Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Lai Jiangshan <jiangshanlai@gmail.com>
To:     linux-kernel@vger.kernel.org
Cc:     Borislav Petkov <bp@alien8.de>,
        Peter Zijlstra <peterz@infradead.org>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Andy Lutomirski <luto@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>, x86@kernel.org,
        Lai Jiangshan <jiangshan.ljs@antgroup.com>,
        Ingo Molnar <mingo@redhat.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        "H. Peter Anvin" <hpa@zytor.com>
Subject: [PATCH V5 2/7] x86/entry: Switch the stack after error_entry() returns
Date:   Tue, 12 Apr 2022 20:15:36 +0800
Message-Id: <20220412121541.4595-3-jiangshanlai@gmail.com>
In-Reply-To: <20220412121541.4595-1-jiangshanlai@gmail.com>
References: <20220412121541.4595-1-jiangshanlai@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Lai Jiangshan <jiangshan.ljs@antgroup.com>

error_entry() calls sync_regs(), and fixup_bad_iret() before sync_regs()
if it is a fault from bad IRET, to copy the pt_regs to the kernel stack
and switches the kernel stack directly after sync_regs().

But error_entry() itself is also a function call, so the code has to
stash the address error_entry() is going to return to, in %r12 and
makes the work complicated.

Move the code of switching stack after error_entry() and get rid of the
need to handle the return address.

Signed-off-by: Lai Jiangshan <jiangshan.ljs@antgroup.com>
---
 arch/x86/entry/entry_64.S | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index e9d896717ab4..e1efc56fbcd4 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -326,6 +326,8 @@ SYM_CODE_END(ret_from_fork)
 .macro idtentry_body cfunc has_error_code:req
 
 	call	error_entry
+	movq	%rax, %rsp			/* switch to the task stack if from userspace */
+	ENCODE_FRAME_POINTER
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi			/* pt_regs pointer into 1st argument*/
@@ -999,14 +1001,10 @@ 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
 
 	/*
@@ -1038,6 +1036,7 @@ 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:
@@ -1058,12 +1057,9 @@ 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)
 
-- 
2.19.1.6.gb485710b