Merge tag 'v6.6-rc4' into x86/entry, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

47 files changed, 463 insertions, 385 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c130bf3176fe..723fd7afef28 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1945,6 +1945,7 @@ config EFI
 	select UCS2_STRING
 	select EFI_RUNTIME_WRAPPERS
 	select ARCH_USE_MEMREMAP_PROT
+	select EFI_RUNTIME_MAP if KEXEC_CORE
 	help
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
@@ -2020,7 +2021,6 @@ config EFI_MAX_FAKE_MEM
 config EFI_RUNTIME_MAP
 	bool "Export EFI runtime maps to sysfs" if EXPERT
 	depends on EFI
-	default KEXEC_CORE
 	help
 	  Export EFI runtime memory regions to /sys/firmware/efi/runtime-map.
 	  That memory map is required by the 2nd kernel to set up EFI virtual
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index bcc956c17872..08f93b0401bb 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -59,6 +59,14 @@ static void *alloc_pgt_page(void *context)
 		return NULL;
 	}
 
+	/* Consumed more tables than expected? */
+	if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) {
+		debug_putstr("pgt_buf running low in " __FILE__ "\n");
+		debug_putstr("Need to raise BOOT_PGT_SIZE?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+	}
+
 	entry = pages->pgt_buf + pages->pgt_buf_offset;
 	pages->pgt_buf_offset += PAGE_SIZE;
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index a34e1a1adcf8..328990dd8632 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -305,7 +305,7 @@ static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 
 	set_irq_regs(old_regs);
 }
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index abadd5f23425..e24976593a29 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu)
 	/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
 	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
 
-	/* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */
-	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask);
+	/*
+	 * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
+	 * and PerfCntrGLobalStatus.PerfCntrOvfl
+	 */
+	wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+	       GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
 }
 
 static int amd_pmu_cpu_prepare(int cpu)
@@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu)
 	int i, nb_id;
 
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
+	amd_pmu_cpu_reset(cpu);
 
 	if (!x86_pmu.amd_nb_constraints)
 		return;
@@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu)
 
 	cpuc->amd_nb->nb_id = nb_id;
 	cpuc->amd_nb->refcnt++;
-
-	amd_pmu_cpu_reset(cpu);
 }
 
 static void amd_pmu_cpu_dead(int cpu)
@@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu)
 
 	kfree(cpuhw->lbr_sel);
 	cpuhw->lbr_sel = NULL;
+	amd_pmu_cpu_reset(cpu);
 
 	if (!x86_pmu.amd_nb_constraints)
 		return;
@@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
 		cpuhw->amd_nb = NULL;
 	}
-
-	amd_pmu_cpu_reset(cpu);
 }
 
 static inline void amd_pmu_set_global_ctl(u64 ctl)
@@ -884,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	struct hw_perf_event *hwc;
 	struct perf_event *event;
 	int handled = 0, idx;
-	u64 status, mask;
+	u64 reserved, status, mask;
 	bool pmu_enabled;
 
 	/*
@@ -909,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		status &= ~GLOBAL_STATUS_LBRS_FROZEN;
 	}
 
+	reserved = status & ~amd_pmu_global_cntr_mask;
+	if (reserved)
+		pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n",
+			     reserved);
+
+	/* Clear any reserved bits set by buggy microcode */
+	status &= amd_pmu_global_cntr_mask;
+
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 4ae14339cb8c..b3a7cfb0d99e 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -40,23 +40,40 @@
 #ifdef CONFIG_X86_64
 # define BOOT_STACK_SIZE	0x4000
 
+/*
+ * Used by decompressor's startup_32() to allocate page tables for identity
+ * mapping of the 4G of RAM in 4-level paging mode:
+ * - 1 level4 table;
+ * - 1 level3 table;
+ * - 4 level2 table that maps everything with 2M pages;
+ *
+ * The additional level5 table needed for 5-level paging is allocated from
+ * trampoline_32bit memory.
+ */
 # define BOOT_INIT_PGT_SIZE	(6*4096)
-# ifdef CONFIG_RANDOMIZE_BASE
+
 /*
- * Assuming all cross the 512GB boundary:
- * 1 page for level4
- * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
- * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
- * Total is 19 pages.
+ * Total number of page tables kernel_add_identity_map() can allocate,
+ * including page tables consumed by startup_32().
+ *
+ * Worst-case scenario:
+ *  - 5-level paging needs 1 level5 table;
+ *  - KASLR needs to map kernel, boot_params, cmdline and randomized kernel,
+ *    assuming all of them cross 256T boundary:
+ *    + 4*2 level4 table;
+ *    + 4*2 level3 table;
+ *    + 4*2 level2 table;
+ *  - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM):
+ *    + 1 level4 table;
+ *    + 1 level3 table;
+ *    + 1 level2 table;
+ * Total: 28 tables
+ *
+ * Add 4 spare table in case decompressor touches anything beyond what is
+ * accounted above. Warn if it happens.
  */
-#  ifdef CONFIG_X86_VERBOSE_BOOTUP
-#   define BOOT_PGT_SIZE	(19*4096)
-#  else /* !CONFIG_X86_VERBOSE_BOOTUP */
-#   define BOOT_PGT_SIZE	(17*4096)
-#  endif
-# else /* !CONFIG_RANDOMIZE_BASE */
-#  define BOOT_PGT_SIZE		BOOT_INIT_PGT_SIZE
-# endif
+# define BOOT_PGT_SIZE_WARN	(28*4096)
+# define BOOT_PGT_SIZE		(32*4096)
 
 #else /* !CONFIG_X86_64 */
 # define BOOT_STACK_SIZE	0x1000
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b0994ae3bc23..c4555b269a1b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -91,19 +91,6 @@ static inline void efi_fpu_end(void)
 
 #ifdef CONFIG_X86_32
 #define EFI_X86_KERNEL_ALLOC_LIMIT		(SZ_512M - 1)
-
-#define arch_efi_call_virt_setup()					\
-({									\
-	efi_fpu_begin();						\
-	firmware_restrict_branch_speculation_start();			\
-})
-
-#define arch_efi_call_virt_teardown()					\
-({									\
-	firmware_restrict_branch_speculation_end();			\
-	efi_fpu_end();							\
-})
-
 #else /* !CONFIG_X86_32 */
 #define EFI_X86_KERNEL_ALLOC_LIMIT		EFI_ALLOC_LIMIT
 
@@ -116,14 +103,6 @@ extern bool efi_disable_ibt_for_runtime;
 	__efi_call(__VA_ARGS__);					\
 })
 
-#define arch_efi_call_virt_setup()					\
-({									\
-	efi_sync_low_kernel_mappings();					\
-	efi_fpu_begin();						\
-	firmware_restrict_branch_speculation_start();			\
-	efi_enter_mm();							\
-})
-
 #undef arch_efi_call_virt
 #define arch_efi_call_virt(p, f, args...) ({				\
 	u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime);		\
@@ -132,13 +111,6 @@ extern bool efi_disable_ibt_for_runtime;
 	ret;								\
 })
 
-#define arch_efi_call_virt_teardown()					\
-({									\
-	efi_leave_mm();							\
-	firmware_restrict_branch_speculation_end();			\
-	efi_fpu_end();							\
-})
-
 #ifdef CONFIG_KASAN
 /*
  * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
@@ -168,8 +140,8 @@ extern void efi_delete_dummy_variable(void);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
 
-void efi_enter_mm(void);
-void efi_leave_mm(void);
+void arch_efi_call_virt_setup(void);
+void arch_efi_call_virt_teardown(void);
 
 /* kexec external ABI */
 struct efi_setup_data {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1a4def36d5bb..17715cb8731d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1419,7 +1419,6 @@ struct kvm_arch {
 	 * the thread holds the MMU lock in write mode.
 	 */
 	spinlock_t tdp_mmu_pages_lock;
-	struct workqueue_struct *tdp_mmu_zap_wq;
 #endif /* CONFIG_X86_64 */
 
 	/*
@@ -1835,7 +1834,7 @@ void kvm_mmu_vendor_module_exit(void);
 
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 
 void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 97a3de7892d3..571fe4d2d232 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,6 +8,14 @@
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
 
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
 #endif /* CONFIG_X86_32 */
@@ -97,6 +105,13 @@
 	CFI_POST_PADDING					\
 	SYM_FUNC_END(__cfi_##name)
 
+/* UML needs to be able to override memcpy() and friends for KASAN. */
+#ifdef CONFIG_UML
+# define SYM_FUNC_ALIAS_MEMFUNC	SYM_FUNC_ALIAS_WEAK
+#else
+# define SYM_FUNC_ALIAS_MEMFUNC	SYM_FUNC_ALIAS
+#endif
+
 /* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
 #define SYM_TYPED_FUNC_START(name)				\
 	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN)	\
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 416901d406f8..8dac45a2c7fc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -186,8 +186,7 @@ do {						\
 #else
 #define deactivate_mm(tsk, mm)			\
 do {						\
-	if (!tsk->vfork_done)			\
-		shstk_free(tsk);		\
+	shstk_free(tsk);			\
 	load_gs_index(0);			\
 	loadsegment(fs, 0);			\
 } while (0)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4acbcddddc29..772d03487520 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -9,13 +9,6 @@ struct paravirt_patch_site {
 	u8 type;		/* type of this instruction */
 	u8 len;			/* length of original instruction */
 };
-
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
-	PARAVIRT_LAZY_NONE,
-	PARAVIRT_LAZY_MMU,
-	PARAVIRT_LAZY_CPU,
-};
 #endif
 
 #ifdef CONFIG_PARAVIRT
@@ -549,14 +542,6 @@ int paravirt_disable_iospace(void);
 	__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2),	\
 		     PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
 
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_start_context_switch(struct task_struct *prev);
-void paravirt_end_context_switch(struct task_struct *next);
-
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-void paravirt_flush_lazy_mmu(void);
-
 void _paravirt_nop(void);
 void paravirt_BUG(void);
 unsigned long paravirt_ret0(void);
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index d6ad98ca1288..e02b179ec659 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -955,6 +955,14 @@ static inline int pte_same(pte_t a, pte_t b)
 	return a.pte == b.pte;
 }
 
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+	if (__pte_needs_invert(pte_val(pte)))
+		return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
+	return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#define pte_next_pfn	pte_next_pfn
+
 static inline int pte_present(pte_t a)
 {
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 93cd28d6f317..6e30b27b1ebe 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -683,13 +683,11 @@ extern u16 get_llc_id(unsigned int cpu);
 #ifdef CONFIG_CPU_SUP_AMD
 extern u32 amd_get_nodes_per_socket(void);
 extern u32 amd_get_highest_perf(void);
-extern bool cpu_has_ibpb_brtype_microcode(void);
 extern void amd_clear_divider(void);
 extern void amd_check_microcode(void);
 #else
 static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
 static inline u32 amd_get_highest_perf(void)		{ return 0; }
-static inline bool cpu_has_ibpb_brtype_microcode(void)	{ return false; }
 static inline void amd_clear_divider(void)		{ }
 static inline void amd_check_microcode(void)		{ }
 #endif
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 5fc35f889cd1..7048dfacc04b 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -36,6 +36,7 @@
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
+#include <asm/bug.h>
 #include <asm/processor.h>
 
 #define XEN_SIGNATURE "XenVMMXenVMM"
@@ -63,4 +64,40 @@ void __init xen_pvh_init(struct boot_params *boot_params);
 void __init mem_map_via_hcall(struct boot_params *boot_params_p);
 #endif
 
+/* Lazy mode for batching updates / context switch */
+enum xen_lazy_mode {
+	XEN_LAZY_NONE,
+	XEN_LAZY_MMU,
+	XEN_LAZY_CPU,
+};
+
+DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode);
+DECLARE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+static inline void enter_lazy(enum xen_lazy_mode mode)
+{
+	enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode);
+
+	if (mode == old_mode) {
+		this_cpu_inc(xen_lazy_nesting);
+		return;
+	}
+
+	BUG_ON(old_mode != XEN_LAZY_NONE);
+
+	this_cpu_write(xen_lazy_mode, mode);
+}
+
+static inline void leave_lazy(enum xen_lazy_mode mode)
+{
+	BUG_ON(this_cpu_read(xen_lazy_mode) != mode);
+
+	if (this_cpu_read(xen_lazy_nesting) == 0)
+		this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
+	else
+		this_cpu_dec(xen_lazy_nesting);
+}
+
+enum xen_lazy_mode xen_get_lazy_mode(void);
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a5ead6a6d233..517ee01503be 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -720,13 +720,8 @@ 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..03ef962a6992 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -766,6 +766,15 @@ 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)
@@ -1301,25 +1310,6 @@ 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 afa755e06ae9..0a3ea787ac51 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1304,7 +1304,7 @@ 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/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/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/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/smpboot.c b/arch/x86/kernel/smpboot.c
index 4e45ff44aa07..48e040618731 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)
 		};
 	}
 
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e1d011c67cc6..f7901cb4d2fa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6167,20 +6167,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
 }
 
-int kvm_mmu_init_vm(struct kvm *kvm)
+void kvm_mmu_init_vm(struct kvm *kvm)
 {
-	int r;
-
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
-	if (tdp_mmu_enabled) {
-		r = kvm_mmu_init_tdp_mmu(kvm);
-		if (r < 0)
-			return r;
-	}
+	if (tdp_mmu_enabled)
+		kvm_mmu_init_tdp_mmu(kvm);
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
@@ -6189,8 +6184,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 
 	kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
 	kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
-
-	return 0;
 }
 
 static void mmu_free_vm_memory_caches(struct kvm *kvm)
@@ -6246,7 +6239,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
 void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 {
 	bool flush;
-	int i;
 
 	if (WARN_ON_ONCE(gfn_end <= gfn_start))
 		return;
@@ -6257,11 +6249,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
-	if (tdp_mmu_enabled) {
-		for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-			flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
-						      gfn_end, true, flush);
-	}
+	if (tdp_mmu_enabled)
+		flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush);
 
 	if (flush)
 		kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index b102014e2c60..decc1f153669 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -58,7 +58,12 @@ struct kvm_mmu_page {
 
 	bool tdp_mmu_page;
 	bool unsync;
-	u8 mmu_valid_gen;
+	union {
+		u8 mmu_valid_gen;
+
+		/* Only accessed under slots_lock.  */
+		bool tdp_mmu_scheduled_root_to_zap;
+	};
 
 	 /*
 	  * The shadow page can't be replaced by an equivalent huge page
@@ -100,13 +105,7 @@ struct kvm_mmu_page {
 		struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 		tdp_ptep_t ptep;
 	};
-	union {
-		DECLARE_BITMAP(unsync_child_bitmap, 512);
-		struct {
-			struct work_struct tdp_mmu_async_work;
-			void *tdp_mmu_async_data;
-		};
-	};
+	DECLARE_BITMAP(unsync_child_bitmap, 512);
 
 	/*
 	 * Tracks shadow pages that, if zapped, would allow KVM to create an NX
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6c63f2d1675f..6cd4dd631a2f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -12,18 +12,10 @@
 #include <trace/events/kvm.h>
 
 /* Initializes the TDP MMU for the VM, if enabled. */
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
 {
-	struct workqueue_struct *wq;
-
-	wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
-	if (!wq)
-		return -ENOMEM;
-
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
 	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
-	kvm->arch.tdp_mmu_zap_wq = wq;
-	return 1;
 }
 
 /* Arbitrarily returns true so that this may be used in if statements. */
@@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	 * ultimately frees all roots.
 	 */
 	kvm_tdp_mmu_invalidate_all_roots(kvm);
-
-	/*
-	 * Destroying a workqueue also first flushes the workqueue, i.e. no
-	 * need to invoke kvm_tdp_mmu_zap_invalidated_roots().
-	 */
-	destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	kvm_tdp_mmu_zap_invalidated_roots(kvm);
 
 	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 
 	/*
 	 * Ensure that all the outstanding RCU callbacks to free shadow pages
-	 * can run before the VM is torn down.  Work items on tdp_mmu_zap_wq
-	 * can call kvm_tdp_mmu_put_root and create new callbacks.
+	 * can run before the VM is torn down.  Putting the last reference to
+	 * zapped roots will create new callbacks.
 	 */
 	rcu_barrier();
 }
@@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
 	tdp_mmu_free_sp(sp);
 }
 
-static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			     bool shared);
-
-static void tdp_mmu_zap_root_work(struct work_struct *work)
-{
-	struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page,
-						 tdp_mmu_async_work);
-	struct kvm *kvm = root->tdp_mmu_async_data;
-
-	read_lock(&kvm->mmu_lock);
-
-	/*
-	 * A TLB flush is not necessary as KVM performs a local TLB flush when
-	 * allocating a new root (see kvm_mmu_load()), and when migrating vCPU
-	 * to a different pCPU.  Note, the local TLB flush on reuse also
-	 * invalidates any paging-structure-cache entries, i.e. TLB entries for
-	 * intermediate paging structures, that may be zapped, as such entries
-	 * are associated with the ASID on both VMX and SVM.
-	 */
-	tdp_mmu_zap_root(kvm, root, true);
-
-	/*
-	 * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for
-	 * avoiding an infinite loop.  By design, the root is reachable while
-	 * it's being asynchronously zapped, thus a different task can put its
-	 * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an
-	 * asynchronously zapped root is unavoidable.
-	 */
-	kvm_tdp_mmu_put_root(kvm, root, true);
-
-	read_unlock(&kvm->mmu_lock);
-}
-
-static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root)
-{
-	root->tdp_mmu_async_data = kvm;
-	INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work);
-	queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work);
-}
-
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared)
 {
@@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
 	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
 
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id)			\
-	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false)
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared)			\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false);		\
+	     _root;								\
+	     _root = tdp_mmu_next_root(_kvm, _root, _shared, false))		\
+		if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) {		\
+		} else
 
 /*
  * Iterate over all TDP MMU roots.  Requires that mmu_lock be held for write,
@@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 	 * by a memslot update or by the destruction of the VM.  Initialize the
 	 * refcount to two; one reference for the vCPU, and one reference for
 	 * the TDP MMU itself, which is held until the root is invalidated and
-	 * is ultimately put by tdp_mmu_zap_root_work().
+	 * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots().
 	 */
 	refcount_set(&root->tdp_mmu_root_count, 2);
 
@@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
  * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or
  * more SPTEs were zapped since the MMU lock was last acquired.
  */
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
-			   bool can_yield, bool flush)
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
-		flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush);
+	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+		flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
 
 	return flush;
 }
@@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
 void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 {
 	struct kvm_mmu_page *root;
-	int i;
 
 	/*
 	 * Zap all roots, including invalid roots, as all SPTEs must be dropped
@@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 	 * is being destroyed or the userspace VMM has exited.  In both cases,
 	 * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
 	 */
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		for_each_tdp_mmu_root_yield_safe(kvm, root, i)
-			tdp_mmu_zap_root(kvm, root, false);
-	}
+	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+		tdp_mmu_zap_root(kvm, root, false);
 }
 
 /*
@@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
  */
 void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 {
-	flush_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	struct kvm_mmu_page *root;
+
+	read_lock(&kvm->mmu_lock);
+
+	for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+		if (!root->tdp_mmu_scheduled_root_to_zap)
+			continue;
+
+		root->tdp_mmu_scheduled_root_to_zap = false;
+		KVM_BUG_ON(!root->role.invalid, kvm);
+
+		/*
+		 * A TLB flush is not necessary as KVM performs a local TLB
+		 * flush when allocating a new root (see kvm_mmu_load()), and
+		 * when migrating a vCPU to a different pCPU.  Note, the local
+		 * TLB flush on reuse also invalidates paging-structure-cache
+		 * entries, i.e. TLB entries for intermediate paging structures,
+		 * that may be zapped, as such entries are associated with the
+		 * ASID on both VMX and SVM.
+		 */
+		tdp_mmu_zap_root(kvm, root, true);
+
+		/*
+		 * The referenced needs to be put *after* zapping the root, as
+		 * the root must be reachable by mmu_notifiers while it's being
+		 * zapped
+		 */
+		kvm_tdp_mmu_put_root(kvm, root, true);
+	}
+
+	read_unlock(&kvm->mmu_lock);
 }
 
 /*
  * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that
  * is about to be zapped, e.g. in response to a memslots update.  The actual
- * zapping is performed asynchronously.  Using a separate workqueue makes it
- * easy to ensure that the destruction is performed before the "fast zap"
- * completes, without keeping a separate list of invalidated roots; the list is
- * effectively the list of work items in the workqueue.
+ * zapping is done separately so that it happens with mmu_lock with read,
+ * whereas invalidating roots must be done with mmu_lock held for write (unless
+ * the VM is being destroyed).
  *
- * Note, the asynchronous worker is gifted the TDP MMU's reference.
+ * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference.
  * See kvm_tdp_mmu_get_vcpu_root_hpa().
  */
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
@@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
 	/*
 	 * As above, mmu_lock isn't held when destroying the VM!  There can't
 	 * be other references to @kvm, i.e. nothing else can invalidate roots
-	 * or be consuming roots, but walking the list of roots does need to be
-	 * guarded against roots being deleted by the asynchronous zap worker.
+	 * or get/put references to roots.
 	 */
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) {
+	list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
+		/*
+		 * Note, invalid roots can outlive a memslot update!  Invalid
+		 * roots must be *zapped* before the memslot update completes,
+		 * but a different task can acquire a reference and keep the
+		 * root alive after its been zapped.
+		 */
 		if (!root->role.invalid) {
+			root->tdp_mmu_scheduled_root_to_zap = true;
 			root->role.invalid = true;
-			tdp_mmu_schedule_zap_root(kvm, root);
 		}
 	}
-
-	rcu_read_unlock();
 }
 
 /*
@@ -1146,8 +1123,13 @@ retry:
 bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush)
 {
-	return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
-				     range->end, range->may_block, flush);
+	struct kvm_mmu_page *root;
+
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+		flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
+					  range->may_block, flush);
+
+	return flush;
 }
 
 typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 0a63b1afabd3..733a3aef3a96 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -7,7 +7,7 @@
 
 #include "spte.h"
 
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
 void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
 
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
@@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared);
 
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
-				 gfn_t end, bool can_yield, bool flush);
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
 bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b9a0a939d59f..4900c078045a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 				    count, in);
 }
 
+static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
+				 guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+
+		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
+	}
+}
+
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_cpuid_entry2 *best;
+
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
+	if (best)
+		vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
+
+	if (sev_es_guest(svm->vcpu.kvm))
+		sev_es_vcpu_after_set_cpuid(svm);
+}
+
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) &&
-	    (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) ||
-	     guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) {
-		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1);
-		if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP))
-			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
-	}
 }
 
 void sev_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f283eb47f6ac..9507df93f410 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -683,6 +683,21 @@ static int svm_hardware_enable(void)
 
 	amd_pmu_enable_virt();
 
+	/*
+	 * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type
+	 * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests.
+	 * Since Linux does not change the value of TSC_AUX once set, prime the
+	 * TSC_AUX field now to avoid a RDMSR on every vCPU run.
+	 */
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		struct sev_es_save_area *hostsa;
+		u32 msr_hi;
+
+		hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
+
+		rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi);
+	}
+
 	return 0;
 }
 
@@ -1532,7 +1547,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	if (tsc_scaling)
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
-	if (likely(tsc_aux_uret_slot >= 0))
+	/*
+	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
+	 * available. The user return MSR support is not required in this case
+	 * because TSC_AUX is restored on #VMEXIT from the host save area
+	 * (which has been initialized in svm_hardware_enable()).
+	 */
+	if (likely(tsc_aux_uret_slot >= 0) &&
+	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
 
 	svm->guest_state_loaded = true;
@@ -3087,6 +3109,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_TSC_AUX:
 		/*
+		 * TSC_AUX is always virtualized for SEV-ES guests when the
+		 * feature is available. The user return MSR support is not
+		 * required in this case because TSC_AUX is restored on #VMEXIT
+		 * from the host save area (which has been initialized in
+		 * svm_hardware_enable()).
+		 */
+		if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
+			break;
+
+		/*
 		 * TSC_AUX is usually changed only during boot and never read
 		 * directly.  Intercept TSC_AUX instead of exposing it to the
 		 * guest via direct_access_msrs, and switch it via user return.
@@ -4284,7 +4316,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
 static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct kvm_cpuid_entry2 *best;
 
 	/*
 	 * SVM doesn't provide a way to disable just XSAVES in the guest, KVM
@@ -4328,12 +4359,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
 				     !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
-	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
-	if (sev_guest(vcpu->kvm)) {
-		best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
-		if (best)
-			vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
-	}
+	if (sev_guest(vcpu->kvm))
+		sev_vcpu_after_set_cpuid(svm);
 
 	init_vmcb_after_set_cpuid(vcpu);
 }
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f41253958357..be67ab7fdd10 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -684,6 +684,7 @@ void __init sev_hardware_setup(void);
 void sev_hardware_unsetup(void);
 int sev_cpu_init(struct svm_cpu_data *sd);
 void sev_init_vmcb(struct vcpu_svm *svm);
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
 void sev_free_vcpu(struct kvm_vcpu *vcpu);
 int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c9c81e82e65..9f18b06bbda6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12308,9 +12308,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out;
 
-	ret = kvm_mmu_init_vm(kvm);
-	if (ret)
-		goto out_page_track;
+	kvm_mmu_init_vm(kvm);
 
 	ret = static_call(kvm_x86_vm_init)(kvm);
 	if (ret)
@@ -12355,7 +12353,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 out_uninit_mmu:
 	kvm_mmu_uninit_vm(kvm);
-out_page_track:
 	kvm_page_track_cleanup(kvm);
 out:
 	return ret;
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 8f95fb267caa..76697df8dfd5 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -40,7 +40,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0559b206fb11..ccdf3a597045 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -212,5 +212,5 @@ SYM_FUNC_START(__memmove)
 SYM_FUNC_END(__memmove)
 EXPORT_SYMBOL(__memmove)
 
-SYM_FUNC_ALIAS(memmove, __memmove)
+SYM_FUNC_ALIAS_MEMFUNC(memmove, __memmove)
 EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 7c59a704c458..3d818b849ec6 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 1451e0c4ae22..235bbda6fc82 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -56,7 +56,6 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
-	ENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -76,7 +75,6 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
-	ENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -96,7 +94,6 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
-	ENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -119,7 +116,6 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
-	ENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index e06a199423c0..b2cc7b4552a1 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -140,3 +140,15 @@ void __init efi_runtime_update_mappings(void)
 		}
 	}
 }
+
+void arch_efi_call_virt_setup(void)
+{
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 77f7ac3668cb..91d31ac422d6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -474,19 +474,34 @@ void __init efi_dump_pagetable(void)
  * can not change under us.
  * It should be ensured that there are no concurrent calls to this function.
  */
-void efi_enter_mm(void)
+static void efi_enter_mm(void)
 {
 	efi_prev_mm = current->active_mm;
 	current->active_mm = &efi_mm;
 	switch_mm(efi_prev_mm, &efi_mm, NULL);
 }
 
-void efi_leave_mm(void)
+static void efi_leave_mm(void)
 {
 	current->active_mm = efi_prev_mm;
 	switch_mm(&efi_mm, efi_prev_mm, NULL);
 }
 
+void arch_efi_call_virt_setup(void)
+{
+	efi_sync_low_kernel_mappings();
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+	efi_enter_mm();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	efi_leave_mm();
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}
+
 static DEFINE_SPINLOCK(efi_runtime_lock);
 
 /*
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index c2a29be35c01..08aa0f25f12a 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -19,6 +19,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
 # optimization flags.
 KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
 
+# When LTO is enabled, llvm emits many text sections, which is not supported
+# by kexec. Remove -flto=* flags.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+
 # When linking purgatory.ro with -r unresolved symbols are not checked,
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
 PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 863d0d6b3edc..7250d0e0e1a9 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -138,7 +138,7 @@ void __init xen_efi_init(struct boot_params *boot_params)
 	if (efi_systab_xen == NULL)
 		return;
 
-	strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
+	strscpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
 			sizeof(boot_params->efi_info.efi_loader_signature));
 	boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
 	boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b8db2148c07d..0337392a3121 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -32,7 +32,7 @@ EXPORT_SYMBOL_GPL(hypercall_page);
  * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
  * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
  * but during boot it is switched to point to xen_vcpu_info.
- * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events.
+ * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events.
  */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 9a192f51f1b0..3f8c34707c50 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -136,7 +136,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback)
 
 	inc_irq_stat(irq_hv_callback_count);
 
-	xen_hvm_evtchn_do_upcall();
+	xen_evtchn_do_upcall();
 
 	set_irq_regs(old_regs);
 }
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 49352fad7d1d..bbbfdd495ebd 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -101,6 +101,17 @@ struct tls_descs {
 	struct desc_struct desc[3];
 };
 
+DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE;
+DEFINE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+enum xen_lazy_mode xen_get_lazy_mode(void)
+{
+	if (in_interrupt())
+		return XEN_LAZY_NONE;
+
+	return this_cpu_read(xen_lazy_mode);
+}
+
 /*
  * Updating the 3 TLS descriptors in the GDT on every task switch is
  * surprisingly expensive so we avoid updating them if they haven't
@@ -362,10 +373,25 @@ static noinstr unsigned long xen_get_debugreg(int reg)
 	return HYPERVISOR_get_debugreg(reg);
 }
 
+static void xen_start_context_switch(struct task_struct *prev)
+{
+	BUG_ON(preemptible());
+
+	if (this_cpu_read(xen_lazy_mode) == XEN_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+	}
+	enter_lazy(XEN_LAZY_CPU);
+}
+
 static void xen_end_context_switch(struct task_struct *next)
 {
+	BUG_ON(preemptible());
+
 	xen_mc_flush();
-	paravirt_end_context_switch(next);
+	leave_lazy(XEN_LAZY_CPU);
+	if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+		arch_enter_lazy_mmu_mode();
 }
 
 static unsigned long xen_store_tr(void)
@@ -472,7 +498,7 @@ static void xen_set_ldt(const void *addr, unsigned entries)
 
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_load_gdt(const struct desc_ptr *dtr)
@@ -568,7 +594,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	 * exception between the new %fs descriptor being loaded and
 	 * %fs being effectively cleared at __switch_to().
 	 */
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+	if (xen_get_lazy_mode() == XEN_LAZY_CPU)
 		loadsegment(fs, 0);
 
 	xen_mc_batch();
@@ -577,7 +603,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
 	load_TLS_descriptor(t, cpu, 1);
 	load_TLS_descriptor(t, cpu, 2);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_load_gs_index(unsigned int idx)
@@ -909,7 +935,7 @@ static void xen_load_sp0(unsigned long sp0)
 
 	mcs = xen_mc_entry(0);
 	MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
@@ -973,7 +999,7 @@ static void xen_write_cr0(unsigned long cr0)
 
 	MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 }
 
 static void xen_write_cr4(unsigned long cr4)
@@ -1156,7 +1182,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = {
 #endif
 		.io_delay = xen_io_delay,
 
-		.start_context_switch = paravirt_start_context_switch,
+		.start_context_switch = xen_start_context_switch,
 		.end_context_switch = xen_end_context_switch,
 	},
 };
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1652c39e3dfb..b6830554ff69 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -236,7 +236,7 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
 	u.val = pmd_val_ma(val);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -270,7 +270,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 {
 	struct mmu_update u;
 
-	if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
+	if (xen_get_lazy_mode() != XEN_LAZY_MMU)
 		return false;
 
 	xen_mc_batch();
@@ -279,7 +279,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
 	u.val = pte_val_ma(pteval);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	return true;
 }
@@ -325,7 +325,7 @@ void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
 	u.val = pte_val_ma(pte);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 /* Assume pteval_t is equivalent to all the other *val_t types. */
@@ -419,7 +419,7 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
 	u.val = pud_val_ma(val);
 	xen_extend_mmu_update(&u);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -499,7 +499,7 @@ static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
 
 	__xen_set_p4d_hyper(ptr, val);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -531,7 +531,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
 	if (user_ptr)
 		__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 #if CONFIG_PGTABLE_LEVELS >= 5
@@ -1245,7 +1245,7 @@ static noinline void xen_flush_tlb(void)
 	op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -1265,7 +1265,7 @@ static void xen_flush_tlb_one_user(unsigned long addr)
 	op->arg1.linear_addr = addr & PAGE_MASK;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
@@ -1302,7 +1302,7 @@ static void xen_flush_tlb_multi(const struct cpumask *cpus,
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 }
 
 static unsigned long xen_read_cr3(void)
@@ -1361,7 +1361,7 @@ static void xen_write_cr3(unsigned long cr3)
 	else
 		__xen_write_cr3(false, 0);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+	xen_mc_issue(XEN_LAZY_CPU);  /* interrupts restored */
 }
 
 /*
@@ -1396,7 +1396,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
 
 	__xen_write_cr3(true, cr3);
 
-	xen_mc_issue(PARAVIRT_LAZY_CPU);  /* interrupts restored */
+	xen_mc_issue(XEN_LAZY_CPU);  /* interrupts restored */
 }
 
 static int xen_pgd_alloc(struct mm_struct *mm)
@@ -1557,7 +1557,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
 		if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
 			__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 
-		xen_mc_issue(PARAVIRT_LAZY_MMU);
+		xen_mc_issue(XEN_LAZY_MMU);
 	}
 }
 
@@ -1587,7 +1587,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
 
 		__set_pfn_prot(pfn, PAGE_KERNEL);
 
-		xen_mc_issue(PARAVIRT_LAZY_MMU);
+		xen_mc_issue(XEN_LAZY_MMU);
 
 		ClearPagePinned(page);
 	}
@@ -1804,7 +1804,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
 	 */
 	xen_mc_batch();
 	__xen_write_cr3(true, __pa(init_top_pgt));
-	xen_mc_issue(PARAVIRT_LAZY_CPU);
+	xen_mc_issue(XEN_LAZY_CPU);
 
 	/* We can't that easily rip out L3 and L2, as the Xen pagetables are
 	 * set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ...  for
@@ -2083,6 +2083,23 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #endif
 }
 
+static void xen_enter_lazy_mmu(void)
+{
+	enter_lazy(XEN_LAZY_MMU);
+}
+
+static void xen_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (xen_get_lazy_mode() == XEN_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 static void __init xen_post_allocator_init(void)
 {
 	pv_ops.mmu.set_pte = xen_set_pte;
@@ -2107,7 +2124,7 @@ static void xen_leave_lazy_mmu(void)
 {
 	preempt_disable();
 	xen_mc_flush();
-	paravirt_leave_lazy_mmu();
+	leave_lazy(XEN_LAZY_MMU);
 	preempt_enable();
 }
 
@@ -2166,9 +2183,9 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.exit_mmap = xen_exit_mmap,
 
 		.lazy_mode = {
-			.enter = paravirt_enter_lazy_mmu,
+			.enter = xen_enter_lazy_mmu,
 			.leave = xen_leave_lazy_mmu,
-			.flush = paravirt_flush_lazy_mmu,
+			.flush = xen_flush_lazy_mmu,
 		},
 
 		.set_fixmap = xen_set_fixmap,
@@ -2385,7 +2402,7 @@ static noinline void xen_flush_tlb_all(void)
 	op->cmd = MMUEXT_TLB_FLUSH_ALL;
 	MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
 
-	xen_mc_issue(PARAVIRT_LAZY_MMU);
+	xen_mc_issue(XEN_LAZY_MMU);
 
 	preempt_enable();
 }
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 1c51b2c87f30..c3867b585e0d 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -26,7 +26,7 @@ static inline void xen_mc_batch(void)
 
 	/* need to disable interrupts until this entry is complete */
 	local_irq_save(flags);
-	trace_xen_mc_batch(paravirt_get_lazy_mode());
+	trace_xen_mc_batch(xen_get_lazy_mode());
 	__this_cpu_write(xen_mc_irq_flags, flags);
 }
 
@@ -44,7 +44,7 @@ static inline void xen_mc_issue(unsigned mode)
 {
 	trace_xen_mc_issue(mode);
 
-	if ((paravirt_get_lazy_mode() & mode) == 0)
+	if ((xen_get_lazy_mode() & mode) == 0)
 		xen_mc_flush();
 
 	/* restore flags saved in xen_mc_batch */