14 files changed, 240 insertions, 246 deletions

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 47368ab0bda0..e59d3073e7cf 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -175,8 +175,7 @@ For 32-bit we have the following conventions - kernel is built with
 #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
+.macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
 	mov	%cr3, \scratch_reg
 
 	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
@@ -206,13 +205,20 @@ For 32-bit we have the following conventions - kernel is built with
 	/* Flip the PGD to the user version */
 	orq     $(PTI_USER_PGTABLE_MASK), \scratch_reg
 	mov	\scratch_reg, %cr3
+.endm
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	SWITCH_TO_USER_CR3 \scratch_reg \scratch_reg2
 .Lend_\@:
 .endm
 
 .macro SWITCH_TO_USER_CR3_STACK	scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
 	pushq	%rax
-	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+	SWITCH_TO_USER_CR3 scratch_reg=\scratch_reg scratch_reg2=%rax
 	popq	%rax
+.Lend_\@:
 .endm
 
 .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6c2826417b33..6356060caaf3 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -19,12 +19,14 @@
 #include <linux/nospec.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/init.h>
 
 #ifdef CONFIG_XEN_PV
 #include <xen/xen-ops.h>
 #include <xen/events.h>
 #endif
 
+#include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -70,7 +72,8 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
 	return false;
 }
 
-__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
+/* Returns true to return using SYSRET, or false to use IRET */
+__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
 {
 	add_random_kstack_offset();
 	nr = syscall_enter_from_user_mode(regs, nr);
@@ -84,6 +87,46 @@ __visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
 
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
+
+	/*
+	 * Check that the register state is valid for using SYSRET to exit
+	 * to userspace.  Otherwise use the slower but fully capable IRET
+	 * exit path.
+	 */
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* SYSRET requires RCX == RIP and R11 == EFLAGS */
+	if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
+		return false;
+
+	/*
+	 * 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.
+	 *
+	 * TASK_SIZE_MAX covers all user-accessible addresses other than
+	 * the deprecated vsyscall page.
+	 */
+	if (unlikely(regs->ip >= TASK_SIZE_MAX))
+		return false;
+
+	/*
+	 * SYSRET cannot restore RF.  It can restore TF, but unlike IRET,
+	 * restoring TF results in a trap from userspace immediately after
+	 * SYSRET.
+	 */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
+		return false;
+
+	/* Use SYSRET to exit to userspace */
+	return true;
 }
 #endif
 
@@ -96,6 +139,16 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs)
 	return (int)regs->orig_ax;
 }
 
+#ifdef CONFIG_IA32_EMULATION
+bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
+
+static int ia32_emulation_override_cmdline(char *arg)
+{
+	return kstrtobool(arg, &__ia32_enabled);
+}
+early_param("ia32_emulation", ia32_emulation_override_cmdline);
+#endif
+
 /*
  * Invoke a 32-bit syscall.  Called with IRQs on in CONTEXT_KERNEL.
  */
@@ -115,7 +168,96 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 	}
 }
 
-/* Handles int $0x80 */
+#ifdef CONFIG_IA32_EMULATION
+static __always_inline bool int80_is_external(void)
+{
+	const unsigned int offs = (0x80 / 32) * 0x10;
+	const u32 bit = BIT(0x80 % 32);
+
+	/* The local APIC on XENPV guests is fake */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/*
+	 * If vector 0x80 is set in the APIC ISR then this is an external
+	 * interrupt. Either from broken hardware or injected by a VMM.
+	 *
+	 * Note: In guest mode this is only valid for secure guests where
+	 * the secure module fully controls the vAPIC exposed to the guest.
+	 */
+	return apic_read(APIC_ISR + offs) & bit;
+}
+
+/**
+ * int80_emulation - 32-bit legacy syscall entry
+ *
+ * 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.
+ *
+ * The arguments for the INT $0x80 based syscall are on stack in the
+ * pt_regs structure:
+ *   eax:				system call number
+ *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
+ */
+DEFINE_IDTENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	/* Kernel does not use INT $0x80! */
+	if (unlikely(!user_mode(regs))) {
+		irqentry_enter(regs);
+		instrumentation_begin();
+		panic("Unexpected external interrupt 0x80\n");
+	}
+
+	/*
+	 * Establish kernel context for instrumentation, including for
+	 * int80_is_external() below which calls into the APIC driver.
+	 * Identical for soft and external interrupts.
+	 */
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/* Validate that this is a soft interrupt to the extent possible */
+	if (unlikely(int80_is_external()))
+		panic("Unexpected external interrupt 0x80\n");
+
+	/*
+	 * The low level idtentry code pushed -1 into regs::orig_ax
+	 * and regs::ax contains the syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#else /* CONFIG_IA32_EMULATION */
+
+/* Handles int $0x80 on a 32bit kernel */
 __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 {
 	int nr = syscall_32_enter(regs);
@@ -134,6 +276,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs)
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
+#endif /* !CONFIG_IA32_EMULATION */
 
 static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 {
@@ -182,8 +325,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
 	return true;
 }
 
-/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
 {
 	/*
 	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
@@ -201,41 +344,36 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
 
 	/* Invoke the syscall. If it failed, keep it simple: use IRET. */
 	if (!__do_fast_syscall_32(regs))
-		return 0;
+		return false;
 
-#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.
+	 * Check that the register state is valid for using SYSRETL/SYSEXIT
+	 * to exit to userspace.  Otherwise use the slower but fully capable
+	 * IRET exit path.
 	 */
-	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
+
+	/* XEN PV guests always use the IRET path */
+	if (cpu_feature_enabled(X86_FEATURE_XENPV))
+		return false;
+
+	/* EIP must point to the VDSO landing pad */
+	if (unlikely(regs->ip != landing_pad))
+		return false;
+
+	/* CS and SS must match the values set in MSR_STAR */
+	if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
+		return false;
+
+	/* If the TF, RF, or VM flags are set, use IRET */
+	if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
+		return false;
+
+	/* Use SYSRETL/SYSEXIT to exit to userspace */
+	return true;
 }
 
-/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible noinstr long do_SYSENTER_32(struct pt_regs *regs)
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
 {
 	/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
 	regs->sp = regs->bp;
@@ -294,7 +432,7 @@ static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 
 	set_irq_regs(old_regs);
 }
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index bfb7bcb362bc..8c8d38f0cb1d 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -3,8 +3,8 @@
  * Common place for both 32- and 64-bit entry routines.
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
-#include <asm/export.h>
 #include <asm/msr-index.h>
 
 .pushsection .noinstr.text, "ax"
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d4e094b2c877..4e295798638b 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -837,7 +837,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 	movl	%esp, %eax
 	call	do_SYSENTER_32
-	testl	%eax, %eax
+	testb	%al, %al
 	jz	.Lsyscall_32_done
 
 	STACKLEAK_ERASE
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 6d236652fceb..567d973eed03 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -18,6 +18,7 @@
  * - SYM_FUNC_START/END:Define functions in the symbol table.
  * - idtentry:		Define exception entry points.
  */
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/cache.h>
@@ -34,7 +35,6 @@
 #include <asm/asm.h>
 #include <asm/smap.h>
 #include <asm/pgtable_types.h>
-#include <asm/export.h>
 #include <asm/frame.h>
 #include <asm/trapnr.h>
 #include <asm/nospec-branch.h>
@@ -126,70 +126,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * In the Xen PV case we must use iret anyway.
 	 */
 
-	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
-		X86_FEATURE_XENPV
-
-	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
+	ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
+		"jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
 	/*
 	 * We win! This label is here just for ease of understanding
@@ -621,17 +559,27 @@ __irqentry_text_end:
 SYM_CODE_START_LOCAL(common_interrupt_return)
 SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	IBRS_EXIT
-#ifdef CONFIG_DEBUG_ENTRY
-	/* Assert that pt_regs indicates user mode. */
-	testb	$3, CS(%rsp)
-	jnz	1f
-	ud2
-1:
-#endif
 #ifdef CONFIG_XEN_PV
 	ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 #endif
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI
+#endif
+
+	STACKLEAK_ERASE
+	POP_REGS
+	add	$8, %rsp	/* orig_ax */
+	UNWIND_HINT_IRET_REGS
 
+.Lswapgs_and_iret:
+	swapgs
+	/* Assert that the IRET frame indicates user mode. */
+	testb	$3, 8(%rsp)
+	jnz	.Lnative_iret
+	ud2
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+.Lpti_restore_regs_and_return_to_usermode:
 	POP_REGS pop_rdi=0
 
 	/*
@@ -658,13 +606,14 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	 */
 	STACKLEAK_ERASE_NOCLOBBER
 
-	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+	push	%rax
+	SWITCH_TO_USER_CR3 scratch_reg=%rdi scratch_reg2=%rax
+	pop	%rax
 
 	/* Restore RDI. */
 	popq	%rdi
-	swapgs
-	jmp	.Lnative_iret
-
+	jmp	.Lswapgs_and_iret
+#endif
 
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
 #ifdef CONFIG_DEBUG_ENTRY
@@ -1509,18 +1458,16 @@ nmi_restore:
 	iretq
 SYM_CODE_END(asm_exc_nmi)
 
-#ifndef CONFIG_IA32_EMULATION
 /*
  * This handles SYSCALL from 32-bit code.  There is no way to program
  * MSRs to fully disable 32-bit SYSCALL.
  */
-SYM_CODE_START(ignore_sysret)
+SYM_CODE_START(entry_SYSCALL32_ignore)
 	UNWIND_HINT_END_OF_STACK
 	ENDBR
 	mov	$-ENOSYS, %eax
 	sysretl
-SYM_CODE_END(ignore_sysret)
-#endif
+SYM_CODE_END(entry_SYSCALL32_ignore)
 
 .pushsection .text, "ax"
 	__FUNC_ALIGN
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 70150298f8bd..de94e2e84ecc 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -118,9 +118,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 
 	movq	%rsp, %rdi
 	call	do_SYSENTER_32
-	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
-		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 	jmp	sysret32_from_system_call
 
 .Lsysenter_fix_flags:
@@ -212,13 +209,15 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
+
+sysret32_from_system_call:
 	/* XEN PV guests always use IRET path */
-	ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
+	ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
 		    "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
 
-	/* Opportunistic SYSRET */
-sysret32_from_system_call:
 	/*
+	 * Opportunistic SYSRET
+	 *
 	 * We are not going to return to userspace from the trampoline
 	 * stack. So let's erase the thread stack right now.
 	 */
@@ -276,80 +275,3 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	int3
 SYM_CODE_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
- * $0x80 regardless of what instruction was originally used to do the
- * system call.
- *
- * This is considered a slow path.  It is not used by most libc
- * implementations on modern hardware except during process startup.
- *
- * Arguments:
- * eax  system call number
- * ebx  arg1
- * ecx  arg2
- * edx  arg3
- * esi  arg4
- * edi  arg5
- * ebp  arg6
- */
-SYM_CODE_START(entry_INT80_compat)
-	UNWIND_HINT_ENTRY
-	ENDBR
-	/*
-	 * Interrupts are off on entry.
-	 */
-	ASM_CLAC			/* Do this early to minimize exposure */
-	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
-
-	/*
-	 * User tracing code (ptrace or signal handlers) might assume that
-	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
-	 * syscall.  Just in case the high bits are nonzero, zero-extend
-	 * the syscall number.  (This could almost certainly be deleted
-	 * with no ill effects.)
-	 */
-	movl	%eax, %eax
-
-	/* switch to thread stack expects orig_ax and rdi to be pushed */
-	pushq	%rax			/* pt_regs->orig_ax */
-
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
-
-	/* In the Xen PV case we already run on the thread stack. */
-	ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
-
-	movq	%rsp, %rax
-	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp
-
-	pushq	5*8(%rax)		/* regs->ss */
-	pushq	4*8(%rax)		/* regs->rsp */
-	pushq	3*8(%rax)		/* regs->eflags */
-	pushq	2*8(%rax)		/* regs->cs */
-	pushq	1*8(%rax)		/* regs->ip */
-	pushq	0*8(%rax)		/* regs->orig_ax */
-.Lint80_keep_stack:
-
-	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
-	UNWIND_HINT_REGS
-
-	cld
-
-	IBRS_ENTER
-	UNTRAIN_RET
-
-	movq	%rsp, %rdi
-	call	do_int80_syscall_32
-	jmp	swapgs_restore_regs_and_return_to_usermode
-SYM_CODE_END(entry_INT80_compat)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 2d0b1bd866ea..5f8591ce7f25 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -264,7 +264,7 @@
 250	i386	fadvise64		sys_ia32_fadvise64
 # 251 is available for reuse (was briefly sys_set_zone_reclaim)
 252	i386	exit_group		sys_exit_group
-253	i386	lookup_dcookie		sys_lookup_dcookie		compat_sys_lookup_dcookie
+253	i386	lookup_dcookie
 254	i386	epoll_create		sys_epoll_create
 255	i386	epoll_ctl		sys_epoll_ctl
 256	i386	epoll_wait		sys_epoll_wait
@@ -457,3 +457,12 @@
 450	i386	set_mempolicy_home_node		sys_set_mempolicy_home_node
 451	i386	cachestat		sys_cachestat
 452	i386	fchmodat2		sys_fchmodat2
+453	i386	map_shadow_stack	sys_map_shadow_stack
+454	i386	futex_wake		sys_futex_wake
+455	i386	futex_wait		sys_futex_wait
+456	i386	futex_requeue		sys_futex_requeue
+457	i386	statmount		sys_statmount
+458	i386	listmount		sys_listmount
+459	i386	lsm_get_self_attr	sys_lsm_get_self_attr
+460	i386	lsm_set_self_attr	sys_lsm_set_self_attr
+461	i386	lsm_list_modules	sys_lsm_list_modules
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 1d6eee30eceb..7e8d46f4147f 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -220,7 +220,7 @@
 209	64	io_submit		sys_io_submit
 210	common	io_cancel		sys_io_cancel
 211	64	get_thread_area
-212	common	lookup_dcookie		sys_lookup_dcookie
+212	common	lookup_dcookie
 213	common	epoll_create		sys_epoll_create
 214	64	epoll_ctl_old
 215	64	epoll_wait_old
@@ -375,6 +375,14 @@
 451	common	cachestat		sys_cachestat
 452	common	fchmodat2		sys_fchmodat2
 453	64	map_shadow_stack	sys_map_shadow_stack
+454	common	futex_wake		sys_futex_wake
+455	common	futex_wait		sys_futex_wait
+456	common	futex_requeue		sys_futex_requeue
+457	common	statmount		sys_statmount
+458	common	listmount		sys_listmount
+459	common	lsm_get_self_attr	sys_lsm_get_self_attr
+460	common	lsm_set_self_attr	sys_lsm_set_self_attr
+461	common	lsm_list_modules	sys_lsm_list_modules
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index ff6e7003da97..0103e103a657 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -4,9 +4,9 @@
  * Copyright 2008 by Steven Rostedt, Red Hat, Inc
  *  (inspired by Andi Kleen's thunk_64.S)
  */
+	#include <linux/export.h>
 	#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
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 27b5da2111ac..416b400f39db 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -4,10 +4,10 @@
  * disturbance of register allocation in some inline assembly constructs.
  * Copyright 2001,2002 by Andi Kleen, SuSE Labs.
  */
+#include <linux/export.h>
 #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
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 6a1821bd7d5e..b1b8dd1608f7 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -42,7 +42,8 @@ vdso_img-$(VDSO64-y)		+= 64
 vdso_img-$(VDSOX32-y)		+= x32
 vdso_img-$(VDSO32-y)		+= 32
 
-obj-$(VDSO32-y)			+= vdso32-setup.o
+obj-$(VDSO32-y)				 += vdso32-setup.o
+OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
 
 vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
 vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F)
@@ -190,31 +191,4 @@ GCOV_PROFILE := n
 quiet_cmd_vdso_and_check = VDSO    $@
       cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check)
 
-#
-# 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/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 7d70935b6758..0debc194bd78 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -11,12 +11,10 @@
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
 #include "../../../../lib/vdso/gettimeofday.c"
 
-extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
-extern __kernel_old_time_t __vdso_time(__kernel_old_time_t *t);
-
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
@@ -35,9 +33,6 @@ __kernel_old_time_t time(__kernel_old_time_t *t)	__attribute__((weak, alias("__v
 
 #if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64)
 /* both 64-bit and x32 use these */
-extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
-extern int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res);
-
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
@@ -56,9 +51,6 @@ int clock_getres(clockid_t, struct __kernel_timespec *)
 
 #else
 /* i386 only */
-extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts);
-extern int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res);
-
 int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts)
 {
 	return __cvdso_clock_gettime32(clock, ts);
diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c
index f3b3cacbcbb0..76e4e74f35b5 100644
--- a/arch/x86/entry/vdso/vdso32-setup.c
+++ b/arch/x86/entry/vdso/vdso32-setup.c
@@ -67,7 +67,6 @@ static struct ctl_table abi_table2[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
 	},
-	{}
 };
 
 static __init int ia32_binfmt_init(void)
diff --git a/arch/x86/entry/vdso/vsgx.S b/arch/x86/entry/vdso/vsgx.S
index d77d278ee9dd..37a3d4c02366 100644
--- a/arch/x86/entry/vdso/vsgx.S
+++ b/arch/x86/entry/vdso/vsgx.S
@@ -1,7 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
 #include <linux/linkage.h>
-#include <asm/export.h>
 #include <asm/errno.h>
 #include <asm/enclu.h>