Merge branch 'speck-v20' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/tip/tip

Merge speculative store buffer bypass fixes from Thomas Gleixner:

 - rework of the SPEC_CTRL MSR management to accomodate the new fancy
   SSBD (Speculative Store Bypass Disable) bit handling.

 - the CPU bug and sysfs infrastructure for the exciting new Speculative
   Store Bypass 'feature'.

 - support for disabling SSB via LS_CFG MSR on AMD CPUs including
   Hyperthread synchronization on ZEN.

 - PRCTL support for dynamic runtime control of SSB

 - SECCOMP integration to automatically disable SSB for sandboxed
   processes with a filter flag for opt-out.

 - KVM integration to allow guests fiddling with SSBD including the new
   software MSR VIRT_SPEC_CTRL to handle the LS_CFG based oddities on
   AMD.

 - BPF protection against SSB

.. this is just the core and x86 side, other architecture support will
come separately.

* 'speck-v20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  bpf: Prevent memory disambiguation attack
  x86/bugs: Rename SSBD_NO to SSB_NO
  KVM: SVM: Implement VIRT_SPEC_CTRL support for SSBD
  x86/speculation, KVM: Implement support for VIRT_SPEC_CTRL/LS_CFG
  x86/bugs: Rework spec_ctrl base and mask logic
  x86/bugs: Remove x86_spec_ctrl_set()
  x86/bugs: Expose x86_spec_ctrl_base directly
  x86/bugs: Unify x86_spec_ctrl_{set_guest,restore_host}
  x86/speculation: Rework speculative_store_bypass_update()
  x86/speculation: Add virtualized speculative store bypass disable support
  x86/bugs, KVM: Extend speculation control for VIRT_SPEC_CTRL
  x86/speculation: Handle HT correctly on AMD
  x86/cpufeatures: Add FEATURE_ZEN
  x86/cpufeatures: Disentangle SSBD enumeration
  x86/cpufeatures: Disentangle MSR_SPEC_CTRL enumeration from IBRS
  x86/speculation: Use synthetic bits for IBRS/IBPB/STIBP
  KVM: SVM: Move spec control call after restore of GS
  x86/cpu: Make alternative_msr_write work for 32-bit code
  x86/bugs: Fix the parameters alignment and missing void
  x86/bugs: Make cpu_show_common() static
  ...

Documentation/ABI/testing/sysfs-devices-system-cpu

@@ -478,6 +478,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/meltdown
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
+		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 Date:		January 2018
 Contact:	Linux kernel mailing list <[email protected]>
 Description:	Information about CPU vulnerabilities

Documentation/admin-guide/kernel-parameters.txt

@@ -2680,6 +2680,9 @@
 			allow data leaks with this option, which is equivalent
 			to spectre_v2=off.
 
+	nospec_store_bypass_disable
+			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
@@ -4025,6 +4028,48 @@
 			Not specifying this option is equivalent to
 			spectre_v2=auto.
 
+	spec_store_bypass_disable=
+			[HW] Control Speculative Store Bypass (SSB) Disable mitigation
+			(Speculative Store Bypass vulnerability)
+
+			Certain CPUs are vulnerable to an exploit against a
+			a common industry wide performance optimization known
+			as "Speculative Store Bypass" in which recent stores
+			to the same memory location may not be observed by
+			later loads during speculative execution. The idea
+			is that such stores are unlikely and that they can
+			be detected prior to instruction retirement at the
+			end of a particular speculation execution window.
+
+			In vulnerable processors, the speculatively forwarded
+			store can be used in a cache side channel attack, for
+			example to read memory to which the attacker does not
+			directly have access (e.g. inside sandboxed code).
+
+			This parameter controls whether the Speculative Store
+			Bypass optimization is used.
+
+			on      - Unconditionally disable Speculative Store Bypass
+			off     - Unconditionally enable Speculative Store Bypass
+			auto    - Kernel detects whether the CPU model contains an
+				  implementation of Speculative Store Bypass and
+				  picks the most appropriate mitigation. If the
+				  CPU is not vulnerable, "off" is selected. If the
+				  CPU is vulnerable the default mitigation is
+				  architecture and Kconfig dependent. See below.
+			prctl   - Control Speculative Store Bypass per thread
+				  via prctl. Speculative Store Bypass is enabled
+				  for a process by default. The state of the control
+				  is inherited on fork.
+			seccomp - Same as "prctl" above, but all seccomp threads
+				  will disable SSB unless they explicitly opt out.
+
+			Not specifying this option is equivalent to
+			spec_store_bypass_disable=auto.
+
+			Default mitigations:
+			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=

Documentation/userspace-api/index.rst

@@ -19,6 +19,7 @@ place where this information is gathered.
    no_new_privs
    seccomp_filter
    unshare
+   spec_ctrl
 
 .. only::  subproject and html
 

Documentation/userspace-api/spec_ctrl.rst

@@ -0,0 +1,94 @@
+===================
+Speculation Control
+===================
+
+Quite some CPUs have speculation-related misfeatures which are in
+fact vulnerabilities causing data leaks in various forms even across
+privilege domains.
+
+The kernel provides mitigation for such vulnerabilities in various
+forms. Some of these mitigations are compile-time configurable and some
+can be supplied on the kernel command line.
+
+There is also a class of mitigations which are very expensive, but they can
+be restricted to a certain set of processes or tasks in controlled
+environments. The mechanism to control these mitigations is via
+:manpage:`prctl(2)`.
+
+There are two prctl options which are related to this:
+
+ * PR_GET_SPECULATION_CTRL
+
+ * PR_SET_SPECULATION_CTRL
+
+PR_GET_SPECULATION_CTRL
+-----------------------
+
+PR_GET_SPECULATION_CTRL returns the state of the speculation misfeature
+which is selected with arg2 of prctl(2). The return value uses bits 0-3 with
+the following meaning:
+
+==== ===================== ===================================================
+Bit  Define                Description
+==== ===================== ===================================================
+0    PR_SPEC_PRCTL         Mitigation can be controlled per task by
+                           PR_SET_SPECULATION_CTRL.
+1    PR_SPEC_ENABLE        The speculation feature is enabled, mitigation is
+                           disabled.
+2    PR_SPEC_DISABLE       The speculation feature is disabled, mitigation is
+                           enabled.
+3    PR_SPEC_FORCE_DISABLE Same as PR_SPEC_DISABLE, but cannot be undone. A
+                           subsequent prctl(..., PR_SPEC_ENABLE) will fail.
+==== ===================== ===================================================
+
+If all bits are 0 the CPU is not affected by the speculation misfeature.
+
+If PR_SPEC_PRCTL is set, then the per-task control of the mitigation is
+available. If not set, prctl(PR_SET_SPECULATION_CTRL) for the speculation
+misfeature will fail.
+
+PR_SET_SPECULATION_CTRL
+-----------------------
+
+PR_SET_SPECULATION_CTRL allows to control the speculation misfeature, which
+is selected by arg2 of :manpage:`prctl(2)` per task. arg3 is used to hand
+in the control value, i.e. either PR_SPEC_ENABLE or PR_SPEC_DISABLE or
+PR_SPEC_FORCE_DISABLE.
+
+Common error codes
+------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+EINVAL  The prctl is not implemented by the architecture or unused
+        prctl(2) arguments are not 0.
+
+ENODEV  arg2 is selecting a not supported speculation misfeature.
+======= =================================================================
+
+PR_SET_SPECULATION_CTRL error codes
+-----------------------------------
+======= =================================================================
+Value   Meaning
+======= =================================================================
+0       Success
+
+ERANGE  arg3 is incorrect, i.e. it's neither PR_SPEC_ENABLE nor
+        PR_SPEC_DISABLE nor PR_SPEC_FORCE_DISABLE.
+
+ENXIO   Control of the selected speculation misfeature is not possible.
+        See PR_GET_SPECULATION_CTRL.
+
+EPERM   Speculation was disabled with PR_SPEC_FORCE_DISABLE and caller
+        tried to enable it again.
+======= =================================================================
+
+Speculation misfeature controls
+-------------------------------
+- PR_SPEC_STORE_BYPASS: Speculative Store Bypass
+
+  Invocations:
+   * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, 0, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0);
+   * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0);

arch/x86/include/asm/cpufeatures.h

@@ -198,7 +198,6 @@
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
 #define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
-
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
@@ -207,13 +206,19 @@
 #define X86_FEATURE_RETPOLINE_AMD	( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_CDP_L2		( 7*32+15) /* Code and Data Prioritization L2 */
-
+#define X86_FEATURE_MSR_SPEC_CTRL	( 7*32+16) /* "" MSR SPEC_CTRL is implemented */
+#define X86_FEATURE_SSBD		( 7*32+17) /* Speculative Store Bypass Disable */
 #define X86_FEATURE_MBA			( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW		( 7*32+19) /* "" Fill RSB on context switches */
 #define X86_FEATURE_SEV			( 7*32+20) /* AMD Secure Encrypted Virtualization */
-
 #define X86_FEATURE_USE_IBPB		( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
 #define X86_FEATURE_USE_IBRS_FW		( 7*32+22) /* "" Use IBRS during runtime firmware calls */
+#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE	( 7*32+23) /* "" Disable Speculative Store Bypass. */
+#define X86_FEATURE_LS_CFG_SSBD		( 7*32+24)  /* "" AMD SSBD implementation via LS_CFG MSR */
+#define X86_FEATURE_IBRS		( 7*32+25) /* Indirect Branch Restricted Speculation */
+#define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
+#define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -274,9 +279,10 @@
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
 #define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
-#define X86_FEATURE_IBPB		(13*32+12) /* Indirect Branch Prediction Barrier */
-#define X86_FEATURE_IBRS		(13*32+14) /* Indirect Branch Restricted Speculation */
-#define X86_FEATURE_STIBP		(13*32+15) /* Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_AMD_IBPB		(13*32+12) /* "" Indirect Branch Prediction Barrier */
+#define X86_FEATURE_AMD_IBRS		(13*32+14) /* "" Indirect Branch Restricted Speculation */
+#define X86_FEATURE_AMD_STIBP		(13*32+15) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
@@ -334,6 +340,7 @@
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
+#define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
 /*
  * BUG word(s)
@@ -363,5 +370,6 @@
 #define X86_BUG_CPU_MELTDOWN		X86_BUG(14) /* CPU is affected by meltdown attack and needs kernel page table isolation */
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
+#define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/kvm_host.h

@@ -924,7 +924,7 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
-	bool (*cpu_has_high_real_mode_segbase)(void);
+	bool (*has_emulated_msr)(int index);
 	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	struct kvm *(*vm_alloc)(void);

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

@@ -42,6 +42,8 @@
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
 #define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP			(1 << 1)   /* Single Thread Indirect Branch Predictors */
+#define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
+#define SPEC_CTRL_SSBD			(1 << SPEC_CTRL_SSBD_SHIFT)   /* Speculative Store Bypass Disable */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
@@ -68,6 +70,11 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_SSB_NO			(1 << 4)   /*
+						    * Not susceptible to Speculative Store Bypass
+						    * attack, so no Speculative Store Bypass
+						    * control required.
+						    */
 
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
@@ -340,6 +347,8 @@
 #define MSR_AMD64_SEV_ENABLED_BIT	0
 #define MSR_AMD64_SEV_ENABLED		BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
 
+#define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 

arch/x86/include/asm/nospec-branch.h

@@ -217,6 +217,14 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_IBRS,
 };
 
+/* The Speculative Store Bypass disable variants */
+enum ssb_mitigation {
+	SPEC_STORE_BYPASS_NONE,
+	SPEC_STORE_BYPASS_DISABLE,
+	SPEC_STORE_BYPASS_PRCTL,
+	SPEC_STORE_BYPASS_SECCOMP,
+};
+
 extern char __indirect_thunk_start[];
 extern char __indirect_thunk_end[];
 
@@ -241,22 +249,27 @@ static inline void vmexit_fill_RSB(void)
 #endif
 }
 
-#define alternative_msr_write(_msr, _val, _feature)		\
-	asm volatile(ALTERNATIVE("",				\
-				 "movl %[msr], %%ecx\n\t"	\
-				 "movl %[val], %%eax\n\t"	\
-				 "movl $0, %%edx\n\t"		\
-				 "wrmsr",			\
-				 _feature)			\
-		     : : [msr] "i" (_msr), [val] "i" (_val)	\
-		     : "eax", "ecx", "edx", "memory")
+static __always_inline
+void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
+{
+	asm volatile(ALTERNATIVE("", "wrmsr", %c[feature])
+		: : "c" (msr),
+		    "a" ((u32)val),
+		    "d" ((u32)(val >> 32)),
+		    [feature] "i" (feature)
+		: "memory");
+}
 
 static inline void indirect_branch_prediction_barrier(void)
 {
-	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
-			      X86_FEATURE_USE_IBPB);
+	u64 val = PRED_CMD_IBPB;
+
+	alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
 }
 
+/* The Intel SPEC CTRL MSR base value cache */
+extern u64 x86_spec_ctrl_base;
+
 /*
  * With retpoline, we must use IBRS to restrict branch prediction
  * before calling into firmware.
@@ -265,14 +278,18 @@ static inline void indirect_branch_prediction_barrier(void)
  */
 #define firmware_restrict_branch_speculation_start()			\
 do {									\
+	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
+									\
 	preempt_disable();						\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS,	\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 } while (0)
 
 #define firmware_restrict_branch_speculation_end()			\
 do {									\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, 0,			\
+	u64 val = x86_spec_ctrl_base;					\
+									\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 	preempt_enable();						\
 } while (0)