x86/speculation: Add RSB VM Exit protections

stable inclusion
from stable-v4.19.255
commit b6c5011934a15762cd694e36fe74f2f2f93eac9b
category: bugfix
bugzilla: 187492, https://gitee.com/src-openeuler/kernel/issues/I5N1SO
CVE: CVE-2022-26373

--------------------------------

commit 2b1299322016731d56807aa49254a5ea3080b6b3 upstream.

tl;dr: The Enhanced IBRS mitigation for Spectre v2 does not work as
documented for RET instructions after VM exits. Mitigate it with a new
one-entry RSB stuffing mechanism and a new LFENCE.

== Background ==

Indirect Branch Restricted Speculation (IBRS) was designed to help
mitigate Branch Target Injection and Speculative Store Bypass, i.e.
Spectre, attacks. IBRS prevents software run in less privileged modes
from affecting branch prediction in more privileged modes. IBRS requires
the MSR to be written on every privilege level change.

To overcome some of the performance issues of IBRS, Enhanced IBRS was
introduced.  eIBRS is an "always on" IBRS, in other words, just turn
it o...

Documentation/admin-guide/hw-vuln/spectre.rst

@@ -422,6 +422,14 @@ The possible values in this file are:
   'RSB filling'   Protection of RSB on context switch enabled
   =============   ===========================================
 
+  - EIBRS Post-barrier Return Stack Buffer (PBRSB) protection status:
+
+  ===========================  =======================================================
+  'PBRSB-eIBRS: SW sequence'   CPU is affected and protection of RSB on VMEXIT enabled
+  'PBRSB-eIBRS: Vulnerable'    CPU is vulnerable
+  'PBRSB-eIBRS: Not affected'  CPU is not affected by PBRSB
+  ===========================  =======================================================
+
 Full mitigation might require a microcode update from the CPU
 vendor. When the necessary microcode is not available, the kernel will
 report vulnerability.

arch/x86/include/asm/cpufeatures.h

@@ -304,6 +304,7 @@
 #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_RSB_VMEXIT_LITE	(11*32+ 6) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -421,5 +422,6 @@
 #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 */
 #define X86_BUG_MMIO_STALE_DATA		X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(26) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

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

@@ -120,6 +120,10 @@
 						 * bit available to control VERW
 						 * behavior.
 						 */
+#define ARCH_CAP_PBRSB_NO		BIT(24)	/*
+						 * Not susceptible to Post-Barrier
+						 * Return Stack Buffer Predictions.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*

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

@@ -54,6 +54,14 @@
 	jnz	771b;				\
 	add	$(BITS_PER_LONG/8) * nr, sp;
 
+/* Sequence to mitigate PBRSB on eIBRS CPUs */
+#define __ISSUE_UNBALANCED_RET_GUARD(sp)	\
+	call	881f;				\
+	int3;					\
+881:						\
+	add	$(BITS_PER_LONG/8), sp;		\
+	lfence;
+
 #ifdef __ASSEMBLY__
 
 /*
@@ -269,6 +277,13 @@ static inline void vmexit_fill_RSB(void)
 		      : "=r" (loops), ASM_CALL_CONSTRAINT
 		      : : "memory" );
 #endif
+	asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
+		      ALTERNATIVE("jmp 920f",
+				  __stringify(__ISSUE_UNBALANCED_RET_GUARD(%0)),
+				  X86_FEATURE_RSB_VMEXIT_LITE)
+		      "920:"
+		      : ASM_CALL_CONSTRAINT
+		      : : "memory" );
 }
 
 static __always_inline

arch/x86/kernel/cpu/bugs.c

@@ -1043,6 +1043,49 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void)
 	return SPECTRE_V2_RETPOLINE;
 }
 
+static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode)
+{
+	/*
+	 * Similar to context switches, there are two types of RSB attacks
+	 * after VM exit:
+	 *
+	 * 1) RSB underflow
+	 *
+	 * 2) Poisoned RSB entry
+	 *
+	 * When retpoline is enabled, both are mitigated by filling/clearing
+	 * the RSB.
+	 *
+	 * When IBRS is enabled, while #1 would be mitigated by the IBRS branch
+	 * prediction isolation protections, RSB still needs to be cleared
+	 * because of #2.  Note that SMEP provides no protection here, unlike
+	 * user-space-poisoned RSB entries.
+	 *
+	 * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB
+	 * bug is present then a LITE version of RSB protection is required,
+	 * just a single call needs to retire before a RET is executed.
+	 */
+	switch (mode) {
+	case SPECTRE_V2_NONE:
+	/* These modes already fill RSB at vmexit */
+	case SPECTRE_V2_LFENCE:
+	case SPECTRE_V2_RETPOLINE:
+	case SPECTRE_V2_EIBRS_RETPOLINE:
+		return;
+
+	case SPECTRE_V2_EIBRS_LFENCE:
+	case SPECTRE_V2_EIBRS:
+		if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
+			setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE);
+			pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n");
+		}
+		return;
+	}
+
+	pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit");
+	dump_stack();
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1135,6 +1178,8 @@ static void __init spectre_v2_select_mitigation(void)
 	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
+	spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
+
 	/*
 	 * Retpoline means the kernel is safe because it has no indirect
 	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
@@ -1854,6 +1899,19 @@ static char *ibpb_state(void)
 	return "";
 }
 
+static char *pbrsb_eibrs_state(void)
+{
+	if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
+		if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) ||
+		    boot_cpu_has(X86_FEATURE_RETPOLINE))
+			return ", PBRSB-eIBRS: SW sequence";
+		else
+			return ", PBRSB-eIBRS: Vulnerable";
+	} else {
+		return ", PBRSB-eIBRS: Not affected";
+	}
+}
+
 static ssize_t spectre_v2_show_state(char *buf)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_LFENCE)
@@ -1866,12 +1924,13 @@ static ssize_t spectre_v2_show_state(char *buf)
 	    spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
 		return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n");
 
-	return sprintf(buf, "%s%s%s%s%s%s\n",
+	return sprintf(buf, "%s%s%s%s%s%s%s\n",
 		       spectre_v2_strings[spectre_v2_enabled],
 		       ibpb_state(),
 		       boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
 		       stibp_state(),
 		       boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
+		       pbrsb_eibrs_state(),
 		       spectre_v2_module_string());
 }
 

arch/x86/kernel/cpu/common.c

@@ -1032,6 +1032,7 @@ 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 NO_EIBRS_PBRSB		BIT(9)
 
 #define VULNWL(_vendor, _family, _model, _whitelist)	\
 	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
@@ -1071,7 +1072,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 
 	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
-	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
 
 	/*
 	 * Technically, swapgs isn't serializing on AMD (despite it previously
@@ -1081,7 +1082,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	 * good enough for our purposes.
 	 */
 
-	VULNWL_INTEL(ATOM_TREMONT_X,		NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_TREMONT,		NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_TREMONT_L,		NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_TREMONT_X,		NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
 
 	/* AMD Family 0xf - 0x12 */
 	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT),
@@ -1242,6 +1245,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	    !arch_cap_mmio_immune(ia32_cap))
 		setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
 
+	if (cpu_has(c, X86_FEATURE_IBRS_ENHANCED) &&
+	    !cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) &&
+	    !(ia32_cap & ARCH_CAP_PBRSB_NO))
+		setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 

arch/x86/kvm/vmx.c

@@ -11008,6 +11008,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 	      );
 
+	/* Eliminate branch target predictions from guest mode */
+	vmexit_fill_RSB();
+
 	vmx_enable_fb_clear(vmx);
 
 	/*
@@ -11030,9 +11033,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
 
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs))
 		current_evmcs->hv_clean_fields |=