x86/traps: Handle #DB for bus lock

Bus locks degrade performance for the whole system, not just for the CPU
that requested the bus lock. Two CPU features "#AC for split lock" and
"#DB for bus lock" provide hooks so that the operating system may choose
one of several mitigation strategies.

#AC for split lock is already implemented. Add code to use the #DB for
bus lock feature to cover additional situations with new options to
mitigate.

split_lock_detect=
		#AC for split lock		#DB for bus lock

off		Do nothing			Do nothing

warn		Kernel OOPs			Warn once per task and
		Warn once per task and		and continues to run.
		disable future checking
	 	When both features are
		supported, warn in #AC

fatal		Kernel OOPs			Send SIGBUS to user.
		Send SIGBUS to user
		When both features are
		supported, fatal in #AC

ratelimit:N	Do nothing			Limit bus lock rate to
						N per second in the
						current non-root user.

Default option is "warn".

Hardware only generates #DB for bus lock detect when CPL>0 to avoid
nested #DB from multiple bus locks while the first #DB is being handled.
So no need to handle #DB for bus lock detected in the kernel.

#DB for bus lock is enabled by bus lock detection bit 2 in DEBUGCTL MSR
while #AC for split lock is enabled by split lock detection bit 29 in
TEST_CTRL MSR.

Both breakpoint and bus lock in the same instruction can trigger one #DB.
The bus lock is handled before the breakpoint in the #DB handler.

Delivery of #DB for bus lock in userspace clears DR6[11], which is set by
the #DB handler right after reading DR6.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/r/20210322135325.682257-3-fenghua.yu@intel.com

1 files changed, 92 insertions, 19 deletions

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 0e422a544835..e25e52bafeb6 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -44,9 +44,9 @@ enum split_lock_detect_state {
 };
 
 /*
- * Default to sld_off because most systems do not support split lock detection
- * split_lock_setup() will switch this to sld_warn on systems that support
- * split lock detect, unless there is a command line override.
+ * Default to sld_off because most systems do not support split lock detection.
+ * sld_state_setup() will switch this to sld_warn on systems that support
+ * split lock/bus lock detect, unless there is a command line override.
  */
 static enum split_lock_detect_state sld_state __ro_after_init = sld_off;
 static u64 msr_test_ctrl_cache __ro_after_init;
@@ -603,6 +603,7 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 }
 
 static void split_lock_init(void);
+static void bus_lock_init(void);
 
 static void init_intel(struct cpuinfo_x86 *c)
 {
@@ -720,6 +721,7 @@ static void init_intel(struct cpuinfo_x86 *c)
 		tsx_disable();
 
 	split_lock_init();
+	bus_lock_init();
 
 	intel_init_thermal(c);
 }
@@ -1020,16 +1022,15 @@ static bool split_lock_verify_msr(bool on)
 	return ctrl == tmp;
 }
 
-static void __init split_lock_setup(void)
+static void __init sld_state_setup(void)
 {
 	enum split_lock_detect_state state = sld_warn;
 	char arg[20];
 	int i, ret;
 
-	if (!split_lock_verify_msr(false)) {
-		pr_info("MSR access failed: Disabled\n");
+	if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
+	    !boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
 		return;
-	}
 
 	ret = cmdline_find_option(boot_command_line, "split_lock_detect",
 				  arg, sizeof(arg));
@@ -1041,17 +1042,14 @@ static void __init split_lock_setup(void)
 			}
 		}
 	}
+	sld_state = state;
+}
 
-	switch (state) {
-	case sld_off:
-		pr_info("disabled\n");
+static void __init __split_lock_setup(void)
+{
+	if (!split_lock_verify_msr(false)) {
+		pr_info("MSR access failed: Disabled\n");
 		return;
-	case sld_warn:
-		pr_info("warning about user-space split_locks\n");
-		break;
-	case sld_fatal:
-		pr_info("sending SIGBUS on user-space split_locks\n");
-		break;
 	}
 
 	rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
@@ -1061,7 +1059,9 @@ static void __init split_lock_setup(void)
 		return;
 	}
 
-	sld_state = state;
+	/* Restore the MSR to its cached value. */
+	wrmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+
 	setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
 }
 
@@ -1118,6 +1118,29 @@ bool handle_guest_split_lock(unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(handle_guest_split_lock);
 
+static void bus_lock_init(void)
+{
+	u64 val;
+
+	/*
+	 * Warn and fatal are handled by #AC for split lock if #AC for
+	 * split lock is supported.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) ||
+	    (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
+	    (sld_state == sld_warn || sld_state == sld_fatal)) ||
+	    sld_state == sld_off)
+		return;
+
+	/*
+	 * Enable #DB for bus lock. All bus locks are handled in #DB except
+	 * split locks are handled in #AC in the fatal case.
+	 */
+	rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
+	val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
+}
+
 bool handle_user_split_lock(struct pt_regs *regs, long error_code)
 {
 	if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal)
@@ -1126,6 +1149,21 @@ bool handle_user_split_lock(struct pt_regs *regs, long error_code)
 	return true;
 }
 
+void handle_bus_lock(struct pt_regs *regs)
+{
+	switch (sld_state) {
+	case sld_off:
+		break;
+	case sld_warn:
+		pr_warn_ratelimited("#DB: %s/%d took a bus_lock trap at address: 0x%lx\n",
+				    current->comm, current->pid, regs->ip);
+		break;
+	case sld_fatal:
+		force_sig_fault(SIGBUS, BUS_ADRALN, NULL);
+		break;
+	}
+}
+
 /*
  * This function is called only when switching between tasks with
  * different split-lock detection modes. It sets the MSR for the
@@ -1166,7 +1204,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
 	{}
 };
 
-void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
+static void __init split_lock_setup(struct cpuinfo_x86 *c)
 {
 	const struct x86_cpu_id *m;
 	u64 ia32_core_caps;
@@ -1193,5 +1231,40 @@ void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
 	}
 
 	cpu_model_supports_sld = true;
-	split_lock_setup();
+	__split_lock_setup();
+}
+
+static void sld_state_show(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) &&
+	    !boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT))
+		return;
+
+	switch (sld_state) {
+	case sld_off:
+		pr_info("disabled\n");
+		break;
+	case sld_warn:
+		if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT))
+			pr_info("#AC: crashing the kernel on kernel split_locks and warning on user-space split_locks\n");
+		else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
+			pr_info("#DB: warning on user-space bus_locks\n");
+		break;
+	case sld_fatal:
+		if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) {
+			pr_info("#AC: crashing the kernel on kernel split_locks and sending SIGBUS on user-space split_locks\n");
+		} else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) {
+			pr_info("#DB: sending SIGBUS on user-space bus_locks%s\n",
+				boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) ?
+				" from non-WB" : "");
+		}
+		break;
+	}
+}
+
+void __init sld_setup(struct cpuinfo_x86 *c)
+{
+	split_lock_setup(c);
+	sld_state_setup();
+	sld_state_show();
 }