outermost" location on the
+ * stack
+ * o Copy the interrupt frame into an "iret" location on the stack
+ * o Continue processing the NMI
+ * If the variable is set or the previous stack is the NMI stack:
+ * o Modify the "iret" location to jump to the repeat_nmi
+ * o return back to the first NMI
+ *
+ * Now on exit of the first NMI, we first clear the stack variable
+ * The NMI stack will tell any nested NMIs at that point that it is
+ * nested. Then we pop the stack normally with iret, and if there was
+ * a nested NMI that updated the copy interrupt stack frame, a
+ * jump will be made to the repeat_nmi code that will handle the second
+ * NMI.
+ *
+ * However, espfix prevents us from directly returning to userspace
+ * with a single IRET instruction. Similarly, IRET to user mode
+ * can fault. We therefore handle NMIs from user space like
+ * other IST entries.
+ */
+
+ ASM_CLAC
+
+ /* Use %rdx as our temp variable throughout */
+ pushq %rdx
+
+ testb $3, CS-RIP+8(%rsp)
+ jz .Lnmi_from_kernel
+
+ /*
+ * NMI from user mode. We need to run on the thread stack, but we
+ * can't go through the normal entry paths: NMIs are masked, and
+ * we don't want to enable interrupts, because then we'll end
+ * up in an awkward situation in which IRQs are on but NMIs
+ * are off.
+ *
+ * We also must not push anything to the stack before switching
+ * stacks lest we corrupt the "NMI executing" variable.
+ */
+
+ swapgs
+ cld
+ FENCE_SWAPGS_USER_ENTRY
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
+ movq %rsp, %rdx
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ UNWIND_HINT_IRET_REGS base=%rdx offset=8
+ pushq 5*8(%rdx) /* pt_regs->ss */
+ pushq 4*8(%rdx) /* pt_regs->rsp */
+ pushq 3*8(%rdx) /* pt_regs->flags */
+ pushq 2*8(%rdx) /* pt_regs->cs */
+ pushq 1*8(%rdx) /* pt_regs->rip */
+ UNWIND_HINT_IRET_REGS
+ pushq $-1 /* pt_regs->orig_ax */
+ PUSH_AND_CLEAR_REGS rdx=(%rdx)
+ ENCODE_FRAME_POINTER
+
+ /*
+ * At this point we no longer need to worry about stack damage
+ * due to nesting -- we're on the normal thread stack and we're
+ * done with the NMI stack.
+ */
+
+ movq %rsp, %rdi
+ movq $-1, %rsi
+ call do_nmi
+
+ /*
+ * Return back to user mode. We must *not* do the normal exit
+ * work, because we don't want to enable interrupts.
+ */
+ jmp swapgs_restore_regs_and_return_to_usermode
+
+.Lnmi_from_kernel:
+ /*
+ * Here's what our stack frame will look like:
+ * +---------------------------------------------------------+
+ * | original SS |
+ * | original Return RSP |
+ * | original RFLAGS |
+ * | original CS |
+ * | original RIP |
+ * +---------------------------------------------------------+
+ * | temp storage for rdx |
+ * +---------------------------------------------------------+
+ * | "NMI executing" variable |
+ * +---------------------------------------------------------+
+ * | iret SS } Copied from "outermost" frame |
+ * | iret Return RSP } on each loop iteration; overwritten |
+ * | iret RFLAGS } by a nested NMI to force another |
+ * | iret CS } iteration if needed. |
+ * | iret RIP } |
+ * +---------------------------------------------------------+
+ * | outermost SS } initialized in first_nmi; |
+ * | outermost Return RSP } will not be changed before |
+ * | outermost RFLAGS } NMI processing is done. |
+ * | outermost CS } Copied to "iret" frame on each |
+ * | outermost RIP } iteration. |
+ * +---------------------------------------------------------+
+ * | pt_regs |
+ * +---------------------------------------------------------+
+ *
+ * The "original" frame is used by hardware. Before re-enabling
+ * NMIs, we need to be done with it, and we need to leave enough
+ * space for the asm code here.
+ *
+ * We return by executing IRET while RSP points to the "iret" frame.
+ * That will either return for real or it will loop back into NMI
+ * processing.
+ *
+ * The "outermost" frame is copied to the "iret" frame on each
+ * iteration of the loop, so each iteration starts with the "iret"
+ * frame pointing to the final return target.
+ */
+
+ /*
+ * Determine whether we're a nested NMI.
+ *
+ * If we interrupted kernel code between repeat_nmi and
+ * end_repeat_nmi, then we are a nested NMI. We must not
+ * modify the "iret" frame because it's being written by
+ * the outer NMI. That's okay; the outer NMI handler is
+ * about to about to call do_nmi anyway, so we can just
+ * resume the outer NMI.
+ */
+
+ movq $repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja 1f
+ movq $end_repeat_nmi, %rdx
+ cmpq 8(%rsp), %rdx
+ ja nested_nmi_out
+1:
+
+ /*
+ * Now check "NMI executing". If it's set, then we're nested.
+ * This will not detect if we interrupted an outer NMI just
+ * before IRET.
+ */
+ cmpl $1, -8(%rsp)
+ je nested_nmi
+
+ /*
+ * Now test if the previous stack was an NMI stack. This covers
+ * the case where we interrupt an outer NMI after it clears
+ * "NMI executing" but before IRET. We need to be careful, though:
+ * there is one case in which RSP could point to the NMI stack
+ * despite there being no NMI active: naughty userspace controls
+ * RSP at the very beginning of the SYSCALL targets. We can
+ * pull a fast one on naughty userspace, though: we program
+ * SYSCALL to mask DF, so userspace cannot cause DF to be set
+ * if it controls the kernel's RSP. We set DF before we clear
+ * "NMI executing".
+ */
+ lea 6*8(%rsp), %rdx
+ /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
+ cmpq %rdx, 4*8(%rsp)
+ /* If the stack pointer is above the NMI stack, this is a normal NMI */
+ ja first_nmi
+
+ subq $EXCEPTION_STKSZ, %rdx
+ cmpq %rdx, 4*8(%rsp)
+ /* If it is below the NMI stack, it is a normal NMI */
+ jb first_nmi
+
+ /* Ah, it is within the NMI stack. */
+
+ testb $(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp)
+ jz first_nmi /* RSP was user controlled. */
+
+ /* This is a nested NMI. */
+
+nested_nmi:
+ /*
+ * Modify the "iret" frame to point to repeat_nmi, forcing another
+ * iteration of NMI handling.
+ */
+ subq $8, %rsp
+ leaq -10*8(%rsp), %rdx
+ pushq $__KERNEL_DS
+ pushq %rdx
+ pushfq
+ pushq $__KERNEL_CS
+ pushq $repeat_nmi
+
+ /* Put stack back */
+ addq $(6*8), %rsp
+
+nested_nmi_out:
+ popq %rdx
+
+ /* We are returning to kernel mode, so this cannot result in a fault. */
+ iretq
+
+first_nmi:
+ /* Restore rdx. */
+ movq (%rsp), %rdx
+
+ /* Make room for "NMI executing". */
+ pushq $0
+
+ /* Leave room for the "iret" frame */
+ subq $(5*8), %rsp
+
+ /* Copy the "original" frame to the "outermost" frame */
+ .rept 5
+ pushq 11*8(%rsp)
+ .endr
+ UNWIND_HINT_IRET_REGS
+
+ /* Everything up to here is safe from nested NMIs */
+
+#ifdef CONFIG_DEBUG_ENTRY
+ /*
+ * For ease of testing, unmask NMIs right away. Disabled by
+ * default because IRET is very expensive.
+ */
+ pushq $0 /* SS */
+ pushq %rsp /* RSP (minus 8 because of the previous push) */
+ addq $8, (%rsp) /* Fix up RSP */
+ pushfq /* RFLAGS */
+ pushq $__KERNEL_CS /* CS */
+ pushq $1f /* RIP */
+ iretq /* continues at repeat_nmi below */
+ UNWIND_HINT_IRET_REGS
+1:
+#endif
+
+repeat_nmi:
+ /*
+ * If there was a nested NMI, the first NMI's iret will return
+ * here. But NMIs are still enabled and we can take another
+ * nested NMI. The nested NMI checks the interrupted RIP to see
+ * if it is between repeat_nmi and end_repeat_nmi, and if so
+ * it will just return, as we are about to repeat an NMI anyway.
+ * This makes it safe to copy to the stack frame that a nested
+ * NMI will update.
+ *
+ * RSP is pointing to "outermost RIP". gsbase is unknown, but, if
+ * we're repeating an NMI, gsbase has the same value that it had on
+ * the first iteration. paranoid_entry will load the kernel
+ * gsbase if needed before we call do_nmi. "NMI executing"
+ * is zero.
+ */
+ movq $1, 10*8(%rsp) /* Set "NMI executing". */
+
+ /*
+ * Copy the "outermost" frame to the "iret" frame. NMIs that nest
+ * here must not modify the "iret" frame while we're writing to
+ * it or it will end up containing garbage.
+ */
+ addq $(10*8), %rsp
+ .rept 5
+ pushq -6*8(%rsp)
+ .endr
+ subq $(5*8), %rsp
+end_repeat_nmi:
+
+ /*
+ * Everything below this point can be preempted by a nested NMI.
+ * If this happens, then the inner NMI will change the "iret"
+ * frame to point back to repeat_nmi.
+ */
+ pushq $-1 /* ORIG_RAX: no syscall to restart */
+
+ /*
+ * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
+ * as we should not be calling schedule in NMI context.
+ * Even with normal interrupts enabled. An NMI should not be
+ * setting NEED_RESCHED or anything that normal interrupts and
+ * exceptions might do.
+ */
+ call paranoid_entry
+ UNWIND_HINT_REGS
+
+ /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
+ movq %rsp, %rdi
+ movq $-1, %rsi
+ call do_nmi
+
+ /* Always restore stashed CR3 value (see paranoid_entry) */
+ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
+ testl %ebx, %ebx /* swapgs needed? */
+ jnz nmi_restore
+nmi_swapgs:
+ SWAPGS_UNSAFE_STACK
+nmi_restore:
+ POP_REGS
+
+ /*
+ * Skip orig_ax and the "outermost" frame to point RSP at the "iret"
+ * at the "iret" frame.
+ */
+ addq $6*8, %rsp
+
+ /*
+ * Clear "NMI executing". Set DF first so that we can easily
+ * distinguish the remaining code between here and IRET from
+ * the SYSCALL entry and exit paths.
+ *
+ * We arguably should just inspect RIP instead, but I (Andy) wrote
+ * this code when I had the misapprehension that Xen PV supported
+ * NMIs, and Xen PV would break that approach.
+ */
+ std
+ movq $0, 5*8(%rsp) /* clear "NMI executing" */
+
+ /*
+ * iretq reads the "iret" frame and exits the NMI stack in a
+ * single instruction. We are returning to kernel mode, so this
+ * cannot result in a fault. Similarly, we don't need to worry
+ * about espfix64 on the way back to kernel mode.
+ */
+ iretq
+END(nmi)
+
+ENTRY(ignore_sysret)
+ UNWIND_HINT_EMPTY
+ mov $-ENOSYS, %eax
+ sysret
+END(ignore_sysret)
+
+ENTRY(rewind_stack_do_exit)
+ UNWIND_HINT_FUNC
+ /* Prevent any naive code from trying to unwind to our caller. */
+ xorl %ebp, %ebp
+
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rax
+ leaq -PTREGS_SIZE(%rax), %rsp
+ UNWIND_HINT_REGS
+
+ call do_exit
+END(rewind_stack_do_exit)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
new file mode 100644
index 000000000..40d2834a8
--- /dev/null
+++ b/arch/x86/entry/entry_64_compat.S
@@ -0,0 +1,414 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Compatibility mode system call entry point for x86-64.
+ *
+ * Copyright 2000-2002 Andi Kleen, SuSE Labs.
+ */
+#include "calling.h"
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/errno.h>
+#include <asm/ia32_unistd.h>
+#include <asm/thread_info.h>
+#include <asm/segment.h>
+#include <asm/irqflags.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <linux/linkage.h>
+#include <linux/err.h>
+
+ .section .entry.text, "ax"
+
+/*
+ * 32-bit SYSENTER entry.
+ *
+ * 32-bit system calls through the vDSO's __kernel_vsyscall enter here
+ * on 64-bit kernels running on Intel CPUs.
+ *
+ * The SYSENTER instruction, in principle, should *only* occur in the
+ * vDSO. In practice, a small number of Android devices were shipped
+ * with a copy of Bionic that inlined a SYSENTER instruction. This
+ * never happened in any of Google's Bionic versions -- it only happened
+ * in a narrow range of Intel-provided versions.
+ *
+ * SYSENTER loads SS, RSP, CS, and RIP from previously programmed MSRs.
+ * IF and VM in RFLAGS are cleared (IOW: interrupts are off).
+ * SYSENTER does not save anything on the stack,
+ * and does not save old RIP (!!!), RSP, or RFLAGS.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp user stack
+ * 0(%ebp) arg6
+ */
+ENTRY(entry_SYSENTER_compat)
+ /* Interrupts are off on entry. */
+ SWAPGS
+
+ /* We are about to clobber %rsp anyway, clobbering here is OK */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /*
+ * 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 */
+ pushq $__USER32_DS /* pt_regs->ss */
+ 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 */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq $0 /* 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 $0 /* pt_regs->r8 = 0 */
+ xorl %r8d, %r8d /* nospec r8 */
+ pushq $0 /* pt_regs->r9 = 0 */
+ xorl %r9d, %r9d /* nospec r9 */
+ pushq $0 /* pt_regs->r10 = 0 */
+ xorl %r10d, %r10d /* nospec r10 */
+ pushq $0 /* pt_regs->r11 = 0 */
+ xorl %r11d, %r11d /* nospec r11 */
+ pushq %rbx /* pt_regs->rbx */
+ xorl %ebx, %ebx /* nospec rbx */
+ pushq %rbp /* pt_regs->rbp (will be overwritten) */
+ xorl %ebp, %ebp /* nospec rbp */
+ pushq $0 /* pt_regs->r12 = 0 */
+ xorl %r12d, %r12d /* nospec r12 */
+ pushq $0 /* pt_regs->r13 = 0 */
+ xorl %r13d, %r13d /* nospec r13 */
+ pushq $0 /* pt_regs->r14 = 0 */
+ xorl %r14d, %r14d /* nospec r14 */
+ pushq $0 /* pt_regs->r15 = 0 */
+ xorl %r15d, %r15d /* nospec r15 */
+ cld
+
+ /*
+ * SYSENTER doesn't filter flags, so we need to clear NT and AC
+ * ourselves. To save a few cycles, we can check whether
+ * either was set instead of doing an unconditional popfq.
+ * This needs to happen before enabling interrupts so that
+ * we don't get preempted with NT set.
+ *
+ * If TF is set, we will single-step all the way to here -- do_debug
+ * will ignore all the traps. (Yes, this is slow, but so is
+ * single-stepping in general. This allows us to avoid having
+ * a more complicated code to handle the case where a user program
+ * forces us to single-step through the SYSENTER entry code.)
+ *
+ * NB.: .Lsysenter_fix_flags is a label with the code under it moved
+ * out-of-line as an optimization: NT is unlikely to be set in the
+ * majority of the cases and instead of polluting the I$ 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|X86_EFLAGS_AC|X86_EFLAGS_TF, EFLAGS(%rsp)
+ jnz .Lsysenter_fix_flags
+.Lsysenter_flags_fixed:
+
+ /*
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
+ */
+ TRACE_IRQS_OFF
+
+ 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
+
+.Lsysenter_fix_flags:
+ pushq $X86_EFLAGS_FIXED
+ popfq
+ jmp .Lsysenter_flags_fixed
+GLOBAL(__end_entry_SYSENTER_compat)
+ENDPROC(entry_SYSENTER_compat)
+
+/*
+ * 32-bit SYSCALL entry.
+ *
+ * 32-bit system calls through the vDSO's __kernel_vsyscall enter here
+ * on 64-bit kernels running on AMD CPUs.
+ *
+ * The SYSCALL instruction, in principle, should *only* occur in the
+ * vDSO. In practice, it appears that this really is the case.
+ * As evidence:
+ *
+ * - The calling convention for SYSCALL has changed several times without
+ * anyone noticing.
+ *
+ * - Prior to the in-kernel X86_BUG_SYSRET_SS_ATTRS fixup, anything
+ * user task that did SYSCALL without immediately reloading SS
+ * would randomly crash.
+ *
+ * - Most programmers do not directly target AMD CPUs, and the 32-bit
+ * SYSCALL instruction does not exist on Intel CPUs. Even on AMD
+ * CPUs, Linux disables the SYSCALL instruction on 32-bit kernels
+ * because the SYSCALL instruction in legacy/native 32-bit mode (as
+ * opposed to compat mode) is sufficiently poorly designed as to be
+ * essentially unusable.
+ *
+ * 32-bit SYSCALL saves RIP to RCX, clears RFLAGS.RF, then saves
+ * RFLAGS to R11, then loads new SS, CS, and RIP from previously
+ * programmed MSRs. RFLAGS gets masked by a value from another MSR
+ * (so CLD and CLAC are not needed). SYSCALL does not save anything on
+ * the stack and does not change RSP.
+ *
+ * Note: RFLAGS saving+masking-with-MSR happens only in Long mode
+ * (in legacy 32-bit mode, IF, RF and VM bits are cleared and that's it).
+ * Don't get confused: RFLAGS saving+masking depends on Long Mode Active bit
+ * (EFER.LMA=1), NOT on bitness of userspace where SYSCALL executes
+ * or target CS descriptor's L bit (SYSCALL does not read segment descriptors).
+ *
+ * Arguments:
+ * eax system call number
+ * ecx return address
+ * ebx arg1
+ * ebp arg2 (note: not saved in the stack frame, should not be touched)
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * esp user stack
+ * 0(%esp) arg6
+ */
+ENTRY(entry_SYSCALL_compat)
+ /* Interrupts are off on entry. */
+ swapgs
+
+ /* Stash user ESP */
+ movl %esp, %r8d
+
+ /* Use %rsp as scratch reg. User ESP is stashed in r8 */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+ /* Switch to the kernel stack */
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /* Construct struct pt_regs on stack */
+ pushq $__USER32_DS /* pt_regs->ss */
+ pushq %r8 /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER32_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+GLOBAL(entry_SYSCALL_compat_after_hwframe)
+ movl %eax, %eax /* discard orig_ax high bits */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+ pushq %rsi /* pt_regs->si */
+ xorl %esi, %esi /* nospec si */
+ pushq %rdx /* pt_regs->dx */
+ xorl %edx, %edx /* nospec dx */
+ pushq %rbp /* pt_regs->cx (stashed in bp) */
+ xorl %ecx, %ecx /* nospec cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq $0 /* pt_regs->r8 = 0 */
+ xorl %r8d, %r8d /* nospec r8 */
+ pushq $0 /* pt_regs->r9 = 0 */
+ xorl %r9d, %r9d /* nospec r9 */
+ pushq $0 /* pt_regs->r10 = 0 */
+ xorl %r10d, %r10d /* nospec r10 */
+ pushq $0 /* pt_regs->r11 = 0 */
+ xorl %r11d, %r11d /* nospec r11 */
+ pushq %rbx /* pt_regs->rbx */
+ xorl %ebx, %ebx /* nospec rbx */
+ pushq %rbp /* pt_regs->rbp (will be overwritten) */
+ xorl %ebp, %ebp /* nospec rbp */
+ pushq $0 /* pt_regs->r12 = 0 */
+ xorl %r12d, %r12d /* nospec r12 */
+ pushq $0 /* pt_regs->r13 = 0 */
+ xorl %r13d, %r13d /* nospec r13 */
+ pushq $0 /* pt_regs->r14 = 0 */
+ xorl %r14d, %r14d /* nospec r14 */
+ pushq $0 /* pt_regs->r15 = 0 */
+ xorl %r15d, %r15d /* nospec r15 */
+
+ /*
+ * User mode is traced as though IRQs are on, and SYSENTER
+ * turned them off.
+ */
+ TRACE_IRQS_OFF
+
+ 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.
+ *
+ * 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.
+ */
+ movq RSP-ORIG_RAX(%rsp), %rsp
+
+ /*
+ * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+ * on the process stack which is not mapped to userspace and
+ * not readable after we SWITCH_TO_USER_CR3. Delay the CR3
+ * switch until after after the last reference to the process
+ * stack.
+ *
+ * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+ */
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
+ xorl %r8d, %r8d
+ xorl %r9d, %r9d
+ xorl %r10d, %r10d
+ swapgs
+ sysretl
+END(entry_SYSCALL_compat)
+
+/*
+ * 32-bit legacy system call entry.
+ *
+ * 32-bit x86 Linux system calls traditionally used the INT $0x80
+ * instruction. INT $0x80 lands here.
+ *
+ * This entry point can be used by 32-bit and 64-bit programs to perform
+ * 32-bit system calls. Instances of INT $0x80 can be found inline in
+ * various programs and libraries. It is also used by the vDSO's
+ * __kernel_vsyscall fallback for hardware that doesn't support a faster
+ * entry method. Restarted 32-bit system calls also fall back to INT
+ * $0x80 regardless of what instruction was originally used to do the
+ * system call.
+ *
+ * This is considered a slow path. It is not used by most libc
+ * implementations on modern hardware except during process startup.
+ *
+ * Arguments:
+ * eax system call number
+ * ebx arg1
+ * ecx arg2
+ * edx arg3
+ * esi arg4
+ * edi arg5
+ * ebp arg6
+ */
+ENTRY(entry_INT80_compat)
+ /*
+ * Interrupts are off on entry.
+ */
+ ASM_CLAC /* Do this early to minimize exposure */
+ SWAPGS
+
+ /*
+ * 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
+
+ /* switch to thread stack expects orig_ax and rdi to be pushed */
+ pushq %rax /* pt_regs->orig_ax */
+ pushq %rdi /* pt_regs->di */
+
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+ /* In the Xen PV case we already run on the thread stack. */
+ ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ pushq 6*8(%rdi) /* regs->ss */
+ pushq 5*8(%rdi) /* regs->rsp */
+ pushq 4*8(%rdi) /* regs->eflags */
+ pushq 3*8(%rdi) /* regs->cs */
+ pushq 2*8(%rdi) /* regs->ip */
+ pushq 1*8(%rdi) /* regs->orig_ax */
+ pushq (%rdi) /* pt_regs->di */
+.Lint80_keep_stack:
+
+ pushq %rsi /* pt_regs->si */
+ xorl %esi, %esi /* nospec si */
+ pushq %rdx /* pt_regs->dx */
+ xorl %edx, %edx /* nospec dx */
+ pushq %rcx /* pt_regs->cx */
+ xorl %ecx, %ecx /* nospec cx */
+ pushq $-ENOSYS /* pt_regs->ax */
+ pushq %r8 /* pt_regs->r8 */
+ xorl %r8d, %r8d /* nospec r8 */
+ pushq %r9 /* pt_regs->r9 */
+ xorl %r9d, %r9d /* nospec r9 */
+ pushq %r10 /* pt_regs->r10*/
+ xorl %r10d, %r10d /* nospec r10 */
+ pushq %r11 /* pt_regs->r11 */
+ xorl %r11d, %r11d /* nospec r11 */
+ pushq %rbx /* pt_regs->rbx */
+ xorl %ebx, %ebx /* nospec rbx */
+ pushq %rbp /* pt_regs->rbp */
+ xorl %ebp, %ebp /* nospec rbp */
+ pushq %r12 /* pt_regs->r12 */
+ xorl %r12d, %r12d /* nospec r12 */
+ pushq %r13 /* pt_regs->r13 */
+ xorl %r13d, %r13d /* nospec r13 */
+ pushq %r14 /* pt_regs->r14 */
+ xorl %r14d, %r14d /* nospec r14 */
+ pushq %r15 /* pt_regs->r15 */
+ xorl %r15d, %r15d /* nospec r15 */
+ cld
+
+ /*
+ * User mode is traced as though IRQs are on, and the interrupt
+ * gate turned them off.
+ */
+ TRACE_IRQS_OFF
+
+ movq %rsp, %rdi
+ call do_int80_syscall_32
+.Lsyscall_32_done:
+
+ /* Go back to user mode. */
+ TRACE_IRQS_ON
+ jmp swapgs_restore_regs_and_return_to_usermode
+END(entry_INT80_compat)
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
new file mode 100644
index 000000000..aa3336a7c
--- /dev/null
+++ b/arch/x86/entry/syscall_32.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+/* System call table for i386. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+#include <asm/syscall.h>
+
+#ifdef CONFIG_IA32_EMULATION
+/* On X86_64, we use struct pt_regs * to pass parameters to syscalls */
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
+
+/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
+extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+
+#else /* CONFIG_IA32_EMULATION */
+#define __SYSCALL_I386(nr, sym, qual) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+#endif /* CONFIG_IA32_EMULATION */
+
+#include <asm/syscalls_32.h>
+#undef __SYSCALL_I386
+
+#define __SYSCALL_I386(nr, sym, qual) [nr] = sym,
+
+__visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_compat_max] = &sys_ni_syscall,
+#include <asm/syscalls_32.h>
+};
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
new file mode 100644
index 000000000..d5252bc1e
--- /dev/null
+++ b/arch/x86/entry/syscall_64.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+/* System call table for x86-64. */
+
+#include <linux/linkage.h>
+#include <linux/sys.h>
+#include <linux/cache.h>
+#include <asm/asm-offsets.h>
+#include <asm/syscall.h>
+
+/* this is a lie, but it does not hurt as sys_ni_syscall just returns -EINVAL */
+extern asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __SYSCALL_64(nr, sym, qual) extern asmlinkage long sym(const struct pt_regs *);
+#include <asm/syscalls_64.h>
+#undef __SYSCALL_64
+
+#define __SYSCALL_64(nr, sym, qual) [nr] = sym,
+
+asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+ /*
+ * Smells like a compiler bug -- it doesn't work
+ * when the & below is removed.
+ */
+ [0 ... __NR_syscall_max] = &sys_ni_syscall,
+#include <asm/syscalls_64.h>
+};
diff --git a/arch/x86/entry/syscalls/Makefile b/arch/x86/entry/syscalls/Makefile
new file mode 100644
index 000000000..6fb9b57ed
--- /dev/null
+++ b/arch/x86/entry/syscalls/Makefile
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: GPL-2.0
+out := arch/$(SRCARCH)/include/generated/asm
+uapi := arch/$(SRCARCH)/include/generated/uapi/asm
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') \
+ $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)')
+
+syscall32 := $(srctree)/$(src)/syscall_32.tbl
+syscall64 := $(srctree)/$(src)/syscall_64.tbl
+
+syshdr := $(srctree)/$(src)/syscallhdr.sh
+systbl := $(srctree)/$(src)/syscalltbl.sh
+
+quiet_cmd_syshdr = SYSHDR $@
+ cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
+ '$(syshdr_abi_$(basetarget))' \
+ '$(syshdr_pfx_$(basetarget))' \
+ '$(syshdr_offset_$(basetarget))'
+quiet_cmd_systbl = SYSTBL $@
+ cmd_systbl = $(CONFIG_SHELL) '$(systbl)' $< $@
+
+quiet_cmd_hypercalls = HYPERCALLS $@
+ cmd_hypercalls = $(CONFIG_SHELL) '$<' $@ $(filter-out $<,$^)
+
+syshdr_abi_unistd_32 := i386
+$(uapi)/unistd_32.h: $(syscall32) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_32_ia32 := i386
+syshdr_pfx_unistd_32_ia32 := ia32_
+$(out)/unistd_32_ia32.h: $(syscall32) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_x32 := common,x32
+syshdr_offset_unistd_x32 := __X32_SYSCALL_BIT
+$(uapi)/unistd_x32.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_64 := common,64
+$(uapi)/unistd_64.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+syshdr_abi_unistd_64_x32 := x32
+syshdr_pfx_unistd_64_x32 := x32_
+$(out)/unistd_64_x32.h: $(syscall64) $(syshdr)
+ $(call if_changed,syshdr)
+
+$(out)/syscalls_32.h: $(syscall32) $(systbl)
+ $(call if_changed,systbl)
+$(out)/syscalls_64.h: $(syscall64) $(systbl)
+ $(call if_changed,systbl)
+
+$(out)/xen-hypercalls.h: $(srctree)/scripts/xen-hypercalls.sh
+ $(call if_changed,hypercalls)
+
+$(out)/xen-hypercalls.h: $(srctree)/include/xen/interface/xen*.h
+
+uapisyshdr-y += unistd_32.h unistd_64.h unistd_x32.h
+syshdr-y += syscalls_32.h
+syshdr-$(CONFIG_X86_64) += unistd_32_ia32.h unistd_64_x32.h
+syshdr-$(CONFIG_X86_64) += syscalls_64.h
+syshdr-$(CONFIG_XEN) += xen-hypercalls.h
+
+targets += $(uapisyshdr-y) $(syshdr-y)
+
+PHONY += all
+all: $(addprefix $(uapi)/,$(uapisyshdr-y))
+all: $(addprefix $(out)/,$(syshdr-y))
+ @:
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
new file mode 100644
index 000000000..3cf7b533b
--- /dev/null
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -0,0 +1,400 @@
+#
+# 32-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point> <compat entry point>
+#
+# The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for
+# sys_*() system calls and compat_sys_*() compat system calls if
+# IA32_EMULATION is defined, and expect struct pt_regs *regs as their only
+# parameter.
+#
+# The abi is always "i386" for this file.
+#
+0 i386 restart_syscall sys_restart_syscall __ia32_sys_restart_syscall
+1 i386 exit sys_exit __ia32_sys_exit
+2 i386 fork sys_fork __ia32_sys_fork
+3 i386 read sys_read __ia32_sys_read
+4 i386 write sys_write __ia32_sys_write
+5 i386 open sys_open __ia32_compat_sys_open
+6 i386 close sys_close __ia32_sys_close
+7 i386 waitpid sys_waitpid __ia32_sys_waitpid
+8 i386 creat sys_creat __ia32_sys_creat
+9 i386 link sys_link __ia32_sys_link
+10 i386 unlink sys_unlink __ia32_sys_unlink
+11 i386 execve sys_execve __ia32_compat_sys_execve
+12 i386 chdir sys_chdir __ia32_sys_chdir
+13 i386 time sys_time __ia32_compat_sys_time
+14 i386 mknod sys_mknod __ia32_sys_mknod
+15 i386 chmod sys_chmod __ia32_sys_chmod
+16 i386 lchown sys_lchown16 __ia32_sys_lchown16
+17 i386 break
+18 i386 oldstat sys_stat __ia32_sys_stat
+19 i386 lseek sys_lseek __ia32_compat_sys_lseek
+20 i386 getpid sys_getpid __ia32_sys_getpid
+21 i386 mount sys_mount __ia32_compat_sys_mount
+22 i386 umount sys_oldumount __ia32_sys_oldumount
+23 i386 setuid sys_setuid16 __ia32_sys_setuid16
+24 i386 getuid sys_getuid16 __ia32_sys_getuid16
+25 i386 stime sys_stime __ia32_compat_sys_stime
+26 i386 ptrace sys_ptrace __ia32_compat_sys_ptrace
+27 i386 alarm sys_alarm __ia32_sys_alarm
+28 i386 oldfstat sys_fstat __ia32_sys_fstat
+29 i386 pause sys_pause __ia32_sys_pause
+30 i386 utime sys_utime __ia32_compat_sys_utime
+31 i386 stty
+32 i386 gtty
+33 i386 access sys_access __ia32_sys_access
+34 i386 nice sys_nice __ia32_sys_nice
+35 i386 ftime
+36 i386 sync sys_sync __ia32_sys_sync
+37 i386 kill sys_kill __ia32_sys_kill
+38 i386 rename sys_rename __ia32_sys_rename
+39 i386 mkdir sys_mkdir __ia32_sys_mkdir
+40 i386 rmdir sys_rmdir __ia32_sys_rmdir
+41 i386 dup sys_dup __ia32_sys_dup
+42 i386 pipe sys_pipe __ia32_sys_pipe
+43 i386 times sys_times __ia32_compat_sys_times
+44 i386 prof
+45 i386 brk sys_brk __ia32_sys_brk
+46 i386 setgid sys_setgid16 __ia32_sys_setgid16
+47 i386 getgid sys_getgid16 __ia32_sys_getgid16
+48 i386 signal sys_signal __ia32_sys_signal
+49 i386 geteuid sys_geteuid16 __ia32_sys_geteuid16
+50 i386 getegid sys_getegid16 __ia32_sys_getegid16
+51 i386 acct sys_acct __ia32_sys_acct
+52 i386 umount2 sys_umount __ia32_sys_umount
+53 i386 lock
+54 i386 ioctl sys_ioctl __ia32_compat_sys_ioctl
+55 i386 fcntl sys_fcntl __ia32_compat_sys_fcntl64
+56 i386 mpx
+57 i386 setpgid sys_setpgid __ia32_sys_setpgid
+58 i386 ulimit
+59 i386 oldolduname sys_olduname __ia32_sys_olduname
+60 i386 umask sys_umask __ia32_sys_umask
+61 i386 chroot sys_chroot __ia32_sys_chroot
+62 i386 ustat sys_ustat __ia32_compat_sys_ustat
+63 i386 dup2 sys_dup2 __ia32_sys_dup2
+64 i386 getppid sys_getppid __ia32_sys_getppid
+65 i386 getpgrp sys_getpgrp __ia32_sys_getpgrp
+66 i386 setsid sys_setsid __ia32_sys_setsid
+67 i386 sigaction sys_sigaction __ia32_compat_sys_sigaction
+68 i386 sgetmask sys_sgetmask __ia32_sys_sgetmask
+69 i386 ssetmask sys_ssetmask __ia32_sys_ssetmask
+70 i386 setreuid sys_setreuid16 __ia32_sys_setreuid16
+71 i386 setregid sys_setregid16 __ia32_sys_setregid16
+72 i386 sigsuspend sys_sigsuspend __ia32_sys_sigsuspend
+73 i386 sigpending sys_sigpending __ia32_compat_sys_sigpending
+74 i386 sethostname sys_sethostname __ia32_sys_sethostname
+75 i386 setrlimit sys_setrlimit __ia32_compat_sys_setrlimit
+76 i386 getrlimit sys_old_getrlimit __ia32_compat_sys_old_getrlimit
+77 i386 getrusage sys_getrusage __ia32_compat_sys_getrusage
+78 i386 gettimeofday sys_gettimeofday __ia32_compat_sys_gettimeofday
+79 i386 settimeofday sys_settimeofday __ia32_compat_sys_settimeofday
+80 i386 getgroups sys_getgroups16 __ia32_sys_getgroups16
+81 i386 setgroups sys_setgroups16 __ia32_sys_setgroups16
+82 i386 select sys_old_select __ia32_compat_sys_old_select
+83 i386 symlink sys_symlink __ia32_sys_symlink
+84 i386 oldlstat sys_lstat __ia32_sys_lstat
+85 i386 readlink sys_readlink __ia32_sys_readlink
+86 i386 uselib sys_uselib __ia32_sys_uselib
+87 i386 swapon sys_swapon __ia32_sys_swapon
+88 i386 reboot sys_reboot __ia32_sys_reboot
+89 i386 readdir sys_old_readdir __ia32_compat_sys_old_readdir
+90 i386 mmap sys_old_mmap __ia32_compat_sys_x86_mmap
+91 i386 munmap sys_munmap __ia32_sys_munmap
+92 i386 truncate sys_truncate __ia32_compat_sys_truncate
+93 i386 ftruncate sys_ftruncate __ia32_compat_sys_ftruncate
+94 i386 fchmod sys_fchmod __ia32_sys_fchmod
+95 i386 fchown sys_fchown16 __ia32_sys_fchown16
+96 i386 getpriority sys_getpriority __ia32_sys_getpriority
+97 i386 setpriority sys_setpriority __ia32_sys_setpriority
+98 i386 profil
+99 i386 statfs sys_statfs __ia32_compat_sys_statfs
+100 i386 fstatfs sys_fstatfs __ia32_compat_sys_fstatfs
+101 i386 ioperm sys_ioperm __ia32_sys_ioperm
+102 i386 socketcall sys_socketcall __ia32_compat_sys_socketcall
+103 i386 syslog sys_syslog __ia32_sys_syslog
+104 i386 setitimer sys_setitimer __ia32_compat_sys_setitimer
+105 i386 getitimer sys_getitimer __ia32_compat_sys_getitimer
+106 i386 stat sys_newstat __ia32_compat_sys_newstat
+107 i386 lstat sys_newlstat __ia32_compat_sys_newlstat
+108 i386 fstat sys_newfstat __ia32_compat_sys_newfstat
+109 i386 olduname sys_uname __ia32_sys_uname
+110 i386 iopl sys_iopl __ia32_sys_iopl
+111 i386 vhangup sys_vhangup __ia32_sys_vhangup
+112 i386 idle
+113 i386 vm86old sys_vm86old sys_ni_syscall
+114 i386 wait4 sys_wait4 __ia32_compat_sys_wait4
+115 i386 swapoff sys_swapoff __ia32_sys_swapoff
+116 i386 sysinfo sys_sysinfo __ia32_compat_sys_sysinfo
+117 i386 ipc sys_ipc __ia32_compat_sys_ipc
+118 i386 fsync sys_fsync __ia32_sys_fsync
+119 i386 sigreturn sys_sigreturn sys32_sigreturn
+120 i386 clone sys_clone __ia32_compat_sys_x86_clone
+121 i386 setdomainname sys_setdomainname __ia32_sys_setdomainname
+122 i386 uname sys_newuname __ia32_sys_newuname
+123 i386 modify_ldt sys_modify_ldt __ia32_sys_modify_ldt
+124 i386 adjtimex sys_adjtimex __ia32_compat_sys_adjtimex
+125 i386 mprotect sys_mprotect __ia32_sys_mprotect
+126 i386 sigprocmask sys_sigprocmask __ia32_compat_sys_sigprocmask
+127 i386 create_module
+128 i386 init_module sys_init_module __ia32_sys_init_module
+129 i386 delete_module sys_delete_module __ia32_sys_delete_module
+130 i386 get_kernel_syms
+131 i386 quotactl sys_quotactl __ia32_compat_sys_quotactl32
+132 i386 getpgid sys_getpgid __ia32_sys_getpgid
+133 i386 fchdir sys_fchdir __ia32_sys_fchdir
+134 i386 bdflush sys_bdflush __ia32_sys_bdflush
+135 i386 sysfs sys_sysfs __ia32_sys_sysfs
+136 i386 personality sys_personality __ia32_sys_personality
+137 i386 afs_syscall
+138 i386 setfsuid sys_setfsuid16 __ia32_sys_setfsuid16
+139 i386 setfsgid sys_setfsgid16 __ia32_sys_setfsgid16
+140 i386 _llseek sys_llseek __ia32_sys_llseek
+141 i386 getdents sys_getdents __ia32_compat_sys_getdents
+142 i386 _newselect sys_select __ia32_compat_sys_select
+143 i386 flock sys_flock __ia32_sys_flock
+144 i386 msync sys_msync __ia32_sys_msync
+145 i386 readv sys_readv __ia32_compat_sys_readv
+146 i386 writev sys_writev __ia32_compat_sys_writev
+147 i386 getsid sys_getsid __ia32_sys_getsid
+148 i386 fdatasync sys_fdatasync __ia32_sys_fdatasync
+149 i386 _sysctl sys_sysctl __ia32_compat_sys_sysctl
+150 i386 mlock sys_mlock __ia32_sys_mlock
+151 i386 munlock sys_munlock __ia32_sys_munlock
+152 i386 mlockall sys_mlockall __ia32_sys_mlockall
+153 i386 munlockall sys_munlockall __ia32_sys_munlockall
+154 i386 sched_setparam sys_sched_setparam __ia32_sys_sched_setparam
+155 i386 sched_getparam sys_sched_getparam __ia32_sys_sched_getparam
+156 i386 sched_setscheduler sys_sched_setscheduler __ia32_sys_sched_setscheduler
+157 i386 sched_getscheduler sys_sched_getscheduler __ia32_sys_sched_getscheduler
+158 i386 sched_yield sys_sched_yield __ia32_sys_sched_yield
+159 i386 sched_get_priority_max sys_sched_get_priority_max __ia32_sys_sched_get_priority_max
+160 i386 sched_get_priority_min sys_sched_get_priority_min __ia32_sys_sched_get_priority_min
+161 i386 sched_rr_get_interval sys_sched_rr_get_interval __ia32_compat_sys_sched_rr_get_interval
+162 i386 nanosleep sys_nanosleep __ia32_compat_sys_nanosleep
+163 i386 mremap sys_mremap __ia32_sys_mremap
+164 i386 setresuid sys_setresuid16 __ia32_sys_setresuid16
+165 i386 getresuid sys_getresuid16 __ia32_sys_getresuid16
+166 i386 vm86 sys_vm86 sys_ni_syscall
+167 i386 query_module
+168 i386 poll sys_poll __ia32_sys_poll
+169 i386 nfsservctl
+170 i386 setresgid sys_setresgid16 __ia32_sys_setresgid16
+171 i386 getresgid sys_getresgid16 __ia32_sys_getresgid16
+172 i386 prctl sys_prctl __ia32_sys_prctl
+173 i386 rt_sigreturn sys_rt_sigreturn sys32_rt_sigreturn
+174 i386 rt_sigaction sys_rt_sigaction __ia32_compat_sys_rt_sigaction
+175 i386 rt_sigprocmask sys_rt_sigprocmask __ia32_sys_rt_sigprocmask
+176 i386 rt_sigpending sys_rt_sigpending __ia32_compat_sys_rt_sigpending
+177 i386 rt_sigtimedwait sys_rt_sigtimedwait __ia32_compat_sys_rt_sigtimedwait
+178 i386 rt_sigqueueinfo sys_rt_sigqueueinfo __ia32_compat_sys_rt_sigqueueinfo
+179 i386 rt_sigsuspend sys_rt_sigsuspend __ia32_sys_rt_sigsuspend
+180 i386 pread64 sys_pread64 __ia32_compat_sys_x86_pread
+181 i386 pwrite64 sys_pwrite64 __ia32_compat_sys_x86_pwrite
+182 i386 chown sys_chown16 __ia32_sys_chown16
+183 i386 getcwd sys_getcwd __ia32_sys_getcwd
+184 i386 capget sys_capget __ia32_sys_capget
+185 i386 capset sys_capset __ia32_sys_capset
+186 i386 sigaltstack sys_sigaltstack __ia32_compat_sys_sigaltstack
+187 i386 sendfile sys_sendfile __ia32_compat_sys_sendfile
+188 i386 getpmsg
+189 i386 putpmsg
+190 i386 vfork sys_vfork __ia32_sys_vfork
+191 i386 ugetrlimit sys_getrlimit __ia32_compat_sys_getrlimit
+192 i386 mmap2 sys_mmap_pgoff __ia32_sys_mmap_pgoff
+193 i386 truncate64 sys_truncate64 __ia32_compat_sys_x86_truncate64
+194 i386 ftruncate64 sys_ftruncate64 __ia32_compat_sys_x86_ftruncate64
+195 i386 stat64 sys_stat64 __ia32_compat_sys_x86_stat64
+196 i386 lstat64 sys_lstat64 __ia32_compat_sys_x86_lstat64
+197 i386 fstat64 sys_fstat64 __ia32_compat_sys_x86_fstat64
+198 i386 lchown32 sys_lchown __ia32_sys_lchown
+199 i386 getuid32 sys_getuid __ia32_sys_getuid
+200 i386 getgid32 sys_getgid __ia32_sys_getgid
+201 i386 geteuid32 sys_geteuid __ia32_sys_geteuid
+202 i386 getegid32 sys_getegid __ia32_sys_getegid
+203 i386 setreuid32 sys_setreuid __ia32_sys_setreuid
+204 i386 setregid32 sys_setregid __ia32_sys_setregid
+205 i386 getgroups32 sys_getgroups __ia32_sys_getgroups
+206 i386 setgroups32 sys_setgroups __ia32_sys_setgroups
+207 i386 fchown32 sys_fchown __ia32_sys_fchown
+208 i386 setresuid32 sys_setresuid __ia32_sys_setresuid
+209 i386 getresuid32 sys_getresuid __ia32_sys_getresuid
+210 i386 setresgid32 sys_setresgid __ia32_sys_setresgid
+211 i386 getresgid32 sys_getresgid __ia32_sys_getresgid
+212 i386 chown32 sys_chown __ia32_sys_chown
+213 i386 setuid32 sys_setuid __ia32_sys_setuid
+214 i386 setgid32 sys_setgid __ia32_sys_setgid
+215 i386 setfsuid32 sys_setfsuid __ia32_sys_setfsuid
+216 i386 setfsgid32 sys_setfsgid __ia32_sys_setfsgid
+217 i386 pivot_root sys_pivot_root __ia32_sys_pivot_root
+218 i386 mincore sys_mincore __ia32_sys_mincore
+219 i386 madvise sys_madvise __ia32_sys_madvise
+220 i386 getdents64 sys_getdents64 __ia32_sys_getdents64
+221 i386 fcntl64 sys_fcntl64 __ia32_compat_sys_fcntl64
+# 222 is unused
+# 223 is unused
+224 i386 gettid sys_gettid __ia32_sys_gettid
+225 i386 readahead sys_readahead __ia32_compat_sys_x86_readahead
+226 i386 setxattr sys_setxattr __ia32_sys_setxattr
+227 i386 lsetxattr sys_lsetxattr __ia32_sys_lsetxattr
+228 i386 fsetxattr sys_fsetxattr __ia32_sys_fsetxattr
+229 i386 getxattr sys_getxattr __ia32_sys_getxattr
+230 i386 lgetxattr sys_lgetxattr __ia32_sys_lgetxattr
+231 i386 fgetxattr sys_fgetxattr __ia32_sys_fgetxattr
+232 i386 listxattr sys_listxattr __ia32_sys_listxattr
+233 i386 llistxattr sys_llistxattr __ia32_sys_llistxattr
+234 i386 flistxattr sys_flistxattr __ia32_sys_flistxattr
+235 i386 removexattr sys_removexattr __ia32_sys_removexattr
+236 i386 lremovexattr sys_lremovexattr __ia32_sys_lremovexattr
+237 i386 fremovexattr sys_fremovexattr __ia32_sys_fremovexattr
+238 i386 tkill sys_tkill __ia32_sys_tkill
+239 i386 sendfile64 sys_sendfile64 __ia32_sys_sendfile64
+240 i386 futex sys_futex __ia32_compat_sys_futex
+241 i386 sched_setaffinity sys_sched_setaffinity __ia32_compat_sys_sched_setaffinity
+242 i386 sched_getaffinity sys_sched_getaffinity __ia32_compat_sys_sched_getaffinity
+243 i386 set_thread_area sys_set_thread_area __ia32_sys_set_thread_area
+244 i386 get_thread_area sys_get_thread_area __ia32_sys_get_thread_area
+245 i386 io_setup sys_io_setup __ia32_compat_sys_io_setup
+246 i386 io_destroy sys_io_destroy __ia32_sys_io_destroy
+247 i386 io_getevents sys_io_getevents __ia32_compat_sys_io_getevents
+248 i386 io_submit sys_io_submit __ia32_compat_sys_io_submit
+249 i386 io_cancel sys_io_cancel __ia32_sys_io_cancel
+250 i386 fadvise64 sys_fadvise64 __ia32_compat_sys_x86_fadvise64
+# 251 is available for reuse (was briefly sys_set_zone_reclaim)
+252 i386 exit_group sys_exit_group __ia32_sys_exit_group
+253 i386 lookup_dcookie sys_lookup_dcookie __ia32_compat_sys_lookup_dcookie
+254 i386 epoll_create sys_epoll_create __ia32_sys_epoll_create
+255 i386 epoll_ctl sys_epoll_ctl __ia32_sys_epoll_ctl
+256 i386 epoll_wait sys_epoll_wait __ia32_sys_epoll_wait
+257 i386 remap_file_pages sys_remap_file_pages __ia32_sys_remap_file_pages
+258 i386 set_tid_address sys_set_tid_address __ia32_sys_set_tid_address
+259 i386 timer_create sys_timer_create __ia32_compat_sys_timer_create
+260 i386 timer_settime sys_timer_settime __ia32_compat_sys_timer_settime
+261 i386 timer_gettime sys_timer_gettime __ia32_compat_sys_timer_gettime
+262 i386 timer_getoverrun sys_timer_getoverrun __ia32_sys_timer_getoverrun
+263 i386 timer_delete sys_timer_delete __ia32_sys_timer_delete
+264 i386 clock_settime sys_clock_settime __ia32_compat_sys_clock_settime
+265 i386 clock_gettime sys_clock_gettime __ia32_compat_sys_clock_gettime
+266 i386 clock_getres sys_clock_getres __ia32_compat_sys_clock_getres
+267 i386 clock_nanosleep sys_clock_nanosleep __ia32_compat_sys_clock_nanosleep
+268 i386 statfs64 sys_statfs64 __ia32_compat_sys_statfs64
+269 i386 fstatfs64 sys_fstatfs64 __ia32_compat_sys_fstatfs64
+270 i386 tgkill sys_tgkill __ia32_sys_tgkill
+271 i386 utimes sys_utimes __ia32_compat_sys_utimes
+272 i386 fadvise64_64 sys_fadvise64_64 __ia32_compat_sys_x86_fadvise64_64
+273 i386 vserver
+274 i386 mbind sys_mbind __ia32_sys_mbind
+275 i386 get_mempolicy sys_get_mempolicy __ia32_compat_sys_get_mempolicy
+276 i386 set_mempolicy sys_set_mempolicy __ia32_sys_set_mempolicy
+277 i386 mq_open sys_mq_open __ia32_compat_sys_mq_open
+278 i386 mq_unlink sys_mq_unlink __ia32_sys_mq_unlink
+279 i386 mq_timedsend sys_mq_timedsend __ia32_compat_sys_mq_timedsend
+280 i386 mq_timedreceive sys_mq_timedreceive __ia32_compat_sys_mq_timedreceive
+281 i386 mq_notify sys_mq_notify __ia32_compat_sys_mq_notify
+282 i386 mq_getsetattr sys_mq_getsetattr __ia32_compat_sys_mq_getsetattr
+283 i386 kexec_load sys_kexec_load __ia32_compat_sys_kexec_load
+284 i386 waitid sys_waitid __ia32_compat_sys_waitid
+# 285 sys_setaltroot
+286 i386 add_key sys_add_key __ia32_sys_add_key
+287 i386 request_key sys_request_key __ia32_sys_request_key
+288 i386 keyctl sys_keyctl __ia32_compat_sys_keyctl
+289 i386 ioprio_set sys_ioprio_set __ia32_sys_ioprio_set
+290 i386 ioprio_get sys_ioprio_get __ia32_sys_ioprio_get
+291 i386 inotify_init sys_inotify_init __ia32_sys_inotify_init
+292 i386 inotify_add_watch sys_inotify_add_watch __ia32_sys_inotify_add_watch
+293 i386 inotify_rm_watch sys_inotify_rm_watch __ia32_sys_inotify_rm_watch
+294 i386 migrate_pages sys_migrate_pages __ia32_sys_migrate_pages
+295 i386 openat sys_openat __ia32_compat_sys_openat
+296 i386 mkdirat sys_mkdirat __ia32_sys_mkdirat
+297 i386 mknodat sys_mknodat __ia32_sys_mknodat
+298 i386 fchownat sys_fchownat __ia32_sys_fchownat
+299 i386 futimesat sys_futimesat __ia32_compat_sys_futimesat
+300 i386 fstatat64 sys_fstatat64 __ia32_compat_sys_x86_fstatat
+301 i386 unlinkat sys_unlinkat __ia32_sys_unlinkat
+302 i386 renameat sys_renameat __ia32_sys_renameat
+303 i386 linkat sys_linkat __ia32_sys_linkat
+304 i386 symlinkat sys_symlinkat __ia32_sys_symlinkat
+305 i386 readlinkat sys_readlinkat __ia32_sys_readlinkat
+306 i386 fchmodat sys_fchmodat __ia32_sys_fchmodat
+307 i386 faccessat sys_faccessat __ia32_sys_faccessat
+308 i386 pselect6 sys_pselect6 __ia32_compat_sys_pselect6
+309 i386 ppoll sys_ppoll __ia32_compat_sys_ppoll
+310 i386 unshare sys_unshare __ia32_sys_unshare
+311 i386 set_robust_list sys_set_robust_list __ia32_compat_sys_set_robust_list
+312 i386 get_robust_list sys_get_robust_list __ia32_compat_sys_get_robust_list
+313 i386 splice sys_splice __ia32_sys_splice
+314 i386 sync_file_range sys_sync_file_range __ia32_compat_sys_x86_sync_file_range
+315 i386 tee sys_tee __ia32_sys_tee
+316 i386 vmsplice sys_vmsplice __ia32_compat_sys_vmsplice
+317 i386 move_pages sys_move_pages __ia32_compat_sys_move_pages
+318 i386 getcpu sys_getcpu __ia32_sys_getcpu
+319 i386 epoll_pwait sys_epoll_pwait __ia32_sys_epoll_pwait
+320 i386 utimensat sys_utimensat __ia32_compat_sys_utimensat
+321 i386 signalfd sys_signalfd __ia32_compat_sys_signalfd
+322 i386 timerfd_create sys_timerfd_create __ia32_sys_timerfd_create
+323 i386 eventfd sys_eventfd __ia32_sys_eventfd
+324 i386 fallocate sys_fallocate __ia32_compat_sys_x86_fallocate
+325 i386 timerfd_settime sys_timerfd_settime __ia32_compat_sys_timerfd_settime
+326 i386 timerfd_gettime sys_timerfd_gettime __ia32_compat_sys_timerfd_gettime
+327 i386 signalfd4 sys_signalfd4 __ia32_compat_sys_signalfd4
+328 i386 eventfd2 sys_eventfd2 __ia32_sys_eventfd2
+329 i386 epoll_create1 sys_epoll_create1 __ia32_sys_epoll_create1
+330 i386 dup3 sys_dup3 __ia32_sys_dup3
+331 i386 pipe2 sys_pipe2 __ia32_sys_pipe2
+332 i386 inotify_init1 sys_inotify_init1 __ia32_sys_inotify_init1
+333 i386 preadv sys_preadv __ia32_compat_sys_preadv
+334 i386 pwritev sys_pwritev __ia32_compat_sys_pwritev
+335 i386 rt_tgsigqueueinfo sys_rt_tgsigqueueinfo __ia32_compat_sys_rt_tgsigqueueinfo
+336 i386 perf_event_open sys_perf_event_open __ia32_sys_perf_event_open
+337 i386 recvmmsg sys_recvmmsg __ia32_compat_sys_recvmmsg
+338 i386 fanotify_init sys_fanotify_init __ia32_sys_fanotify_init
+339 i386 fanotify_mark sys_fanotify_mark __ia32_compat_sys_fanotify_mark
+340 i386 prlimit64 sys_prlimit64 __ia32_sys_prlimit64
+341 i386 name_to_handle_at sys_name_to_handle_at __ia32_sys_name_to_handle_at
+342 i386 open_by_handle_at sys_open_by_handle_at __ia32_compat_sys_open_by_handle_at
+343 i386 clock_adjtime sys_clock_adjtime __ia32_compat_sys_clock_adjtime
+344 i386 syncfs sys_syncfs __ia32_sys_syncfs
+345 i386 sendmmsg sys_sendmmsg __ia32_compat_sys_sendmmsg
+346 i386 setns sys_setns __ia32_sys_setns
+347 i386 process_vm_readv sys_process_vm_readv __ia32_compat_sys_process_vm_readv
+348 i386 process_vm_writev sys_process_vm_writev __ia32_compat_sys_process_vm_writev
+349 i386 kcmp sys_kcmp __ia32_sys_kcmp
+350 i386 finit_module sys_finit_module __ia32_sys_finit_module
+351 i386 sched_setattr sys_sched_setattr __ia32_sys_sched_setattr
+352 i386 sched_getattr sys_sched_getattr __ia32_sys_sched_getattr
+353 i386 renameat2 sys_renameat2 __ia32_sys_renameat2
+354 i386 seccomp sys_seccomp __ia32_sys_seccomp
+355 i386 getrandom sys_getrandom __ia32_sys_getrandom
+356 i386 memfd_create sys_memfd_create __ia32_sys_memfd_create
+357 i386 bpf sys_bpf __ia32_sys_bpf
+358 i386 execveat sys_execveat __ia32_compat_sys_execveat
+359 i386 socket sys_socket __ia32_sys_socket
+360 i386 socketpair sys_socketpair __ia32_sys_socketpair
+361 i386 bind sys_bind __ia32_sys_bind
+362 i386 connect sys_connect __ia32_sys_connect
+363 i386 listen sys_listen __ia32_sys_listen
+364 i386 accept4 sys_accept4 __ia32_sys_accept4
+365 i386 getsockopt sys_getsockopt __ia32_compat_sys_getsockopt
+366 i386 setsockopt sys_setsockopt __ia32_compat_sys_setsockopt
+367 i386 getsockname sys_getsockname __ia32_sys_getsockname
+368 i386 getpeername sys_getpeername __ia32_sys_getpeername
+369 i386 sendto sys_sendto __ia32_sys_sendto
+370 i386 sendmsg sys_sendmsg __ia32_compat_sys_sendmsg
+371 i386 recvfrom sys_recvfrom __ia32_compat_sys_recvfrom
+372 i386 recvmsg sys_recvmsg __ia32_compat_sys_recvmsg
+373 i386 shutdown sys_shutdown __ia32_sys_shutdown
+374 i386 userfaultfd sys_userfaultfd __ia32_sys_userfaultfd
+375 i386 membarrier sys_membarrier __ia32_sys_membarrier
+376 i386 mlock2 sys_mlock2 __ia32_sys_mlock2
+377 i386 copy_file_range sys_copy_file_range __ia32_sys_copy_file_range
+378 i386 preadv2 sys_preadv2 __ia32_compat_sys_preadv2
+379 i386 pwritev2 sys_pwritev2 __ia32_compat_sys_pwritev2
+380 i386 pkey_mprotect sys_pkey_mprotect __ia32_sys_pkey_mprotect
+381 i386 pkey_alloc sys_pkey_alloc __ia32_sys_pkey_alloc
+382 i386 pkey_free sys_pkey_free __ia32_sys_pkey_free
+383 i386 statx sys_statx __ia32_sys_statx
+384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl
+385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents
+386 i386 rseq sys_rseq __ia32_sys_rseq
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
new file mode 100644
index 000000000..f0b1709a5
--- /dev/null
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -0,0 +1,388 @@
+#
+# 64-bit system call numbers and entry vectors
+#
+# The format is:
+# <number> <abi> <name> <entry point>
+#
+# The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
+#
+# The abi is "common", "64" or "x32" for this file.
+#
+0 common read __x64_sys_read
+1 common write __x64_sys_write
+2 common open __x64_sys_open
+3 common close __x64_sys_close
+4 common stat __x64_sys_newstat
+5 common fstat __x64_sys_newfstat
+6 common lstat __x64_sys_newlstat
+7 common poll __x64_sys_poll
+8 common lseek __x64_sys_lseek
+9 common mmap __x64_sys_mmap
+10 common mprotect __x64_sys_mprotect
+11 common munmap __x64_sys_munmap
+12 common brk __x64_sys_brk
+13 64 rt_sigaction __x64_sys_rt_sigaction
+14 common rt_sigprocmask __x64_sys_rt_sigprocmask
+15 64 rt_sigreturn __x64_sys_rt_sigreturn/ptregs
+16 64 ioctl __x64_sys_ioctl
+17 common pread64 __x64_sys_pread64
+18 common pwrite64 __x64_sys_pwrite64
+19 64 readv __x64_sys_readv
+20 64 writev __x64_sys_writev
+21 common access __x64_sys_access
+22 common pipe __x64_sys_pipe
+23 common select __x64_sys_select
+24 common sched_yield __x64_sys_sched_yield
+25 common mremap __x64_sys_mremap
+26 common msync __x64_sys_msync
+27 common mincore __x64_sys_mincore
+28 common madvise __x64_sys_madvise
+29 common shmget __x64_sys_shmget
+30 common shmat __x64_sys_shmat
+31 common shmctl __x64_sys_shmctl
+32 common dup __x64_sys_dup
+33 common dup2 __x64_sys_dup2
+34 common pause __x64_sys_pause
+35 common nanosleep __x64_sys_nanosleep
+36 common getitimer __x64_sys_getitimer
+37 common alarm __x64_sys_alarm
+38 common setitimer __x64_sys_setitimer
+39 common getpid __x64_sys_getpid
+40 common sendfile __x64_sys_sendfile64
+41 common socket __x64_sys_socket
+42 common connect __x64_sys_connect
+43 common accept __x64_sys_accept
+44 common sendto __x64_sys_sendto
+45 64 recvfrom __x64_sys_recvfrom
+46 64 sendmsg __x64_sys_sendmsg
+47 64 recvmsg __x64_sys_recvmsg
+48 common shutdown __x64_sys_shutdown
+49 common bind __x64_sys_bind
+50 common listen __x64_sys_listen
+51 common getsockname __x64_sys_getsockname
+52 common getpeername __x64_sys_getpeername
+53 common socketpair __x64_sys_socketpair
+54 64 setsockopt __x64_sys_setsockopt
+55 64 getsockopt __x64_sys_getsockopt
+56 common clone __x64_sys_clone/ptregs
+57 common fork __x64_sys_fork/ptregs
+58 common vfork __x64_sys_vfork/ptregs
+59 64 execve __x64_sys_execve/ptregs
+60 common exit __x64_sys_exit
+61 common wait4 __x64_sys_wait4
+62 common kill __x64_sys_kill
+63 common uname __x64_sys_newuname
+64 common semget __x64_sys_semget
+65 common semop __x64_sys_semop
+66 common semctl __x64_sys_semctl
+67 common shmdt __x64_sys_shmdt
+68 common msgget __x64_sys_msgget
+69 common msgsnd __x64_sys_msgsnd
+70 common msgrcv __x64_sys_msgrcv
+71 common msgctl __x64_sys_msgctl
+72 common fcntl __x64_sys_fcntl
+73 common flock __x64_sys_flock
+74 common fsync __x64_sys_fsync
+75 common fdatasync __x64_sys_fdatasync
+76 common truncate __x64_sys_truncate
+77 common ftruncate __x64_sys_ftruncate
+78 common getdents __x64_sys_getdents
+79 common getcwd __x64_sys_getcwd
+80 common chdir __x64_sys_chdir
+81 common fchdir __x64_sys_fchdir
+82 common rename __x64_sys_rename
+83 common mkdir __x64_sys_mkdir
+84 common rmdir __x64_sys_rmdir
+85 common creat __x64_sys_creat
+86 common link __x64_sys_link
+87 common unlink __x64_sys_unlink
+88 common symlink __x64_sys_symlink
+89 common readlink __x64_sys_readlink
+90 common chmod __x64_sys_chmod
+91 common fchmod __x64_sys_fchmod
+92 common chown __x64_sys_chown
+93 common fchown __x64_sys_fchown
+94 common lchown __x64_sys_lchown
+95 common umask __x64_sys_umask
+96 common gettimeofday __x64_sys_gettimeofday
+97 common getrlimit __x64_sys_getrlimit
+98 common getrusage __x64_sys_getrusage
+99 common sysinfo __x64_sys_sysinfo
+100 common times __x64_sys_times
+101 64 ptrace __x64_sys_ptrace
+102 common getuid __x64_sys_getuid
+103 common syslog __x64_sys_syslog
+104 common getgid __x64_sys_getgid
+105 common setuid __x64_sys_setuid
+106 common setgid __x64_sys_setgid
+107 common geteuid __x64_sys_geteuid
+108 common getegid __x64_sys_getegid
+109 common setpgid __x64_sys_setpgid
+110 common getppid __x64_sys_getppid
+111 common getpgrp __x64_sys_getpgrp
+112 common setsid __x64_sys_setsid
+113 common setreuid __x64_sys_setreuid
+114 common setregid __x64_sys_setregid
+115 common getgroups __x64_sys_getgroups
+116 common setgroups __x64_sys_setgroups
+117 common setresuid __x64_sys_setresuid
+118 common getresuid __x64_sys_getresuid
+119 common setresgid __x64_sys_setresgid
+120 common getresgid __x64_sys_getresgid
+121 common getpgid __x64_sys_getpgid
+122 common setfsuid __x64_sys_setfsuid
+123 common setfsgid __x64_sys_setfsgid
+124 common getsid __x64_sys_getsid
+125 common capget __x64_sys_capget
+126 common capset __x64_sys_capset
+127 64 rt_sigpending __x64_sys_rt_sigpending
+128 64 rt_sigtimedwait __x64_sys_rt_sigtimedwait
+129 64 rt_sigqueueinfo __x64_sys_rt_sigqueueinfo
+130 common rt_sigsuspend __x64_sys_rt_sigsuspend
+131 64 sigaltstack __x64_sys_sigaltstack
+132 common utime __x64_sys_utime
+133 common mknod __x64_sys_mknod
+134 64 uselib
+135 common personality __x64_sys_personality
+136 common ustat __x64_sys_ustat
+137 common statfs __x64_sys_statfs
+138 common fstatfs __x64_sys_fstatfs
+139 common sysfs __x64_sys_sysfs
+140 common getpriority __x64_sys_getpriority
+141 common setpriority __x64_sys_setpriority
+142 common sched_setparam __x64_sys_sched_setparam
+143 common sched_getparam __x64_sys_sched_getparam
+144 common sched_setscheduler __x64_sys_sched_setscheduler
+145 common sched_getscheduler __x64_sys_sched_getscheduler
+146 common sched_get_priority_max __x64_sys_sched_get_priority_max
+147 common sched_get_priority_min __x64_sys_sched_get_priority_min
+148 common sched_rr_get_interval __x64_sys_sched_rr_get_interval
+149 common mlock __x64_sys_mlock
+150 common munlock __x64_sys_munlock
+151 common mlockall __x64_sys_mlockall
+152 common munlockall __x64_sys_munlockall
+153 common vhangup __x64_sys_vhangup
+154 common modify_ldt __x64_sys_modify_ldt
+155 common pivot_root __x64_sys_pivot_root
+156 64 _sysctl __x64_sys_sysctl
+157 common prctl __x64_sys_prctl
+158 common arch_prctl __x64_sys_arch_prctl
+159 common adjtimex __x64_sys_adjtimex
+160 common setrlimit __x64_sys_setrlimit
+161 common chroot __x64_sys_chroot
+162 common sync __x64_sys_sync
+163 common acct __x64_sys_acct
+164 common settimeofday __x64_sys_settimeofday
+165 common mount __x64_sys_mount
+166 common umount2 __x64_sys_umount
+167 common swapon __x64_sys_swapon
+168 common swapoff __x64_sys_swapoff
+169 common reboot __x64_sys_reboot
+170 common sethostname __x64_sys_sethostname
+171 common setdomainname __x64_sys_setdomainname
+172 common iopl __x64_sys_iopl/ptregs
+173 common ioperm __x64_sys_ioperm
+174 64 create_module
+175 common init_module __x64_sys_init_module
+176 common delete_module __x64_sys_delete_module
+177 64 get_kernel_syms
+178 64 query_module
+179 common quotactl __x64_sys_quotactl
+180 64 nfsservctl
+181 common getpmsg
+182 common putpmsg
+183 common afs_syscall
+184 common tuxcall
+185 common security
+186 common gettid __x64_sys_gettid
+187 common readahead __x64_sys_readahead
+188 common setxattr __x64_sys_setxattr
+189 common lsetxattr __x64_sys_lsetxattr
+190 common fsetxattr __x64_sys_fsetxattr
+191 common getxattr __x64_sys_getxattr
+192 common lgetxattr __x64_sys_lgetxattr
+193 common fgetxattr __x64_sys_fgetxattr
+194 common listxattr __x64_sys_listxattr
+195 common llistxattr __x64_sys_llistxattr
+196 common flistxattr __x64_sys_flistxattr
+197 common removexattr __x64_sys_removexattr
+198 common lremovexattr __x64_sys_lremovexattr
+199 common fremovexattr __x64_sys_fremovexattr
+200 common tkill __x64_sys_tkill
+201 common time __x64_sys_time
+202 common futex __x64_sys_futex
+203 common sched_setaffinity __x64_sys_sched_setaffinity
+204 common sched_getaffinity __x64_sys_sched_getaffinity
+205 64 set_thread_area
+206 64 io_setup __x64_sys_io_setup
+207 common io_destroy __x64_sys_io_destroy
+208 common io_getevents __x64_sys_io_getevents
+209 64 io_submit __x64_sys_io_submit
+210 common io_cancel __x64_sys_io_cancel
+211 64 get_thread_area
+212 common lookup_dcookie __x64_sys_lookup_dcookie
+213 common epoll_create __x64_sys_epoll_create
+214 64 epoll_ctl_old
+215 64 epoll_wait_old
+216 common remap_file_pages __x64_sys_remap_file_pages
+217 common getdents64 __x64_sys_getdents64
+218 common set_tid_address __x64_sys_set_tid_address
+219 common restart_syscall __x64_sys_restart_syscall
+220 common semtimedop __x64_sys_semtimedop
+221 common fadvise64 __x64_sys_fadvise64
+222 64 timer_create __x64_sys_timer_create
+223 common timer_settime __x64_sys_timer_settime
+224 common timer_gettime __x64_sys_timer_gettime
+225 common timer_getoverrun __x64_sys_timer_getoverrun
+226 common timer_delete __x64_sys_timer_delete
+227 common clock_settime __x64_sys_clock_settime
+228 common clock_gettime __x64_sys_clock_gettime
+229 common clock_getres __x64_sys_clock_getres
+230 common clock_nanosleep __x64_sys_clock_nanosleep
+231 common exit_group __x64_sys_exit_group
+232 common epoll_wait __x64_sys_epoll_wait
+233 common epoll_ctl __x64_sys_epoll_ctl
+234 common tgkill __x64_sys_tgkill
+235 common utimes __x64_sys_utimes
+236 64 vserver
+237 common mbind __x64_sys_mbind
+238 common set_mempolicy __x64_sys_set_mempolicy
+239 common get_mempolicy __x64_sys_get_mempolicy
+240 common mq_open __x64_sys_mq_open
+241 common mq_unlink __x64_sys_mq_unlink
+242 common mq_timedsend __x64_sys_mq_timedsend
+243 common mq_timedreceive __x64_sys_mq_timedreceive
+244 64 mq_notify __x64_sys_mq_notify
+245 common mq_getsetattr __x64_sys_mq_getsetattr
+246 64 kexec_load __x64_sys_kexec_load
+247 64 waitid __x64_sys_waitid
+248 common add_key __x64_sys_add_key
+249 common request_key __x64_sys_request_key
+250 common keyctl __x64_sys_keyctl
+251 common ioprio_set __x64_sys_ioprio_set
+252 common ioprio_get __x64_sys_ioprio_get
+253 common inotify_init __x64_sys_inotify_init
+254 common inotify_add_watch __x64_sys_inotify_add_watch
+255 common inotify_rm_watch __x64_sys_inotify_rm_watch
+256 common migrate_pages __x64_sys_migrate_pages
+257 common openat __x64_sys_openat
+258 common mkdirat __x64_sys_mkdirat
+259 common mknodat __x64_sys_mknodat
+260 common fchownat __x64_sys_fchownat
+261 common futimesat __x64_sys_futimesat
+262 common newfstatat __x64_sys_newfstatat
+263 common unlinkat __x64_sys_unlinkat
+264 common renameat __x64_sys_renameat
+265 common linkat __x64_sys_linkat
+266 common symlinkat __x64_sys_symlinkat
+267 common readlinkat __x64_sys_readlinkat
+268 common fchmodat __x64_sys_fchmodat
+269 common faccessat __x64_sys_faccessat
+270 common pselect6 __x64_sys_pselect6
+271 common ppoll __x64_sys_ppoll
+272 common unshare __x64_sys_unshare
+273 64 set_robust_list __x64_sys_set_robust_list
+274 64 get_robust_list __x64_sys_get_robust_list
+275 common splice __x64_sys_splice
+276 common tee __x64_sys_tee
+277 common sync_file_range __x64_sys_sync_file_range
+278 64 vmsplice __x64_sys_vmsplice
+279 64 move_pages __x64_sys_move_pages
+280 common utimensat __x64_sys_utimensat
+281 common epoll_pwait __x64_sys_epoll_pwait
+282 common signalfd __x64_sys_signalfd
+283 common timerfd_create __x64_sys_timerfd_create
+284 common eventfd __x64_sys_eventfd
+285 common fallocate __x64_sys_fallocate
+286 common timerfd_settime __x64_sys_timerfd_settime
+287 common timerfd_gettime __x64_sys_timerfd_gettime
+288 common accept4 __x64_sys_accept4
+289 common signalfd4 __x64_sys_signalfd4
+290 common eventfd2 __x64_sys_eventfd2
+291 common epoll_create1 __x64_sys_epoll_create1
+292 common dup3 __x64_sys_dup3
+293 common pipe2 __x64_sys_pipe2
+294 common inotify_init1 __x64_sys_inotify_init1
+295 64 preadv __x64_sys_preadv
+296 64 pwritev __x64_sys_pwritev
+297 64 rt_tgsigqueueinfo __x64_sys_rt_tgsigqueueinfo
+298 common perf_event_open __x64_sys_perf_event_open
+299 64 recvmmsg __x64_sys_recvmmsg
+300 common fanotify_init __x64_sys_fanotify_init
+301 common fanotify_mark __x64_sys_fanotify_mark
+302 common prlimit64 __x64_sys_prlimit64
+303 common name_to_handle_at __x64_sys_name_to_handle_at
+304 common open_by_handle_at __x64_sys_open_by_handle_at
+305 common clock_adjtime __x64_sys_clock_adjtime
+306 common syncfs __x64_sys_syncfs
+307 64 sendmmsg __x64_sys_sendmmsg
+308 common setns __x64_sys_setns
+309 common getcpu __x64_sys_getcpu
+310 64 process_vm_readv __x64_sys_process_vm_readv
+311 64 process_vm_writev __x64_sys_process_vm_writev
+312 common kcmp __x64_sys_kcmp
+313 common finit_module __x64_sys_finit_module
+314 common sched_setattr __x64_sys_sched_setattr
+315 common sched_getattr __x64_sys_sched_getattr
+316 common renameat2 __x64_sys_renameat2
+317 common seccomp __x64_sys_seccomp
+318 common getrandom __x64_sys_getrandom
+319 common memfd_create __x64_sys_memfd_create
+320 common kexec_file_load __x64_sys_kexec_file_load
+321 common bpf __x64_sys_bpf
+322 64 execveat __x64_sys_execveat/ptregs
+323 common userfaultfd __x64_sys_userfaultfd
+324 common membarrier __x64_sys_membarrier
+325 common mlock2 __x64_sys_mlock2
+326 common copy_file_range __x64_sys_copy_file_range
+327 64 preadv2 __x64_sys_preadv2
+328 64 pwritev2 __x64_sys_pwritev2
+329 common pkey_mprotect __x64_sys_pkey_mprotect
+330 common pkey_alloc __x64_sys_pkey_alloc
+331 common pkey_free __x64_sys_pkey_free
+332 common statx __x64_sys_statx
+333 common io_pgetevents __x64_sys_io_pgetevents
+334 common rseq __x64_sys_rseq
+
+#
+# x32-specific system call numbers start at 512 to avoid cache impact
+# for native 64-bit operation. The __x32_compat_sys stubs are created
+# on-the-fly for compat_sys_*() compatibility system calls if X86_X32
+# is defined.
+#
+512 x32 rt_sigaction __x32_compat_sys_rt_sigaction
+513 x32 rt_sigreturn sys32_x32_rt_sigreturn
+514 x32 ioctl __x32_compat_sys_ioctl
+515 x32 readv __x32_compat_sys_readv
+516 x32 writev __x32_compat_sys_writev
+517 x32 recvfrom __x32_compat_sys_recvfrom
+518 x32 sendmsg __x32_compat_sys_sendmsg
+519 x32 recvmsg __x32_compat_sys_recvmsg
+520 x32 execve __x32_compat_sys_execve/ptregs
+521 x32 ptrace __x32_compat_sys_ptrace
+522 x32 rt_sigpending __x32_compat_sys_rt_sigpending
+523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait
+524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo
+525 x32 sigaltstack __x32_compat_sys_sigaltstack
+526 x32 timer_create __x32_compat_sys_timer_create
+527 x32 mq_notify __x32_compat_sys_mq_notify
+528 x32 kexec_load __x32_compat_sys_kexec_load
+529 x32 waitid __x32_compat_sys_waitid
+530 x32 set_robust_list __x32_compat_sys_set_robust_list
+531 x32 get_robust_list __x32_compat_sys_get_robust_list
+532 x32 vmsplice __x32_compat_sys_vmsplice
+533 x32 move_pages __x32_compat_sys_move_pages
+534 x32 preadv __x32_compat_sys_preadv64
+535 x32 pwritev __x32_compat_sys_pwritev64
+536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo
+537 x32 recvmmsg __x32_compat_sys_recvmmsg
+538 x32 sendmmsg __x32_compat_sys_sendmmsg
+539 x32 process_vm_readv __x32_compat_sys_process_vm_readv
+540 x32 process_vm_writev __x32_compat_sys_process_vm_writev
+541 x32 setsockopt __x32_compat_sys_setsockopt
+542 x32 getsockopt __x32_compat_sys_getsockopt
+543 x32 io_setup __x32_compat_sys_io_setup
+544 x32 io_submit __x32_compat_sys_io_submit
+545 x32 execveat __x32_compat_sys_execveat/ptregs
+546 x32 preadv2 __x32_compat_sys_preadv64v2
+547 x32 pwritev2 __x32_compat_sys_pwritev64v2
diff --git a/arch/x86/entry/syscalls/syscallhdr.sh b/arch/x86/entry/syscalls/syscallhdr.sh
new file mode 100644
index 000000000..12fbbcfe7
--- /dev/null
+++ b/arch/x86/entry/syscalls/syscallhdr.sh
@@ -0,0 +1,28 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+in="$1"
+out="$2"
+my_abis=`echo "($3)" | tr ',' '|'`
+prefix="$4"
+offset="$5"
+
+fileguard=_ASM_X86_`basename "$out" | sed \
+ -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
+ -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
+grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
+ echo "#ifndef ${fileguard}"
+ echo "#define ${fileguard} 1"
+ echo ""
+
+ while read nr abi name entry ; do
+ if [ -z "$offset" ]; then
+ echo "#define __NR_${prefix}${name} $nr"
+ else
+ echo "#define __NR_${prefix}${name} ($offset + $nr)"
+ fi
+ done
+
+ echo ""
+ echo "#endif /* ${fileguard} */"
+) > "$out"
diff --git a/arch/x86/entry/syscalls/syscalltbl.sh b/arch/x86/entry/syscalls/syscalltbl.sh
new file mode 100644
index 000000000..94fcd1951
--- /dev/null
+++ b/arch/x86/entry/syscalls/syscalltbl.sh
@@ -0,0 +1,81 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+in="$1"
+out="$2"
+
+syscall_macro() {
+ abi="$1"
+ nr="$2"
+ entry="$3"
+
+ # Entry can be either just a function name or "function/qualifier"
+ real_entry="${entry%%/*}"
+ if [ "$entry" = "$real_entry" ]; then
+ qualifier=
+ else
+ qualifier=${entry#*/}
+ fi
+
+ echo "__SYSCALL_${abi}($nr, $real_entry, $qualifier)"
+}
+
+emit() {
+ abi="$1"
+ nr="$2"
+ entry="$3"
+ compat="$4"
+ umlentry=""
+
+ if [ "$abi" = "64" -a -n "$compat" ]; then
+ echo "a compat entry for a 64-bit syscall makes no sense" >&2
+ exit 1
+ fi
+
+ # For CONFIG_UML, we need to strip the __x64_sys prefix
+ if [ "$abi" = "64" -a "${entry}" != "${entry#__x64_sys}" ]; then
+ umlentry="sys${entry#__x64_sys}"
+ fi
+
+ if [ -z "$compat" ]; then
+ if [ -n "$entry" -a -z "$umlentry" ]; then
+ syscall_macro "$abi" "$nr" "$entry"
+ elif [ -n "$umlentry" ]; then # implies -n "$entry"
+ echo "#ifdef CONFIG_X86"
+ syscall_macro "$abi" "$nr" "$entry"
+ echo "#else /* CONFIG_UML */"
+ syscall_macro "$abi" "$nr" "$umlentry"
+ echo "#endif"
+ fi
+ else
+ echo "#ifdef CONFIG_X86_32"
+ if [ -n "$entry" ]; then
+ syscall_macro "$abi" "$nr" "$entry"
+ fi
+ echo "#else"
+ syscall_macro "$abi" "$nr" "$compat"
+ echo "#endif"
+ fi
+}
+
+grep '^[0-9]' "$in" | sort -n | (
+ while read nr abi name entry compat; do
+ abi=`echo "$abi" | tr '[a-z]' '[A-Z]'`
+ if [ "$abi" = "COMMON" -o "$abi" = "64" ]; then
+ # COMMON is the same as 64, except that we don't expect X32
+ # programs to use it. Our expectation has nothing to do with
+ # any generated code, so treat them the same.
+ emit 64 "$nr" "$entry" "$compat"
+ elif [ "$abi" = "X32" ]; then
+ # X32 is equivalent to 64 on an X32-compatible kernel.
+ echo "#ifdef CONFIG_X86_X32_ABI"
+ emit 64 "$nr" "$entry" "$compat"
+ echo "#endif"
+ elif [ "$abi" = "I386" ]; then
+ emit "$abi" "$nr" "$entry" "$compat"
+ else
+ echo "Unknown abi $abi" >&2
+ exit 1
+ fi
+ done
+) > "$out"
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
new file mode 100644
index 000000000..fee6bc79b
--- /dev/null
+++ b/arch/x86/entry/thunk_32.S
@@ -0,0 +1,43 @@
+/*
+ * Trampoline to trace irqs off. (otherwise CALLER_ADDR1 might crash)
+ * Copyright 2008 by Steven Rostedt, Red Hat, Inc
+ * (inspired by Andi Kleen's thunk_64.S)
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+ #include <linux/linkage.h>
+ #include <asm/asm.h>
+ #include <asm/export.h>
+
+ /* put return address in eax (arg1) */
+ .macro THUNK name, func, put_ret_addr_in_eax=0
+ .globl \name
+\name:
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+
+ .if \put_ret_addr_in_eax
+ /* Place EIP in the arg1 */
+ movl 3*4(%esp), %eax
+ .endif
+
+ call \func
+ popl %edx
+ popl %ecx
+ popl %eax
+ ret
+ _ASM_NOKPROBE(\name)
+ .endm
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+ THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+ THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
+ EXPORT_SYMBOL(___preempt_schedule)
+ EXPORT_SYMBOL(___preempt_schedule_notrace)
+#endif
+
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
new file mode 100644
index 000000000..be36bf4e0
--- /dev/null
+++ b/arch/x86/entry/thunk_64.S
@@ -0,0 +1,73 @@
+/*
+ * Save registers before calling assembly functions. This avoids
+ * disturbance of register allocation in some inline assembly constructs.
+ * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
+ * Added trace_hardirqs callers - Copyright 2007 Steven Rostedt, Red Hat, Inc.
+ * Subject to the GNU public license, v.2. No warranty of any kind.
+ */
+#include <linux/linkage.h>
+#include "calling.h"
+#include <asm/asm.h>
+#include <asm/export.h>
+
+ /* rdi: arg1 ... normal C conventions. rax is saved/restored. */
+ .macro THUNK name, func, put_ret_addr_in_rdi=0
+ .globl \name
+ .type \name, @function
+\name:
+ pushq %rbp
+ movq %rsp, %rbp
+
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %rax
+ pushq %r8
+ pushq %r9
+ pushq %r10
+ pushq %r11
+
+ .if \put_ret_addr_in_rdi
+ /* 8(%rbp) is return addr on stack */
+ movq 8(%rbp), %rdi
+ .endif
+
+ call \func
+ jmp .L_restore
+ _ASM_NOKPROBE(\name)
+ .endm
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+ THUNK trace_hardirqs_on_thunk,trace_hardirqs_on_caller,1
+ THUNK trace_hardirqs_off_thunk,trace_hardirqs_off_caller,1
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ THUNK lockdep_sys_exit_thunk,lockdep_sys_exit
+#endif
+
+#ifdef CONFIG_PREEMPT
+ THUNK ___preempt_schedule, preempt_schedule
+ THUNK ___preempt_schedule_notrace, preempt_schedule_notrace
+ EXPORT_SYMBOL(___preempt_schedule)
+ EXPORT_SYMBOL(___preempt_schedule_notrace)
+#endif
+
+#if defined(CONFIG_TRACE_IRQFLAGS) \
+ || defined(CONFIG_DEBUG_LOCK_ALLOC) \
+ || defined(CONFIG_PREEMPT)
+.L_restore:
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
+ popq %rbp
+ ret
+ _ASM_NOKPROBE(.L_restore)
+#endif
diff --git a/arch/x86/entry/vdso/.gitignore b/arch/x86/entry/vdso/.gitignore
new file mode 100644
index 000000000..aae8ffdd5
--- /dev/null
+++ b/arch/x86/entry/vdso/.gitignore
@@ -0,0 +1,7 @@
+vdso.lds
+vdsox32.lds
+vdso32-syscall-syms.lds
+vdso32-sysenter-syms.lds
+vdso32-int80-syms.lds
+vdso-image-*.c
+vdso2c
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
new file mode 100644
index 000000000..5bfe2243a
--- /dev/null
+++ b/arch/x86/entry/vdso/Makefile
@@ -0,0 +1,205 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Building vDSO images for x86.
+#
+
+KBUILD_CFLAGS += $(DISABLE_LTO)
+KASAN_SANITIZE := n
+UBSAN_SANITIZE := n
+OBJECT_FILES_NON_STANDARD := y
+
+# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
+KCOV_INSTRUMENT := n
+
+VDSO64-$(CONFIG_X86_64) := y
+VDSOX32-$(CONFIG_X86_X32_ABI) := y
+VDSO32-$(CONFIG_X86_32) := y
+VDSO32-$(CONFIG_IA32_EMULATION) := y
+
+# files to link into the vdso
+vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
+
+# files to link into kernel
+obj-y += vma.o
+OBJECT_FILES_NON_STANDARD_vma.o := n
+
+# vDSO images to build
+vdso_img-$(VDSO64-y) += 64
+vdso_img-$(VDSOX32-y) += x32
+vdso_img-$(VDSO32-y) += 32
+
+obj-$(VDSO32-y) += vdso32-setup.o
+
+vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
+
+$(obj)/vdso.o: $(obj)/vdso.so
+
+targets += vdso.lds $(vobjs-y)
+
+# Build the vDSO image C files and link them in.
+vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
+vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
+vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
+obj-y += $(vdso_img_objs)
+targets += $(vdso_img_cfiles)
+targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
+
+CPPFLAGS_vdso.lds += -P -C
+
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+ -z max-page-size=4096
+
+$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
+ $(call if_changed,vdso)
+
+HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/$(SUBARCH)/include/uapi
+hostprogs-y += vdso2c
+
+quiet_cmd_vdso2c = VDSO2C $@
+ cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@
+
+$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ $(call if_changed,vdso2c)
+
+#
+# Don't omit frame pointers for ease of userspace debugging, but do
+# optimize sibling calls.
+#
+CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+ CFL += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+
+#
+# vDSO code runs in userspace and -pg doesn't help with profiling anyway.
+#
+CFLAGS_REMOVE_vdso-note.o = -pg
+CFLAGS_REMOVE_vclock_gettime.o = -pg
+CFLAGS_REMOVE_vgetcpu.o = -pg
+CFLAGS_REMOVE_vvar.o = -pg
+
+#
+# X32 processes use x32 vDSO to access 64bit kernel data.
+#
+# Build x32 vDSO image:
+# 1. Compile x32 vDSO as 64bit.
+# 2. Convert object files to x32.
+# 3. Build x32 VDSO image with x32 objects, which contains 64bit codes
+# so that it can reach 64bit address space with 64bit pointers.
+#
+
+CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
+ -z max-page-size=4096
+
+# x32-rebranded versions
+vobjx32s-y := $(vobjs-y:.o=-x32.o)
+
+# same thing, but in the output directory
+vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
+
+# Convert 64bit object file to x32 for x32 vDSO.
+quiet_cmd_x32 = X32 $@
+ cmd_x32 = $(OBJCOPY) -O elf32-x86-64 $< $@
+
+$(obj)/%-x32.o: $(obj)/%.o FORCE
+ $(call if_changed,x32)
+
+targets += vdsox32.lds $(vobjx32s-y)
+
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg
+ $(call if_changed,objcopy)
+
+$(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
+ $(call if_changed,vdso)
+
+CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
+VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
+
+targets += vdso32/vdso32.lds
+targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
+targets += vdso32/vclock_gettime.o
+
+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))
+KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
+KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
+KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
+KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+ KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
+$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+
+$(obj)/vdso32.so.dbg: FORCE \
+ $(obj)/vdso32/vdso32.lds \
+ $(obj)/vdso32/vclock_gettime.o \
+ $(obj)/vdso32/note.o \
+ $(obj)/vdso32/system_call.o \
+ $(obj)/vdso32/sigreturn.o
+ $(call if_changed,vdso)
+
+#
+# The DSO images are built using a special linker script.
+#
+quiet_cmd_vdso = VDSO $@
+ cmd_vdso = $(LD) -nostdlib -o $@ \
+ $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
+ -T $(filter %.lds,$^) $(filter %.o,$^) && \
+ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
+
+VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \
+ $(call ld-option, --build-id) $(call ld-option, --eh-frame-hdr) \
+ -Bsymbolic
+GCOV_PROFILE := n
+
+#
+# Install the unstripped copies of vdso*.so. If our toolchain supports
+# build-id, install .build-id links as well.
+#
+quiet_cmd_vdso_install = INSTALL $(@:install_%=%)
+define cmd_vdso_install
+ cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \
+ if readelf -n $< |grep -q 'Build ID'; then \
+ buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \
+ first=`echo $$buildid | cut -b-2`; \
+ last=`echo $$buildid | cut -b3-`; \
+ mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \
+ ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \
+ fi
+endef
+
+vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%)
+
+$(MODLIB)/vdso: FORCE
+ @mkdir -p $(MODLIB)/vdso
+
+$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso
+ $(call cmd,vdso_install)
+
+PHONY += vdso_install $(vdso_img_insttargets)
+vdso_install: $(vdso_img_insttargets)
+
+clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so*
diff --git a/arch/x86/entry/vdso/checkundef.sh b/arch/x86/entry/vdso/checkundef.sh
new file mode 100755
index 000000000..7ee90a9b5
--- /dev/null
+++ b/arch/x86/entry/vdso/checkundef.sh
@@ -0,0 +1,10 @@
+#!/bin/sh
+nm="$1"
+file="$2"
+$nm "$file" | grep '^ *U' > /dev/null 2>&1
+if [ $? -eq 1 ]; then
+ exit 0
+else
+ echo "$file: undefined symbols found" >&2
+ exit 1
+fi
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
new file mode 100644
index 000000000..8a88e738f
--- /dev/null
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of clock_gettime, gettimeofday, and time.
+ *
+ * 32 Bit compat layer by Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
+ * The code should have no internal unresolved relocations.
+ * Check with readelf after changing.
+ */
+
+#include <uapi/linux/time.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+#include <asm/unistd.h>
+#include <asm/msr.h>
+#include <asm/pvclock.h>
+#include <asm/mshyperv.h>
+#include <linux/math64.h>
+#include <linux/time.h>
+#include <linux/kernel.h>
+
+#define gtod (&VVAR(vsyscall_gtod_data))
+
+extern int __vdso_clock_gettime(clockid_t clock, struct timespec *ts);
+extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
+extern time_t __vdso_time(time_t *t);
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+extern u8 pvclock_page[PAGE_SIZE]
+ __attribute__((visibility("hidden")));
+#endif
+
+#ifdef CONFIG_HYPERV_TSCPAGE
+extern u8 hvclock_page[PAGE_SIZE]
+ __attribute__((visibility("hidden")));
+#endif
+
+#ifndef BUILD_VDSO32
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+ long ret;
+ asm ("syscall" : "=a" (ret), "=m" (*ts) :
+ "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
+ "memory", "rcx", "r11");
+ return ret;
+}
+
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+ long ret;
+
+ asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) :
+ "0" (__NR_gettimeofday), "D" (tv), "S" (tz) :
+ "memory", "rcx", "r11");
+ return ret;
+}
+
+
+#else
+
+notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[clock], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*ts)
+ : "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
+ : "memory", "edx");
+ return ret;
+}
+
+notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
+{
+ long ret;
+
+ asm (
+ "mov %%ebx, %%edx \n"
+ "mov %[tv], %%ebx \n"
+ "call __kernel_vsyscall \n"
+ "mov %%edx, %%ebx \n"
+ : "=a" (ret), "=m" (*tv), "=m" (*tz)
+ : "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
+ : "memory", "edx");
+ return ret;
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT_CLOCK
+static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void)
+{
+ return (const struct pvclock_vsyscall_time_info *)&pvclock_page;
+}
+
+static notrace u64 vread_pvclock(int *mode)
+{
+ const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti;
+ u64 ret;
+ u64 last;
+ u32 version;
+
+ /*
+ * Note: The kernel and hypervisor must guarantee that cpu ID
+ * number maps 1:1 to per-CPU pvclock time info.
+ *
+ * Because the hypervisor is entirely unaware of guest userspace
+ * preemption, it cannot guarantee that per-CPU pvclock time
+ * info is updated if the underlying CPU changes or that that
+ * version is increased whenever underlying CPU changes.
+ *
+ * On KVM, we are guaranteed that pvti updates for any vCPU are
+ * atomic as seen by *all* vCPUs. This is an even stronger
+ * guarantee than we get with a normal seqlock.
+ *
+ * On Xen, we don't appear to have that guarantee, but Xen still
+ * supplies a valid seqlock using the version field.
+ *
+ * We only do pvclock vdso timing at all if
+ * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to
+ * mean that all vCPUs have matching pvti and that the TSC is
+ * synced, so we can just look at vCPU 0's pvti.
+ */
+
+ do {
+ version = pvclock_read_begin(pvti);
+
+ if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) {
+ *mode = VCLOCK_NONE;
+ return 0;
+ }
+
+ ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
+ } while (pvclock_read_retry(pvti, version));
+
+ /* refer to vread_tsc() comment for rationale */
+ last = gtod->cycle_last;
+
+ if (likely(ret >= last))
+ return ret;
+
+ return last;
+}
+#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+static notrace u64 vread_hvclock(int *mode)
+{
+ const struct ms_hyperv_tsc_page *tsc_pg =
+ (const struct ms_hyperv_tsc_page *)&hvclock_page;
+ u64 current_tick = hv_read_tsc_page(tsc_pg);
+
+ if (current_tick != U64_MAX)
+ return current_tick;
+
+ *mode = VCLOCK_NONE;
+ return 0;
+}
+#endif
+
+notrace static u64 vread_tsc(void)
+{
+ u64 ret = (u64)rdtsc_ordered();
+ u64 last = gtod->cycle_last;
+
+ if (likely(ret >= last))
+ return ret;
+
+ /*
+ * GCC likes to generate cmov here, but this branch is extremely
+ * predictable (it's just a function of time and the likely is
+ * very likely) and there's a data dependence, so force GCC
+ * to generate a branch instead. I don't barrier() because
+ * we don't actually need a barrier, and if this function
+ * ever gets inlined it will generate worse code.
+ */
+ asm volatile ("");
+ return last;
+}
+
+notrace static inline u64 vgetsns(int *mode)
+{
+ u64 v;
+ cycles_t cycles;
+
+ if (gtod->vclock_mode == VCLOCK_TSC)
+ cycles = vread_tsc();
+
+ /*
+ * For any memory-mapped vclock type, we need to make sure that gcc
+ * doesn't cleverly hoist a load before the mode check. Otherwise we
+ * might end up touching the memory-mapped page even if the vclock in
+ * question isn't enabled, which will segfault. Hence the barriers.
+ */
+#ifdef CONFIG_PARAVIRT_CLOCK
+ else if (gtod->vclock_mode == VCLOCK_PVCLOCK) {
+ barrier();
+ cycles = vread_pvclock(mode);
+ }
+#endif
+#ifdef CONFIG_HYPERV_TSCPAGE
+ else if (gtod->vclock_mode == VCLOCK_HVCLOCK) {
+ barrier();
+ cycles = vread_hvclock(mode);
+ }
+#endif
+ else
+ return 0;
+ v = (cycles - gtod->cycle_last) & gtod->mask;
+ return v * gtod->mult;
+}
+
+/* Code size doesn't matter (vdso is 4k anyway) and this is faster. */
+notrace static int __always_inline do_realtime(struct timespec *ts)
+{
+ unsigned long seq;
+ u64 ns;
+ int mode;
+
+ do {
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
+ ts->tv_sec = gtod->wall_time_sec;
+ ns = gtod->wall_time_snsec;
+ ns += vgetsns(&mode);
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
+
+ return mode;
+}
+
+notrace static int __always_inline do_monotonic(struct timespec *ts)
+{
+ unsigned long seq;
+ u64 ns;
+ int mode;
+
+ do {
+ seq = gtod_read_begin(gtod);
+ mode = gtod->vclock_mode;
+ ts->tv_sec = gtod->monotonic_time_sec;
+ ns = gtod->monotonic_time_snsec;
+ ns += vgetsns(&mode);
+ ns >>= gtod->shift;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+
+ ts->tv_sec += __iter_div_u64_rem(ns, NSEC_PER_SEC, &ns);
+ ts->tv_nsec = ns;
+
+ return mode;
+}
+
+notrace static void do_realtime_coarse(struct timespec *ts)
+{
+ unsigned long seq;
+ do {
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->wall_time_coarse_sec;
+ ts->tv_nsec = gtod->wall_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+}
+
+notrace static void do_monotonic_coarse(struct timespec *ts)
+{
+ unsigned long seq;
+ do {
+ seq = gtod_read_begin(gtod);
+ ts->tv_sec = gtod->monotonic_time_coarse_sec;
+ ts->tv_nsec = gtod->monotonic_time_coarse_nsec;
+ } while (unlikely(gtod_read_retry(gtod, seq)));
+}
+
+notrace int __vdso_clock_gettime(clockid_t clock, struct timespec *ts)
+{
+ switch (clock) {
+ case CLOCK_REALTIME:
+ if (do_realtime(ts) == VCLOCK_NONE)
+ goto fallback;
+ break;
+ case CLOCK_MONOTONIC:
+ if (do_monotonic(ts) == VCLOCK_NONE)
+ goto fallback;
+ break;
+ case CLOCK_REALTIME_COARSE:
+ do_realtime_coarse(ts);
+ break;
+ case CLOCK_MONOTONIC_COARSE:
+ do_monotonic_coarse(ts);
+ break;
+ default:
+ goto fallback;
+ }
+
+ return 0;
+fallback:
+ return vdso_fallback_gettime(clock, ts);
+}
+int clock_gettime(clockid_t, struct timespec *)
+ __attribute__((weak, alias("__vdso_clock_gettime")));
+
+notrace int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ if (likely(tv != NULL)) {
+ if (unlikely(do_realtime((struct timespec *)tv) == VCLOCK_NONE))
+ return vdso_fallback_gtod(tv, tz);
+ tv->tv_usec /= 1000;
+ }
+ if (unlikely(tz != NULL)) {
+ tz->tz_minuteswest = gtod->tz_minuteswest;
+ tz->tz_dsttime = gtod->tz_dsttime;
+ }
+
+ return 0;
+}
+int gettimeofday(struct timeval *, struct timezone *)
+ __attribute__((weak, alias("__vdso_gettimeofday")));
+
+/*
+ * This will break when the xtime seconds get inaccurate, but that is
+ * unlikely
+ */
+notrace time_t __vdso_time(time_t *t)
+{
+ /* This is atomic on x86 so we don't need any locks. */
+ time_t result = READ_ONCE(gtod->wall_time_sec);
+
+ if (t)
+ *t = result;
+ return result;
+}
+time_t time(time_t *t)
+ __attribute__((weak, alias("__vdso_time")));
diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S
new file mode 100644
index 000000000..acfd5ba7d
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso-layout.lds.S
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <asm/vdso.h>
+
+/*
+ * Linker script for vDSO. This is an ELF shared object prelinked to
+ * its virtual address, and with only one read-only segment.
+ * This script controls its layout.
+ */
+
+#if defined(BUILD_VDSO64)
+# define SHDR_SIZE 64
+#elif defined(BUILD_VDSO32) || defined(BUILD_VDSOX32)
+# define SHDR_SIZE 40
+#else
+# error unknown VDSO target
+#endif
+
+#define NUM_FAKE_SHDRS 13
+
+SECTIONS
+{
+ /*
+ * User/kernel shared data is before the vDSO. This may be a little
+ * uglier than putting it after the vDSO, but it avoids issues with
+ * non-allocatable things that dangle past the end of the PT_LOAD
+ * segment.
+ */
+
+ vvar_start = . - 3 * PAGE_SIZE;
+ vvar_page = vvar_start;
+
+ /* Place all vvars at the offsets in asm/vvar.h. */
+#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset;
+#define __VVAR_KERNEL_LDS
+#include <asm/vvar.h>
+#undef __VVAR_KERNEL_LDS
+#undef EMIT_VVAR
+
+ pvclock_page = vvar_start + PAGE_SIZE;
+ hvclock_page = vvar_start + 2 * PAGE_SIZE;
+
+ . = SIZEOF_HEADERS;
+
+ .hash : { *(.hash) } :text
+ .gnu.hash : { *(.gnu.hash) }
+ .dynsym : { *(.dynsym) }
+ .dynstr : { *(.dynstr) }
+ .gnu.version : { *(.gnu.version) }
+ .gnu.version_d : { *(.gnu.version_d) }
+ .gnu.version_r : { *(.gnu.version_r) }
+
+ .dynamic : { *(.dynamic) } :text :dynamic
+
+ .rodata : {
+ *(.rodata*)
+ *(.data*)
+ *(.sdata*)
+ *(.got.plt) *(.got)
+ *(.gnu.linkonce.d.*)
+ *(.bss*)
+ *(.dynbss*)
+ *(.gnu.linkonce.b.*)
+
+ /*
+ * Ideally this would live in a C file, but that won't
+ * work cleanly for x32 until we start building the x32
+ * C code using an x32 toolchain.
+ */
+ VDSO_FAKE_SECTION_TABLE_START = .;
+ . = . + NUM_FAKE_SHDRS * SHDR_SIZE;
+ VDSO_FAKE_SECTION_TABLE_END = .;
+ } :text
+
+ .fake_shstrtab : { *(.fake_shstrtab) } :text
+
+
+ .note : { *(.note.*) } :text :note
+
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+
+
+ /*
+ * Text is well-separated from actual data: there's plenty of
+ * stuff that isn't used at runtime in between.
+ */
+
+ .text : { *(.text*) } :text =0x90909090,
+
+ /*
+ * At the end so that eu-elflint stays happy when vdso2c strips
+ * these. A better implementation would avoid allocating space
+ * for these.
+ */
+ .altinstructions : { *(.altinstructions) } :text
+ .altinstr_replacement : { *(.altinstr_replacement) } :text
+
+ /DISCARD/ : {
+ *(.discard)
+ *(.discard.*)
+ *(__bug_table)
+ }
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME 0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+ text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */
+ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */
+ note PT_NOTE FLAGS(4); /* PF_R */
+ eh_frame_hdr PT_GNU_EH_FRAME;
+}
diff --git a/arch/x86/entry/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S
new file mode 100644
index 000000000..794231701
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso-note.S
@@ -0,0 +1,15 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/build-salt.h>
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+ .long LINUX_VERSION_CODE
+ELFNOTE_END
+
+BUILD_SALT
diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S
new file mode 100644
index 000000000..d3a2dce4c
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso.lds.S
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linker script for 64-bit vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#define BUILD_VDSO64
+
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+ LINUX_2.6 {
+ global:
+ clock_gettime;
+ __vdso_clock_gettime;
+ gettimeofday;
+ __vdso_gettimeofday;
+ getcpu;
+ __vdso_getcpu;
+ time;
+ __vdso_time;
+ local: *;
+ };
+}
diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c
new file mode 100644
index 000000000..4674f5858
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso2c.c
@@ -0,0 +1,260 @@
+/*
+ * vdso2c - A vdso image preparation tool
+ * Copyright (c) 2014 Andy Lutomirski and others
+ * Licensed under the GPL v2
+ *
+ * vdso2c requires stripped and unstripped input. It would be trivial
+ * to fully strip the input in here, but, for reasons described below,
+ * we need to write a section table. Doing this is more or less
+ * equivalent to dropping all non-allocatable sections, but it's
+ * easier to let objcopy handle that instead of doing it ourselves.
+ * If we ever need to do something fancier than what objcopy provides,
+ * it would be straightforward to add here.
+ *
+ * We're keep a section table for a few reasons:
+ *
+ * The Go runtime had a couple of bugs: it would read the section
+ * table to try to figure out how many dynamic symbols there were (it
+ * shouldn't have looked at the section table at all) and, if there
+ * were no SHT_SYNDYM section table entry, it would use an
+ * uninitialized value for the number of symbols. An empty DYNSYM
+ * table would work, but I see no reason not to write a valid one (and
+ * keep full performance for old Go programs). This hack is only
+ * needed on x86_64.
+ *
+ * The bug was introduced on 2012-08-31 by:
+ * https://code.google.com/p/go/source/detail?r=56ea40aac72b
+ * and was fixed on 2014-06-13 by:
+ * https://code.google.com/p/go/source/detail?r=fc1cd5e12595
+ *
+ * Binutils has issues debugging the vDSO: it reads the section table to
+ * find SHT_NOTE; it won't look at PT_NOTE for the in-memory vDSO, which
+ * would break build-id if we removed the section table. Binutils
+ * also requires that shstrndx != 0. See:
+ * https://sourceware.org/bugzilla/show_bug.cgi?id=17064
+ *
+ * elfutils might not look for PT_NOTE if there is a section table at
+ * all. I don't know whether this matters for any practical purpose.
+ *
+ * For simplicity, rather than hacking up a partial section table, we
+ * just write a mostly complete one. We omit non-dynamic symbols,
+ * though, since they're rather large.
+ *
+ * Once binutils gets fixed, we might be able to drop this for all but
+ * the 64-bit vdso, since build-id only works in kernel RPMs, and
+ * systems that update to new enough kernel RPMs will likely update
+ * binutils in sync. build-id has never worked for home-built kernel
+ * RPMs without manual symlinking, and I suspect that no one ever does
+ * that.
+ */
+
+#include <inttypes.h>
+#include <stdint.h>
+#include <unistd.h>
+#include <stdarg.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <fcntl.h>
+#include <err.h>
+
+#include <sys/mman.h>
+#include <sys/types.h>
+
+#include <tools/le_byteshift.h>
+
+#include <linux/elf.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+const char *outfilename;
+
+/* Symbols that we need in vdso2c. */
+enum {
+ sym_vvar_start,
+ sym_vvar_page,
+ sym_hpet_page,
+ sym_pvclock_page,
+ sym_hvclock_page,
+ sym_VDSO_FAKE_SECTION_TABLE_START,
+ sym_VDSO_FAKE_SECTION_TABLE_END,
+};
+
+const int special_pages[] = {
+ sym_vvar_page,
+ sym_hpet_page,
+ sym_pvclock_page,
+ sym_hvclock_page,
+};
+
+struct vdso_sym {
+ const char *name;
+ bool export;
+};
+
+struct vdso_sym required_syms[] = {
+ [sym_vvar_start] = {"vvar_start", true},
+ [sym_vvar_page] = {"vvar_page", true},
+ [sym_hpet_page] = {"hpet_page", true},
+ [sym_pvclock_page] = {"pvclock_page", true},
+ [sym_hvclock_page] = {"hvclock_page", true},
+ [sym_VDSO_FAKE_SECTION_TABLE_START] = {
+ "VDSO_FAKE_SECTION_TABLE_START", false
+ },
+ [sym_VDSO_FAKE_SECTION_TABLE_END] = {
+ "VDSO_FAKE_SECTION_TABLE_END", false
+ },
+ {"VDSO32_NOTE_MASK", true},
+ {"__kernel_vsyscall", true},
+ {"__kernel_sigreturn", true},
+ {"__kernel_rt_sigreturn", true},
+ {"int80_landing_pad", true},
+};
+
+__attribute__((format(printf, 1, 2))) __attribute__((noreturn))
+static void fail(const char *format, ...)
+{
+ va_list ap;
+ va_start(ap, format);
+ fprintf(stderr, "Error: ");
+ vfprintf(stderr, format, ap);
+ if (outfilename)
+ unlink(outfilename);
+ exit(1);
+ va_end(ap);
+}
+
+/*
+ * Evil macros for little-endian reads and writes
+ */
+#define GLE(x, bits, ifnot) \
+ __builtin_choose_expr( \
+ (sizeof(*(x)) == bits/8), \
+ (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot)
+
+extern void bad_get_le(void);
+#define LAST_GLE(x) \
+ __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le())
+
+#define GET_LE(x) \
+ GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x))))
+
+#define PLE(x, val, bits, ifnot) \
+ __builtin_choose_expr( \
+ (sizeof(*(x)) == bits/8), \
+ put_unaligned_le##bits((val), (x)), ifnot)
+
+extern void bad_put_le(void);
+#define LAST_PLE(x, val) \
+ __builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le())
+
+#define PUT_LE(x, val) \
+ PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val))))
+
+
+#define NSYMS ARRAY_SIZE(required_syms)
+
+#define BITSFUNC3(name, bits, suffix) name##bits##suffix
+#define BITSFUNC2(name, bits, suffix) BITSFUNC3(name, bits, suffix)
+#define BITSFUNC(name) BITSFUNC2(name, ELF_BITS, )
+
+#define INT_BITS BITSFUNC2(int, ELF_BITS, _t)
+
+#define ELF_BITS_XFORM2(bits, x) Elf##bits##_##x
+#define ELF_BITS_XFORM(bits, x) ELF_BITS_XFORM2(bits, x)
+#define ELF(x) ELF_BITS_XFORM(ELF_BITS, x)
+
+#define ELF_BITS 64
+#include "vdso2c.h"
+#undef ELF_BITS
+
+#define ELF_BITS 32
+#include "vdso2c.h"
+#undef ELF_BITS
+
+static void go(void *raw_addr, size_t raw_len,
+ void *stripped_addr, size_t stripped_len,
+ FILE *outfile, const char *name)
+{
+ Elf64_Ehdr *hdr = (Elf64_Ehdr *)raw_addr;
+
+ if (hdr->e_ident[EI_CLASS] == ELFCLASS64) {
+ go64(raw_addr, raw_len, stripped_addr, stripped_len,
+ outfile, name);
+ } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) {
+ go32(raw_addr, raw_len, stripped_addr, stripped_len,
+ outfile, name);
+ } else {
+ fail("unknown ELF class\n");
+ }
+}
+
+static void map_input(const char *name, void **addr, size_t *len, int prot)
+{
+ off_t tmp_len;
+
+ int fd = open(name, O_RDONLY);
+ if (fd == -1)
+ err(1, "%s", name);
+
+ tmp_len = lseek(fd, 0, SEEK_END);
+ if (tmp_len == (off_t)-1)
+ err(1, "lseek");
+ *len = (size_t)tmp_len;
+
+ *addr = mmap(NULL, tmp_len, prot, MAP_PRIVATE, fd, 0);
+ if (*addr == MAP_FAILED)
+ err(1, "mmap");
+
+ close(fd);
+}
+
+int main(int argc, char **argv)
+{
+ size_t raw_len, stripped_len;
+ void *raw_addr, *stripped_addr;
+ FILE *outfile;
+ char *name, *tmp;
+ int namelen;
+
+ if (argc != 4) {
+ printf("Usage: vdso2c RAW_INPUT STRIPPED_INPUT OUTPUT\n");
+ return 1;
+ }
+
+ /*
+ * Figure out the struct name. If we're writing to a .so file,
+ * generate raw output insted.
+ */
+ name = strdup(argv[3]);
+ namelen = strlen(name);
+ if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) {
+ name = NULL;
+ } else {
+ tmp = strrchr(name, '/');
+ if (tmp)
+ name = tmp + 1;
+ tmp = strchr(name, '.');
+ if (tmp)
+ *tmp = '\0';
+ for (tmp = name; *tmp; tmp++)
+ if (*tmp == '-')
+ *tmp = '_';
+ }
+
+ map_input(argv[1], &raw_addr, &raw_len, PROT_READ);
+ map_input(argv[2], &stripped_addr, &stripped_len, PROT_READ);
+
+ outfilename = argv[3];
+ outfile = fopen(outfilename, "w");
+ if (!outfile)
+ err(1, "%s", argv[2]);
+
+ go(raw_addr, raw_len, stripped_addr, stripped_len, outfile, name);
+
+ munmap(raw_addr, raw_len);
+ munmap(stripped_addr, stripped_len);
+ fclose(outfile);
+
+ return 0;
+}
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
new file mode 100644
index 000000000..fa847a620
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -0,0 +1,175 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file is included twice from vdso2c.c. It generates code for 32-bit
+ * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs
+ * are built for 32-bit userspace.
+ */
+
+static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
+ void *stripped_addr, size_t stripped_len,
+ FILE *outfile, const char *name)
+{
+ int found_load = 0;
+ unsigned long load_size = -1; /* Work around bogus warning */
+ unsigned long mapping_size;
+ ELF(Ehdr) *hdr = (ELF(Ehdr) *)raw_addr;
+ int i;
+ unsigned long j;
+ ELF(Shdr) *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr,
+ *alt_sec = NULL;
+ ELF(Dyn) *dyn = 0, *dyn_end = 0;
+ const char *secstrings;
+ INT_BITS syms[NSYMS] = {};
+
+ ELF(Phdr) *pt = (ELF(Phdr) *)(raw_addr + GET_LE(&hdr->e_phoff));
+
+ if (GET_LE(&hdr->e_type) != ET_DYN)
+ fail("input is not a shared object\n");
+
+ /* Walk the segment table. */
+ for (i = 0; i < GET_LE(&hdr->e_phnum); i++) {
+ if (GET_LE(&pt[i].p_type) == PT_LOAD) {
+ if (found_load)
+ fail("multiple PT_LOAD segs\n");
+
+ if (GET_LE(&pt[i].p_offset) != 0 ||
+ GET_LE(&pt[i].p_vaddr) != 0)
+ fail("PT_LOAD in wrong place\n");
+
+ if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz))
+ fail("cannot handle memsz != filesz\n");
+
+ load_size = GET_LE(&pt[i].p_memsz);
+ found_load = 1;
+ } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) {
+ dyn = raw_addr + GET_LE(&pt[i].p_offset);
+ dyn_end = raw_addr + GET_LE(&pt[i].p_offset) +
+ GET_LE(&pt[i].p_memsz);
+ }
+ }
+ if (!found_load)
+ fail("no PT_LOAD seg\n");
+
+ if (stripped_len < load_size)
+ fail("stripped input is too short\n");
+
+ if (!dyn)
+ fail("input has no PT_DYNAMIC section -- your toolchain is buggy\n");
+
+ /* Walk the dynamic table */
+ for (i = 0; dyn + i < dyn_end &&
+ GET_LE(&dyn[i].d_tag) != DT_NULL; i++) {
+ typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag);
+ if (tag == DT_REL || tag == DT_RELSZ || tag == DT_RELA ||
+ tag == DT_RELENT || tag == DT_TEXTREL)
+ fail("vdso image contains dynamic relocations\n");
+ }
+
+ /* Walk the section table */
+ secstrings_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
+ GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx);
+ secstrings = raw_addr + GET_LE(&secstrings_hdr->sh_offset);
+ for (i = 0; i < GET_LE(&hdr->e_shnum); i++) {
+ ELF(Shdr) *sh = raw_addr + GET_LE(&hdr->e_shoff) +
+ GET_LE(&hdr->e_shentsize) * i;
+ if (GET_LE(&sh->sh_type) == SHT_SYMTAB)
+ symtab_hdr = sh;
+
+ if (!strcmp(secstrings + GET_LE(&sh->sh_name),
+ ".altinstructions"))
+ alt_sec = sh;
+ }
+
+ if (!symtab_hdr)
+ fail("no symbol table\n");
+
+ strtab_hdr = raw_addr + GET_LE(&hdr->e_shoff) +
+ GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link);
+
+ /* Walk the symbol table */
+ for (i = 0;
+ i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize);
+ i++) {
+ int k;
+ ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
+ GET_LE(&symtab_hdr->sh_entsize) * i;
+ const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
+ GET_LE(&sym->st_name);
+
+ for (k = 0; k < NSYMS; k++) {
+ if (!strcmp(name, required_syms[k].name)) {
+ if (syms[k]) {
+ fail("duplicate symbol %s\n",
+ required_syms[k].name);
+ }
+
+ /*
+ * Careful: we use negative addresses, but
+ * st_value is unsigned, so we rely
+ * on syms[k] being a signed type of the
+ * correct width.
+ */
+ syms[k] = GET_LE(&sym->st_value);
+ }
+ }
+ }
+
+ /* Validate mapping addresses. */
+ for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) {
+ INT_BITS symval = syms[special_pages[i]];
+
+ if (!symval)
+ continue; /* The mapping isn't used; ignore it. */
+
+ if (symval % 4096)
+ fail("%s must be a multiple of 4096\n",
+ required_syms[i].name);
+ if (symval + 4096 < syms[sym_vvar_start])
+ fail("%s underruns vvar_start\n",
+ required_syms[i].name);
+ if (symval + 4096 > 0)
+ fail("%s is on the wrong side of the vdso text\n",
+ required_syms[i].name);
+ }
+ if (syms[sym_vvar_start] % 4096)
+ fail("vvar_begin must be a multiple of 4096\n");
+
+ if (!name) {
+ fwrite(stripped_addr, stripped_len, 1, outfile);
+ return;
+ }
+
+ mapping_size = (stripped_len + 4095) / 4096 * 4096;
+
+ fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n");
+ fprintf(outfile, "#include <linux/linkage.h>\n");
+ fprintf(outfile, "#include <asm/page_types.h>\n");
+ fprintf(outfile, "#include <asm/vdso.h>\n");
+ fprintf(outfile, "\n");
+ fprintf(outfile,
+ "static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {",
+ mapping_size);
+ for (j = 0; j < stripped_len; j++) {
+ if (j % 10 == 0)
+ fprintf(outfile, "\n\t");
+ fprintf(outfile, "0x%02X, ",
+ (int)((unsigned char *)stripped_addr)[j]);
+ }
+ fprintf(outfile, "\n};\n\n");
+
+ fprintf(outfile, "const struct vdso_image %s = {\n", name);
+ fprintf(outfile, "\t.data = raw_data,\n");
+ fprintf(outfile, "\t.size = %lu,\n", mapping_size);
+ if (alt_sec) {
+ fprintf(outfile, "\t.alt = %lu,\n",
+ (unsigned long)GET_LE(&alt_sec->sh_offset));
+ fprintf(outfile, "\t.alt_len = %lu,\n",
+ (unsigned long)GET_LE(&alt_sec->sh_size));
+ }
+ for (i = 0; i < NSYMS; i++) {
+ if (required_syms[i].export && syms[i])
+ fprintf(outfile, "\t.sym_%s = %" PRIi64 ",\n",
+ required_syms[i].name, (int64_t)syms[i]);
+ }
+ fprintf(outfile, "};\n");
+}
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
new file mode 100644
index 000000000..ddff0ca6f
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * (C) Copyright 2002 Linus Torvalds
+ * Portions based on the vdso-randomization code from exec-shield:
+ * Copyright(C) 2005-2006, Red Hat, Inc., Ingo Molnar
+ *
+ * This file contains the needed initializations to support sysenter.
+ */
+
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/kernel.h>
+#include <linux/mm_types.h>
+#include <linux/elf.h>
+
+#include <asm/processor.h>
+#include <asm/vdso.h>
+
+#ifdef CONFIG_COMPAT_VDSO
+#define VDSO_DEFAULT 0
+#else
+#define VDSO_DEFAULT 1
+#endif
+
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT;
+
+static int __init vdso32_setup(char *s)
+{
+ vdso32_enabled = simple_strtoul(s, NULL, 0);
+
+ if (vdso32_enabled > 1) {
+ pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n");
+ vdso32_enabled = 0;
+ }
+
+ return 1;
+}
+
+/*
+ * For consistency, the argument vdso32=[012] affects the 32-bit vDSO
+ * behavior on both 64-bit and 32-bit kernels.
+ * On 32-bit kernels, vdso=[012] means the same thing.
+ */
+__setup("vdso32=", vdso32_setup);
+
+#ifdef CONFIG_X86_32
+__setup_param("vdso=", vdso_setup, vdso32_setup, 0);
+#endif
+
+int __init sysenter_setup(void)
+{
+ init_vdso_image(&vdso_image_32);
+
+ return 0;
+}
+
+#ifdef CONFIG_X86_64
+
+subsys_initcall(sysenter_setup);
+
+#ifdef CONFIG_SYSCTL
+/* Register vsyscall32 into the ABI table */
+#include <linux/sysctl.h>
+
+static const int zero;
+static const int one = 1;
+
+static struct ctl_table abi_table2[] = {
+ {
+ .procname = "vsyscall32",
+ .data = &vdso32_enabled,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = (int *)&zero,
+ .extra2 = (int *)&one,
+ },
+ {}
+};
+
+static struct ctl_table abi_root_table2[] = {
+ {
+ .procname = "abi",
+ .mode = 0555,
+ .child = abi_table2
+ },
+ {}
+};
+
+static __init int ia32_binfmt_init(void)
+{
+ register_sysctl_table(abi_root_table2);
+ return 0;
+}
+__initcall(ia32_binfmt_init);
+#endif /* CONFIG_SYSCTL */
+
+#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/vdso/vdso32/.gitignore b/arch/x86/entry/vdso/vdso32/.gitignore
new file mode 100644
index 000000000..e45fba9d0
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/.gitignore
@@ -0,0 +1 @@
+vdso32.lds
diff --git a/arch/x86/entry/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
new file mode 100644
index 000000000..e78047d11
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/note.S
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/build-salt.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+/* Ideally this would use UTS_NAME, but using a quoted string here
+ doesn't work. Remember to change this when changing the
+ kernel's name. */
+ELFNOTE_START(Linux, 0, "a")
+ .long LINUX_VERSION_CODE
+ELFNOTE_END
+
+BUILD_SALT
+
+#ifdef CONFIG_XEN
+/*
+ * Add a special note telling glibc's dynamic linker a fake hardware
+ * flavor that it will use to choose the search path for libraries in the
+ * same way it uses real hardware capabilities like "mmx".
+ * We supply "nosegneg" as the fake capability, to indicate that we
+ * do not like negative offsets in instructions using segment overrides,
+ * since we implement those inefficiently. This makes it possible to
+ * install libraries optimized to avoid those access patterns in someplace
+ * like /lib/i686/tls/nosegneg. Note that an /etc/ld.so.conf.d/file
+ * corresponding to the bits here is needed to make ldconfig work right.
+ * It should contain:
+ * hwcap 1 nosegneg
+ * to match the mapping of bit to name that we give here.
+ *
+ * At runtime, the fake hardware feature will be considered to be present
+ * if its bit is set in the mask word. So, we start with the mask 0, and
+ * at boot time we set VDSO_NOTE_NONEGSEG_BIT if running under Xen.
+ */
+
+#include "../../xen/vdso.h" /* Defines VDSO_NOTE_NONEGSEG_BIT. */
+
+ELFNOTE_START(GNU, 2, "a")
+ .long 1 /* ncaps */
+VDSO32_NOTE_MASK: /* Symbol used by arch/x86/xen/setup.c */
+ .long 0 /* mask */
+ .byte VDSO_NOTE_NONEGSEG_BIT; .asciz "nosegneg" /* bit, name */
+ELFNOTE_END
+#endif
diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
new file mode 100644
index 000000000..c3233ee98
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/unistd_32.h>
+#include <asm/asm-offsets.h>
+
+#ifndef SYSCALL_ENTER_KERNEL
+#define SYSCALL_ENTER_KERNEL int $0x80
+#endif
+
+ .text
+ .globl __kernel_sigreturn
+ .type __kernel_sigreturn,@function
+ nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
+ ALIGN
+__kernel_sigreturn:
+.LSTART_sigreturn:
+ popl %eax /* XXX does this mean it needs unwind info? */
+ movl $__NR_sigreturn, %eax
+ SYSCALL_ENTER_KERNEL
+.LEND_sigreturn:
+ nop
+ .size __kernel_sigreturn,.-.LSTART_sigreturn
+
+ .globl __kernel_rt_sigreturn
+ .type __kernel_rt_sigreturn,@function
+ ALIGN
+__kernel_rt_sigreturn:
+.LSTART_rt_sigreturn:
+ movl $__NR_rt_sigreturn, %eax
+ SYSCALL_ENTER_KERNEL
+.LEND_rt_sigreturn:
+ nop
+ .size __kernel_rt_sigreturn,.-.LSTART_rt_sigreturn
+ .previous
+
+ .section .eh_frame,"a",@progbits
+.LSTARTFRAMEDLSI1:
+ .long .LENDCIEDLSI1-.LSTARTCIEDLSI1
+.LSTARTCIEDLSI1:
+ .long 0 /* CIE ID */
+ .byte 1 /* Version number */
+ .string "zRS" /* 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 0 /* DW_CFA_nop */
+ .align 4
+.LENDCIEDLSI1:
+ .long .LENDFDEDLSI1-.LSTARTFDEDLSI1 /* Length FDE */
+.LSTARTFDEDLSI1:
+ .long .LSTARTFDEDLSI1-.LSTARTFRAMEDLSI1 /* CIE pointer */
+ /* HACK: The dwarf2 unwind routines will subtract 1 from the
+ return address to get an address in the middle of the
+ presumed call instruction. Since we didn't get here via
+ a call, we need to include the nop before the real start
+ to make up for it. */
+ .long .LSTART_sigreturn-1-. /* PC-relative start address */
+ .long .LEND_sigreturn-.LSTART_sigreturn+1
+ .uleb128 0 /* Augmentation */
+ /* What follows are the instructions for the table generation.
+ We record the locations of each register saved. This is
+ complicated by the fact that the "CFA" is always assumed to
+ be the value of the stack pointer in the caller. This means
+ that we must define the CFA of this body of code to be the
+ saved value of the stack pointer in the sigcontext. Which
+ also means that there is no fixed relation to the other
+ saved registers, which means that we must use DW_CFA_expression
+ to compute their addresses. It also means that when we
+ adjust the stack with the popl, we have to do it all over again. */
+
+#define do_cfa_expr(offset) \
+ .byte 0x0f; /* DW_CFA_def_cfa_expression */ \
+ .uleb128 1f-0f; /* length */ \
+0: .byte 0x74; /* DW_OP_breg4 */ \
+ .sleb128 offset; /* offset */ \
+ .byte 0x06; /* DW_OP_deref */ \
+1:
+
+#define do_expr(regno, offset) \
+ .byte 0x10; /* DW_CFA_expression */ \
+ .uleb128 regno; /* regno */ \
+ .uleb128 1f-0f; /* length */ \
+0: .byte 0x74; /* DW_OP_breg4 */ \
+ .sleb128 offset; /* offset */ \
+1:
+
+ do_cfa_expr(IA32_SIGCONTEXT_sp+4)
+ do_expr(0, IA32_SIGCONTEXT_ax+4)
+ do_expr(1, IA32_SIGCONTEXT_cx+4)
+ do_expr(2, IA32_SIGCONTEXT_dx+4)
+ do_expr(3, IA32_SIGCONTEXT_bx+4)
+ do_expr(5, IA32_SIGCONTEXT_bp+4)
+ do_expr(6, IA32_SIGCONTEXT_si+4)
+ do_expr(7, IA32_SIGCONTEXT_di+4)
+ do_expr(8, IA32_SIGCONTEXT_ip+4)
+
+ .byte 0x42 /* DW_CFA_advance_loc 2 -- nop; popl eax. */
+
+ do_cfa_expr(IA32_SIGCONTEXT_sp)
+ do_expr(0, IA32_SIGCONTEXT_ax)
+ do_expr(1, IA32_SIGCONTEXT_cx)
+ do_expr(2, IA32_SIGCONTEXT_dx)
+ do_expr(3, IA32_SIGCONTEXT_bx)
+ do_expr(5, IA32_SIGCONTEXT_bp)
+ do_expr(6, IA32_SIGCONTEXT_si)
+ do_expr(7, IA32_SIGCONTEXT_di)
+ do_expr(8, IA32_SIGCONTEXT_ip)
+
+ .align 4
+.LENDFDEDLSI1:
+
+ .long .LENDFDEDLSI2-.LSTARTFDEDLSI2 /* Length FDE */
+.LSTARTFDEDLSI2:
+ .long .LSTARTFDEDLSI2-.LSTARTFRAMEDLSI1 /* CIE pointer */
+ /* HACK: See above wrt unwind library assumptions. */
+ .long .LSTART_rt_sigreturn-1-. /* PC-relative start address */
+ .long .LEND_rt_sigreturn-.LSTART_rt_sigreturn+1
+ .uleb128 0 /* Augmentation */
+ /* What follows are the instructions for the table generation.
+ We record the locations of each register saved. This is
+ slightly less complicated than the above, since we don't
+ modify the stack pointer in the process. */
+
+ do_cfa_expr(IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_sp)
+ do_expr(0, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ax)
+ do_expr(1, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_cx)
+ do_expr(2, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_dx)
+ do_expr(3, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bx)
+ do_expr(5, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_bp)
+ do_expr(6, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_si)
+ do_expr(7, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_di)
+ do_expr(8, IA32_RT_SIGFRAME_sigcontext-4 + IA32_SIGCONTEXT_ip)
+
+ .align 4
+.LENDFDEDLSI2:
+ .previous
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..263d7433d
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AT_SYSINFO entry point
+*/
+
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative-asm.h>
+
+ .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
new file mode 100644
index 000000000..9242b2841
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/vclock_gettime.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0
+#define BUILD_VDSO32
+
+#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+#undef CONFIG_OPTIMIZE_INLINING
+#endif
+
+#ifdef CONFIG_X86_64
+
+/*
+ * in case of a 32 bit VDSO for a 64 bit kernel fake a 32 bit kernel
+ * configuration
+ */
+#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
+
+#define BUILD_VDSO32_64
+
+#endif
+
+#include "../vclock_gettime.c"
diff --git a/arch/x86/entry/vdso/vdso32/vdso32.lds.S b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
new file mode 100644
index 000000000..422764a81
--- /dev/null
+++ b/arch/x86/entry/vdso/vdso32/vdso32.lds.S
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linker script for 32-bit vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#include <asm/page.h>
+
+#define BUILD_VDSO32
+
+#include "../vdso-layout.lds.S"
+
+/* The ELF entry point can be used to set the AT_SYSINFO value. */
+ENTRY(__kernel_vsyscall);
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION
+{
+ LINUX_2.6 {
+ global:
+ __vdso_clock_gettime;
+ __vdso_gettimeofday;
+ __vdso_time;
+ };
+
+ LINUX_2.5 {
+ global:
+ __kernel_vsyscall;
+ __kernel_sigreturn;
+ __kernel_rt_sigreturn;
+ local: *;
+ };
+}
diff --git a/arch/x86/entry/vdso/vdsox32.lds.S b/arch/x86/entry/vdso/vdsox32.lds.S
new file mode 100644
index 000000000..05cd1c5c4
--- /dev/null
+++ b/arch/x86/entry/vdso/vdsox32.lds.S
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linker script for x32 vDSO.
+ * We #include the file to define the layout details.
+ *
+ * This file defines the version script giving the user-exported symbols in
+ * the DSO.
+ */
+
+#define BUILD_VDSOX32
+
+#include "vdso-layout.lds.S"
+
+/*
+ * This controls what userland symbols we export from the vDSO.
+ */
+VERSION {
+ LINUX_2.6 {
+ global:
+ __vdso_clock_gettime;
+ __vdso_gettimeofday;
+ __vdso_getcpu;
+ __vdso_time;
+ local: *;
+ };
+}
diff --git a/arch/x86/entry/vdso/vgetcpu.c b/arch/x86/entry/vdso/vgetcpu.c
new file mode 100644
index 000000000..8ec3d1f4c
--- /dev/null
+++ b/arch/x86/entry/vdso/vgetcpu.c
@@ -0,0 +1,28 @@
+/*
+ * Copyright 2006 Andi Kleen, SUSE Labs.
+ * Subject to the GNU Public License, v.2
+ *
+ * Fast user context implementation of getcpu()
+ */
+
+#include <linux/kernel.h>
+#include <linux/getcpu.h>
+#include <linux/time.h>
+#include <asm/vgtod.h>
+
+notrace long
+__vdso_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *unused)
+{
+ unsigned int p;
+
+ p = __getcpu();
+
+ if (cpu)
+ *cpu = p & VGETCPU_CPU_MASK;
+ if (node)
+ *node = p >> 12;
+ return 0;
+}
+
+long getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *tcache)
+ __attribute__((weak, alias("__vdso_getcpu")));
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
new file mode 100644
index 000000000..a1c31bb23
--- /dev/null
+++ b/arch/x86/entry/vdso/vma.c
@@ -0,0 +1,383 @@
+/*
+ * Copyright 2007 Andi Kleen, SUSE Labs.
+ * Subject to the GPL, v.2
+ *
+ * This contains most of the x86 vDSO kernel-side code.
+ */
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <linux/elf.h>
+#include <linux/cpu.h>
+#include <linux/ptrace.h>
+#include <asm/pvclock.h>
+#include <asm/vgtod.h>
+#include <asm/proto.h>
+#include <asm/vdso.h>
+#include <asm/vvar.h>
+#include <asm/page.h>
+#include <asm/desc.h>
+#include <asm/cpufeature.h>
+#include <asm/mshyperv.h>
+
+#if defined(CONFIG_X86_64)
+unsigned int __read_mostly vdso64_enabled = 1;
+#endif
+
+void __init init_vdso_image(const struct vdso_image *image)
+{
+ BUG_ON(image->size % PAGE_SIZE != 0);
+
+ apply_alternatives((struct alt_instr *)(image->data + image->alt),
+ (struct alt_instr *)(image->data + image->alt +
+ image->alt_len));
+}
+
+struct linux_binprm;
+
+static int vdso_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+
+ if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
+ return VM_FAULT_SIGBUS;
+
+ vmf->page = virt_to_page(image->data + (vmf->pgoff << PAGE_SHIFT));
+ get_page(vmf->page);
+ return 0;
+}
+
+static void vdso_fix_landing(const struct vdso_image *image,
+ struct vm_area_struct *new_vma)
+{
+#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
+ if (in_ia32_syscall() && image == &vdso_image_32) {
+ struct pt_regs *regs = current_pt_regs();
+ unsigned long vdso_land = image->sym_int80_landing_pad;
+ unsigned long old_land_addr = vdso_land +
+ (unsigned long)current->mm->context.vdso;
+
+ /* Fixing userspace landing - look at do_fast_syscall_32 */
+ if (regs->ip == old_land_addr)
+ regs->ip = new_vma->vm_start + vdso_land;
+ }
+#endif
+}
+
+static int vdso_mremap(const struct vm_special_mapping *sm,
+ struct vm_area_struct *new_vma)
+{
+ unsigned long new_size = new_vma->vm_end - new_vma->vm_start;
+ const struct vdso_image *image = current->mm->context.vdso_image;
+
+ if (image->size != new_size)
+ return -EINVAL;
+
+ vdso_fix_landing(image, new_vma);
+ current->mm->context.vdso = (void __user *)new_vma->vm_start;
+
+ return 0;
+}
+
+static int vvar_fault(const struct vm_special_mapping *sm,
+ struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ const struct vdso_image *image = vma->vm_mm->context.vdso_image;
+ long sym_offset;
+ int ret = -EFAULT;
+
+ if (!image)
+ return VM_FAULT_SIGBUS;
+
+ sym_offset = (long)(vmf->pgoff << PAGE_SHIFT) +
+ image->sym_vvar_start;
+
+ /*
+ * Sanity check: a symbol offset of zero means that the page
+ * does not exist for this vdso image, not that the page is at
+ * offset zero relative to the text mapping. This should be
+ * impossible here, because sym_offset should only be zero for
+ * the page past the end of the vvar mapping.
+ */
+ if (sym_offset == 0)
+ return VM_FAULT_SIGBUS;
+
+ if (sym_offset == image->sym_vvar_page) {
+ ret = vm_insert_pfn(vma, vmf->address,
+ __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+ } else if (sym_offset == image->sym_pvclock_page) {
+ struct pvclock_vsyscall_time_info *pvti =
+ pvclock_get_pvti_cpu0_va();
+ if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
+ ret = vm_insert_pfn_prot(
+ vma,
+ vmf->address,
+ __pa(pvti) >> PAGE_SHIFT,
+ pgprot_decrypted(vma->vm_page_prot));
+ }
+ } else if (sym_offset == image->sym_hvclock_page) {
+ struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();
+
+ if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
+ ret = vm_insert_pfn(vma, vmf->address,
+ vmalloc_to_pfn(tsc_pg));
+ }
+
+ if (ret == 0 || ret == -EBUSY)
+ return VM_FAULT_NOPAGE;
+
+ return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_special_mapping vdso_mapping = {
+ .name = "[vdso]",
+ .fault = vdso_fault,
+ .mremap = vdso_mremap,
+};
+static const struct vm_special_mapping vvar_mapping = {
+ .name = "[vvar]",
+ .fault = vvar_fault,
+};
+
+/*
+ * Add vdso and vvar mappings to current process.
+ * @image - blob to map
+ * @addr - request a specific address (zero to map at free addr)
+ */
+static int map_vdso(const struct vdso_image *image, unsigned long addr)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ unsigned long text_start;
+ int ret = 0;
+
+ if (down_write_killable(&mm->mmap_sem))
+ return -EINTR;
+
+ addr = get_unmapped_area(NULL, addr,
+ image->size - image->sym_vvar_start, 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = addr;
+ goto up_fail;
+ }
+
+ text_start = addr - image->sym_vvar_start;
+
+ /*
+ * MAYWRITE to allow gdb to COW and set breakpoints
+ */
+ vma = _install_special_mapping(mm,
+ text_start,
+ image->size,
+ VM_READ|VM_EXEC|
+ VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC,
+ &vdso_mapping);
+
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ goto up_fail;
+ }
+
+ vma = _install_special_mapping(mm,
+ addr,
+ -image->sym_vvar_start,
+ VM_READ|VM_MAYREAD|VM_IO|VM_DONTDUMP|
+ VM_PFNMAP,
+ &vvar_mapping);
+
+ if (IS_ERR(vma)) {
+ ret = PTR_ERR(vma);
+ do_munmap(mm, text_start, image->size, NULL);
+ } else {
+ current->mm->context.vdso = (void __user *)text_start;
+ current->mm->context.vdso_image = image;
+ }
+
+up_fail:
+ up_write(&mm->mmap_sem);
+ return ret;
+}
+
+#ifdef CONFIG_X86_64
+/*
+ * Put the vdso above the (randomized) stack with another randomized
+ * offset. This way there is no hole in the middle of address space.
+ * To save memory make sure it is still in the same PTE as the stack
+ * top. This doesn't give that many random bits.
+ *
+ * Note that this algorithm is imperfect: the distribution of the vdso
+ * start address within a PMD is biased toward the end.
+ *
+ * Only used for the 64-bit and x32 vdsos.
+ */
+static unsigned long vdso_addr(unsigned long start, unsigned len)
+{
+ unsigned long addr, end;
+ unsigned offset;
+
+ /*
+ * Round up the start address. It can start out unaligned as a result
+ * of stack start randomization.
+ */
+ start = PAGE_ALIGN(start);
+
+ /* Round the lowest possible end address up to a PMD boundary. */
+ end = (start + len + PMD_SIZE - 1) & PMD_MASK;
+ if (end >= TASK_SIZE_MAX)
+ end = TASK_SIZE_MAX;
+ end -= len;
+
+ if (end > start) {
+ offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1);
+ addr = start + (offset << PAGE_SHIFT);
+ } else {
+ addr = start;
+ }
+
+ /*
+ * Forcibly align the final address in case we have a hardware
+ * issue that requires alignment for performance reasons.
+ */
+ addr = align_vdso_addr(addr);
+
+ return addr;
+}
+
+static int map_vdso_randomized(const struct vdso_image *image)
+{
+ unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);
+
+ return map_vdso(image, addr);
+}
+#endif
+
+int map_vdso_once(const struct vdso_image *image, unsigned long addr)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+
+ down_write(&mm->mmap_sem);
+ /*
+ * Check if we have already mapped vdso blob - fail to prevent
+ * abusing from userspace install_speciall_mapping, which may
+ * not do accounting and rlimit right.
+ * We could search vma near context.vdso, but it's a slowpath,
+ * so let's explicitely check all VMAs to be completely sure.
+ */
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (vma_is_special_mapping(vma, &vdso_mapping) ||
+ vma_is_special_mapping(vma, &vvar_mapping)) {
+ up_write(&mm->mmap_sem);
+ return -EEXIST;
+ }
+ }
+ up_write(&mm->mmap_sem);
+
+ return map_vdso(image, addr);
+}
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+static int load_vdso32(void)
+{
+ if (vdso32_enabled != 1) /* Other values all mean "disabled" */
+ return 0;
+
+ return map_vdso(&vdso_image_32, 0);
+}
+#endif
+
+#ifdef CONFIG_X86_64
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ if (!vdso64_enabled)
+ return 0;
+
+ return map_vdso_randomized(&vdso_image_64);
+}
+
+#ifdef CONFIG_COMPAT
+int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp)
+{
+#ifdef CONFIG_X86_X32_ABI
+ if (test_thread_flag(TIF_X32)) {
+ if (!vdso64_enabled)
+ return 0;
+ return map_vdso_randomized(&vdso_image_x32);
+ }
+#endif
+#ifdef CONFIG_IA32_EMULATION
+ return load_vdso32();
+#else
+ return 0;
+#endif
+}
+#endif
+#else
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+ return load_vdso32();
+}
+#endif
+
+#ifdef CONFIG_X86_64
+static __init int vdso_setup(char *s)
+{
+ vdso64_enabled = simple_strtoul(s, NULL, 0);
+ return 1;
+}
+__setup("vdso=", vdso_setup);
+#endif
+
+#ifdef CONFIG_X86_64
+static void vgetcpu_cpu_init(void *arg)
+{
+ int cpu = smp_processor_id();
+ struct desc_struct d = { };
+ unsigned long node = 0;
+#ifdef CONFIG_NUMA
+ node = cpu_to_node(cpu);
+#endif
+ if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID))
+ write_rdtscp_aux((node << 12) | cpu);
+
+ /*
+ * Store cpu number in limit so that it can be loaded
+ * quickly in user space in vgetcpu. (12 bits for the CPU
+ * and 8 bits for the node)
+ */
+ d.limit0 = cpu | ((node & 0xf) << 12);
+ d.limit1 = node >> 4;
+ d.type = 5; /* RO data, expand down, accessed */
+ d.dpl = 3; /* Visible to user code */
+ d.s = 1; /* Not a system segment */
+ d.p = 1; /* Present */
+ d.d = 1; /* 32-bit */
+
+ write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
+}
+
+static int vgetcpu_online(unsigned int cpu)
+{
+ return smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
+}
+
+static int __init init_vdso(void)
+{
+ init_vdso_image(&vdso_image_64);
+
+#ifdef CONFIG_X86_X32_ABI
+ init_vdso_image(&vdso_image_x32);
+#endif
+
+ /* notifier priority > KVM */
+ return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
+ "x86/vdso/vma:online", vgetcpu_online, NULL);
+}
+subsys_initcall(init_vdso);
+#endif /* CONFIG_X86_64 */
diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 000000000..a9f4856f6
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-y := vsyscall_gtod.o
+
+obj-$(CONFIG_X86_VSYSCALL_EMULATION) += vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
new file mode 100644
index 000000000..82ed001e8
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -0,0 +1,375 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
+ *
+ * Based on the original implementation which is:
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ * Parts of the original code have been moved to arch/x86/vdso/vma.c
+ *
+ * This file implements vsyscall emulation. vsyscalls are a legacy ABI:
+ * Userspace can request certain kernel services by calling fixed
+ * addresses. This concept is problematic:
+ *
+ * - It interferes with ASLR.
+ * - It's awkward to write code that lives in kernel addresses but is
+ * callable by userspace at fixed addresses.
+ * - The whole concept is impossible for 32-bit compat userspace.
+ * - UML cannot easily virtualize a vsyscall.
+ *
+ * As of mid-2014, I believe that there is no new userspace code that
+ * will use a vsyscall if the vDSO is present. I hope that there will
+ * soon be no new userspace code that will ever use a vsyscall.
+ *
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
+ */
+
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/sched/signal.h>
+#include <linux/mm_types.h>
+#include <linux/syscalls.h>
+#include <linux/ratelimit.h>
+
+#include <asm/vsyscall.h>
+#include <asm/unistd.h>
+#include <asm/fixmap.h>
+#include <asm/traps.h>
+#include <asm/paravirt.h>
+
+#define CREATE_TRACE_POINTS
+#include "vsyscall_trace.h"
+
+static enum { EMULATE, NONE } vsyscall_mode =
+#ifdef CONFIG_LEGACY_VSYSCALL_NONE
+ NONE;
+#else
+ EMULATE;
+#endif
+
+static int __init vsyscall_setup(char *str)
+{
+ if (str) {
+ if (!strcmp("emulate", str))
+ vsyscall_mode = EMULATE;
+ else if (!strcmp("none", str))
+ vsyscall_mode = NONE;
+ else
+ return -EINVAL;
+
+ return 0;
+ }
+
+ return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
+static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
+ const char *message)
+{
+ if (!show_unhandled_signals)
+ return;
+
+ printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+ level, current->comm, task_pid_nr(current),
+ message, regs->ip, regs->cs,
+ regs->sp, regs->ax, regs->si, regs->di);
+}
+
+static int addr_to_vsyscall_nr(unsigned long addr)
+{
+ int nr;
+
+ if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
+ return -EINVAL;
+
+ nr = (addr & 0xC00UL) >> 10;
+ if (nr >= 3)
+ return -EINVAL;
+
+ return nr;
+}
+
+static bool write_ok_or_segv(unsigned long ptr, size_t size)
+{
+ /*
+ * XXX: if access_ok, get_user, and put_user handled
+ * sig_on_uaccess_err, this could go away.
+ */
+
+ if (!access_ok(VERIFY_WRITE, (void __user *)ptr, size)) {
+ siginfo_t info;
+ struct thread_struct *thread = &current->thread;
+
+ thread->error_code = 6; /* user fault, no page, write */
+ thread->cr2 = ptr;
+ thread->trap_nr = X86_TRAP_PF;
+
+ clear_siginfo(&info);
+ info.si_signo = SIGSEGV;
+ info.si_errno = 0;
+ info.si_code = SEGV_MAPERR;
+ info.si_addr = (void __user *)ptr;
+
+ force_sig_info(SIGSEGV, &info, current);
+ return false;
+ } else {
+ return true;
+ }
+}
+
+bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
+{
+ struct task_struct *tsk;
+ unsigned long caller;
+ int vsyscall_nr, syscall_nr, tmp;
+ int prev_sig_on_uaccess_err;
+ long ret;
+ unsigned long orig_dx;
+
+ /*
+ * No point in checking CS -- the only way to get here is a user mode
+ * trap to a high address, which means that we're in 64-bit user code.
+ */
+
+ WARN_ON_ONCE(address != regs->ip);
+
+ if (vsyscall_mode == NONE) {
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall attempted with vsyscall=none");
+ return false;
+ }
+
+ vsyscall_nr = addr_to_vsyscall_nr(address);
+
+ trace_emulate_vsyscall(vsyscall_nr);
+
+ if (vsyscall_nr < 0) {
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
+ goto sigsegv;
+ }
+
+ if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
+ warn_bad_vsyscall(KERN_WARNING, regs,
+ "vsyscall with bad stack (exploit attempt?)");
+ goto sigsegv;
+ }
+
+ tsk = current;
+
+ /*
+ * Check for access_ok violations and find the syscall nr.
+ *
+ * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
+ * 64-bit, so we don't need to special-case it here. For all the
+ * vsyscalls, NULL means "don't write anything" not "write it at
+ * address 0".
+ */
+ switch (vsyscall_nr) {
+ case 0:
+ if (!write_ok_or_segv(regs->di, sizeof(struct timeval)) ||
+ !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_gettimeofday;
+ break;
+
+ case 1:
+ if (!write_ok_or_segv(regs->di, sizeof(time_t))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_time;
+ break;
+
+ case 2:
+ if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
+ !write_ok_or_segv(regs->si, sizeof(unsigned))) {
+ ret = -EFAULT;
+ goto check_fault;
+ }
+
+ syscall_nr = __NR_getcpu;
+ break;
+ }
+
+ /*
+ * Handle seccomp. regs->ip must be the original value.
+ * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst.
+ *
+ * We could optimize the seccomp disabled case, but performance
+ * here doesn't matter.
+ */
+ regs->orig_ax = syscall_nr;
+ regs->ax = -ENOSYS;
+ tmp = secure_computing(NULL);
+ if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
+ warn_bad_vsyscall(KERN_DEBUG, regs,
+ "seccomp tried to change syscall nr or ip");
+ do_exit(SIGSYS);
+ }
+ regs->orig_ax = -1;
+ if (tmp)
+ goto do_ret; /* skip requested */
+
+ /*
+ * With a real vsyscall, page faults cause SIGSEGV. We want to
+ * preserve that behavior to make writing exploits harder.
+ */
+ prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
+ current->thread.sig_on_uaccess_err = 1;
+
+ ret = -EFAULT;
+ switch (vsyscall_nr) {
+ case 0:
+ /* this decodes regs->di and regs->si on its own */
+ ret = __x64_sys_gettimeofday(regs);
+ break;
+
+ case 1:
+ /* this decodes regs->di on its own */
+ ret = __x64_sys_time(regs);
+ break;
+
+ case 2:
+ /* while we could clobber regs->dx, we didn't in the past... */
+ orig_dx = regs->dx;
+ regs->dx = 0;
+ /* this decodes regs->di, regs->si and regs->dx on its own */
+ ret = __x64_sys_getcpu(regs);
+ regs->dx = orig_dx;
+ break;
+ }
+
+ current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
+
+check_fault:
+ if (ret == -EFAULT) {
+ /* Bad news -- userspace fed a bad pointer to a vsyscall. */
+ warn_bad_vsyscall(KERN_INFO, regs,
+ "vsyscall fault (exploit attempt?)");
+
+ /*
+ * If we failed to generate a signal for any reason,
+ * generate one here. (This should be impossible.)
+ */
+ if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
+ !sigismember(&tsk->pending.signal, SIGSEGV)))
+ goto sigsegv;
+
+ return true; /* Don't emulate the ret. */
+ }
+
+ regs->ax = ret;
+
+do_ret:
+ /* Emulate a ret instruction. */
+ regs->ip = caller;
+ regs->sp += 8;
+ return true;
+
+sigsegv:
+ force_sig(SIGSEGV, current);
+ return true;
+}
+
+/*
+ * A pseudo VMA to allow ptrace access for the vsyscall page. This only
+ * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
+ * not need special handling anymore:
+ */
+static const char *gate_vma_name(struct vm_area_struct *vma)
+{
+ return "[vsyscall]";
+}
+static const struct vm_operations_struct gate_vma_ops = {
+ .name = gate_vma_name,
+};
+static struct vm_area_struct gate_vma = {
+ .vm_start = VSYSCALL_ADDR,
+ .vm_end = VSYSCALL_ADDR + PAGE_SIZE,
+ .vm_page_prot = PAGE_READONLY_EXEC,
+ .vm_flags = VM_READ | VM_EXEC,
+ .vm_ops = &gate_vma_ops,
+};
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+#ifdef CONFIG_COMPAT
+ if (!mm || mm->context.ia32_compat)
+ return NULL;
+#endif
+ if (vsyscall_mode == NONE)
+ return NULL;
+ return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma = get_gate_vma(mm);
+
+ if (!vma)
+ return 0;
+
+ return (addr >= vma->vm_start) && (addr < vma->vm_end);
+}
+
+/*
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
+ */
+int in_gate_area_no_mm(unsigned long addr)
+{
+ return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
+}
+
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range. Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present. If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+ set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+ p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+ set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
+#endif
+ pud = pud_offset(p4d, VSYSCALL_ADDR);
+ set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+ pmd = pmd_offset(pud, VSYSCALL_ADDR);
+ set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
+void __init map_vsyscall(void)
+{
+ extern char __vsyscall_page;
+ unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
+
+ if (vsyscall_mode != NONE) {
+ __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
+ PAGE_KERNEL_VVAR);
+ set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+ }
+
+ BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
+ (unsigned long)VSYSCALL_ADDR);
+}
diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
new file mode 100644
index 000000000..c9596a9af
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
@@ -0,0 +1,37 @@
+/*
+ * vsyscall_emu_64.S: Vsyscall emulation page
+ *
+ * Copyright (c) 2011 Andy Lutomirski
+ *
+ * Subject to the GNU General Public License, version 2
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
+
+__PAGE_ALIGNED_DATA
+ .globl __vsyscall_page
+ .balign PAGE_SIZE, 0xcc
+ .type __vsyscall_page, @object
+__vsyscall_page:
+
+ mov $__NR_gettimeofday, %rax
+ syscall
+ ret
+
+ .balign 1024, 0xcc
+ mov $__NR_time, %rax
+ syscall
+ ret
+
+ .balign 1024, 0xcc
+ mov $__NR_getcpu, %rax
+ syscall
+ ret
+
+ .balign 4096, 0xcc
+
+ .size __vsyscall_page, 4096
diff --git a/arch/x86/entry/vsyscall/vsyscall_gtod.c b/arch/x86/entry/vsyscall/vsyscall_gtod.c
new file mode 100644
index 000000000..e1216dd95
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_gtod.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ * Modified for x86 32 bit architecture by
+ * Stefani Seibold <stefani@seibold.net>
+ * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany
+ *
+ * Thanks to hpa@transmeta.com for some useful hint.
+ * Special thanks to Ingo Molnar for his early experience with
+ * a different vsyscall implementation for Linux/IA32 and for the name.
+ *
+ */
+
+#include <linux/timekeeper_internal.h>
+#include <asm/vgtod.h>
+#include <asm/vvar.h>
+
+int vclocks_used __read_mostly;
+
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
+
+void update_vsyscall_tz(void)
+{
+ vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest;
+ vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime;
+}
+
+void update_vsyscall(struct timekeeper *tk)
+{
+ int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode;
+ struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data;
+
+ /* Mark the new vclock used. */
+ BUILD_BUG_ON(VCLOCK_MAX >= 32);
+ WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode));
+
+ gtod_write_begin(vdata);
+
+ /* copy vsyscall data */
+ vdata->vclock_mode = vclock_mode;
+ vdata->cycle_last = tk->tkr_mono.cycle_last;
+ vdata->mask = tk->tkr_mono.mask;
+ vdata->mult = tk->tkr_mono.mult;
+ vdata->shift = tk->tkr_mono.shift;
+
+ vdata->wall_time_sec = tk->xtime_sec;
+ vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec;
+
+ vdata->monotonic_time_sec = tk->xtime_sec
+ + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec
+ + ((u64)tk->wall_to_monotonic.tv_nsec
+ << tk->tkr_mono.shift);
+ while (vdata->monotonic_time_snsec >=
+ (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) {
+ vdata->monotonic_time_snsec -=
+ ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift;
+ vdata->monotonic_time_sec++;
+ }
+
+ vdata->wall_time_coarse_sec = tk->xtime_sec;
+ vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >>
+ tk->tkr_mono.shift);
+
+ vdata->monotonic_time_coarse_sec =
+ vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec;
+ vdata->monotonic_time_coarse_nsec =
+ vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec;
+
+ while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) {
+ vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC;
+ vdata->monotonic_time_coarse_sec++;
+ }
+
+ gtod_write_end(vdata);
+}
diff --git a/arch/x86/entry/vsyscall/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
new file mode 100644
index 000000000..3c3f9765a
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+ TP_PROTO(int nr),
+
+ TP_ARGS(nr),
+
+ TP_STRUCT__entry(__field(int, nr)),
+
+ TP_fast_assign(
+ __entry->nr = nr;
+ ),
+
+ TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>