Merge tag 'x86-splitlock-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 splitlock updates from Thomas Gleixner:
 "Support for 'split lock' detection:

  Atomic operations (lock prefixed instructions) which span two cache
  lines have to acquire the global bus lock. This is at least 1k cycles
  slower than an atomic operation within a cache line and disrupts
  performance on other cores. Aside of performance disruption this is a
  unpriviledged form of DoS.

  Some newer CPUs have the capability to raise an #AC trap when such an
  operation is attempted. The detection is by default enabled in warning
  mode which will warn once when a user space application is caught. A
  command line option allows to disable the detection or to select fatal
  mode which will terminate offending applications with SIGBUS"

* tag 'x86-splitlock-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/split_lock: Avoid runtime reads of the TEST_CTRL MSR
  x86/split_lock: Rework the initialization flow of split lock detection
  x86/split_lock: Enable split lock detection by kernel

Documentation/admin-guide/kernel-parameters.txt

@@ -4711,6 +4711,28 @@
 	spia_pedr=
 	spia_peddr=
 
+	split_lock_detect=
+			[X86] Enable split lock detection
+
+			When enabled (and if hardware support is present), atomic
+			instructions that access data across cache line
+			boundaries will result in an alignment check exception.
+
+			off	- not enabled
+
+			warn	- the kernel will emit rate limited warnings
+				  about applications triggering the #AC
+				  exception. This mode is the default on CPUs
+				  that supports split lock detection.
+
+			fatal	- the kernel will send SIGBUS to applications
+				  that trigger the #AC exception.
+
+			If an #AC exception is hit in the kernel or in
+			firmware (i.e. not while executing in user mode)
+			the kernel will oops in either "warn" or "fatal"
+			mode.
+
 	srcutree.counter_wrap_check [KNL]
 			Specifies how frequently to check for
 			grace-period sequence counter wrap for the

arch/x86/include/asm/cpu.h

@@ -40,4 +40,16 @@ int mwait_usable(const struct cpuinfo_x86 *);
 unsigned int x86_family(unsigned int sig);
 unsigned int x86_model(unsigned int sig);
 unsigned int x86_stepping(unsigned int sig);
+#ifdef CONFIG_CPU_SUP_INTEL
+extern void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c);
+extern void switch_to_sld(unsigned long tifn);
+extern bool handle_user_split_lock(struct pt_regs *regs, long error_code);
+#else
+static inline void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) {}
+static inline void switch_to_sld(unsigned long tifn) {}
+static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code)
+{
+	return false;
+}
+#endif
 #endif /* _ASM_X86_CPU_H */

arch/x86/include/asm/cpufeatures.h

@@ -285,6 +285,7 @@
 #define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
 #define X86_FEATURE_FENCE_SWAPGS_USER	(11*32+ 4) /* "" LFENCE in user entry SWAPGS path */
 #define X86_FEATURE_FENCE_SWAPGS_KERNEL	(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
+#define X86_FEATURE_SPLIT_LOCK_DETECT	(11*32+ 6) /* #AC for split lock */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -368,6 +369,7 @@
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_CORE_CAPABILITIES	(18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*

arch/x86/include/asm/msr-index.h

@@ -41,6 +41,10 @@
 
 /* Intel MSRs. Some also available on other CPUs */
 
+#define MSR_TEST_CTRL				0x00000033
+#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT	29
+#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT		BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT)
+
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			BIT(0)	   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP_SHIFT		1	   /* Single Thread Indirect Branch Predictor (STIBP) bit */
@@ -70,6 +74,11 @@
  */
 #define MSR_IA32_UMWAIT_CONTROL_TIME_MASK	(~0x03U)
 
+/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */
+#define MSR_IA32_CORE_CAPS			  0x000000cf
+#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT  5
+#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT	  BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT)
+
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)

arch/x86/include/asm/thread_info.h

@@ -92,6 +92,7 @@ struct thread_info {
 #define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
+#define TIF_SLD			18	/* Restore split lock detection on context switch */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
 #define TIF_IO_BITMAP		22	/* uses I/O bitmap */
@@ -121,6 +122,7 @@ struct thread_info {
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_SLD		(1 << TIF_SLD)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
 #define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
@@ -139,7 +141,7 @@ struct thread_info {
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW_BASE					\
 	(_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP |		\
-	 _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE)
+	 _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE | _TIF_SLD)
 
 /*
  * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated.

arch/x86/kernel/cpu/common.c

@@ -1224,6 +1224,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	cpu_set_bug_bits(c);
 
+	cpu_set_core_cap_bits(c);
+
 	fpu__init_system(c);
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/cpu/intel.c

@@ -19,6 +19,8 @@
 #include <asm/microcode_intel.h>
 #include <asm/hwcap2.h>
 #include <asm/elf.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cmdline.h>
 
 #ifdef CONFIG_X86_64
 #include <linux/topology.h>
@@ -31,6 +33,20 @@
 #include <asm/apic.h>
 #endif
 
+enum split_lock_detect_state {
+	sld_off = 0,
+	sld_warn,
+	sld_fatal,
+};
+
+/*
+ * 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.
+ */
+static enum split_lock_detect_state sld_state __ro_after_init = sld_off;
+static u64 msr_test_ctrl_cache __ro_after_init;
+
 /*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
@@ -570,6 +586,8 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
 	wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
 }
 
+static void split_lock_init(void);
+
 static void init_intel(struct cpuinfo_x86 *c)
 {
 	early_init_intel(c);
@@ -684,6 +702,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		tsx_enable();
 	if (tsx_ctrl_state == TSX_CTRL_DISABLE)
 		tsx_disable();
+
+	split_lock_init();
 }
 
 #ifdef CONFIG_X86_32
@@ -945,3 +965,166 @@ static const struct cpu_dev intel_cpu_dev = {
 };
 
 cpu_dev_register(intel_cpu_dev);
+
+#undef pr_fmt
+#define pr_fmt(fmt) "x86/split lock detection: " fmt
+
+static const struct {
+	const char			*option;
+	enum split_lock_detect_state	state;
+} sld_options[] __initconst = {
+	{ "off",	sld_off   },
+	{ "warn",	sld_warn  },
+	{ "fatal",	sld_fatal },
+};
+
+static inline bool match_option(const char *arg, int arglen, const char *opt)
+{
+	int len = strlen(opt);
+
+	return len == arglen && !strncmp(arg, opt, len);
+}
+
+static bool split_lock_verify_msr(bool on)
+{
+	u64 ctrl, tmp;
+
+	if (rdmsrl_safe(MSR_TEST_CTRL, &ctrl))
+		return false;
+	if (on)
+		ctrl |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
+	else
+		ctrl &= ~MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
+	if (wrmsrl_safe(MSR_TEST_CTRL, ctrl))
+		return false;
+	rdmsrl(MSR_TEST_CTRL, tmp);
+	return ctrl == tmp;
+}
+
+static void __init split_lock_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");
+		return;
+	}
+
+	ret = cmdline_find_option(boot_command_line, "split_lock_detect",
+				  arg, sizeof(arg));
+	if (ret >= 0) {
+		for (i = 0; i < ARRAY_SIZE(sld_options); i++) {
+			if (match_option(arg, ret, sld_options[i].option)) {
+				state = sld_options[i].state;
+				break;
+			}
+		}
+	}
+
+	switch (state) {
+	case sld_off:
+		pr_info("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);
+
+	if (!split_lock_verify_msr(true)) {
+		pr_info("MSR access failed: Disabled\n");
+		return;
+	}
+
+	sld_state = state;
+	setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
+}
+
+/*
+ * MSR_TEST_CTRL is per core, but we treat it like a per CPU MSR. Locking
+ * is not implemented as one thread could undo the setting of the other
+ * thread immediately after dropping the lock anyway.
+ */
+static void sld_update_msr(bool on)
+{
+	u64 test_ctrl_val = msr_test_ctrl_cache;
+
+	if (on)
+		test_ctrl_val |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
+
+	wrmsrl(MSR_TEST_CTRL, test_ctrl_val);
+}
+
+static void split_lock_init(void)
+{
+	split_lock_verify_msr(sld_state != sld_off);
+}
+
+bool handle_user_split_lock(struct pt_regs *regs, long error_code)
+{
+	if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal)
+		return false;
+
+	pr_warn_ratelimited("#AC: %s/%d took a split_lock trap at address: 0x%lx\n",
+			    current->comm, current->pid, regs->ip);
+
+	/*
+	 * Disable the split lock detection for this task so it can make
+	 * progress and set TIF_SLD so the detection is re-enabled via
+	 * switch_to_sld() when the task is scheduled out.
+	 */
+	sld_update_msr(false);
+	set_tsk_thread_flag(current, TIF_SLD);
+	return true;
+}
+
+/*
+ * This function is called only when switching between tasks with
+ * different split-lock detection modes. It sets the MSR for the
+ * mode of the new task. This is right most of the time, but since
+ * the MSR is shared by hyperthreads on a physical core there can
+ * be glitches when the two threads need different modes.
+ */
+void switch_to_sld(unsigned long tifn)
+{
+	sld_update_msr(!(tifn & _TIF_SLD));
+}
+
+#define SPLIT_LOCK_CPU(model) {X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY}
+
+/*
+ * The following processors have the split lock detection feature. But
+ * since they don't have the IA32_CORE_CAPABILITIES MSR, the feature cannot
+ * be enumerated. Enable it by family and model matching on these
+ * processors.
+ */
+static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = {
+	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_X),
+	SPLIT_LOCK_CPU(INTEL_FAM6_ICELAKE_L),
+	{}
+};
+
+void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
+{
+	u64 ia32_core_caps = 0;
+
+	if (c->x86_vendor != X86_VENDOR_INTEL)
+		return;
+	if (cpu_has(c, X86_FEATURE_CORE_CAPABILITIES)) {
+		/* Enumerate features reported in IA32_CORE_CAPABILITIES MSR. */
+		rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
+	} else if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		/* Enumerate split lock detection by family and model. */
+		if (x86_match_cpu(split_lock_cpu_ids))
+			ia32_core_caps |= MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT;
+	}
+
+	if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
+		split_lock_setup();
+}

arch/x86/kernel/process.c

@@ -649,6 +649,9 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
 		/* Enforce MSR update to ensure consistent state */
 		__speculation_ctrl_update(~tifn, tifn);
 	}
+
+	if ((tifp ^ tifn) & _TIF_SLD)
+		switch_to_sld(tifn);
 }
 
 /*

arch/x86/kernel/traps.c

@@ -46,6 +46,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/fpu/internal.h>
+#include <asm/cpu.h>
 #include <asm/cpu_entry_area.h>
 #include <asm/mce.h>
 #include <asm/fixmap.h>
@@ -242,7 +243,6 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs,
 {
 	struct task_struct *tsk = current;
 
-
 	if (!do_trap_no_signal(tsk, trapnr, str, regs, error_code))
 		return;
 
@@ -288,9 +288,29 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE,           0, NULL, "coprocessor segment overru
 DO_ERROR(X86_TRAP_TS,     SIGSEGV,          0, NULL, "invalid TSS",         invalid_TSS)
 DO_ERROR(X86_TRAP_NP,     SIGBUS,           0, NULL, "segment not present", segment_not_present)
 DO_ERROR(X86_TRAP_SS,     SIGBUS,           0, NULL, "stack segment",       stack_segment)
-DO_ERROR(X86_TRAP_AC,     SIGBUS,  BUS_ADRALN, NULL, "alignment check",     alignment_check)
 #undef IP
 
+dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code)
+{
+	char *str = "alignment check";
+
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+
+	if (notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_AC, SIGBUS) == NOTIFY_STOP)
+		return;
+
+	if (!user_mode(regs))
+		die("Split lock detected\n", regs, error_code);
+
+	local_irq_enable();
+
+	if (handle_user_split_lock(regs, error_code))
+		return;
+
+	do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs,
+		error_code, BUS_ADRALN, NULL);
+}
+
 #ifdef CONFIG_VMAP_STACK
 __visible void __noreturn handle_stack_overflow(const char *message,
 						struct pt_regs *regs,