Merge tag 'gds-for-linus-2023-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86/gds fixes from Dave Hansen:
 "Mitigate Gather Data Sampling issue:

   - Add Base GDS mitigation

   - Support GDS_NO under KVM

   - Fix a documentation typo"

* tag 'gds-for-linus-2023-08-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Documentation/x86: Fix backwards on/off logic about YMM support
  KVM: Add GDS_NO support to KVM
  x86/speculation: Add Kconfig option for GDS
  x86/speculation: Add force option to GDS mitigation
  x86/speculation: Add Gather Data Sampling mitigation

7 files changed, 221 insertions, 10 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d29f1e28a93635..e36261b4ea14f2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2610,6 +2610,25 @@ config SLS
 	  against straight line speculation. The kernel image might be slightly
 	  larger.
 
+config GDS_FORCE_MITIGATION
+	bool "Force GDS Mitigation"
+	depends on CPU_SUP_INTEL
+	default n
+	help
+	  Gather Data Sampling (GDS) is a hardware vulnerability which allows
+	  unprivileged speculative access to data which was previously stored in
+	  vector registers.
+
+	  This option is equivalent to setting gather_data_sampling=force on the
+	  command line. The microcode mitigation is used if present, otherwise
+	  AVX is disabled as a mitigation. On affected systems that are missing
+	  the microcode any userspace code that unconditionally uses AVX will
+	  break with this option set.
+
+	  Setting this option on systems not vulnerable to GDS has no effect.
+
+	  If in doubt, say N.
+
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 7600a8a1589f5a..094f88fee53697 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -491,6 +491,7 @@
 #define X86_BUG_RETBLEED		X86_BUG(27) /* CPU is affected by RETBleed */
 #define X86_BUG_EIBRS_PBRSB		X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 #define X86_BUG_SMT_RSB			X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS			X86_BUG(30) /* CPU is affected by Gather Data Sampling */
 
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index d5dcbf25e71146..1d111350197f31 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -156,6 +156,15 @@
 						 * Not susceptible to Post-Barrier
 						 * Return Stack Buffer Predictions.
 						 */
+#define ARCH_CAP_GDS_CTRL		BIT(25)	/*
+						 * CPU is vulnerable to Gather
+						 * Data Sampling (GDS) and
+						 * has controls for mitigation.
+						 */
+#define ARCH_CAP_GDS_NO			BIT(26)	/*
+						 * CPU is not vulnerable to Gather
+						 * Data Sampling (GDS).
+						 */
 
 #define ARCH_CAP_XAPIC_DISABLE		BIT(21)	/*
 						 * IA32_XAPIC_DISABLE_STATUS MSR
@@ -179,6 +188,8 @@
 #define RNGDS_MITG_DIS			BIT(0)	/* SRBDS support */
 #define RTM_ALLOW			BIT(1)	/* TSX development mode */
 #define FB_CLEAR_DIS			BIT(3)	/* CPU Fill buffer clear disable */
+#define GDS_MITG_DIS			BIT(4)	/* Disable GDS mitigation */
+#define GDS_MITG_LOCKED			BIT(5)	/* GDS mitigation locked */
 
 #define MSR_IA32_SYSENTER_CS		0x00000174
 #define MSR_IA32_SYSENTER_ESP		0x00000175
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d81f40aa843d79..d02f73c5339dd3 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -48,6 +48,7 @@ static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);
 static void __init srso_select_mitigation(void);
+static void __init gds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -165,6 +166,7 @@ void __init cpu_select_mitigations(void)
 	srbds_select_mitigation();
 	l1d_flush_select_mitigation();
 	srso_select_mitigation();
+	gds_select_mitigation();
 }
 
 /*
@@ -651,6 +653,149 @@ static int __init l1d_flush_parse_cmdline(char *str)
 early_param("l1d_flush", l1d_flush_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"GDS: " fmt
+
+enum gds_mitigations {
+	GDS_MITIGATION_OFF,
+	GDS_MITIGATION_UCODE_NEEDED,
+	GDS_MITIGATION_FORCE,
+	GDS_MITIGATION_FULL,
+	GDS_MITIGATION_FULL_LOCKED,
+	GDS_MITIGATION_HYPERVISOR,
+};
+
+#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION)
+static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE;
+#else
+static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL;
+#endif
+
+static const char * const gds_strings[] = {
+	[GDS_MITIGATION_OFF]		= "Vulnerable",
+	[GDS_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[GDS_MITIGATION_FORCE]		= "Mitigation: AVX disabled, no microcode",
+	[GDS_MITIGATION_FULL]		= "Mitigation: Microcode",
+	[GDS_MITIGATION_FULL_LOCKED]	= "Mitigation: Microcode (locked)",
+	[GDS_MITIGATION_HYPERVISOR]	= "Unknown: Dependent on hypervisor status",
+};
+
+bool gds_ucode_mitigated(void)
+{
+	return (gds_mitigation == GDS_MITIGATION_FULL ||
+		gds_mitigation == GDS_MITIGATION_FULL_LOCKED);
+}
+EXPORT_SYMBOL_GPL(gds_ucode_mitigated);
+
+void update_gds_msr(void)
+{
+	u64 mcu_ctrl_after;
+	u64 mcu_ctrl;
+
+	switch (gds_mitigation) {
+	case GDS_MITIGATION_OFF:
+		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		mcu_ctrl |= GDS_MITG_DIS;
+		break;
+	case GDS_MITIGATION_FULL_LOCKED:
+		/*
+		 * The LOCKED state comes from the boot CPU. APs might not have
+		 * the same state. Make sure the mitigation is enabled on all
+		 * CPUs.
+		 */
+	case GDS_MITIGATION_FULL:
+		rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+		mcu_ctrl &= ~GDS_MITG_DIS;
+		break;
+	case GDS_MITIGATION_FORCE:
+	case GDS_MITIGATION_UCODE_NEEDED:
+	case GDS_MITIGATION_HYPERVISOR:
+		return;
+	};
+
+	wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+	/*
+	 * Check to make sure that the WRMSR value was not ignored. Writes to
+	 * GDS_MITG_DIS will be ignored if this processor is locked but the boot
+	 * processor was not.
+	 */
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
+	WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after);
+}
+
+static void __init gds_select_mitigation(void)
+{
+	u64 mcu_ctrl;
+
+	if (!boot_cpu_has_bug(X86_BUG_GDS))
+		return;
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		gds_mitigation = GDS_MITIGATION_HYPERVISOR;
+		goto out;
+	}
+
+	if (cpu_mitigations_off())
+		gds_mitigation = GDS_MITIGATION_OFF;
+	/* Will verify below that mitigation _can_ be disabled */
+
+	/* No microcode */
+	if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) {
+		if (gds_mitigation == GDS_MITIGATION_FORCE) {
+			/*
+			 * This only needs to be done on the boot CPU so do it
+			 * here rather than in update_gds_msr()
+			 */
+			setup_clear_cpu_cap(X86_FEATURE_AVX);
+			pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
+		} else {
+			gds_mitigation = GDS_MITIGATION_UCODE_NEEDED;
+		}
+		goto out;
+	}
+
+	/* Microcode has mitigation, use it */
+	if (gds_mitigation == GDS_MITIGATION_FORCE)
+		gds_mitigation = GDS_MITIGATION_FULL;
+
+	rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+	if (mcu_ctrl & GDS_MITG_LOCKED) {
+		if (gds_mitigation == GDS_MITIGATION_OFF)
+			pr_warn("Mitigation locked. Disable failed.\n");
+
+		/*
+		 * The mitigation is selected from the boot CPU. All other CPUs
+		 * _should_ have the same state. If the boot CPU isn't locked
+		 * but others are then update_gds_msr() will WARN() of the state
+		 * mismatch. If the boot CPU is locked update_gds_msr() will
+		 * ensure the other CPUs have the mitigation enabled.
+		 */
+		gds_mitigation = GDS_MITIGATION_FULL_LOCKED;
+	}
+
+	update_gds_msr();
+out:
+	pr_info("%s\n", gds_strings[gds_mitigation]);
+}
+
+static int __init gds_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!boot_cpu_has_bug(X86_BUG_GDS))
+		return 0;
+
+	if (!strcmp(str, "off"))
+		gds_mitigation = GDS_MITIGATION_OFF;
+	else if (!strcmp(str, "force"))
+		gds_mitigation = GDS_MITIGATION_FORCE;
+
+	return 0;
+}
+early_param("gather_data_sampling", gds_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V1 : " fmt
 
 enum spectre_v1_mitigation {
@@ -2556,6 +2701,11 @@ static ssize_t srso_show_state(char *buf)
 			  (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode"));
 }
 
+static ssize_t gds_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -2608,6 +2758,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_SRSO:
 		return srso_show_state(buf);
 
+	case X86_BUG_GDS:
+		return gds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -2677,4 +2830,9 @@ ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribut
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SRSO);
 }
+
+ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_GDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 1d7e22836540d4..e3a65e9fc750db 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1252,6 +1252,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define SMT_RSB		BIT(4)
 /* CPU is affected by SRSO */
 #define SRSO		BIT(5)
+/* CPU is affected by GDS */
+#define GDS		BIT(6)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
@@ -1264,19 +1266,21 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(BROADWELL_X,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	X86_STEPPING_ANY,		MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPING_ANY,		SRBDS | MMIO | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(CANNONLAKE_L,	X86_STEPPING_ANY,		RETBLEED),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPING_ANY,		MMIO),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPING_ANY,		MMIO | GDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPING_ANY,		MMIO | GDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x0, 0x0),	MMIO | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED | GDS),
+	VULNBL_INTEL_STEPPINGS(TIGERLAKE_L,	X86_STEPPING_ANY,		GDS),
+	VULNBL_INTEL_STEPPINGS(TIGERLAKE,	X86_STEPPING_ANY,		GDS),
 	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS | RETBLEED),
-	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED),
+	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPING_ANY,		MMIO | RETBLEED | GDS),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPING_ANY,		MMIO | MMIO_SBDS),
@@ -1414,6 +1418,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_SRSO);
 	}
 
+	/*
+	 * Check if CPU is vulnerable to GDS. If running in a virtual machine on
+	 * an affected processor, the VMM may have disabled the use of GATHER by
+	 * disabling AVX2. The only way to do this in HW is to clear XCR0[2],
+	 * which means that AVX will be disabled.
+	 */
+	if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) &&
+	    boot_cpu_has(X86_FEATURE_AVX))
+		setup_force_cpu_bug(X86_BUG_GDS);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
@@ -1970,6 +1984,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 	validate_apic_and_package_id(c);
 	x86_spec_ctrl_setup_ap();
 	update_srbds_msr();
+	if (boot_cpu_has_bug(X86_BUG_GDS))
+		update_gds_msr();
 
 	tsx_ap_init();
 }
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1c44630d47891c..1dcd7d4e38ef17 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -83,6 +83,7 @@ void cpu_select_mitigations(void);
 
 extern void x86_spec_ctrl_setup_ap(void);
 extern void update_srbds_msr(void);
+extern void update_gds_msr(void);
 
 extern enum spectre_v2_mitigation spectre_v2_enabled;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 278dbd37dab244..19d9ff92d69910 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -314,6 +314,8 @@ u64 __read_mostly host_xcr0;
 
 static struct kmem_cache *x86_emulator_cache;
 
+extern bool gds_ucode_mitigated(void);
+
 /*
  * When called, it means the previous get/set msr reached an invalid msr.
  * Return true if we want to ignore/silent this failed msr access.
@@ -1616,7 +1618,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
 	 ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
 	 ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
 	 ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
-	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)
+	 ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO)
 
 static u64 kvm_get_arch_capabilities(void)
 {
@@ -1673,6 +1675,9 @@ static u64 kvm_get_arch_capabilities(void)
 		 */
 	}
 
+	if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated())
+		data |= ARCH_CAP_GDS_NO;
+
 	return data;
 }