[PATCH v3 2/5] x86/msr: Carry on after a non-"safe" MSR access fails without !panic_on_oops

[Andy Lutomirski]

This demotes an OOPS and likely panic due to a failed non-"safe" MSR
access to a WARN and, for RDMSR, a return value of zero.  If
panic_on_oops is set, then failed unsafe MSR accesses will still
oops and panic.

To be clear, this type of failure should *not* happen.  This patch
exists to minimize the chance of nasty undebuggable failures due on
systems that used to work due to a now-fixed CONFIG_PARAVIRT=y bug.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
 arch/x86/include/asm/msr.h | 10 ++++++++--
 arch/x86/mm/extable.c      | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 93fb7c1cffda..1487054a1a70 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -92,7 +92,10 @@ static inline unsigned long long native_read_msr(unsigned int msr)
 {
 	DECLARE_ARGS(val, low, high);
 
-	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+	asm volatile("1: rdmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_rdmsr_unsafe)
+		     : EAX_EDX_RET(val, low, high) : "c" (msr));
 	if (msr_tracepoint_active(__tracepoint_read_msr))
 		do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0);
 	return EAX_EDX_VAL(val, low, high);
@@ -119,7 +122,10 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr,
 static inline void native_write_msr(unsigned int msr,
 				    unsigned low, unsigned high)
 {
-	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+	asm volatile("1: wrmsr\n"
+		     "2:\n"
+		     _ASM_EXTABLE_HANDLE(1b, 2b, ex_handler_wrmsr_unsafe)
+		     : : "c" (msr), "a"(low), "d" (high) : "memory");
 	if (msr_tracepoint_active(__tracepoint_read_msr))
 		do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
 }
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 9dd7e4b7fcde..f310714e6e6d 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -49,6 +49,39 @@ bool ex_handler_ext(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL(ex_handler_ext);
 
+bool ex_handler_rdmsr_unsafe(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, int trapnr)
+{
+	WARN(1, "unsafe MSR access error: RDMSR from 0x%x",
+	     (unsigned int)regs->cx);
+
+	/* If panic_on_oops is set, don't try to recover. */
+	if (panic_on_oops)
+		return false;
+
+	regs->ip = ex_fixup_addr(fixup);
+	regs->ax = 0;
+	regs->dx = 0;
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_rdmsr_unsafe);
+
+bool ex_handler_wrmsr_unsafe(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, int trapnr)
+{
+	WARN(1, "unsafe MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x)\n",
+	     (unsigned int)regs->cx,
+	     (unsigned int)regs->dx, (unsigned int)regs->ax);
+
+	/* If panic_on_oops is set, don't try to recover. */
+	if (panic_on_oops)
+		return false;
+
+	regs->ip = ex_fixup_addr(fixup);
+	return true;
+}
+EXPORT_SYMBOL(ex_handler_wrmsr_unsafe);
+
 bool ex_has_fault_handler(unsigned long ip)
 {
 	const struct exception_table_entry *e;
-- 
2.5.0