[PATCH 2/2] x86/paravirt: add extra clobbers with ZERO_CALL_USED_REGS enabled

From: Bill Wendling <morbo@google.com>
To: Juergen Gross <jgross@suse.com>,
	"Srivatsa S. Bhat (VMware)" <srivatsa@csail.mit.edu>,
	 Alexey Makhalov <amakhalov@vmware.com>,
	VMware PV-Drivers Reviewers <pv-drivers@vmware.com>,
	 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>,
	virtualization@lists.linux-foundation.org,
	 linux-kernel@vger.kernel.org,
	Nathan Chancellor <nathan@kernel.org>,
	 Nick Desaulniers <ndesaulniers@google.com>,
	llvm@lists.linux.dev
Cc: Bill Wendling <morbo@google.com>
Subject: [PATCH 2/2] x86/paravirt: add extra clobbers with ZERO_CALL_USED_REGS enabled
Date: Fri,  2 Sep 2022 21:37:50 +0000	[thread overview]
Message-ID: <20220902213750.1124421-3-morbo@google.com> (raw)
In-Reply-To: <20220902213750.1124421-1-morbo@google.com>

The ZERO_CALL_USED_REGS feature may zero out caller-saved registers
before returning.

In spurious_kernel_fault(), the "pte_offset_kernel()" call results in
this assembly code:

.Ltmp151:
        #APP
        # ALT: oldnstr
.Ltmp152:
.Ltmp153:
.Ltmp154:
        .section        .discard.retpoline_safe,"",@progbits
        .quad   .Ltmp154
        .text

        callq   *pv_ops+536(%rip)

.Ltmp155:
        .section        .parainstructions,"a",@progbits
        .p2align        3, 0x0
        .quad   .Ltmp153
        .byte   67
        .byte   .Ltmp155-.Ltmp153
        .short  1
        .text
.Ltmp156:
        # ALT: padding
        .zero   (-(((.Ltmp157-.Ltmp158)-(.Ltmp156-.Ltmp152))>0))*((.Ltmp157-.Ltmp158)-(.Ltmp156-.Ltmp152)),144
.Ltmp159:
        .section        .altinstructions,"a",@progbits
.Ltmp160:
        .long   .Ltmp152-.Ltmp160
.Ltmp161:
        .long   .Ltmp158-.Ltmp161
        .short  33040
        .byte   .Ltmp159-.Ltmp152
        .byte   .Ltmp157-.Ltmp158
        .text

        .section        .altinstr_replacement,"ax",@progbits
        # ALT: replacement 1
.Ltmp158:
        movq    %rdi, %rax
.Ltmp157:
        .text
        #NO_APP
.Ltmp162:
        testb   $-128, %dil

The "testb" here is using %dil, but the %rdi register was cleared before
returning from "callq *pv_ops+536(%rip)". Adding the proper constraints
results in the use of a different register:

        movq    %r11, %rdi

        # Similar to above.

        testb   $-128, %r11b

Link: https://github.com/KSPP/linux/issues/192
Signed-off-by: Bill Wendling <morbo@google.com>
Reported-and-tested-by: Nathan Chancellor <nathan@kernel.org>
---
 arch/x86/include/asm/paravirt_types.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index f04157456a49..b1ab5d94881b 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -414,8 +414,17 @@ int paravirt_disable_iospace(void);
 				"=c" (__ecx)
 #define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
 
-/* void functions are still allowed [re]ax for scratch */
+/*
+ * void functions are still allowed [re]ax for scratch.
+ *
+ * The ZERO_CALL_USED REGS feature may end up zeroing out callee-saved
+ * registers. Make sure we model this with the appropriate clobbers.
+ */
+#ifdef CONFIG_ZERO_CALL_USED_REGS
+#define PVOP_VCALLEE_CLOBBERS	"=a" (__eax), PVOP_VCALL_CLOBBERS
+#else
 #define PVOP_VCALLEE_CLOBBERS	"=a" (__eax)
+#endif
 #define PVOP_CALLEE_CLOBBERS	PVOP_VCALLEE_CLOBBERS
 
 #define EXTRA_CLOBBERS	 , "r8", "r9", "r10", "r11"
-- 
2.37.2.789.g6183377224-goog

