Skip to contentSkip to conversation

x86/entry: Clean up entry code

PATCH Superseded Lai Jiangshan 2 participants 12 messages Mar 3, 2022 – Mar 7, 2022

Subsystems (2)

v2 of 7 Superseded Latest is v7 →

lore
Share & tools
lore
#0 lore raw

v2 cover x86/entry: Clean up entry code

From: Lai Jiangshan <[email protected]>

This patchset moves the stack-switch code to the place where error_entry() return, unravels error_entry() from XENpv and makes entry_INT80_compat use idtentry macro.

This patchset is highly related to XENpv, because it does the extra cleanup to convert SWAPGS to swapgs after major cleanup is done.

The patches are the version 2 of
https://lore.kernel.org/lkml/[email protected]/
which are picked from the patchset
https://lore.kernel.org/lkml/[email protected]/
which coverts ASM code to C code. These patches are prepared for that purpose. But this patchset has it own value: it simplifies the stack switch, avoids leaving the old stack inside a function call, and separates XENpv code with native code without adding new code.

Changed from V1
Squash cleanup patches converting SWAPGS to swapgs into one patch

Use my official email address (Ant Group). The work is backed by my company and I was incorrectly misunderstood that [email protected] is the only portal for opensource work in the corporate group.

PS: I think the work is ready to be queued and I'm deeply sorry not to resend it for more reviews for the last two months because I have been obsessed with a boardgame and my brain power was drained.

Lai Jiangshan (7):
x86/traps: Move pt_regs only in fixup_bad_iret() x86/entry: Switch the stack after error_entry() returns x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry x86/entry: Move cld to the start of idtentry x86/entry: Don't call error_entry for XENPV x86/entry: Use idtentry macro for entry_INT80_compat x86/entry: Convert SWAPGS to swapgs and remove the definition of
SWAPGS

 arch/x86/entry/entry_64.S        |  65 +++++++++++++------
 arch/x86/entry/entry_64_compat.S | 104 +------------------------------
 arch/x86/include/asm/idtentry.h  |  47 ++++++++++++++
 arch/x86/include/asm/irqflags.h  |   2 -
 arch/x86/include/asm/proto.h     |   4 --
 arch/x86/include/asm/traps.h     |   2 +-
 arch/x86/kernel/traps.c          |  17 ++---
 7 files changed, 102 insertions(+), 139 deletions(-)
Signature · 1 line
2.19.1.6.gb485710b
#1 lore raw

PATCH v2 1/7 x86/traps: Move pt_regs only in fixup_bad_iret()

From: Lai Jiangshan <[email protected]>

fixup_bad_iret() and sync_regs() have similar arguments and do similar work that copies full or partial pt_regs to a place and switches stack after return. They are quite the same, but fixup_bad_iret() not only copies the pt_regs but also the return address of error_entry() while sync_regs() copies the pt_regs only and the return address of error_entry() was preserved and handled in ASM code.

This patch makes fixup_bad_iret() work like sync_regs() and the handling of the return address of error_entry() is moved in ASM code.

It removes the need to use the struct bad_iret_stack, simplifies fixup_bad_iret() and makes the ASM error_entry() call fixup_bad_iret() as the same as calling sync_regs() which adds readability because the calling patterns are exactly the same.

It is prepared for later patch to do the stack switch after the error_entry() which simplifies the code further.

---
 arch/x86/entry/entry_64.S    |  5 ++++-
 arch/x86/include/asm/traps.h |  2 +-
 arch/x86/kernel/traps.c      | 17 ++++++-----------
 3 files changed, 11 insertions(+), 13 deletions(-)
arch/x86/entry/entry_64.S +4 -1
index 466df3e50276..24846284eda5 100644
@@ -1039,9 +1039,12 @@ 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
+	popq	%r12				/* save return addr in %12 */
+	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
 	mov	%rax, %rsp
+	ENCODE_FRAME_POINTER
+	pushq	%r12
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
arch/x86/include/asm/traps.h +1 -1
index 6221be7cafc3..1cdd7e8bcba7 100644
@@ -13,7 +13,7 @@
 #ifdef CONFIG_X86_64
 asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs);
 asmlinkage __visible notrace
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s);
+struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs);
 void __init trap_init(void);
 asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs);
 #endif
arch/x86/kernel/traps.c +6 -11
index 7ef00dee35be..2b1f049afb14 100644
@@ -816,13 +816,8 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r
 }
 #endif
 
-struct bad_iret_stack {
-	void *error_entry_ret;
-	struct pt_regs regs;
-};
-
 asmlinkage __visible noinstr
-struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs)
 {
 	/*
 	 * This is called from entry_64.S early in handling a fault
@@ -832,19 +827,19 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
 	 * just below the IRET frame) and we want to pretend that the
 	 * exception came from the IRET target.
 	 */
-	struct bad_iret_stack tmp, *new_stack =
-		(struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
+	struct pt_regs tmp, *new_stack =
+		(struct pt_regs *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1;
 
 	/* Copy the IRET target to the temporary storage. */
-	__memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8);
+	__memcpy(&tmp.ip, (void *)bad_regs->sp, 5*8);
 
 	/* Copy the remainder of the stack from the current stack. */
-	__memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip));
+	__memcpy(&tmp, bad_regs, offsetof(struct pt_regs, ip));
 
 	/* Update the entry stack */
 	__memcpy(new_stack, &tmp, sizeof(tmp));
 
-	BUG_ON(!user_mode(&new_stack->regs));
+	BUG_ON(!user_mode(new_stack));
 	return new_stack;
 }
 #endif
Signature · 1 line
2.19.1.6.gb485710b
#2 lore raw

PATCH v2 2/7 x86/entry: Switch the stack after error_entry() returns

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

error_entry() calls sync_regs() to settle/copy the pt_regs and switches the stack directly after sync_regs(). But error_entry() itself is also a function call, the switching has to handle the return address of it together, which causes the work complicated and tangly.

Switching to the stack after error_entry() makes the code simpler and intuitive.

---
 arch/x86/entry/entry_64.S | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)
arch/x86/entry/entry_64.S +6 -10
index 24846284eda5..a51cad2b7fff 100644
@@ -323,6 +323,8 @@ SYM_CODE_END(ret_from_fork)
 .macro idtentry_body cfunc has_error_code:req
 
 	call	error_entry
+	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
@@ -980,14 +982,10 @@ SYM_CODE_START_LOCAL(error_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
 
 	/*
@@ -1019,6 +1017,7 @@ 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:
@@ -1039,12 +1038,9 @@ 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.
 	 */
-	popq	%r12				/* save return addr in %12 */
-	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
-	mov	%rax, %rsp
-	ENCODE_FRAME_POINTER
-	pushq	%r12
+	mov	%rax, %rdi
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)
 
Signature · 1 line
2.19.1.6.gb485710b
#3 lore raw

Re: [PATCH V2 2/7] x86/entry: Switch the stack after error_entry() returns

Quoted 56 lines · Lai Jiangshan

From: Lai Jiangshan <[email protected]>

error_entry() calls sync_regs() to settle/copy the pt_regs and switches the stack directly after sync_regs(). But error_entry() itself is also a function call, the switching has to handle the return address of it together, which causes the work complicated and tangly.

Switching to the stack after error_entry() makes the code simpler and intuitive.

---
 arch/x86/entry/entry_64.S | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)
arch/x86/entry/entry_64.S +4 -5
index 24846284eda5..a51cad2b7fff 100644
@@ -323,6 +323,8 @@ SYM_CODE_END(ret_from_fork)
 .macro idtentry_body cfunc has_error_code:req
 
 	call	error_entry
+	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
@@ -980,14 +982,10 @@ SYM_CODE_START_LOCAL(error_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
 
 	/*
@@ -1019,6 +1017,7 @@ 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:
@@ -1039,12 +1038,9 @@ 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.
 	 */

arch/x86/entry/entry_64.S SYM_CODE_START_LOCAL(error_entry) · line 1045

Quoted 10 lines
arch/x86/entry/entry_64.S +2 -5
-	popq	%r12				/* save return addr in %12 */
-	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
+	leaq	8(%rsp), %rdi			/* arg0 = pt_regs pointer */
 	call	fixup_bad_iret
-	mov	%rax, %rsp
-	ENCODE_FRAME_POINTER
-	pushq	%r12
+	mov	%rax, %rdi
 	jmp	.Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)

I can't seem to follow; perhaps I need more wake-up-juice?

Suppose we have .Lerror_bad_iret, then the code flow is something like:

	old						new

.Lerror_bad_iret

				SWAWPGS business

	popq	%r12					leaq	8(%rsp), %rsi
	movq	%rsp, %rdi
	call	fixup_bad_iret				call	fixup_bad_iret
	mov	%rax, %rsp				mov	%rax, %rdi
	ENCODE_FRAME_POINTER
	pushq	%r12

		jmp	.Lerror_entry_from_usermode_after_swapgs

.Lerror_entry_from_usermode_after_swapgs

	pop	%r12
	movq	%rsp, %rdi
	call	sync_regs				call	sync_regs
	mov	%rax, %rsp
	ENCODE_FRAME_POINTER
	push	%r12
	RET						RET

The thing that appears to me is that syn_regs is called one stack switch short. This isn't mentioned in the Changelog nor in the comments. Why is this OK?

#4 lore raw

Re: [PATCH V2 2/7] x86/entry: Switch the stack after error_entry() returns

Quoted 93 lines · Peter Zijlstra
Quoted 56 lines · Lai Jiangshan

From: Lai Jiangshan <[email protected]>

error_entry() calls sync_regs() to settle/copy the pt_regs and switches the stack directly after sync_regs(). But error_entry() itself is also a function call, the switching has to handle the return address of it together, which causes the work complicated and tangly.

Switching to the stack after error_entry() makes the code simpler and intuitive.

---
 arch/x86/entry/entry_64.S | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)
arch/x86/entry/entry_64.S +4 -5
index 24846284eda5..a51cad2b7fff 100644
@@ -323,6 +323,8 @@ SYM_CODE_END(ret_from_fork)
 .macro idtentry_body cfunc has_error_code:req
 
      call    error_entry
+     movq    %rax, %rsp                      /* switch stack settled by sync_regs() */
+     ENCODE_FRAME_POINTER
      UNWIND_HINT_REGS
 
      movq    %rsp, %rdi                      /* pt_regs pointer into 1st argument*/
@@ -980,14 +982,10 @@ SYM_CODE_START_LOCAL(error_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
 
      /*
@@ -1019,6 +1017,7 @@ 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:
@@ -1039,12 +1038,9 @@ 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.
       */

arch/x86/entry/entry_64.S SYM_CODE_START_LOCAL(error_entry) · line 1045

Quoted 10 lines
arch/x86/entry/entry_64.S +2 -5
-     popq    %r12                            /* save return addr in %12 */
-     movq    %rsp, %rdi                      /* arg0 = pt_regs pointer */
+     leaq    8(%rsp), %rdi                   /* arg0 = pt_regs pointer */
      call    fixup_bad_iret
-     mov     %rax, %rsp
-     ENCODE_FRAME_POINTER
-     pushq   %r12
+     mov     %rax, %rdi
      jmp     .Lerror_entry_from_usermode_after_swapgs
 SYM_CODE_END(error_entry)

I can't seem to follow; perhaps I need more wake-up-juice?

Suppose we have .Lerror_bad_iret, then the code flow is something like:

old new

.Lerror_bad_iret
SWAWPGS business

popq %r12 leaq 8(%rsp), %rsi
movq %rsp, %rdi
call fixup_bad_iret call fixup_bad_iret
mov %rax, %rsp mov %rax, %rdi
ENCODE_FRAME_POINTER
pushq %r12

jmp .Lerror_entry_from_usermode_after_swapgs

.Lerror_entry_from_usermode_after_swapgs

        pop     %r12
        movq    %rsp, %rdi
        call    sync_regs                               call    sync_regs
        mov     %rax, %rsp
Quoted 10 lines

ENCODE_FRAME_POINTER
push %r12
RET RET

The thing that appears to me is that syn_regs is called one stack switch short. This isn't mentioned in the Changelog nor in the comments. Why is this OK?

I has not been confident enough with the meaning of "short" or "call short" in my understanding of English.

So I tried hard to find the semantic difference between the code before and after the patch.

The logic are the same:
1) feed fixup_bad_iret() with the pt_regs pushed by ASM code
2) fixup_bad_iret() moves the partial pt_regs up
3) feed sync_regs() with the pt_regs returned by fixup_bad_iret()
4) sync_regs() copies the whole pt_regs to kernel stack if needed
5) after error_entry(), it is in kernel stack with the pt_regs

Differences:
Old code switches to copied pt_regs immediately twice in error_entry() while new code switches to the copied pt_regs only once after error_entry() returns.
It is correct since sync_regs() doesn't need to be called close to the pt_regs it handles. And this is the point of this patch which switches stack once only.

Old code stashes the return-address of error_entry() in a scratch register and new code doesn't stash it.
It relies on the fact that fixup_bad_iret() and sync_regs() don't corrupt the return-address of error_entry(). But even the old code also relies on the fact that fixup_bad_iret() and sync_regs() don't corrupt the return-address of themselves. They are the same reliance.

The code had been tested with my additial tracing code in kernel and the x86 selftest code which includes all kinds of cases for bad iret. (tools/testing/selftests/x86/sigreturn.c)

#5 lore raw

PATCH v2 3/7 x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Moving PUSH_AND_CLEAR_REGS out of error_entry doesn't change any functionality. It will enlarge the size:

size arch/x86/entry/entry_64.o.before:
text data bss dec hex filename
17916 384 0 18300 477c arch/x86/entry/entry_64.o

size --format=SysV arch/x86/entry/entry_64.o.before:

.entry.text                      5528      0
.orc_unwind                      6456      0
.orc_unwind_ip                   4304      0

size arch/x86/entry/entry_64.o.after:
text data bss dec hex filename
26868 384 0 27252 6a74 arch/x86/entry/entry_64.o

size --format=SysV arch/x86/entry/entry_64.o.after:

.entry.text                      8200      0
.orc_unwind                     10224      0
.orc_unwind_ip                   6816      0

But .entry.text in x86_64 is 2M aligned, enlarging it to 8.2k doesn't enlarge the final text size.

The tables .orc_unwind[_ip] are enlarged due to it adds many pushes.

It is prepared for not calling error_entry() from XENPV in later patch and for future converting the whole error_entry into C code.

---
 arch/x86/entry/entry_64.S | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
arch/x86/entry/entry_64.S +3 -2
index a51cad2b7fff..3ca64bad4697 100644
@@ -322,6 +322,9 @@ SYM_CODE_END(ret_from_fork)
  */
 .macro idtentry_body cfunc has_error_code:req
 
+	PUSH_AND_CLEAR_REGS
+	ENCODE_FRAME_POINTER
+
 	call	error_entry
 	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
 	ENCODE_FRAME_POINTER
@@ -968,8 +971,6 @@ SYM_CODE_END(paranoid_exit)
 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
 
Signature · 1 line
2.19.1.6.gb485710b
#6 lore raw

Re: [PATCH V2 3/7] x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry

Quoted 23 lines · Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Moving PUSH_AND_CLEAR_REGS out of error_entry doesn't change any functionality. It will enlarge the size:

size arch/x86/entry/entry_64.o.before:
text data bss dec hex filename
17916 384 0 18300 477c arch/x86/entry/entry_64.o

size --format=SysV arch/x86/entry/entry_64.o.before:

.entry.text                      5528      0
.orc_unwind                      6456      0
.orc_unwind_ip                   4304      0

size arch/x86/entry/entry_64.o.after:
text data bss dec hex filename
26868 384 0 27252 6a74 arch/x86/entry/entry_64.o

size --format=SysV arch/x86/entry/entry_64.o.after:

.entry.text                      8200      0
.orc_unwind                     10224      0
.orc_unwind_ip                   6816      0
Quoted 7 lines

But .entry.text in x86_64 is 2M aligned, enlarging it to 8.2k doesn't enlarge the final text size.

The tables .orc_unwind[_ip] are enlarged due to it adds many pushes.

It is prepared for not calling error_entry() from XENPV in later patch and for future converting the whole error_entry into C code.

And also, IIUC, folding that int80 thing a few patches down, right?

#7 lore raw

Re: [PATCH V2 3/7] x86/entry: move PUSH_AND_CLEAR_REGS out of error_entry

Quoted 2 lines · Peter Zijlstra

And also, IIUC, folding that int80 thing a few patches down, right?

I don't think folding that int80 thing into idtentry requires this patch.

I didn't notice int80 is a huge ASM code in a different file until I finished converting the entry code to C code. So folding int80 thing is a patch later.

It is possible to move this patch of folding int80 thing as the first patch, but several patches need to be updated respectively. But I'm afraid of updating ASM code without good reason which requires several days of debugging even if there is a slight mistake, for example, forgetting to update the offset of the stack or register name when switching two lines of code.

#8 lore raw

PATCH v2 4/7 x86/entry: Move cld to the start of idtentry

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

Make it next to CLAC

---
 arch/x86/entry/entry_64.S | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)
arch/x86/entry/entry_64.S +5 -3
index 3ca64bad4697..630bf8164a09 100644
@@ -356,6 +356,7 @@ SYM_CODE_END(ret_from_fork)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 	ASM_CLAC
+	cld
 
 	.if \has_error_code == 0
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
@@ -423,6 +424,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	pushq	$-1			/* ORIG_RAX: no syscall to restart */
 
@@ -478,6 +480,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS
 	ASM_CLAC
+	cld
 
 	/*
 	 * If the entry is from userspace, switch stacks and treat it as
@@ -539,6 +542,7 @@ SYM_CODE_END(\asmsym)
 SYM_CODE_START(\asmsym)
 	UNWIND_HINT_IRET_REGS offset=8
 	ASM_CLAC
+	cld
 
 	/* paranoid_entry returns GS information for paranoid_exit in EBX. */
 	call	paranoid_entry
@@ -852,7 +856,6 @@ 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
 
@@ -970,7 +973,6 @@ SYM_CODE_END(paranoid_exit)
  */
 SYM_CODE_START_LOCAL(error_entry)
 	UNWIND_HINT_FUNC
-	cld
 	testb	$3, CS+8(%rsp)
 	jz	.Lerror_kernelspace
 
@@ -1103,6 +1105,7 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	ASM_CLAC
+	cld
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
@@ -1122,7 +1125,6 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	swapgs
-	cld
 	FENCE_SWAPGS_USER_ENTRY
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
Signature · 1 line
2.19.1.6.gb485710b
#9 lore raw

PATCH v2 5/7 x86/entry: Don't call error_entry for XENPV

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

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 CR3. So there is no reason to call error_entry() in XENPV.

---
 arch/x86/entry/entry_64.S | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
arch/x86/entry/entry_64.S +11 -2
index 630bf8164a09..adc9f7619d1b 100644
@@ -325,8 +325,17 @@ SYM_CODE_END(ret_from_fork)
 	PUSH_AND_CLEAR_REGS
 	ENCODE_FRAME_POINTER
 
-	call	error_entry
-	movq	%rax, %rsp			/* switch stack settled by sync_regs() */
+	/*
+	 * Call error_entry and switch stack settled by sync_regs().
+	 *
+	 * 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 CR3.  So it can skip invoking error_entry().
+	 */
+	ALTERNATIVE "call error_entry; movq %rax, %rsp", \
+		"", X86_FEATURE_XENPV
+
 	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
Signature · 1 line
2.19.1.6.gb485710b
#10 lore raw

PATCH v2 6/7 x86/entry: Use idtentry macro for entry_INT80_compat

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

entry_INT80_compat is identical to idtentry macro except a special handling for %rax in the prolog.

Add the prolog to idtentry and use idtentry for entry_INT80_compat.

---
 arch/x86/entry/entry_64.S        |  18 ++++++
 arch/x86/entry/entry_64_compat.S | 102 -------------------------------
 arch/x86/include/asm/idtentry.h  |  47 ++++++++++++++
 arch/x86/include/asm/proto.h     |   4 --
 4 files changed, 65 insertions(+), 106 deletions(-)
arch/x86/entry/entry_64.S +18 -0
index adc9f7619d1b..88b61f310289 100644
@@ -371,6 +371,24 @@ SYM_CODE_START(\asmsym)
 		pushq	$-1			/* ORIG_RAX: no syscall to restart */
 	.endif
 
+	.if \vector == IA32_SYSCALL_VECTOR
+		/*
+		 * 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
+
+		/*
+		 * do_int80_syscall_32() expects regs->orig_ax to be user ax,
+		 * and regs->ax to be $-ENOSYS.
+		 */
+		movq	%rax, (%rsp)
+		movq	$-ENOSYS, %rax
+	.endif
+
 	.if \vector == X86_TRAP_BP
 		/*
 		 * If coming from kernel space, create a 6-word gap to allow the
arch/x86/entry/entry_64_compat.S +0 -102

105 lines not on this page · raw message

arch/x86/include/asm/idtentry.h +47 -0

65 lines not on this page · raw message

arch/x86/include/asm/proto.h +0 -4
index feed36d44d04..c4d331fe65ff 100644
@@ -28,10 +28,6 @@ void entry_SYSENTER_compat(void);
 void __end_entry_SYSENTER_compat(void);
 void entry_SYSCALL_compat(void);
 void entry_SYSCALL_compat_safe_stack(void);
-void entry_INT80_compat(void);
-#ifdef CONFIG_XEN_PV
-void xen_entry_INT80_compat(void);
-#endif
 #endif
 
 void x86_configure_nx(void);
Signature · 1 line
2.19.1.6.gb485710b
#11 lore raw

PATCH v2 7/7 x86/entry: Convert SWAPGS to swapgs and remove the definition of SWAPGS

In reply to Lai Jiangshan

From: Lai Jiangshan <[email protected]>

XENPV doesn't use swapgs_restore_regs_and_return_to_usermode(), error_entry() and entry_SYSENTER_compat(), so the PV-awared SWAPGS in them can be changed to swapgs. There is no user of the SWAPGS anymore after this change.

The INTERRUPT_RETURN in swapgs_restore_regs_and_return_to_usermode() is also converted.

---
 arch/x86/entry/entry_64.S        | 10 +++++-----
 arch/x86/entry/entry_64_compat.S |  2 +-
 arch/x86/include/asm/irqflags.h  |  2 --
 3 files changed, 6 insertions(+), 8 deletions(-)
arch/x86/entry/entry_64.S +5 -5
index 88b61f310289..d9c885400034 100644
@@ -644,8 +644,8 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 
 	/* Restore RDI. */
 	popq	%rdi
-	SWAPGS
-	INTERRUPT_RETURN
+	swapgs
+	jmp	native_iret
 
 
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
@@ -1007,7 +1007,7 @@ 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
@@ -1039,7 +1039,7 @@ 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
@@ -1060,7 +1060,7 @@ 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
 
arch/x86/entry/entry_64_compat.S +1 -1
index a4fcea0cab14..72e017c3941f 100644
@@ -49,7 +49,7 @@
 SYM_CODE_START(entry_SYSENTER_compat)
 	UNWIND_HINT_EMPTY
 	/* Interrupts are off on entry. */
-	SWAPGS
+	swapgs
 
 	pushq	%rax
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
arch/x86/include/asm/irqflags.h +0 -2
index 87761396e8cc..ac2e4cc47210 100644
@@ -140,13 +140,11 @@ static __always_inline void arch_local_irq_restore(unsigned long flags)
 #else
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_XEN_PV
-#define SWAPGS	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
 #define INTERRUPT_RETURN						\
 	ANNOTATE_RETPOLINE_SAFE;					\
 	ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);",		\
 		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 #else
-#define SWAPGS	swapgs
 #define INTERRUPT_RETURN	jmp native_iret
 #endif
 #endif
Signature · 1 line
2.19.1.6.gb485710b