Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Lai Jiangshan <jiangshanlai@gmail.com>
To:     linux-kernel@vger.kernel.org
Cc:     x86@kernel.org, Lai Jiangshan <laijs@linux.alibaba.com>,
        Andy Lutomirski <luto@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
        "H. Peter Anvin" <hpa@zytor.com>
Subject: [PATCH V3 02/49] x86/entry: Use the correct fence macro after swapgs in kernel CR3
Date:   Thu, 14 Oct 2021 11:13:25 +0800
Message-Id: <20211014031413.14471-3-jiangshanlai@gmail.com>
In-Reply-To: <20211014031413.14471-1-jiangshanlai@gmail.com>
References: <20211014031413.14471-1-jiangshanlai@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Lai Jiangshan <laijs@linux.alibaba.com>

The commit c75890700455 ("x86/entry/64: Remove unneeded kernel CR3
switching") removes a CR3 write in the faulting path of load_gs_index.

But the path's FENCE_SWAPGS_USER_ENTRY has no fence operation if PTI
is enabled.  Rahter, it depends on the CR3 write of SWITCH_TO_KERNEL_CR3.
So the path should use FENCE_SWAPGS_KERNEL_ENTRY if SWITCH_TO_KERNEL_CR3
is removed.

Fixes: c75890700455 ("x86/entry/64: Remove unneeded kernel CR3 switching")
Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
---
 arch/x86/entry/entry_64.S | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1f98188e83ef..9d468c8877e2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -994,11 +994,6 @@ SYM_CODE_START_LOCAL(error_entry)
 	pushq	%r12
 	ret
 
-.Lerror_entry_done_lfence:
-	FENCE_SWAPGS_KERNEL_ENTRY
-.Lerror_entry_done:
-	ret
-
 	/*
 	 * There are two places in the kernel that can potentially fault with
 	 * usergs. Handle them here.  B stepping K8s sometimes report a
@@ -1021,8 +1016,15 @@ SYM_CODE_START_LOCAL(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
-	FENCE_SWAPGS_USER_ENTRY
-	jmp .Lerror_entry_done
+
+	/*
+	 * The above code has no serializing instruction.  So do an lfence
+	 * to prevent GS speculation, regardless of whether it is kernel
+	 * gsbase or user gsbase.
+	 */
+.Lerror_entry_done_lfence:
+	FENCE_SWAPGS_KERNEL_ENTRY
+	ret
 
 .Lbstep_iret:
 	/* Fix truncated RIP */
-- 
2.19.1.6.gb485710b