Merge tag 'v5.2' into perf/core, to pick up fixes

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

17 files changed, 140 insertions, 100 deletions

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f0e4804515d8..ffc015bd257e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -561,14 +561,14 @@ int x86_pmu_hw_config(struct perf_event *event)
 	}
 
 	/* sample_regs_user never support XMM registers */
-	if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+	if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK))
 		return -EINVAL;
 	/*
 	 * Besides the general purpose registers, XMM registers may
 	 * be collected in PEBS on some platforms, e.g. Icelake
 	 */
-	if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
-		if (x86_pmu.pebs_no_xmm_regs)
+	if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) {
+		if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS))
 			return -EINVAL;
 
 		if (!event->attr.precise_ip)
@@ -2328,13 +2328,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_hw_regs(regs)) {
-		if (perf_callchain_store(entry, regs->ip))
-			return;
+	if (perf_callchain_store(entry, regs->ip))
+		return;
+
+	if (perf_hw_regs(regs))
 		unwind_start(&state, current, regs, NULL);
-	} else {
+	else
 		unwind_start(&state, current, NULL, (void *)regs->sp);
-	}
 
 	for (; !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7acc526b4ad2..505c73dc6a73 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -987,7 +987,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event)
 		pebs_data_cfg |= PEBS_DATACFG_GP;
 
 	if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
-	    (attr->sample_regs_intr & PEBS_XMM_REGS))
+	    (attr->sample_regs_intr & PERF_REG_EXTENDED_MASK))
 		pebs_data_cfg |= PEBS_DATACFG_XMMS;
 
 	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
@@ -1964,10 +1964,9 @@ void __init intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
-	if (x86_pmu.version <= 4) {
+	if (x86_pmu.version <= 4)
 		x86_pmu.pebs_no_isolation = 1;
-		x86_pmu.pebs_no_xmm_regs = 1;
-	}
+
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		char *pebs_qual = "";
@@ -2020,9 +2019,9 @@ void __init intel_ds_init(void)
 					PERF_SAMPLE_TIME;
 				x86_pmu.flags |= PMU_FL_PEBS_ALL;
 				pebs_qual = "-baseline";
+				x86_get_pmu()->capabilities |= PERF_PMU_CAP_EXTENDED_REGS;
 			} else {
 				/* Only basic record supported */
-				x86_pmu.pebs_no_xmm_regs = 1;
 				x86_pmu.large_pebs_flags &=
 					~(PERF_SAMPLE_ADDR |
 					  PERF_SAMPLE_TIME |
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9bcec3f99e4a..8751008fc170 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -121,24 +121,6 @@ struct amd_nb {
 	 (1ULL << PERF_REG_X86_R14)   | \
 	 (1ULL << PERF_REG_X86_R15))
 
-#define PEBS_XMM_REGS                   \
-	((1ULL << PERF_REG_X86_XMM0)  | \
-	 (1ULL << PERF_REG_X86_XMM1)  | \
-	 (1ULL << PERF_REG_X86_XMM2)  | \
-	 (1ULL << PERF_REG_X86_XMM3)  | \
-	 (1ULL << PERF_REG_X86_XMM4)  | \
-	 (1ULL << PERF_REG_X86_XMM5)  | \
-	 (1ULL << PERF_REG_X86_XMM6)  | \
-	 (1ULL << PERF_REG_X86_XMM7)  | \
-	 (1ULL << PERF_REG_X86_XMM8)  | \
-	 (1ULL << PERF_REG_X86_XMM9)  | \
-	 (1ULL << PERF_REG_X86_XMM10) | \
-	 (1ULL << PERF_REG_X86_XMM11) | \
-	 (1ULL << PERF_REG_X86_XMM12) | \
-	 (1ULL << PERF_REG_X86_XMM13) | \
-	 (1ULL << PERF_REG_X86_XMM14) | \
-	 (1ULL << PERF_REG_X86_XMM15))
-
 /*
  * Per register state.
  */
@@ -665,8 +647,7 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1,
-			pebs_no_xmm_regs	:1;
+			pebs_no_isolation	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
 	int		max_pebs_events;
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index ac67bbea10ca..7c9d2bb3833b 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -52,4 +52,7 @@ enum perf_event_x86_regs {
 	/* These include both GPRs and XMMX registers */
 	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
+
+#define PERF_REG_EXTENDED_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
+
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 177aa8ef2afa..85be316665b4 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1464,7 +1464,8 @@ static void apic_pending_intr_clear(void)
 		if (queued) {
 			if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) {
 				ntsc = rdtsc();
-				max_loops = (cpu_khz << 10) - (ntsc - tsc);
+				max_loops = (long long)cpu_khz << 10;
+				max_loops -= ntsc - tsc;
 			} else {
 				max_loops--;
 			}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 03b4cc0ec3a7..66ca906aa790 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -836,6 +836,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 	}
 
 	/*
+	 * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper
+	 * bit in the mask to allow guests to use the mitigation even in the
+	 * case where the host does not enable it.
+	 */
+	if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+	    static_cpu_has(X86_FEATURE_AMD_SSBD)) {
+		x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
+	}
+
+	/*
 	 * We have three CPU feature flags that are in play here:
 	 *  - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
 	 *  - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
@@ -852,7 +862,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 			x86_amd_ssb_disable();
 		} else {
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
-			x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
 			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
 		}
 	}
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index a813987b5552..cb0fdcaf1415 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -789,13 +789,16 @@ static struct syscore_ops mc_syscore_ops = {
 	.resume			= mc_bp_resume,
 };
 
-static int mc_cpu_online(unsigned int cpu)
+static int mc_cpu_starting(unsigned int cpu)
 {
-	struct device *dev;
-
-	dev = get_cpu_device(cpu);
 	microcode_update_cpu(cpu);
 	pr_debug("CPU%d added\n", cpu);
+	return 0;
+}
+
+static int mc_cpu_online(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
 
 	if (sysfs_create_group(&dev->kobj, &mc_attr_group))
 		pr_err("Failed to create group for CPU%d\n", cpu);
@@ -872,7 +875,9 @@ int __init microcode_init(void)
 		goto out_ucode_group;
 
 	register_syscore_ops(&mc_syscore_ops);
-	cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:online",
+	cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting",
+				  mc_cpu_starting, NULL);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
 				  mc_cpu_online, mc_cpu_down_prep);
 
 	pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION);
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 2131b8bbaad7..2f4824793798 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -796,8 +796,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
-	u32 sw_shareable = 0, hw_shareable = 0;
-	u32 exclusive = 0, pseudo_locked = 0;
+	/*
+	 * Use unsigned long even though only 32 bits are used to ensure
+	 * test_bit() is used safely.
+	 */
+	unsigned long sw_shareable = 0, hw_shareable = 0;
+	unsigned long exclusive = 0, pseudo_locked = 0;
 	struct rdt_domain *dom;
 	int i, hwb, swb, excl, psl;
 	enum rdtgrp_mode mode;
@@ -842,10 +846,10 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 		}
 		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
 			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
-			hwb = test_bit(i, (unsigned long *)&hw_shareable);
-			swb = test_bit(i, (unsigned long *)&sw_shareable);
-			excl = test_bit(i, (unsigned long *)&exclusive);
-			psl = test_bit(i, (unsigned long *)&pseudo_locked);
+			hwb = test_bit(i, &hw_shareable);
+			swb = test_bit(i, &sw_shareable);
+			excl = test_bit(i, &exclusive);
+			psl = test_bit(i, &pseudo_locked);
 			if (hwb && swb)
 				seq_putc(seq, 'X');
 			else if (hwb && !swb)
@@ -2486,26 +2490,19 @@ out_destroy:
  */
 static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
 {
-	/*
-	 * Convert the u32 _val to an unsigned long required by all the bit
-	 * operations within this function. No more than 32 bits of this
-	 * converted value can be accessed because all bit operations are
-	 * additionally provided with cbm_len that is initialized during
-	 * hardware enumeration using five bits from the EAX register and
-	 * thus never can exceed 32 bits.
-	 */
-	unsigned long *val = (unsigned long *)_val;
+	unsigned long val = *_val;
 	unsigned int cbm_len = r->cache.cbm_len;
 	unsigned long first_bit, zero_bit;
 
-	if (*val == 0)
+	if (val == 0)
 		return;
 
-	first_bit = find_first_bit(val, cbm_len);
-	zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+	first_bit = find_first_bit(&val, cbm_len);
+	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
 	/* Clear any remaining bits to ensure contiguous region */
-	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+	bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
+	*_val = (u32)val;
 }
 
 /*
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 0927bb158ffc..76228525acd0 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -22,6 +22,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/module.h>
+#include <linux/memory.h>
 
 #include <trace/syscall.h>
 
@@ -34,16 +35,25 @@
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 int ftrace_arch_code_modify_prepare(void)
+    __acquires(&text_mutex)
 {
+	/*
+	 * Need to grab text_mutex to prevent a race from module loading
+	 * and live kernel patching from changing the text permissions while
+	 * ftrace has it set to "read/write".
+	 */
+	mutex_lock(&text_mutex);
 	set_kernel_text_rw();
 	set_all_modules_text_rw();
 	return 0;
 }
 
 int ftrace_arch_code_modify_post_process(void)
+    __releases(&text_mutex)
 {
 	set_all_modules_text_ro();
 	set_kernel_text_ro();
+	mutex_unlock(&text_mutex);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 16b1cbd3a61e..29ffa495bd1c 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -184,24 +184,25 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
 
 	if (la57) {
-		p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr);
+		p4d = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++],
+				    physaddr);
 
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
 		pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
 		pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
 
-		i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D;
-		p4d[i + 0] = (pgdval_t)pud + pgtable_flags;
-		p4d[i + 1] = (pgdval_t)pud + pgtable_flags;
+		i = physaddr >> P4D_SHIFT;
+		p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+		p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
 	} else {
 		i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
 		pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
 		pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
 	}
 
-	i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD;
-	pud[i + 0] = (pudval_t)pmd + pgtable_flags;
-	pud[i + 1] = (pudval_t)pmd + pgtable_flags;
+	i = physaddr >> PUD_SHIFT;
+	pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+	pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
 
 	pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
 	/* Filter out unsupported __PAGE_KERNEL_* bits: */
@@ -211,8 +212,9 @@ unsigned long __head __startup_64(unsigned long physaddr,
 	pmd_entry +=  physaddr;
 
 	for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) {
-		int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD;
-		pmd[idx] = pmd_entry + i * PMD_SIZE;
+		int idx = i + (physaddr >> PMD_SHIFT);
+
+		pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
 	}
 
 	/*
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index 07c30ee17425..bb7e1132290b 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -74,6 +74,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
+#define PERF_REG_X86_RESERVED	(((1ULL << PERF_REG_X86_XMM0) - 1) & \
+				 ~((1ULL << PERF_REG_X86_MAX) - 1))
+
 #ifdef CONFIG_X86_32
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
 		       (1ULL << PERF_REG_X86_R9) | \
@@ -86,7 +89,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & REG_NOSUPPORT))
+	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
 		return -EINVAL;
 
 	return 0;
@@ -112,7 +115,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || (mask & REG_NOSUPPORT))
+	if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED)))
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 33b66b5c5aec..72b997eaa1fc 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -82,9 +82,9 @@ static struct orc_entry *orc_find(unsigned long ip);
  * But they are copies of the ftrace entries that are static and
  * defined in ftrace_*.S, which do have orc entries.
  *
- * If the undwinder comes across a ftrace trampoline, then find the
+ * If the unwinder comes across a ftrace trampoline, then find the
  * ftrace function that was used to create it, and use that ftrace
- * function's orc entrie, as the placement of the return code in
+ * function's orc entry, as the placement of the return code in
  * the stack will be identical.
  */
 static struct orc_entry *orc_ftrace_find(unsigned long ip)
@@ -128,6 +128,16 @@ static struct orc_entry null_orc_entry = {
 	.type = ORC_TYPE_CALL
 };
 
+/* Fake frame pointer entry -- used as a fallback for generated code */
+static struct orc_entry orc_fp_entry = {
+	.type		= ORC_TYPE_CALL,
+	.sp_reg		= ORC_REG_BP,
+	.sp_offset	= 16,
+	.bp_reg		= ORC_REG_PREV_SP,
+	.bp_offset	= -16,
+	.end		= 0,
+};
+
 static struct orc_entry *orc_find(unsigned long ip)
 {
 	static struct orc_entry *orc;
@@ -392,8 +402,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	 * calls and calls to noreturn functions.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
-	if (!orc)
-		goto err;
+	if (!orc) {
+		/*
+		 * As a fallback, try to assume this code uses a frame pointer.
+		 * This is useful for generated code, like BPF, which ORC
+		 * doesn't know about.  This is just a guess, so the rest of
+		 * the unwind is no longer considered reliable.
+		 */
+		orc = &orc_fp_entry;
+		state->error = true;
+	}
 
 	/* End-of-stack check for kernel threads: */
 	if (orc->sp_reg == ORC_REG_UNDEFINED) {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index a21c440ff356..4dabc318adb8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2339,7 +2339,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!apic_enabled(apic))
+	if (!kvm_apic_hw_enabled(apic))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 5f9c1a200201..46af3a5e9209 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5240,9 +5240,6 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 	vmx = to_vmx(vcpu);
 	vmcs12 = get_vmcs12(vcpu);
 
-	if (nested_vmx_allowed(vcpu) && vmx->nested.enlightened_vmcs_enabled)
-		kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
-
 	if (nested_vmx_allowed(vcpu) &&
 	    (vmx->nested.vmxon || vmx->nested.smm.vmxon)) {
 		kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr;
@@ -5251,6 +5248,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 		if (vmx_has_valid_vmcs12(vcpu)) {
 			kvm_state.size += sizeof(user_vmx_nested_state->vmcs12);
 
+			if (vmx->nested.hv_evmcs)
+				kvm_state.flags |= KVM_STATE_NESTED_EVMCS;
+
 			if (is_guest_mode(vcpu) &&
 			    nested_cpu_has_shadow_vmcs(vmcs12) &&
 			    vmcs12->vmcs_link_pointer != -1ull)
@@ -5350,6 +5350,15 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		if (kvm_state->hdr.vmx.vmcs12_pa != -1ull)
 			return -EINVAL;
 
+		/*
+		 * KVM_STATE_NESTED_EVMCS used to signal that KVM should
+		 * enable eVMCS capability on vCPU. However, since then
+		 * code was changed such that flag signals vmcs12 should
+		 * be copied into eVMCS in guest memory.
+		 *
+		 * To preserve backwards compatability, allow user
+		 * to set this flag even when there is no VMXON region.
+		 */
 		if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS)
 			return -EINVAL;
 	} else {
@@ -5358,7 +5367,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 
 		if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa))
 			return -EINVAL;
-    	}
+	}
 
 	if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
 	    (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
@@ -5373,20 +5382,21 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
 	 * must be zero.
 	 */
-	if (is_smm(vcpu) ? kvm_state->flags : kvm_state->hdr.vmx.smm.flags)
+	if (is_smm(vcpu) ?
+		(kvm_state->flags &
+		 (KVM_STATE_NESTED_GUEST_MODE | KVM_STATE_NESTED_RUN_PENDING))
+		: kvm_state->hdr.vmx.smm.flags)
 		return -EINVAL;
 
 	if ((kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_GUEST_MODE) &&
 	    !(kvm_state->hdr.vmx.smm.flags & KVM_STATE_NESTED_SMM_VMXON))
 		return -EINVAL;
 
-	vmx_leave_nested(vcpu);
-	if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
-		if (!nested_vmx_allowed(vcpu))
+	if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) &&
+		(!nested_vmx_allowed(vcpu) || !vmx->nested.enlightened_vmcs_enabled))
 			return -EINVAL;
 
-		nested_enable_evmcs(vcpu, NULL);
-	}
+	vmx_leave_nested(vcpu);
 
 	if (kvm_state->hdr.vmx.vmxon_pa == -1ull)
 		return 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9857992d4e58..fafd81d2c9ea 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1554,7 +1554,7 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 			vcpu->arch.tsc_always_catchup = 1;
 			return 0;
 		} else {
-			WARN(1, "user requested TSC rate below hardware speed\n");
+			pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
 			return -1;
 		}
 	}
@@ -1564,8 +1564,8 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
 				user_tsc_khz, tsc_khz);
 
 	if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
-		WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
-			  user_tsc_khz);
+		pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+			            user_tsc_khz);
 		return -1;
 	}
 
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 693aaf28d5fe..0f01c7b1d217 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -671,23 +671,25 @@ static unsigned long __meminit
 phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 	      unsigned long page_size_mask, bool init)
 {
-	unsigned long paddr_next, paddr_last = paddr_end;
-	unsigned long vaddr = (unsigned long)__va(paddr);
-	int i = p4d_index(vaddr);
+	unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last;
+
+	paddr_last = paddr_end;
+	vaddr = (unsigned long)__va(paddr);
+	vaddr_end = (unsigned long)__va(paddr_end);
 
 	if (!pgtable_l5_enabled())
 		return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end,
 				     page_size_mask, init);
 
-	for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) {
-		p4d_t *p4d;
+	for (; vaddr < vaddr_end; vaddr = vaddr_next) {
+		p4d_t *p4d = p4d_page + p4d_index(vaddr);
 		pud_t *pud;
 
-		vaddr = (unsigned long)__va(paddr);
-		p4d = p4d_page + p4d_index(vaddr);
-		paddr_next = (paddr & P4D_MASK) + P4D_SIZE;
+		vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE;
+		paddr = __pa(vaddr);
 
 		if (paddr >= paddr_end) {
+			paddr_next = __pa(vaddr_next);
 			if (!after_bootmem &&
 			    !e820__mapped_any(paddr & P4D_MASK, paddr_next,
 					     E820_TYPE_RAM) &&
@@ -699,13 +701,13 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end,
 
 		if (!p4d_none(*p4d)) {
 			pud = pud_offset(p4d, 0);
-			paddr_last = phys_pud_init(pud, paddr, paddr_end,
-						   page_size_mask, init);
+			paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
+					page_size_mask, init);
 			continue;
 		}
 
 		pud = alloc_low_page();
-		paddr_last = phys_pud_init(pud, paddr, paddr_end,
+		paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end),
 					   page_size_mask, init);
 
 		spin_lock(&init_mm.page_table_lock);
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 632b83885867..3b9fd679cea9 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -728,7 +728,7 @@ void efi_recover_from_page_fault(unsigned long phys_addr)
 	 * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so
 	 * page faulting on these addresses isn't expected.
 	 */
-	if (phys_addr >= 0x0000 && phys_addr <= 0x0fff)
+	if (phys_addr <= 0x0fff)
 		return;
 
 	/*