[PATCH v2 1/6] x86/bugs: Add asm helpers for executing VERW

From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
To: Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	x86@kernel.org, "H. Peter Anvin" <hpa@zytor.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Josh Poimboeuf <jpoimboe@kernel.org>,
	Andy Lutomirski <luto@kernel.org>,
	Jonathan Corbet <corbet@lwn.net>,
	Sean Christopherson <seanjc@google.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	tony.luck@intel.com, ak@linux.intel.com,
	tim.c.chen@linux.intel.com
Cc: linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
	kvm@vger.kernel.org,
	Alyssa Milburn <alyssa.milburn@linux.intel.com>,
	Daniel Sneddon <daniel.sneddon@linux.intel.com>,
	antonio.gomez.iglesias@linux.intel.com,
	Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
	Alyssa Milburn <alyssa.milburn@intel.com>
Subject: [PATCH  v2 1/6] x86/bugs: Add asm helpers for executing VERW
Date: Tue, 24 Oct 2023 01:08:21 -0700	[thread overview]
Message-ID: <20231024-delay-verw-v2-1-f1881340c807@linux.intel.com> (raw)
In-Reply-To: <20231024-delay-verw-v2-0-f1881340c807@linux.intel.com>

MDS mitigation requires clearing the CPU buffers before returning to
user. This needs to be done late in the exit-to-user path. Current
location of VERW leaves a possibility of kernel data ending up in CPU
buffers for memory accesses done after VERW such as:

  1. Kernel data accessed by an NMI between VERW and return-to-user can
     remain in CPU buffers ( since NMI returning to kernel does not
     execute VERW to clear CPU buffers.
  2. Alyssa reported that after VERW is executed,
     CONFIG_GCC_PLUGIN_STACKLEAK=y scrubs the stack used by a system
     call. Memory accesses during stack scrubbing can move kernel stack
     contents into CPU buffers.
  3. When caller saved registers are restored after a return from
     function executing VERW, the kernel stack accesses can remain in
     CPU buffers(since they occur after VERW).

To fix this VERW needs to be moved very late in exit-to-user path.

In preparation for moving VERW to entry/exit asm code, create macros
that can be used in asm. Also make them depend on a new feature flag
X86_FEATURE_CLEAR_CPU_BUF.

Reported-by: Alyssa Milburn <alyssa.milburn@intel.com>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
---
 arch/x86/include/asm/cpufeatures.h   |  2 +-
 arch/x86/include/asm/nospec-branch.h | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 58cb9495e40f..f21fc0f12737 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -308,10 +308,10 @@
 #define X86_FEATURE_SMBA		(11*32+21) /* "" Slow Memory Bandwidth Allocation */
 #define X86_FEATURE_BMEC		(11*32+22) /* "" Bandwidth Monitoring Event Configuration */
 #define X86_FEATURE_USER_SHSTK		(11*32+23) /* Shadow stack support for user mode applications */
-
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
 #define X86_FEATURE_IBPB_ON_VMEXIT	(11*32+26) /* "" Issue an IBPB only on VMEXIT */
+#define X86_FEATURE_CLEAR_CPU_BUF	(11*32+27) /* "" Clear CPU buffers */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index c55cc243592e..c269ee74682c 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -329,6 +329,25 @@
 #endif
 .endm
 
+/*
+ * Macro to execute VERW instruction to mitigate transient data sampling
+ * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ *
+ * Note: Only the memory operand variant of VERW clears the CPU buffers. To
+ * handle the case when VERW is executed after user registers are restored, use
+ * RIP to point the memory operand to a part NOPL instruction that contains
+ * __KERNEL_DS.
+ */
+.macro CLEAR_CPU_BUFFERS
+	ALTERNATIVE "jmp .Lskip_verw_\@;", "jmp .Ldo_verw_\@", X86_FEATURE_CLEAR_CPU_BUF
+		/* nopl __KERNEL_DS(%rax) */
+		.byte 0x0f, 0x1f, 0x80, 0x00, 0x00;
+.Lverw_arg_\@:	.word __KERNEL_DS;
+.Ldo_verw_\@:	verw _ASM_RIP(.Lverw_arg_\@);
+.Lskip_verw_\@:
+.endm
+
 #else /* __ASSEMBLY__ */
 
 #define ANNOTATE_RETPOLINE_SAFE					\

-- 
2.34.1


