Merge tag 'x86_bugs_pbrsb' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 eIBRS fixes from Borislav Petkov:
 "More from the CPU vulnerability nightmares front:

  Intel eIBRS machines do not sufficiently mitigate against RET
  mispredictions when doing a VM Exit therefore an additional RSB,
  one-entry stuffing is needed"

* tag 'x86_bugs_pbrsb' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/speculation: Add LFENCE to RSB fill sequence
  x86/speculation: Add RSB VM Exit protections

9 files changed, 116 insertions, 30 deletions

diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index 9e9556826450b..2ce2a38cdd556 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/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.
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 14ed039dff551..235dc85c91c3e 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -303,6 +303,7 @@
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
@@ -457,5 +458,6 @@
 #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_RETBLEED		X86_BUG(26) /* CPU is affected by RETBleed */
+#define X86_BUG_EIBRS_PBRSB		X86_BUG(27) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 182b2a1f71fea..6674bdb096f34 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -150,6 +150,10 @@
 						 * are restricted to targets in
 						 * kernel.
 						 */
+#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)	/*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index cba942006ffe4..e64fd20778b61 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -60,7 +60,9 @@
 774:						\
 	add	$(BITS_PER_LONG/8) * 2, sp;	\
 	dec	reg;				\
-	jnz	771b;
+	jnz	771b;				\
+	/* barrier for jnz misprediction */	\
+	lfence;
 
 #ifdef __ASSEMBLY__
 
@@ -130,13 +132,28 @@
 #endif
 .endm
 
+.macro ISSUE_UNBALANCED_RET_GUARD
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call .Lunbalanced_ret_guard_\@
+	int3
+.Lunbalanced_ret_guard_\@:
+	add $(BITS_PER_LONG/8), %_ASM_SP
+	lfence
+.endm
+
  /*
   * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
   * monstrosity above, manually.
   */
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2
+.ifb \ftr2
 	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
+.else
+	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", "", \ftr, "jmp .Lunbalanced_\@", \ftr2
+.endif
 	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
+.Lunbalanced_\@:
+	ISSUE_UNBALANCED_RET_GUARD
 .Lskip_rsb_\@:
 .endm
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 6761668100b9f..9f7e751b91df9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1335,6 +1335,53 @@ static void __init spec_ctrl_disable_kernel_rrsba(void)
 	}
 }
 
+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:
+		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;
+
+	case SPECTRE_V2_EIBRS_RETPOLINE:
+	case SPECTRE_V2_RETPOLINE:
+	case SPECTRE_V2_LFENCE:
+	case SPECTRE_V2_IBRS:
+		setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
+		pr_info("Spectre v2 / SpectreRSB : Filling RSB 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();
@@ -1485,28 +1532,7 @@ 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");
 
-	/*
-	 * Similar to context switches, there are two types of RSB attacks
-	 * after vmexit:
-	 *
-	 * 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, on the other hand, has RSB-poisoning protections, so it
-	 * doesn't need RSB clearing after vmexit.
-	 */
-	if (boot_cpu_has(X86_FEATURE_RETPOLINE) ||
-	    boot_cpu_has(X86_FEATURE_KERNEL_IBRS))
-		setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT);
+	spectre_v2_determine_rsb_fill_type_at_vmexit(mode);
 
 	/*
 	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
@@ -2292,6 +2318,19 @@ 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_RSB_VMEXIT))
+			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)
@@ -2304,12 +2343,13 @@ 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());
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 736262a76a12b..64a73f415f036 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1135,6 +1135,7 @@ 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_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1177,7 +1178,7 @@ 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_D,		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
@@ -1187,7 +1188,9 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	 * good enough for our purposes.
 	 */
 
-	VULNWL_INTEL(ATOM_TREMONT_D,		NO_ITLB_MULTIHIT),
+	VULNWL_INTEL(ATOM_TREMONT,		NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_TREMONT_L,		NO_EIBRS_PBRSB),
+	VULNWL_INTEL(ATOM_TREMONT_D,		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),
@@ -1365,6 +1368,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_RETBLEED);
 	}
 
+	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;
 
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 4182c7ffc9091..6de96b9438044 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -227,11 +227,13 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
 	 * entries and (in some cases) RSB underflow.
 	 *
 	 * eIBRS has its own protection against poisoned RSB, so it doesn't
-	 * need the RSB filling sequence.  But it does need to be enabled
-	 * before the first unbalanced RET.
+	 * need the RSB filling sequence.  But it does need to be enabled, and a
+	 * single call to retire, before the first unbalanced RET.
          */
 
-	FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
+	FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
+			   X86_FEATURE_RSB_VMEXIT_LITE
+
 
 	pop %_ASM_ARG2	/* @flags */
 	pop %_ASM_ARG1	/* @vmx */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index a77b915d36a8e..8323ac5b7eee5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -303,6 +303,7 @@
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index cc615be27a54b..e057e039173cb 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -150,6 +150,10 @@
 						 * are restricted to targets in
 						 * kernel.
 						 */
+#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)	/*