21 files changed, 262 insertions, 238 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a5ead6a6d233..73be3931e4f0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -403,6 +403,17 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	u8 insn_buff[MAX_PATCH_LEN];
 
 	DPRINTK(ALT, "alt table %px, -> %px", start, end);
+
+	/*
+	 * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using
+	 * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here.
+	 * During the process, KASAN becomes confused seeing partial LA57
+	 * conversion and triggers a false-positive out-of-bound report.
+	 *
+	 * Disable KASAN until the patching is complete.
+	 */
+	kasan_disable_current();
+
 	/*
 	 * The scan order should be from start to end. A later scanned
 	 * alternative code can overwrite previously scanned alternative code.
@@ -452,6 +463,8 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 
 		text_poke_early(instr, insn_buff, insn_buff_sz);
 	}
+
+	kasan_enable_current();
 }
 
 static inline bool is_jcc32(struct insn *insn)
@@ -720,13 +733,8 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
-	/*
-	 * Do not patch out the default return thunks if those needed are the
-	 * ones generated by the compiler.
-	 */
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK) &&
-	    (x86_return_thunk == __x86_return_thunk))
-		return;
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		static_call_force_reinit();
 
 	for (s = start; s < end; s++) {
 		void *dest = NULL, *addr = (void *)s + *s;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d9f5d7492f83..205cee567629 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1533,7 +1533,7 @@ static void __init build_socket_tables(void)
 {
 	struct uv_gam_range_entry *gre = uv_gre_table;
 	int nums, numn, nump;
-	int cpu, i, lnid;
+	int i, lnid, apicid;
 	int minsock = _min_socket;
 	int maxsock = _max_socket;
 	int minpnode = _min_pnode;
@@ -1584,15 +1584,14 @@ static void __init build_socket_tables(void)
 
 	/* Set socket -> node values: */
 	lnid = NUMA_NO_NODE;
-	for_each_possible_cpu(cpu) {
-		int nid = cpu_to_node(cpu);
-		int apicid, sockid;
+	for (apicid = 0; apicid < ARRAY_SIZE(__apicid_to_node); apicid++) {
+		int nid = __apicid_to_node[apicid];
+		int sockid;
 
-		if (lnid == nid)
+		if ((nid == NUMA_NO_NODE) || (lnid == nid))
 			continue;
 		lnid = nid;
 
-		apicid = per_cpu(x86_cpu_to_apicid, cpu);
 		sockid = apicid >> uv_cpuid.socketid_shift;
 
 		if (_socket_to_node[sockid - minsock] == SOCK_EMPTY)
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index c06bfc086565..faa9f2299848 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -272,7 +272,6 @@ void __init callthunks_patch_builtin_calls(void)
 	pr_info("Setting up call depth tracking\n");
 	mutex_lock(&text_mutex);
 	callthunks_setup(&cs, &builtin_coretext);
-	static_call_force_reinit();
 	thunks_initialized = true;
 	mutex_unlock(&text_mutex);
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index dd8379d84445..ece2b5b7b0fe 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -80,6 +80,10 @@ static const int amd_div0[] =
 	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf),
 			   AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf));
 
+static const int amd_erratum_1485[] =
+	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
+			   AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf));
+
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {
 	int osvw_id = *erratum++;
@@ -766,6 +770,15 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 	if (cpu_has(c, X86_FEATURE_TOPOEXT))
 		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
+		if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
+			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+		else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+			setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+			setup_force_cpu_cap(X86_FEATURE_SBPB);
+		}
+	}
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -1140,6 +1153,10 @@ static void init_amd(struct cpuinfo_x86 *c)
 		pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
 		setup_force_cpu_bug(X86_BUG_DIV0);
 	}
+
+	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
+	     cpu_has_amd_erratum(c, amd_erratum_1485))
+		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
 }
 
 #ifdef CONFIG_X86_32
@@ -1301,25 +1318,6 @@ void amd_check_microcode(void)
 	on_each_cpu(zenbleed_check_cpu, NULL, 1);
 }
 
-bool cpu_has_ibpb_brtype_microcode(void)
-{
-	switch (boot_cpu_data.x86) {
-	/* Zen1/2 IBPB flushes branch type predictions too. */
-	case 0x17:
-		return boot_cpu_has(X86_FEATURE_AMD_IBPB);
-	case 0x19:
-		/* Poke the MSR bit on Zen3/4 to check its presence. */
-		if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
-			setup_force_cpu_cap(X86_FEATURE_SBPB);
-			return true;
-		} else {
-			return false;
-		}
-	default:
-		return false;
-	}
-}
-
 /*
  * Issue a DIV 0/1 insn to clear any division data from previous DIV
  * operations.
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index f081d26616ac..10499bcd4e39 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -2404,27 +2404,16 @@ early_param("spec_rstack_overflow", srso_parse_cmdline);
 
 static void __init srso_select_mitigation(void)
 {
-	bool has_microcode;
+	bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE);
 
 	if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off())
 		goto pred_cmd;
 
-	/*
-	 * The first check is for the kernel running as a guest in order
-	 * for guests to verify whether IBPB is a viable mitigation.
-	 */
-	has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode();
 	if (!has_microcode) {
 		pr_warn("IBPB-extending microcode not applied!\n");
 		pr_warn(SRSO_NOTICE);
 	} else {
 		/*
-		 * Enable the synthetic (even if in a real CPUID leaf)
-		 * flags for guests.
-		 */
-		setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
-
-		/*
 		 * Zen1/2 with SMT off aren't vulnerable after the right
 		 * IBPB microcode has been applied.
 		 */
@@ -2444,7 +2433,7 @@ static void __init srso_select_mitigation(void)
 
 	switch (srso_cmd) {
 	case SRSO_CMD_OFF:
-		return;
+		goto pred_cmd;
 
 	case SRSO_CMD_MICROCODE:
 		if (has_microcode) {
@@ -2717,7 +2706,7 @@ static ssize_t srso_show_state(char *buf)
 
 	return sysfs_emit(buf, "%s%s\n",
 			  srso_strings[srso_mitigation],
-			  (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode"));
+			  boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode");
 }
 
 static ssize_t gds_show_state(char *buf)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 382d4e6b848d..4e5ffc8b0e46 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1303,7 +1303,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_AMD(0x15, RETBLEED),
 	VULNBL_AMD(0x16, RETBLEED),
 	VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
-	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
+	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
 	VULNBL_AMD(0x19, SRSO),
 	{}
 };
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index ded1fc7cb7cb..f136ac046851 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -30,15 +30,15 @@ struct rmid_entry {
 	struct list_head		list;
 };
 
-/**
- * @rmid_free_lru    A least recently used list of free RMIDs
+/*
+ * @rmid_free_lru - A least recently used list of free RMIDs
  *     These RMIDs are guaranteed to have an occupancy less than the
  *     threshold occupancy
  */
 static LIST_HEAD(rmid_free_lru);
 
-/**
- * @rmid_limbo_count     count of currently unused but (potentially)
+/*
+ * @rmid_limbo_count - count of currently unused but (potentially)
  *     dirty RMIDs.
  *     This counts RMIDs that no one is currently using but that
  *     may have a occupancy value > resctrl_rmid_realloc_threshold. User can
@@ -46,7 +46,7 @@ static LIST_HEAD(rmid_free_lru);
  */
 static unsigned int rmid_limbo_count;
 
-/**
+/*
  * @rmid_entry - The entry in the limbo and free lists.
  */
 static struct rmid_entry	*rmid_ptrs;
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 91fa70e51004..279148e72459 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -235,6 +235,21 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
 	return epc_page;
 }
 
+/*
+ * Ensure the SECS page is not swapped out.  Must be called with encl->lock
+ * to protect the enclave states including SECS and ensure the SECS page is
+ * not swapped out again while being used.
+ */
+static struct sgx_epc_page *sgx_encl_load_secs(struct sgx_encl *encl)
+{
+	struct sgx_epc_page *epc_page = encl->secs.epc_page;
+
+	if (!epc_page)
+		epc_page = sgx_encl_eldu(&encl->secs, NULL);
+
+	return epc_page;
+}
+
 static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
 						  struct sgx_encl_page *entry)
 {
@@ -248,11 +263,9 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
 		return entry;
 	}
 
-	if (!(encl->secs.epc_page)) {
-		epc_page = sgx_encl_eldu(&encl->secs, NULL);
-		if (IS_ERR(epc_page))
-			return ERR_CAST(epc_page);
-	}
+	epc_page = sgx_encl_load_secs(encl);
+	if (IS_ERR(epc_page))
+		return ERR_CAST(epc_page);
 
 	epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
 	if (IS_ERR(epc_page))
@@ -339,6 +352,13 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
 
 	mutex_lock(&encl->lock);
 
+	epc_page = sgx_encl_load_secs(encl);
+	if (IS_ERR(epc_page)) {
+		if (PTR_ERR(epc_page) == -EBUSY)
+			vmret = VM_FAULT_NOPAGE;
+		goto err_out_unlock;
+	}
+
 	epc_page = sgx_alloc_epc_page(encl_page, false);
 	if (IS_ERR(epc_page)) {
 		if (PTR_ERR(epc_page) == -EBUSY)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index a86d37052a64..a21a4d0ecc34 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
 EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
 
 void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
-				    unsigned int size, u32 pkru)
+				    unsigned int size, u64 xfeatures, u32 pkru)
 {
 	struct fpstate *kstate = gfpu->fpstate;
 	union fpregs_state *ustate = buf;
 	struct membuf mb = { .p = buf, .left = size };
 
 	if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
-		__copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE);
+		__copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru,
+					  XSTATE_COPY_XSAVE);
 	} else {
 		memcpy(&ustate->fxsave, &kstate->regs.fxsave,
 		       sizeof(ustate->fxsave));
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index cadf68737e6b..ef6906107c54 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1049,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
  * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
  * @to:		membuf descriptor
  * @fpstate:	The fpstate buffer from which to copy
+ * @xfeatures:	The mask of xfeatures to save (XSAVE mode only)
  * @pkru_val:	The PKRU value to store in the PKRU component
  * @copy_mode:	The requested copy mode
  *
@@ -1059,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
  * It supports partial copy but @to.pos always starts from zero.
  */
 void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
-			       u32 pkru_val, enum xstate_copy_mode copy_mode)
+			       u64 xfeatures, u32 pkru_val,
+			       enum xstate_copy_mode copy_mode)
 {
 	const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
 	struct xregs_state *xinit = &init_fpstate.regs.xsave;
@@ -1083,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 		break;
 
 	case XSTATE_COPY_XSAVE:
-		header.xfeatures &= fpstate->user_xfeatures;
+		header.xfeatures &= fpstate->user_xfeatures & xfeatures;
 		break;
 	}
 
@@ -1185,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 			     enum xstate_copy_mode copy_mode)
 {
 	__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
+				  tsk->thread.fpu.fpstate->user_xfeatures,
 				  tsk->thread.pkru, copy_mode);
 }
 
@@ -1536,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
 		fpregs_restore_userregs();
 
 	newfps->xfeatures = curfps->xfeatures | xfeatures;
-
-	if (!guest_fpu)
-		newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
-
+	newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
 	newfps->xfd = curfps->xfd & ~xfeatures;
 
 	/* Do the final updates within the locked region */
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index a4ecb04d8d64..3518fb26d06b 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -43,7 +43,8 @@ enum xstate_copy_mode {
 
 struct membuf;
 extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
-				      u32 pkru_val, enum xstate_copy_mode copy_mode);
+				      u64 xfeatures, u32 pkru_val,
+				      enum xstate_copy_mode copy_mode);
 extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
 				    enum xstate_copy_mode mode);
 extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 3a43a2dee658..9c9faa1634fb 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -695,7 +695,6 @@ void kgdb_arch_exit(void)
 }
 
 /**
- *
  *	kgdb_skipexception - Bail out of KGDB when we've been triggered.
  *	@exception: Exception vector number
  *	@regs: Current &struct pt_regs.
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 975f98d5eee5..97f1436c1a20 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -143,66 +143,7 @@ int paravirt_disable_iospace(void)
 	return request_resource(&ioport_resource, &reserve_ioports);
 }
 
-static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
-
-static inline void enter_lazy(enum paravirt_lazy_mode mode)
-{
-	BUG_ON(this_cpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-
-	this_cpu_write(paravirt_lazy_mode, mode);
-}
-
-static void leave_lazy(enum paravirt_lazy_mode mode)
-{
-	BUG_ON(this_cpu_read(paravirt_lazy_mode) != mode);
-
-	this_cpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
-}
-
-void paravirt_enter_lazy_mmu(void)
-{
-	enter_lazy(PARAVIRT_LAZY_MMU);
-}
-
-void paravirt_leave_lazy_mmu(void)
-{
-	leave_lazy(PARAVIRT_LAZY_MMU);
-}
-
-void paravirt_flush_lazy_mmu(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 #ifdef CONFIG_PARAVIRT_XXL
-void paravirt_start_context_switch(struct task_struct *prev)
-{
-	BUG_ON(preemptible());
-
-	if (this_cpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
-	}
-	enter_lazy(PARAVIRT_LAZY_CPU);
-}
-
-void paravirt_end_context_switch(struct task_struct *next)
-{
-	BUG_ON(preemptible());
-
-	leave_lazy(PARAVIRT_LAZY_CPU);
-
-	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
-		arch_enter_lazy_mmu_mode();
-}
-
 static noinstr void pv_native_write_cr2(unsigned long val)
 {
 	native_write_cr2(val);
@@ -229,14 +170,6 @@ static noinstr void pv_native_safe_halt(void)
 }
 #endif
 
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
-{
-	if (in_interrupt())
-		return PARAVIRT_LAZY_NONE;
-
-	return this_cpu_read(paravirt_lazy_mode);
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 #ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9f0909142a0a..b6f4e8399fca 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -257,13 +257,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
 		io_bitmap_share(p);
 
-	/*
-	 * If copy_thread() if failing, don't leak the shadow stack possibly
-	 * allocated in shstk_alloc_thread_stack() above.
-	 */
-	if (ret)
-		shstk_free(p);
-
 	return ret;
 }
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b9145a63da77..b098b1fa2470 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -358,15 +358,11 @@ static void __init add_early_ima_buffer(u64 phys_addr)
 #if defined(CONFIG_HAVE_IMA_KEXEC) && !defined(CONFIG_OF_FLATTREE)
 int __init ima_free_kexec_buffer(void)
 {
-	int rc;
-
 	if (!ima_kexec_buffer_size)
 		return -ENOENT;
 
-	rc = memblock_phys_free(ima_kexec_buffer_phys,
-				ima_kexec_buffer_size);
-	if (rc)
-		return rc;
+	memblock_free_late(ima_kexec_buffer_phys,
+			   ima_kexec_buffer_size);
 
 	ima_kexec_buffer_phys = 0;
 	ima_kexec_buffer_size = 0;
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 2eabccde94fb..ccb0915e84e1 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -256,7 +256,7 @@ static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg)
 	return 0;
 }
 
-static int sev_cpuid_hv(struct cpuid_leaf *leaf)
+static int __sev_cpuid_hv_msr(struct cpuid_leaf *leaf)
 {
 	int ret;
 
@@ -279,6 +279,45 @@ static int sev_cpuid_hv(struct cpuid_leaf *leaf)
 	return ret;
 }
 
+static int __sev_cpuid_hv_ghcb(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+{
+	u32 cr4 = native_read_cr4();
+	int ret;
+
+	ghcb_set_rax(ghcb, leaf->fn);
+	ghcb_set_rcx(ghcb, leaf->subfn);
+
+	if (cr4 & X86_CR4_OSXSAVE)
+		/* Safe to read xcr0 */
+		ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
+	else
+		/* xgetbv will cause #UD - use reset value for xcr0 */
+		ghcb_set_xcr0(ghcb, 1);
+
+	ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
+	if (ret != ES_OK)
+		return ret;
+
+	if (!(ghcb_rax_is_valid(ghcb) &&
+	      ghcb_rbx_is_valid(ghcb) &&
+	      ghcb_rcx_is_valid(ghcb) &&
+	      ghcb_rdx_is_valid(ghcb)))
+		return ES_VMM_ERROR;
+
+	leaf->eax = ghcb->save.rax;
+	leaf->ebx = ghcb->save.rbx;
+	leaf->ecx = ghcb->save.rcx;
+	leaf->edx = ghcb->save.rdx;
+
+	return ES_OK;
+}
+
+static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+{
+	return ghcb ? __sev_cpuid_hv_ghcb(ghcb, ctxt, leaf)
+		    : __sev_cpuid_hv_msr(leaf);
+}
+
 /*
  * This may be called early while still running on the initial identity
  * mapping. Use RIP-relative addressing to obtain the correct address
@@ -388,19 +427,20 @@ snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
 	return false;
 }
 
-static void snp_cpuid_hv(struct cpuid_leaf *leaf)
+static void snp_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 {
-	if (sev_cpuid_hv(leaf))
+	if (sev_cpuid_hv(ghcb, ctxt, leaf))
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV);
 }
 
-static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
+static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+				 struct cpuid_leaf *leaf)
 {
 	struct cpuid_leaf leaf_hv = *leaf;
 
 	switch (leaf->fn) {
 	case 0x1:
-		snp_cpuid_hv(&leaf_hv);
+		snp_cpuid_hv(ghcb, ctxt, &leaf_hv);
 
 		/* initial APIC ID */
 		leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0));
@@ -419,7 +459,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
 		break;
 	case 0xB:
 		leaf_hv.subfn = 0;
-		snp_cpuid_hv(&leaf_hv);
+		snp_cpuid_hv(ghcb, ctxt, &leaf_hv);
 
 		/* extended APIC ID */
 		leaf->edx = leaf_hv.edx;
@@ -467,7 +507,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
 		}
 		break;
 	case 0x8000001E:
-		snp_cpuid_hv(&leaf_hv);
+		snp_cpuid_hv(ghcb, ctxt, &leaf_hv);
 
 		/* extended APIC ID */
 		leaf->eax = leaf_hv.eax;
@@ -488,7 +528,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
  * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
  * should be treated as fatal by caller.
  */
-static int snp_cpuid(struct cpuid_leaf *leaf)
+static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
 
@@ -522,7 +562,7 @@ static int snp_cpuid(struct cpuid_leaf *leaf)
 			return 0;
 	}
 
-	return snp_cpuid_postprocess(leaf);
+	return snp_cpuid_postprocess(ghcb, ctxt, leaf);
 }
 
 /*
@@ -544,14 +584,14 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
 	leaf.fn = fn;
 	leaf.subfn = subfn;
 
-	ret = snp_cpuid(&leaf);
+	ret = snp_cpuid(NULL, NULL, &leaf);
 	if (!ret)
 		goto cpuid_done;
 
 	if (ret != -EOPNOTSUPP)
 		goto fail;
 
-	if (sev_cpuid_hv(&leaf))
+	if (__sev_cpuid_hv_msr(&leaf))
 		goto fail;
 
 cpuid_done:
@@ -592,6 +632,23 @@ fail:
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
 }
 
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+					   unsigned long address,
+					   bool write)
+{
+	if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+		ctxt->fi.vector     = X86_TRAP_PF;
+		ctxt->fi.error_code = X86_PF_USER;
+		ctxt->fi.cr2        = address;
+		if (write)
+			ctxt->fi.error_code |= X86_PF_WRITE;
+
+		return ES_EXCEPTION;
+	}
+
+	return ES_OK;
+}
+
 static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
 					  void *src, char *buf,
 					  unsigned int data_size,
@@ -599,7 +656,12 @@ static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
 					  bool backwards)
 {
 	int i, b = backwards ? -1 : 1;
-	enum es_result ret = ES_OK;
+	unsigned long address = (unsigned long)src;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, false);
+	if (ret != ES_OK)
+		return ret;
 
 	for (i = 0; i < count; i++) {
 		void *s = src + (i * data_size * b);
@@ -620,7 +682,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
 					   bool backwards)
 {
 	int i, s = backwards ? -1 : 1;
-	enum es_result ret = ES_OK;
+	unsigned long address = (unsigned long)dst;
+	enum es_result ret;
+
+	ret = vc_insn_string_check(ctxt, address, true);
+	if (ret != ES_OK)
+		return ret;
 
 	for (i = 0; i < count; i++) {
 		void *d = dst + (i * data_size * s);
@@ -656,6 +723,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
 static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 {
 	struct insn *insn = &ctxt->insn;
+	size_t size;
+	u64 port;
+
 	*exitinfo = 0;
 
 	switch (insn->opcode.bytes[0]) {
@@ -664,7 +734,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0x6d:
 		*exitinfo |= IOIO_TYPE_INS;
 		*exitinfo |= IOIO_SEG_ES;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	/* OUTS opcodes */
@@ -672,41 +742,43 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0x6f:
 		*exitinfo |= IOIO_TYPE_OUTS;
 		*exitinfo |= IOIO_SEG_DS;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	/* IN immediate opcodes */
 	case 0xe4:
 	case 0xe5:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (u8)insn->immediate.value << 16;
+		port	   = (u8)insn->immediate.value & 0xffff;
 		break;
 
 	/* OUT immediate opcodes */
 	case 0xe6:
 	case 0xe7:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (u8)insn->immediate.value << 16;
+		port	   = (u8)insn->immediate.value & 0xffff;
 		break;
 
 	/* IN register opcodes */
 	case 0xec:
 	case 0xed:
 		*exitinfo |= IOIO_TYPE_IN;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	/* OUT register opcodes */
 	case 0xee:
 	case 0xef:
 		*exitinfo |= IOIO_TYPE_OUT;
-		*exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+		port	   = ctxt->regs->dx & 0xffff;
 		break;
 
 	default:
 		return ES_DECODE_FAILED;
 	}
 
+	*exitinfo |= port << 16;
+
 	switch (insn->opcode.bytes[0]) {
 	case 0x6c:
 	case 0x6e:
@@ -716,12 +788,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	case 0xee:
 		/* Single byte opcodes */
 		*exitinfo |= IOIO_DATA_8;
+		size       = 1;
 		break;
 	default:
 		/* Length determined by instruction parsing */
 		*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
 						     : IOIO_DATA_32;
+		size       = (insn->opnd_bytes == 2) ? 2 : 4;
 	}
+
 	switch (insn->addr_bytes) {
 	case 2:
 		*exitinfo |= IOIO_ADDR_16;
@@ -737,7 +812,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
 	if (insn_has_rep_prefix(insn))
 		*exitinfo |= IOIO_REP;
 
-	return ES_OK;
+	return vc_ioio_check(ctxt, (u16)port, size);
 }
 
 static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
@@ -848,14 +923,15 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 	return ret;
 }
 
-static int vc_handle_cpuid_snp(struct pt_regs *regs)
+static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 {
+	struct pt_regs *regs = ctxt->regs;
 	struct cpuid_leaf leaf;
 	int ret;
 
 	leaf.fn = regs->ax;
 	leaf.subfn = regs->cx;
-	ret = snp_cpuid(&leaf);
+	ret = snp_cpuid(ghcb, ctxt, &leaf);
 	if (!ret) {
 		regs->ax = leaf.eax;
 		regs->bx = leaf.ebx;
@@ -874,7 +950,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
 	enum es_result ret;
 	int snp_cpuid_ret;
 
-	snp_cpuid_ret = vc_handle_cpuid_snp(regs);
+	snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
 	if (!snp_cpuid_ret)
 		return ES_OK;
 	if (snp_cpuid_ret != -EOPNOTSUPP)
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 2787826d9f60..6395bfd87b68 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -524,6 +524,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
 	return ES_OK;
 }
 
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+	BUG_ON(size > 4);
+
+	if (user_mode(ctxt->regs)) {
+		struct thread_struct *t = &current->thread;
+		struct io_bitmap *iobm = t->io_bitmap;
+		size_t idx;
+
+		if (!iobm)
+			goto fault;
+
+		for (idx = port; idx < port + size; ++idx) {
+			if (test_bit(idx, iobm->bitmap))
+				goto fault;
+		}
+	}
+
+	return ES_OK;
+
+fault:
+	ctxt->fi.vector = X86_TRAP_GP;
+	ctxt->fi.error_code = 0;
+
+	return ES_EXCEPTION;
+}
+
 /* Include code shared with pre-decompression boot stage */
 #include "sev-shared.c"
 
@@ -868,8 +895,7 @@ void snp_set_memory_private(unsigned long vaddr, unsigned long npages)
 
 void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 {
-	unsigned long vaddr;
-	unsigned int npages;
+	unsigned long vaddr, npages;
 
 	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
 		return;
@@ -1509,6 +1535,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
 			return ES_DECODE_FAILED;
 	}
 
+	if (user_mode(ctxt->regs))
+		return ES_UNSUPPORTED;
+
 	switch (mmio) {
 	case INSN_MMIO_WRITE:
 		memcpy(ghcb->shared_buffer, reg_data, bytes);
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index fd689921a1db..59e15dd8d0f8 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -205,10 +205,21 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long cl
 		return 0;
 
 	/*
-	 * For CLONE_VM, except vfork, the child needs a separate shadow
+	 * For CLONE_VFORK the child will share the parents shadow stack.
+	 * Make sure to clear the internal tracking of the thread shadow
+	 * stack so the freeing logic run for child knows to leave it alone.
+	 */
+	if (clone_flags & CLONE_VFORK) {
+		shstk->base = 0;
+		shstk->size = 0;
+		return 0;
+	}
+
+	/*
+	 * For !CLONE_VM the child will use a copy of the parents shadow
 	 * stack.
 	 */
-	if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM)
+	if (!(clone_flags & CLONE_VM))
 		return 0;
 
 	size = adjust_shstk_size(stack_size);
@@ -408,7 +419,25 @@ void shstk_free(struct task_struct *tsk)
 	if (!tsk->mm || tsk->mm != current->mm)
 		return;
 
+	/*
+	 * If shstk->base is NULL, then this task is not managing its
+	 * own shadow stack (CLONE_VFORK). So skip freeing it.
+	 */
+	if (!shstk->base)
+		return;
+
+	/*
+	 * shstk->base is NULL for CLONE_VFORK child tasks, and so is
+	 * normal. But size = 0 on a shstk->base is not normal and
+	 * indicated an attempt to free the thread shadow stack twice.
+	 * Warn about it.
+	 */
+	if (WARN_ON(!shstk->size))
+		return;
+
 	unmap_shadow_stack(shstk->base, shstk->size);
+
+	shstk->size = 0;
 }
 
 static int wrss_control(bool enable)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 6eb06d001bcc..96a771f9f930 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -131,7 +131,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 }
 
 /*
- * Disable virtualization, APIC etc. and park the CPU in a HLT loop
+ * this function calls the 'stop' function on all other CPUs in the system.
  */
 DEFINE_IDTENTRY_SYSVEC(sysvec_reboot)
 {
@@ -172,17 +172,13 @@ static void native_stop_other_cpus(int wait)
 	 * 2) Wait for all other CPUs to report that they reached the
 	 *    HLT loop in stop_this_cpu()
 	 *
-	 * 3) If the system uses INIT/STARTUP for CPU bringup, then
-	 *    send all present CPUs an INIT vector, which brings them
-	 *    completely out of the way.
+	 * 3) If #2 timed out send an NMI to the CPUs which did not
+	 *    yet report
 	 *
-	 * 4) If #3 is not possible and #2 timed out send an NMI to the
-	 *    CPUs which did not yet report
-	 *
-	 * 5) Wait for all other CPUs to report that they reached the
+	 * 4) Wait for all other CPUs to report that they reached the
 	 *    HLT loop in stop_this_cpu()
 	 *
-	 * #4 can obviously race against a CPU reaching the HLT loop late.
+	 * #3 can obviously race against a CPU reaching the HLT loop late.
 	 * That CPU will have reported already and the "have all CPUs
 	 * reached HLT" condition will be true despite the fact that the
 	 * other CPU is still handling the NMI. Again, there is no
@@ -198,7 +194,7 @@ static void native_stop_other_cpus(int wait)
 		/*
 		 * Don't wait longer than a second for IPI completion. The
 		 * wait request is not checked here because that would
-		 * prevent an NMI/INIT shutdown in case that not all
+		 * prevent an NMI shutdown attempt in case that not all
 		 * CPUs reach shutdown state.
 		 */
 		timeout = USEC_PER_SEC;
@@ -206,27 +202,7 @@ static void native_stop_other_cpus(int wait)
 			udelay(1);
 	}
 
-	/*
-	 * Park all other CPUs in INIT including "offline" CPUs, if
-	 * possible. That's a safe place where they can't resume execution
-	 * of HLT and then execute the HLT loop from overwritten text or
-	 * page tables.
-	 *
-	 * The only downside is a broadcast MCE, but up to the point where
-	 * the kexec() kernel brought all APs online again an MCE will just
-	 * make HLT resume and handle the MCE. The machine crashes and burns
-	 * due to overwritten text, page tables and data. So there is a
-	 * choice between fire and frying pan. The result is pretty much
-	 * the same. Chose frying pan until x86 provides a sane mechanism
-	 * to park a CPU.
-	 */
-	if (smp_park_other_cpus_in_init())
-		goto done;
-
-	/*
-	 * If park with INIT was not possible and the REBOOT_VECTOR didn't
-	 * take all secondary CPUs offline, try with the NMI.
-	 */
+	/* if the REBOOT_VECTOR didn't work, try with the NMI */
 	if (!cpumask_empty(&cpus_stop_mask)) {
 		/*
 		 * If NMI IPI is enabled, try to register the stop handler
@@ -249,7 +225,6 @@ static void native_stop_other_cpus(int wait)
 			udelay(1);
 	}
 
-done:
 	local_irq_save(flags);
 	disable_local_APIC();
 	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4e45ff44aa07..2a187c0cbd5b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -579,7 +579,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 }
 
 
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
 	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -603,7 +602,14 @@ static int x86_cluster_flags(void)
 	return cpu_cluster_flags() | x86_sched_itmt_flags();
 }
 #endif
-#endif
+
+static int x86_die_flags(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	       return x86_sched_itmt_flags();
+
+	return 0;
+}
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.
@@ -640,7 +646,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
 		};
 	}
 
@@ -1234,33 +1240,6 @@ void arch_thaw_secondary_cpus_end(void)
 	cache_aps_init();
 }
 
-bool smp_park_other_cpus_in_init(void)
-{
-	unsigned int cpu, this_cpu = smp_processor_id();
-	unsigned int apicid;
-
-	if (apic->wakeup_secondary_cpu_64 || apic->wakeup_secondary_cpu)
-		return false;
-
-	/*
-	 * If this is a crash stop which does not execute on the boot CPU,
-	 * then this cannot use the INIT mechanism because INIT to the boot
-	 * CPU will reset the machine.
-	 */
-	if (this_cpu)
-		return false;
-
-	for_each_cpu_and(cpu, &cpus_booted_once_mask, cpu_present_mask) {
-		if (cpu == this_cpu)
-			continue;
-		apicid = apic->cpu_present_to_apicid(cpu);
-		if (apicid == BAD_APICID)
-			continue;
-		send_init_sequence(apicid);
-	}
-	return true;
-}
-
 /*
  * Early setup to make printk work.
  */
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index ca004e2e4469..0bab03130033 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -54,7 +54,7 @@ void arch_unregister_cpu(int num)
 EXPORT_SYMBOL(arch_unregister_cpu);
 #else /* CONFIG_HOTPLUG_CPU */
 
-static int __init arch_register_cpu(int num)
+int __init arch_register_cpu(int num)
 {
 	return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
 }