6 files changed, 70 insertions, 129 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index a4c061fb7c6e..29b36e9e4e74 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -63,7 +63,7 @@ For 32-bit we have the following conventions - kernel is built with
  * for assembly code:
  */
 
-.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0
+.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0
 	.if \save_ret
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
@@ -73,7 +73,7 @@ For 32-bit we have the following conventions - kernel is built with
 	pushq   %rsi		/* pt_regs->si */
 	.endif
 	pushq	\rdx		/* pt_regs->dx */
-	pushq   %rcx		/* pt_regs->cx */
+	pushq   \rcx		/* pt_regs->cx */
 	pushq   \rax		/* pt_regs->ax */
 	pushq   %r8		/* pt_regs->r8 */
 	pushq   %r9		/* pt_regs->r9 */
@@ -99,6 +99,7 @@ For 32-bit we have the following conventions - kernel is built with
 	 * well before they could be put to use in a speculative execution
 	 * gadget.
 	 */
+	xorl	%esi,  %esi	/* nospec si  */
 	xorl	%edx,  %edx	/* nospec dx  */
 	xorl	%ecx,  %ecx	/* nospec cx  */
 	xorl	%r8d,  %r8d	/* nospec r8  */
@@ -114,32 +115,24 @@ For 32-bit we have the following conventions - kernel is built with
 
 .endm
 
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
-	PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0
+	PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret
 	CLEAR_REGS
 .endm
 
-.macro POP_REGS pop_rdi=1 skip_r11rcx=0
+.macro POP_REGS pop_rdi=1
 	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
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73d958522b6a..4300ba49b5ee 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -191,8 +191,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	 * 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
+	POP_REGS pop_rdi=0
 
 	/*
 	 * Now all regs are restored except RSP and RDI.
@@ -215,8 +214,13 @@ syscall_return_via_sysret:
 
 	popq	%rdi
 	popq	%rsp
+SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
 	swapgs
 	sysretq
+SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	int3
 SYM_CODE_END(entry_SYSCALL_64)
 
 /*
@@ -318,6 +322,14 @@ SYM_CODE_END(ret_from_fork)
 #endif
 .endm
 
+/* Save all registers in pt_regs */
+SYM_CODE_START_LOCAL(push_and_clear_regs)
+	UNWIND_HINT_FUNC
+	PUSH_AND_CLEAR_REGS save_ret=1
+	ENCODE_FRAME_POINTER 8
+	RET
+SYM_CODE_END(push_and_clear_regs)
+
 /**
  * idtentry_body - Macro to emit code calling the C function
  * @cfunc:		C function to be called
@@ -325,7 +337,21 @@ SYM_CODE_END(ret_from_fork)
  */
 .macro idtentry_body cfunc has_error_code:req
 
-	call	error_entry
+	call push_and_clear_regs
+	UNWIND_HINT_REGS
+
+	/*
+	 * Call error_entry() and switch to the task stack if from userspace.
+	 *
+	 * When in XENPV, it is already in the task stack, and it can't fault
+	 * for native_iret() nor native_load_gs_index() since XENPV uses its
+	 * own pvops for IRET and load_gs_index().  And it doesn't need to
+	 * switch the CR3.  So it can skip invoking error_entry().
+	 */
+	ALTERNATIVE "call error_entry; movq %rax, %rsp", \
+		"", X86_FEATURE_XENPV
+
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
@@ -358,6 +384,7 @@ SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 	ENDBR
 	ASM_CLAC
+	cld
 
 	.if \has_error_code == 0
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
@@ -426,6 +453,7 @@ SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ENDBR
 	ASM_CLAC
+	cld
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
 
@@ -482,6 +510,7 @@ SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ENDBR
 	ASM_CLAC
+	cld
 
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
@@ -508,6 +537,7 @@ SYM_CODE_START(\asmsym)
 	call	vc_switch_off_ist
 	movq	%rax, %rsp		/* Switch to new stack */
 
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	/* Update pt_regs */
@@ -544,6 +574,7 @@ SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=8
 	ENDBR
 	ASM_CLAC
+	cld
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
 	call	paranoid_entry
@@ -869,7 +900,6 @@ SYM_CODE_END(xen_failsafe_callback)
  */
 SYM_CODE_START_LOCAL(paranoid_entry)
 	UNWIND_HINT_FUNC
-	cld
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 
@@ -983,13 +1013,10 @@ SYM_CODE_START_LOCAL(paranoid_exit)
 SYM_CODE_END(paranoid_exit)
 
 /*
- * Save all registers in pt_regs, and switch GS if needed.
+ * Switch GS and CR3 if needed.
  */
 SYM_CODE_START_LOCAL(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
 
@@ -997,19 +1024,15 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * We entered from user mode or we're pretending to have entered
 	 * from user mode due to an IRET fault.
 	 */
-	SWAPGS
+	swapgs
 	FENCE_SWAPGS_USER_ENTRY
 	/* We have user CR3.  Change to kernel CR3. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 .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
 	RET
 
 	/*
@@ -1033,7 +1056,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * gsbase and proceed.  We'll fix up the exception and land in
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
-	SWAPGS
+	swapgs
 
 	/*
 	 * Issue an LFENCE to prevent GS speculation, regardless of whether it is a
@@ -1041,6 +1064,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 */
 .Lerror_entry_done_lfence:
 	FENCE_SWAPGS_KERNEL_ENTRY
+	leaq	8(%rsp), %rax			/* return pt_regs pointer */
 	RET
 
 .Lbstep_iret:
@@ -1053,7 +1077,7 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * We came from an IRET to user mode, so we have user
 	 * gsbase and CR3.  Switch to kernel gsbase and CR3:
 	 */
-	SWAPGS
+	swapgs
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
@@ -1061,9 +1085,9 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * Pretend that the exception came from user mode: set up pt_regs
 	 * as if we faulted immediately after IRET.
 	 */
-	mov	%rsp, %rdi
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
-	mov	%rax, %rsp
+	mov	%rax, %rdi
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
@@ -1126,6 +1150,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	ASM_CLAC
+	cld
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
@@ -1145,7 +1170,6 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	swapgs
-	cld
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 4fdb007cddbd..d1052742ad0c 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -50,7 +50,7 @@ SYM_CODE_START(entry_SYSENTER_compat)
 	UNWIND_HINT_EMPTY
 	ENDBR
 	/* Interrupts are off on entry. */
-	SWAPGS
+	swapgs
 
 	pushq	%rax
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
@@ -83,32 +83,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 	movl	%eax, %eax
 
 	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   $0			/* pt_regs->r15 = 0 */
-	xorl	%r15d, %r15d		/* nospec   r15 */
-
+	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
 	UNWIND_HINT_REGS
 
 	cld
@@ -225,35 +200,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
 SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 	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   $0			/* pt_regs->r15 = 0 */
-	xorl	%r15d, %r15d		/* nospec   r15 */
-
+	PUSH_AND_CLEAR_REGS rcx=%rbp rax=$-ENOSYS
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi
@@ -297,6 +244,8 @@ sysret32_from_system_call:
 	 * code.  We zero R8-R10 to avoid info leaks.
          */
 	movq	RSP-ORIG_RAX(%rsp), %rsp
+SYM_INNER_LABEL(entry_SYSRETL_compat_unsafe_stack, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
 
 	/*
 	 * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
@@ -314,6 +263,9 @@ sysret32_from_system_call:
 	xorl	%r10d, %r10d
 	swapgs
 	sysretl
+SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	int3
 SYM_CODE_END(entry_SYSCALL_compat)
 
 /*
@@ -362,54 +314,25 @@ SYM_CODE_START(entry_INT80_compat)
 
 	/* 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
+	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, %rdi
+	movq	%rsp, %rax
 	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 */
+	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:
 
-	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	$-ENOSYS		/* pt_regs->ax */
-	pushq   %r8			/* pt_regs->r8 */
-	xorl	%r8d, %r8d		/* nospec   r8 */
-	pushq   %r9			/* pt_regs->r9 */
-	xorl	%r9d, %r9d		/* nospec   r9 */
-	pushq   %r10			/* pt_regs->r10*/
-	xorl	%r10d, %r10d		/* nospec   r10 */
-	pushq   %r11			/* pt_regs->r11 */
-	xorl	%r11d, %r11d		/* nospec   r11 */
-	pushq   %rbx                    /* pt_regs->rbx */
-	xorl	%ebx, %ebx		/* nospec   rbx */
-	pushq   %rbp                    /* pt_regs->rbp */
-	xorl	%ebp, %ebp		/* nospec   rbp */
-	pushq   %r12                    /* pt_regs->r12 */
-	xorl	%r12d, %r12d		/* nospec   r12 */
-	pushq   %r13                    /* pt_regs->r13 */
-	xorl	%r13d, %r13d		/* nospec   r13 */
-	pushq   %r14                    /* pt_regs->r14 */
-	xorl	%r14d, %r14d		/* nospec   r14 */
-	pushq   %r15                    /* pt_regs->r15 */
-	xorl	%r15d, %r15d		/* nospec   r15 */
-
+	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
 	UNWIND_HINT_REGS
 
 	cld
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 693f8b9031fb..c2a8b76ae0bc 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -91,7 +91,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
 endif
 endif
 
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.
@@ -148,6 +148,7 @@ 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 $(RANDSTRUCT_CFLAGS),$(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 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 235a5794296a..1000d457c332 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -438,7 +438,7 @@ bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
 static __init int vdso_setup(char *s)
 {
 	vdso64_enabled = simple_strtoul(s, NULL, 0);
-	return 0;
+	return 1;
 }
 __setup("vdso=", vdso_setup);
 
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index fd2ee9408e91..4af81df133ee 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -48,7 +48,7 @@ static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init =
 #elif defined(CONFIG_LEGACY_VSYSCALL_XONLY)
 	XONLY;
 #else
-	EMULATE;
+	#error VSYSCALL config is broken
 #endif
 
 static int __init vsyscall_setup(char *str)