[MODERATED] [PATCH 1/2] v3 more sampling fun 1

From: mark gross <[email protected]>
Subject: [PATCH 1/2] x86/speculation: Special Register Buffer Data Sampling
 (SRBDS) mitigation control.

SRBDS is an MDS-like speculative side channel that can leak bits from
the RNG across cores and threads. New microcode serializes the processor
access during the execution of RDRAND and RDSEED ensures that the shared
buffer is overwritten before it is released for reuse.

This vulnerability comes in two classes:
Processor models that are vulnerable and models with TSX enumerating
MDS_NO which are only vulnerable when TSX is enabled.

The mitigation is activated by default on affected processors and it
increases latency for RDRAND and RDSEED instructions.  Among other
effects this will reduce throughput from /dev/urandom.

This patch:
* enables administrator to configure the mitigation off when desired
  using either mitigations=off or srbds=off.
* exports vulnerability status via sysfs

Signed-off-by: Mark Gross <[email protected]>
Reviewed-by: Tony Luck <[email protected]>
Reviewed-by: Pawan Gupta <[email protected]>
Tested-by: Neelima Krishnan <[email protected]>
---
 .../admin-guide/kernel-parameters.txt         |  11 ++
 arch/x86/include/asm/cpu_device_id.h          |  12 ++
 arch/x86/include/asm/cpufeatures.h            |   2 +
 arch/x86/include/asm/msr-index.h              |   4 +
 arch/x86/kernel/cpu/bugs.c                    | 110 ++++++++++++++++++
 arch/x86/kernel/cpu/common.c                  |  41 +++++++
 arch/x86/kernel/cpu/cpu.h                     |  13 +++
 arch/x86/kernel/cpu/intel.c                   |   2 +
 arch/x86/kernel/cpu/match.c                   |  26 +++++
 drivers/base/cpu.c                            |   8 ++
 10 files changed, 229 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c07815d230bc..71cf7e7eae45 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4659,6 +4659,17 @@
 	spia_pedr=
 	spia_peddr=
 
+	srbds=		[x86]
+			Special Register Buffer Data Sampling mitigation
+			control.
+
+			On CPUs vulnerable to this issue and users impacted by
+			the mitigation slowing down RDRAND and RDSEED can
+			disable by setting this:
+
+			off:	disable mitigation and remove performance
+				impact to rdrand and rdseed
+
 	srcutree.counter_wrap_check [KNL]
 			Specifies how frequently to check for
 			grace-period sequence counter wrap for the
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index 31c379c1da41..1128e211cdb6 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -35,7 +35,19 @@ struct x86_cpu_desc {
 	.x86_microcode_rev	= (revision),			\
 }
 
+/*
+ * Match a range of steppings
+ */
+
+struct x86_cpu_id_ext {
+	struct x86_cpu_id id;
+	__u16 steppings; /* bit map of steppings to match against */
+};
+
+#define X86_STEPPING_ANY GENMASK(15, 0)
+
 extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
+const struct x86_cpu_id_ext *x86_match_cpu_ext(const struct x86_cpu_id_ext *match);
 extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table);
 
 #endif /* _ASM_X86_CPU_DEVICE_ID */
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f3327cb56edf..69f7dcb1fa5c 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -360,6 +360,7 @@
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
 #define X86_FEATURE_FSRM		(18*32+ 4) /* Fast Short Rep Mov */
 #define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
+#define X86_FEATURE_SRBDS_CTRL		(18*32+ 9) /* "" SRBDS mitigation MSR available */
 #define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
@@ -404,5 +405,6 @@
 #define X86_BUG_SWAPGS			X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
 #define X86_BUG_TAA			X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
 #define X86_BUG_ITLB_MULTIHIT		X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS			X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d5e517d1c3dd..af64c8e80ff4 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -119,6 +119,10 @@
 #define TSX_CTRL_RTM_DISABLE		BIT(0)	/* Disable RTM feature */
 #define TSX_CTRL_CPUID_CLEAR		BIT(1)	/* Disable TSX enumeration */
 
+/* SRBDS support */
+#define MSR_IA32_MCU_OPT_CTRL		0x00000123
+#define RNGDS_MITG_DIS			BIT(0)
+
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
 #define MSR_IA32_SYSENTER_EIP		0x00000176
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index ed54b3b21c39..48fdc01eb95c 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
 static void __init mds_print_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init srbds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -108,6 +109,7 @@ void __init check_bugs(void)
 	l1tf_select_mitigation();
 	mds_select_mitigation();
 	taa_select_mitigation();
+	srbds_select_mitigation();
 
 	/*
 	 * As MDS and TAA mitigations are inter-related, print MDS
@@ -397,6 +399,101 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
 }
 early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"SRBDS: " fmt
+
+enum srbds_mitigations srbds_mitigation __ro_after_init = SRBDS_MITIGATION_FULL;
+static const char * const srbds_strings[] = {
+	[SRBDS_NOT_AFFECTED]		= "Not affected",
+	[SRBDS_MITIGATION_OFF]		= "Vulnerable",
+	[SRBDS_MITIGATION_UCODE_NEEDED]	= "Vulnerable: no microcode",
+	[SRBDS_MITIGATION_FULL]		= "Mitigated",
+	[SRBDS_TSX_NOT_AFFECTED]	= "Not affected (TSX disabled)",
+	[SRBDS_HYPERVISOR]		= "Unknown",
+};
+
+static bool srbds_off;
+
+void srbds_configure_mitigation(void)
+{
+	u64 mcu_ctrl;
+
+	if (srbds_mitigation == SRBDS_NOT_AFFECTED)
+		return;
+
+	if (srbds_mitigation == SRBDS_HYPERVISOR)
+		return;
+
+	if (srbds_mitigation == SRBDS_MITIGATION_UCODE_NEEDED)
+		return;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+	switch (srbds_mitigation) {
+	case SRBDS_MITIGATION_OFF:
+	case SRBDS_TSX_NOT_AFFECTED:
+		mcu_ctrl |= RNGDS_MITG_DIS;
+		break;
+	case SRBDS_MITIGATION_FULL:
+		mcu_ctrl &= ~RNGDS_MITG_DIS;
+		break;
+	default:
+		break;
+	}
+
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+}
+
+static void __init srbds_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_SRBDS)) {
+		srbds_mitigation = SRBDS_NOT_AFFECTED;
+		return;
+	}
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		srbds_mitigation = SRBDS_HYPERVISOR;
+		return;
+	}
+
+	if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL)) {
+		srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED;
+		return;
+	}
+
+	if (boot_cpu_has_bug(X86_BUG_SRBDS)) {
+		srbds_mitigation = SRBDS_MITIGATION_FULL;
+
+		ia32_cap = x86_read_arch_cap_msr();
+		if (ia32_cap & ARCH_CAP_MDS_NO) {
+			if (!boot_cpu_has(X86_FEATURE_RTM))
+				srbds_mitigation = SRBDS_TSX_NOT_AFFECTED;
+		}
+	}
+
+	if (cpu_mitigations_off() || srbds_off) {
+		if (srbds_mitigation != SRBDS_TSX_NOT_AFFECTED)
+			srbds_mitigation = SRBDS_MITIGATION_OFF;
+	}
+
+	srbds_configure_mitigation();
+}
+
+static int __init srbds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		srbds_off = true;
+
+	return 0;
+}
+
+early_param("srbds", srbds_parse_cmdline);
+
 #undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
@@ -1528,6 +1625,11 @@ static char *ibpb_state(void)
 	return "";
 }
 
+static ssize_t srbds_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -1572,6 +1674,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITLB_MULTIHIT:
 		return itlb_multihit_show_state(buf);
 
+	case X86_BUG_SRBDS:
+		return srbds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1618,4 +1723,9 @@ ssize_t cpu_show_itlb_multihit(struct device *dev, struct device_attribute *attr
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITLB_MULTIHIT);
 }
+
+ssize_t cpu_show_special_register_data_sampling(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4cdb123ff66a..055ccbe6b364 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1007,6 +1007,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_SWAPGS		BIT(6)
 #define NO_ITLB_MULTIHIT	BIT(7)
 #define NO_SPECTRE_V2		BIT(8)
+#define SRBDS			BIT(9)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1020,6 +1021,15 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define VULNWL_HYGON(family, whitelist)		\
 	VULNWL(HYGON, family, X86_MODEL_ANY, whitelist)
 
+#define VULNWL_EXT(_vendor, _family, _model, _steppings, _whitelist)	\
+	{ VULNWL(_vendor, _family, _model, _whitelist), _steppings }
+
+#define VULNWL_INTEL_EXT(model,  whitelist)		\
+	VULNWL_EXT(INTEL, 6, INTEL_FAM6_##model, X86_STEPPING_ANY, whitelist)
+
+#define VULNWL_INTEL_STEPPING(model, stepping, whitelist)		\
+	VULNWL_EXT(INTEL, 6, INTEL_FAM6_##model, stepping, whitelist)
+
 static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	VULNWL(ANY,	4, X86_MODEL_ANY,	NO_SPECULATION),
 	VULNWL(CENTAUR,	5, X86_MODEL_ANY,	NO_SPECULATION),
@@ -1075,6 +1085,27 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	{}
 };
 
+/*
+ * to avoide corrupting the whiltelist with blacklist items lets create a list
+ * of affected processors for issues that cannot be enumerated other than by
+ * family/model/stepping
+ */
+static const struct x86_cpu_id_ext affected_cpus[] __initconst = {
+	VULNWL_INTEL_EXT(IVYBRIDGE,		SRBDS),
+	VULNWL_INTEL_EXT(HASWELL,		SRBDS),
+	VULNWL_INTEL_EXT(HASWELL_L,		SRBDS),
+	VULNWL_INTEL_EXT(HASWELL_G,		SRBDS),
+	VULNWL_INTEL_EXT(BROADWELL_G,		SRBDS),
+	VULNWL_INTEL_EXT(BROADWELL,		SRBDS),
+	VULNWL_INTEL_EXT(SKYLAKE_L,		SRBDS),
+	VULNWL_INTEL_EXT(SKYLAKE,		SRBDS),
+	VULNWL_INTEL_STEPPING(KABYLAKE_L, GENMASK(0xA, 0),	SRBDS), /*06_8E steppings <=A*/
+	VULNWL_INTEL_STEPPING(KABYLAKE_L, GENMASK(0xC, 0xB),	SRBDS), /*06_8E stepping = 0xB|0xC if TSX enabled*/
+	VULNWL_INTEL_STEPPING(KABYLAKE, GENMASK(0xB, 0),	SRBDS), /*06_9E steppings <=B*/
+	VULNWL_INTEL_STEPPING(KABYLAKE, GENMASK(0xD, 0xC),	SRBDS), /*06_9E stepping = 0xC if TSX enabled*/
+	{}
+};
+
 static bool __init cpu_matches(unsigned long which)
 {
 	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
@@ -1082,6 +1113,13 @@ static bool __init cpu_matches(unsigned long which)
 	return m && !!(m->driver_data & which);
 }
 
+static bool __init cpu_affected(unsigned long which)
+{
+	const struct x86_cpu_id_ext *m = x86_match_cpu_ext(affected_cpus);
+
+	return m && !!(m->id.driver_data & which);
+}
+
 u64 x86_read_arch_cap_msr(void)
 {
 	u64 ia32_cap = 0;
@@ -1124,6 +1162,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (!cpu_matches(NO_SWAPGS))
 		setup_force_cpu_bug(X86_BUG_SWAPGS);
 
+	if (cpu_affected(SRBDS))
+		setup_force_cpu_bug(X86_BUG_SRBDS);
+
 	/*
 	 * When the CPU is not mitigated for TAA (TAA_NO=0) set TAA bug when:
 	 *	- TSX is supported or
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 37fdefd14f28..22d419080fd6 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -44,7 +44,20 @@ struct _tlb_table {
 extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
+enum srbds_mitigations {
+	SRBDS_NOT_AFFECTED,
+	SRBDS_MITIGATION_OFF,
+	SRBDS_MITIGATION_UCODE_NEEDED,
+	SRBDS_MITIGATION_FULL,
+	SRBDS_TSX_NOT_AFFECTED,
+	SRBDS_HYPERVISOR,
+};
+
+extern __ro_after_init enum srbds_mitigations srbds_mitigation;
+void srbds_configure_mitigation(void);
+
 #ifdef CONFIG_CPU_SUP_INTEL
+
 enum tsx_ctrl_states {
 	TSX_CTRL_ENABLE,
 	TSX_CTRL_DISABLE,
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index be82cd5841c3..1b083a2a415b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -684,6 +684,8 @@ static void init_intel(struct cpuinfo_x86 *c)
 		tsx_enable();
 	if (tsx_ctrl_state == TSX_CTRL_DISABLE)
 		tsx_disable();
+
+	srbds_configure_mitigation();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c
index 6dd78d8235e4..118c503b1c36 100644
--- a/arch/x86/kernel/cpu/match.c
+++ b/arch/x86/kernel/cpu/match.c
@@ -49,6 +49,32 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match)
 }
 EXPORT_SYMBOL(x86_match_cpu);
 
+/*
+ * Extend x86_match_cpu to support matching a range of steppings.
+ */
+const struct x86_cpu_id_ext *x86_match_cpu_ext(const struct x86_cpu_id_ext *match)
+{
+	const struct x86_cpu_id_ext *m;
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+
+	for (m = match; m->id.vendor | m->id.family | m->id.model | m->id.feature; m++) {
+		if (m->id.vendor != X86_VENDOR_ANY && c->x86_vendor != m->id.vendor)
+			continue;
+		if (m->id.family != X86_FAMILY_ANY && c->x86 != m->id.family)
+			continue;
+		if (m->id.model != X86_MODEL_ANY && c->x86_model != m->id.model)
+			continue;
+		if (m->steppings != X86_STEPPING_ANY &&
+		    !(BIT(c->x86_stepping) & m->steppings))
+			continue;
+		if (m->id.feature != X86_FEATURE_ANY && !cpu_has(c, m->id.feature))
+			continue;
+		return m;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(x86_match_cpu_ext);
+
 static const struct x86_cpu_desc *
 x86_match_cpu_with_stepping(const struct x86_cpu_desc *match)
 {
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 6265871a4af2..d69e094e790c 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -567,6 +567,12 @@ ssize_t __weak cpu_show_itlb_multihit(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_special_register_data_sampling(struct device *dev,
+						       struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
@@ -575,6 +581,7 @@ static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
 static DEVICE_ATTR(tsx_async_abort, 0444, cpu_show_tsx_async_abort, NULL);
 static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
+static DEVICE_ATTR(special_register_data_sampling, 0444, cpu_show_special_register_data_sampling, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -585,6 +592,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_mds.attr,
 	&dev_attr_tsx_async_abort.attr,
 	&dev_attr_itlb_multihit.attr,
+	&dev_attr_special_register_data_sampling.attr,
 	NULL
 };
 
-- 
2.17.1