Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

include/net/sock.h
  310731e2f161 ("net: Fix data-races around sysctl_mem.")
  e70f3c701276 ("Revert "net: set SK_MEM_QUANTUM to 4096"")
https://lore.kernel.org/all/20220711120211.7c8b7cba@canb.auug.org.au/

net/ipv4/fib_semantics.c
  747c14307214 ("ip: fix dflt addr selection for connected nexthop")
  d62607c3fe45 ("net: rename reference+tracking helpers")

net/tls/tls.h
include/net/tls.h
  3d8c51b25a23 ("net/tls: Check for errors in tls_device_init")
  587903142308 ("tls: create an internal header")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

18 files changed, 689 insertions, 123 deletions

diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 8b8cbf22461a..734b96454896 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -11,6 +11,16 @@
 
 /* Refer to drivers/acpi/cppc_acpi.c for the description of functions */
 
+bool cpc_supported_by_cpu(void)
+{
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_AMD:
+	case X86_VENDOR_HYGON:
+		return boot_cpu_has(X86_FEATURE_CPPC);
+	}
+	return false;
+}
+
 bool cpc_ffh_supported(void)
 {
 	return true;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e257f6c80372..d6858533e6e5 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -115,6 +115,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 }
 
 extern s32 __retpoline_sites[], __retpoline_sites_end[];
+extern s32 __return_sites[], __return_sites_end[];
 extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
@@ -507,9 +508,76 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 	}
 }
 
+#ifdef CONFIG_RETHUNK
+/*
+ * Rewrite the compiler generated return thunk tail-calls.
+ *
+ * For example, convert:
+ *
+ *   JMP __x86_return_thunk
+ *
+ * into:
+ *
+ *   RET
+ */
+static int patch_return(void *addr, struct insn *insn, u8 *bytes)
+{
+	int i = 0;
+
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		return -1;
+
+	bytes[i++] = RET_INSN_OPCODE;
+
+	for (; i < insn->length;)
+		bytes[i++] = INT3_INSN_OPCODE;
+
+	return i;
+}
+
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *dest = NULL, *addr = (void *)s + *s;
+		struct insn insn;
+		int len, ret;
+		u8 bytes[16];
+		u8 op;
+
+		ret = insn_decode_kernel(&insn, addr);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op = insn.opcode.bytes[0];
+		if (op == JMP32_INSN_OPCODE)
+			dest = addr + insn.length + insn.immediate.value;
+
+		if (__static_call_fixup(addr, op, dest) ||
+		    WARN_ON_ONCE(dest != &__x86_return_thunk))
+			continue;
+
+		DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",
+			addr, addr, insn.length,
+			addr + insn.length + insn.immediate.value);
+
+		len = patch_return(addr, &insn, bytes);
+		if (len == insn.length) {
+			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
+			text_poke_early(addr, bytes, len);
+		}
+	}
+}
+#else
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+#endif /* CONFIG_RETHUNK */
+
 #else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */
 
 void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */
 
@@ -860,6 +928,7 @@ void __init alternative_instructions(void)
 	 * those can rewrite the retpoline thunks.
 	 */
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
 
 	/*
 	 * Then patch alternatives, such that those paravirt calls that are in
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 437308004ef2..cb50589a7102 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -19,6 +19,7 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 #include <asm/tdx.h>
+#include "../kvm/vmx/vmx.h"
 
 #ifdef CONFIG_XEN
 #include <xen/interface/xen.h>
@@ -107,4 +108,9 @@ static void __used common(void)
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
 	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
+
+	if (IS_ENABLED(CONFIG_KVM_INTEL)) {
+		BLANK();
+		OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl);
+	}
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0c0b09796ced..35d5288394cb 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -862,6 +862,28 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 	clear_rdrand_cpuid_bit(c);
 }
 
+void init_spectral_chicken(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_CPU_UNRET_ENTRY
+	u64 value;
+
+	/*
+	 * On Zen2 we offer this chicken (bit) on the altar of Speculation.
+	 *
+	 * This suppresses speculation from the middle of a basic block, i.e. it
+	 * suppresses non-branch predictions.
+	 *
+	 * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H
+	 */
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) {
+		if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+			value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
+			wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+		}
+	}
+#endif
+}
+
 static void init_amd_zn(struct cpuinfo_x86 *c)
 {
 	set_cpu_cap(c, X86_FEATURE_ZEN);
@@ -870,12 +892,21 @@ static void init_amd_zn(struct cpuinfo_x86 *c)
 	node_reclaim_distance = 32;
 #endif
 
-	/*
-	 * Fix erratum 1076: CPB feature bit not being set in CPUID.
-	 * Always set it, except when running under a hypervisor.
-	 */
-	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB))
-		set_cpu_cap(c, X86_FEATURE_CPB);
+	/* Fix up CPUID bits, but only if not virtualised. */
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
+
+		/* Erratum 1076: CPB feature bit not being set in CPUID. */
+		if (!cpu_has(c, X86_FEATURE_CPB))
+			set_cpu_cap(c, X86_FEATURE_CPB);
+
+		/*
+		 * Zen3 (Fam19 model < 0x10) parts are not susceptible to
+		 * Branch Type Confusion, but predate the allocation of the
+		 * BTC_NO bit.
+		 */
+		if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO))
+			set_cpu_cap(c, X86_FEATURE_BTC_NO);
+	}
 }
 
 static void init_amd(struct cpuinfo_x86 *c)
@@ -907,7 +938,8 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x12: init_amd_ln(c); break;
 	case 0x15: init_amd_bd(c); break;
 	case 0x16: init_amd_jg(c); break;
-	case 0x17: fallthrough;
+	case 0x17: init_spectral_chicken(c);
+		   fallthrough;
 	case 0x19: init_amd_zn(c); break;
 	}
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 74c62cc47a5f..0dd04713434b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -38,6 +38,8 @@
 
 static void __init spectre_v1_select_mitigation(void);
 static void __init spectre_v2_select_mitigation(void);
+static void __init retbleed_select_mitigation(void);
+static void __init spectre_v2_user_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
@@ -48,16 +50,40 @@ static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);
 
-/* The base value of the SPEC_CTRL MSR that always has to be preserved. */
+/* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
 EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
+
+/* The current value of the SPEC_CTRL MSR with task-specific bits set */
+DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
+EXPORT_SYMBOL_GPL(x86_spec_ctrl_current);
+
 static DEFINE_MUTEX(spec_ctrl_mutex);
 
 /*
- * The vendor and possibly platform specific bits which can be modified in
- * x86_spec_ctrl_base.
+ * Keep track of the SPEC_CTRL MSR value for the current task, which may differ
+ * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update().
  */
-static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS;
+void write_spec_ctrl_current(u64 val, bool force)
+{
+	if (this_cpu_read(x86_spec_ctrl_current) == val)
+		return;
+
+	this_cpu_write(x86_spec_ctrl_current, val);
+
+	/*
+	 * When KERNEL_IBRS this MSR is written on return-to-user, unless
+	 * forced the update can be delayed until that time.
+	 */
+	if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
+		wrmsrl(MSR_IA32_SPEC_CTRL, val);
+}
+
+u64 spec_ctrl_current(void)
+{
+	return this_cpu_read(x86_spec_ctrl_current);
+}
+EXPORT_SYMBOL_GPL(spec_ctrl_current);
 
 /*
  * AMD specific MSR info for Speculative Store Bypass control.
@@ -114,13 +140,21 @@ void __init check_bugs(void)
 	if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
 		rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 
-	/* Allow STIBP in MSR_SPEC_CTRL if supported */
-	if (boot_cpu_has(X86_FEATURE_STIBP))
-		x86_spec_ctrl_mask |= SPEC_CTRL_STIBP;
-
 	/* Select the proper CPU mitigations before patching alternatives: */
 	spectre_v1_select_mitigation();
 	spectre_v2_select_mitigation();
+	/*
+	 * retbleed_select_mitigation() relies on the state set by
+	 * spectre_v2_select_mitigation(); specifically it wants to know about
+	 * spectre_v2=ibrs.
+	 */
+	retbleed_select_mitigation();
+	/*
+	 * spectre_v2_user_select_mitigation() relies on the state set by
+	 * retbleed_select_mitigation(); specifically the STIBP selection is
+	 * forced for UNRET.
+	 */
+	spectre_v2_user_select_mitigation();
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
 	md_clear_select_mitigation();
@@ -161,31 +195,17 @@ void __init check_bugs(void)
 #endif
 }
 
+/*
+ * NOTE: This function is *only* called for SVM.  VMX spec_ctrl handling is
+ * done in vmenter.S.
+ */
 void
 x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 {
-	u64 msrval, guestval, hostval = x86_spec_ctrl_base;
+	u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current();
 	struct thread_info *ti = current_thread_info();
 
-	/* Is MSR_SPEC_CTRL implemented ? */
 	if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
-		/*
-		 * Restrict guest_spec_ctrl to supported values. Clear the
-		 * modifiable bits in the host base value and or the
-		 * modifiable bits from the guest value.
-		 */
-		guestval = hostval & ~x86_spec_ctrl_mask;
-		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
-
-		/* SSBD controlled in MSR_SPEC_CTRL */
-		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
-		    static_cpu_has(X86_FEATURE_AMD_SSBD))
-			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
-
-		/* Conditional STIBP enabled? */
-		if (static_branch_unlikely(&switch_to_cond_stibp))
-			hostval |= stibp_tif_to_spec_ctrl(ti->flags);
-
 		if (hostval != guestval) {
 			msrval = setguest ? guestval : hostval;
 			wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
@@ -752,12 +772,180 @@ static int __init nospectre_v1_cmdline(char *str)
 }
 early_param("nospectre_v1", nospectre_v1_cmdline);
 
-#undef pr_fmt
-#define pr_fmt(fmt)     "Spectre V2 : " fmt
-
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
 	SPECTRE_V2_NONE;
 
+#undef pr_fmt
+#define pr_fmt(fmt)     "RETBleed: " fmt
+
+enum retbleed_mitigation {
+	RETBLEED_MITIGATION_NONE,
+	RETBLEED_MITIGATION_UNRET,
+	RETBLEED_MITIGATION_IBPB,
+	RETBLEED_MITIGATION_IBRS,
+	RETBLEED_MITIGATION_EIBRS,
+};
+
+enum retbleed_mitigation_cmd {
+	RETBLEED_CMD_OFF,
+	RETBLEED_CMD_AUTO,
+	RETBLEED_CMD_UNRET,
+	RETBLEED_CMD_IBPB,
+};
+
+const char * const retbleed_strings[] = {
+	[RETBLEED_MITIGATION_NONE]	= "Vulnerable",
+	[RETBLEED_MITIGATION_UNRET]	= "Mitigation: untrained return thunk",
+	[RETBLEED_MITIGATION_IBPB]	= "Mitigation: IBPB",
+	[RETBLEED_MITIGATION_IBRS]	= "Mitigation: IBRS",
+	[RETBLEED_MITIGATION_EIBRS]	= "Mitigation: Enhanced IBRS",
+};
+
+static enum retbleed_mitigation retbleed_mitigation __ro_after_init =
+	RETBLEED_MITIGATION_NONE;
+static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init =
+	RETBLEED_CMD_AUTO;
+
+static int __ro_after_init retbleed_nosmt = false;
+
+static int __init retbleed_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	while (str) {
+		char *next = strchr(str, ',');
+		if (next) {
+			*next = 0;
+			next++;
+		}
+
+		if (!strcmp(str, "off")) {
+			retbleed_cmd = RETBLEED_CMD_OFF;
+		} else if (!strcmp(str, "auto")) {
+			retbleed_cmd = RETBLEED_CMD_AUTO;
+		} else if (!strcmp(str, "unret")) {
+			retbleed_cmd = RETBLEED_CMD_UNRET;
+		} else if (!strcmp(str, "ibpb")) {
+			retbleed_cmd = RETBLEED_CMD_IBPB;
+		} else if (!strcmp(str, "nosmt")) {
+			retbleed_nosmt = true;
+		} else {
+			pr_err("Ignoring unknown retbleed option (%s).", str);
+		}
+
+		str = next;
+	}
+
+	return 0;
+}
+early_param("retbleed", retbleed_parse_cmdline);
+
+#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n"
+#define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n"
+
+static void __init retbleed_select_mitigation(void)
+{
+	bool mitigate_smt = false;
+
+	if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off())
+		return;
+
+	switch (retbleed_cmd) {
+	case RETBLEED_CMD_OFF:
+		return;
+
+	case RETBLEED_CMD_UNRET:
+		if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) {
+			retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
+		} else {
+			pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n");
+			goto do_cmd_auto;
+		}
+		break;
+
+	case RETBLEED_CMD_IBPB:
+		if (!boot_cpu_has(X86_FEATURE_IBPB)) {
+			pr_err("WARNING: CPU does not support IBPB.\n");
+			goto do_cmd_auto;
+		} else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) {
+			retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+		} else {
+			pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
+			goto do_cmd_auto;
+		}
+		break;
+
+do_cmd_auto:
+	case RETBLEED_CMD_AUTO:
+	default:
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+		    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+			if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY))
+				retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
+			else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB))
+				retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+		}
+
+		/*
+		 * The Intel mitigation (IBRS or eIBRS) was already selected in
+		 * spectre_v2_select_mitigation().  'retbleed_mitigation' will
+		 * be set accordingly below.
+		 */
+
+		break;
+	}
+
+	switch (retbleed_mitigation) {
+	case RETBLEED_MITIGATION_UNRET:
+		setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+		setup_force_cpu_cap(X86_FEATURE_UNRET);
+
+		if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
+		    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
+			pr_err(RETBLEED_UNTRAIN_MSG);
+
+		mitigate_smt = true;
+		break;
+
+	case RETBLEED_MITIGATION_IBPB:
+		setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+		mitigate_smt = true;
+		break;
+
+	default:
+		break;
+	}
+
+	if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) &&
+	    (retbleed_nosmt || cpu_mitigations_auto_nosmt()))
+		cpu_smt_disable(false);
+
+	/*
+	 * Let IBRS trump all on Intel without affecting the effects of the
+	 * retbleed= cmdline option.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+		switch (spectre_v2_enabled) {
+		case SPECTRE_V2_IBRS:
+			retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
+			break;
+		case SPECTRE_V2_EIBRS:
+		case SPECTRE_V2_EIBRS_RETPOLINE:
+		case SPECTRE_V2_EIBRS_LFENCE:
+			retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
+			break;
+		default:
+			pr_err(RETBLEED_INTEL_MSG);
+		}
+	}
+
+	pr_info("%s\n", retbleed_strings[retbleed_mitigation]);
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt)     "Spectre V2 : " fmt
+
 static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init =
 	SPECTRE_V2_USER_NONE;
 static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init =
@@ -828,6 +1016,7 @@ enum spectre_v2_mitigation_cmd {
 	SPECTRE_V2_CMD_EIBRS,
 	SPECTRE_V2_CMD_EIBRS_RETPOLINE,
 	SPECTRE_V2_CMD_EIBRS_LFENCE,
+	SPECTRE_V2_CMD_IBRS,
 };
 
 enum spectre_v2_user_cmd {
@@ -868,13 +1057,15 @@ static void __init spec_v2_user_print_cond(const char *reason, bool secure)
 		pr_info("spectre_v2_user=%s forced on command line.\n", reason);
 }
 
+static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd;
+
 static enum spectre_v2_user_cmd __init
-spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd)
+spectre_v2_parse_user_cmdline(void)
 {
 	char arg[20];
 	int ret, i;
 
-	switch (v2_cmd) {
+	switch (spectre_v2_cmd) {
 	case SPECTRE_V2_CMD_NONE:
 		return SPECTRE_V2_USER_CMD_NONE;
 	case SPECTRE_V2_CMD_FORCE:
@@ -900,15 +1091,16 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd)
 	return SPECTRE_V2_USER_CMD_AUTO;
 }
 
-static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode)
+static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
 {
-	return (mode == SPECTRE_V2_EIBRS ||
-		mode == SPECTRE_V2_EIBRS_RETPOLINE ||
-		mode == SPECTRE_V2_EIBRS_LFENCE);
+	return mode == SPECTRE_V2_IBRS ||
+	       mode == SPECTRE_V2_EIBRS ||
+	       mode == SPECTRE_V2_EIBRS_RETPOLINE ||
+	       mode == SPECTRE_V2_EIBRS_LFENCE;
 }
 
 static void __init
-spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
+spectre_v2_user_select_mitigation(void)
 {
 	enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
 	bool smt_possible = IS_ENABLED(CONFIG_SMP);
@@ -921,7 +1113,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	    cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
 		smt_possible = false;
 
-	cmd = spectre_v2_parse_user_cmdline(v2_cmd);
+	cmd = spectre_v2_parse_user_cmdline();
 	switch (cmd) {
 	case SPECTRE_V2_USER_CMD_NONE:
 		goto set_mode;
@@ -969,12 +1161,12 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	}
 
 	/*
-	 * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not
-	 * required.
+	 * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible,
+	 * STIBP is not required.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
 	    !smt_possible ||
-	    spectre_v2_in_eibrs_mode(spectre_v2_enabled))
+	    spectre_v2_in_ibrs_mode(spectre_v2_enabled))
 		return;
 
 	/*
@@ -986,6 +1178,13 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd)
 	    boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
 		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
 
+	if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET) {
+		if (mode != SPECTRE_V2_USER_STRICT &&
+		    mode != SPECTRE_V2_USER_STRICT_PREFERRED)
+			pr_info("Selecting STIBP always-on mode to complement retbleed mitigation'\n");
+		mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+	}
+
 	spectre_v2_user_stibp = mode;
 
 set_mode:
@@ -999,6 +1198,7 @@ static const char * const spectre_v2_strings[] = {
 	[SPECTRE_V2_EIBRS]			= "Mitigation: Enhanced IBRS",
 	[SPECTRE_V2_EIBRS_LFENCE]		= "Mitigation: Enhanced IBRS + LFENCE",
 	[SPECTRE_V2_EIBRS_RETPOLINE]		= "Mitigation: Enhanced IBRS + Retpolines",
+	[SPECTRE_V2_IBRS]			= "Mitigation: IBRS",
 };
 
 static const struct {
@@ -1016,6 +1216,7 @@ static const struct {
 	{ "eibrs,lfence",	SPECTRE_V2_CMD_EIBRS_LFENCE,	  false },
 	{ "eibrs,retpoline",	SPECTRE_V2_CMD_EIBRS_RETPOLINE,	  false },
 	{ "auto",		SPECTRE_V2_CMD_AUTO,		  false },
+	{ "ibrs",		SPECTRE_V2_CMD_IBRS,              false },
 };
 
 static void __init spec_v2_print_cond(const char *reason, bool secure)
@@ -1078,6 +1279,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 		return SPECTRE_V2_CMD_AUTO;
 	}
 
+	if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) {
+		pr_err("%s selected but not compiled in. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
+		pr_err("%s selected but not Intel CPU. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) {
+		pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
+	if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) {
+		pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n",
+		       mitigation_options[i].option);
+		return SPECTRE_V2_CMD_AUTO;
+	}
+
 	spec_v2_print_cond(mitigation_options[i].option,
 			   mitigation_options[i].secure);
 	return cmd;
@@ -1093,6 +1318,22 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void)
 	return SPECTRE_V2_RETPOLINE;
 }
 
+/* Disable in-kernel use of non-RSB RET predictors */
+static void __init spec_ctrl_disable_kernel_rrsba(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL))
+		return;
+
+	ia32_cap = x86_read_arch_cap_msr();
+
+	if (ia32_cap & ARCH_CAP_RRSBA) {
+		x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S;
+		write_spec_ctrl_current(x86_spec_ctrl_base, true);
+	}
+}
+
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1117,6 +1358,15 @@ static void __init spectre_v2_select_mitigation(void)
 			break;
 		}
 
+		if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) &&
+		    boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+		    retbleed_cmd != RETBLEED_CMD_OFF &&
+		    boot_cpu_has(X86_FEATURE_IBRS) &&
+		    boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+			mode = SPECTRE_V2_IBRS;
+			break;
+		}
+
 		mode = spectre_v2_select_retpoline();
 		break;
 
@@ -1133,6 +1383,10 @@ static void __init spectre_v2_select_mitigation(void)
 		mode = spectre_v2_select_retpoline();
 		break;
 
+	case SPECTRE_V2_CMD_IBRS:
+		mode = SPECTRE_V2_IBRS;
+		break;
+
 	case SPECTRE_V2_CMD_EIBRS:
 		mode = SPECTRE_V2_EIBRS;
 		break;
@@ -1149,10 +1403,9 @@ static void __init spectre_v2_select_mitigation(void)
 	if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
 		pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
 
-	if (spectre_v2_in_eibrs_mode(mode)) {
-		/* Force it so VMEXIT will restore correctly */
+	if (spectre_v2_in_ibrs_mode(mode)) {
 		x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
-		wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+		write_spec_ctrl_current(x86_spec_ctrl_base, true);
 	}
 
 	switch (mode) {
@@ -1160,6 +1413,10 @@ static void __init spectre_v2_select_mitigation(void)
 	case SPECTRE_V2_EIBRS:
 		break;
 
+	case SPECTRE_V2_IBRS:
+		setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS);
+		break;
+
 	case SPECTRE_V2_LFENCE:
 	case SPECTRE_V2_EIBRS_LFENCE:
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE);
@@ -1171,43 +1428,107 @@ static void __init spectre_v2_select_mitigation(void)
 		break;
 	}
 
+	/*
+	 * Disable alternate RSB predictions in kernel when indirect CALLs and
+	 * JMPs gets protection against BHI and Intramode-BTI, but RET
+	 * prediction from a non-RSB predictor is still a risk.
+	 */
+	if (mode == SPECTRE_V2_EIBRS_LFENCE ||
+	    mode == SPECTRE_V2_EIBRS_RETPOLINE ||
+	    mode == SPECTRE_V2_RETPOLINE)
+		spec_ctrl_disable_kernel_rrsba();
+
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If spectre v2 protection has been enabled, unconditionally fill
-	 * RSB during a context switch; this protects against two independent
-	 * issues:
+	 * If Spectre v2 protection has been enabled, fill the RSB during a
+	 * context switch.  In general there are two types of RSB attacks
+	 * across context switches, for which the CALLs/RETs may be unbalanced.
 	 *
-	 *	- RSB underflow (and switch to BTB) on Skylake+
-	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
+	 * 1) RSB underflow
+	 *
+	 *    Some Intel parts have "bottomless RSB".  When the RSB is empty,
+	 *    speculated return targets may come from the branch predictor,
+	 *    which could have a user-poisoned BTB or BHB entry.
+	 *
+	 *    AMD has it even worse: *all* returns are speculated from the BTB,
+	 *    regardless of the state of the RSB.
+	 *
+	 *    When IBRS or eIBRS is enabled, the "user -> kernel" attack
+	 *    scenario is mitigated by the IBRS branch prediction isolation
+	 *    properties, so the RSB buffer filling wouldn't be necessary to
+	 *    protect against this type of attack.
+	 *
+	 *    The "user -> user" attack scenario is mitigated by RSB filling.
+	 *
+	 * 2) Poisoned RSB entry
+	 *
+	 *    If the 'next' in-kernel return stack is shorter than 'prev',
+	 *    'next' could be tricked into speculating with a user-poisoned RSB
+	 *    entry.
+	 *
+	 *    The "user -> kernel" attack scenario is mitigated by SMEP and
+	 *    eIBRS.
+	 *
+	 *    The "user -> user" scenario, also known as SpectreBHB, requires
+	 *    RSB clearing.
+	 *
+	 * So to mitigate all cases, unconditionally fill RSB on context
+	 * switches.
+	 *
+	 * FIXME: Is this pointless for retbleed-affected AMD?
 	 */
 	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
 	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
 	/*
-	 * Retpoline means the kernel is safe because it has no indirect
-	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
-	 * speculation around firmware calls only when Enhanced IBRS isn't
-	 * supported.
+	 * 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);
+
+	/*
+	 * Retpoline protects the kernel, but doesn't protect firmware.  IBRS
+	 * and Enhanced IBRS protect firmware too, so enable IBRS around
+	 * firmware calls only when IBRS / Enhanced IBRS aren't otherwise
+	 * enabled.
 	 *
 	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
 	 * the user might select retpoline on the kernel command line and if
 	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
 	 * enable IBRS around firmware calls.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) {
+	if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
 
 	/* Set up IBPB and STIBP depending on the general spectre V2 command */
-	spectre_v2_user_select_mitigation(cmd);
+	spectre_v2_cmd = cmd;
 }
 
 static void update_stibp_msr(void * __unused)
 {
-	wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+	u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP);
+	write_spec_ctrl_current(val, true);
 }
 
 /* Update x86_spec_ctrl_base in case SMT state changed. */
@@ -1424,16 +1745,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 	}
 
 	/*
-	 * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper
-	 * bit in the mask to allow guests to use the mitigation even in the
-	 * case where the host does not enable it.
-	 */
-	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
-	    static_cpu_has(X86_FEATURE_AMD_SSBD)) {
-		x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
-	}
-
-	/*
 	 * We have three CPU feature flags that are in play here:
 	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
 	 *  - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
@@ -1450,7 +1761,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 			x86_amd_ssb_disable();
 		} else {
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
-			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			write_spec_ctrl_current(x86_spec_ctrl_base, true);
 		}
 	}
 
@@ -1701,7 +2012,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 void x86_spec_ctrl_setup_ap(void)