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

Conflicts:

MAINTAINERS
 - keep Chandrasekar
drivers/net/ethernet/mellanox/mlx5/core/en_main.c
 - simple fix + trust the code re-added to param.c in -next is fine
include/linux/bpf.h
 - trivial
include/linux/ethtool.h
 - trivial, fix kdoc while at it
include/linux/skmsg.h
 - move to relevant place in tcp.c, comment re-wrapped
net/core/skmsg.c
 - add the sk = sk // sk = NULL around calls
net/tipc/crypto.c
 - trivial

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

19 files changed, 176 insertions, 100 deletions

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d6d5a28c3bf..9a85eae37b17 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -27,7 +27,7 @@ endif
 REALMODE_CFLAGS	:= -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
 		   -fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-		   -mno-mmx -mno-sse
+		   -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
 
 REALMODE_CFLAGS += -ffreestanding
 REALMODE_CFLAGS += -fno-stack-protector
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index c0538f82c9a2..630ff08532be 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,6 +132,7 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
+void cond_wakeup_cpu0(void);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 7068e4bb057d..1a162e559753 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -87,18 +87,6 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
 #endif
 
 /*
- * The maximum amount of extra memory compared to the base size.  The
- * main scaling factor is the size of struct page.  At extreme ratios
- * of base:extra, all the base memory can be filled with page
- * structures for the extra memory, leaving no space for anything
- * else.
- *
- * 10x seems like a reasonable balance between scaling flexibility and
- * leaving a practically usable system.
- */
-#define XEN_EXTRA_MEM_RATIO	(10)
-
-/*
  * Helper functions to write or read unsigned long values to/from
  * memory, when the access may fault.
  */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 7bdc0239a943..14cd3186dc77 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void)
 	/*
 	 * Initialize the ACPI boot-time table parser.
 	 */
-	if (acpi_table_init()) {
+	if (acpi_locate_initial_tables())
 		disable_acpi();
-		return;
-	}
+	else
+		acpi_reserve_initial_tables();
+}
+
+int __init early_acpi_boot_init(void)
+{
+	if (acpi_disabled)
+		return 1;
+
+	acpi_table_init_complete();
 
 	acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
 
@@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void)
 		} else {
 			printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
 			disable_acpi();
-			return;
+			return 1;
 		}
 	}
-}
-
-int __init early_acpi_boot_init(void)
-{
-	/*
-	 * If acpi_disabled, bail out
-	 */
-	if (acpi_disabled)
-		return 1;
 
 	/*
 	 * Process the Multiple APIC Description Table (MADT), if present
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d883176ef2ce..5ecd69a48393 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1045,6 +1045,9 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
+	/* Look for ACPI tables and reserve memory occupied by them. */
+	acpi_boot_table_init();
+
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
@@ -1136,11 +1139,6 @@ void __init setup_arch(char **cmdline_p)
 
 	early_platform_quirks();
 
-	/*
-	 * Parse the ACPI tables for possible boot-time SMP configuration.
-	 */
-	acpi_boot_table_init();
-
 	early_acpi_boot_init();
 
 	initmem_init();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 02813a7f3a7c..16703c35a944 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,13 +1659,17 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-static bool wakeup_cpu0(void)
+/**
+ * cond_wakeup_cpu0 - Wake up CPU0 if needed.
+ *
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+void cond_wakeup_cpu0(void)
 {
 	if (smp_processor_id() == 0 && enable_start_cpu0)
-		return true;
-
-	return false;
+		start_cpu0();
 }
+EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);
 
 /*
  * We need to flush the caches before going to sleep, lest we have
@@ -1734,11 +1738,8 @@ static inline void mwait_play_dead(void)
 		__monitor(mwait_ptr, 0, 0);
 		mb();
 		__mwait(eax, 0);
-		/*
-		 * If NMI wants to wake up CPU0, start CPU0.
-		 */
-		if (wakeup_cpu0())
-			start_cpu0();
+
+		cond_wakeup_cpu0();
 	}
 }
 
@@ -1749,11 +1750,8 @@ void hlt_play_dead(void)
 
 	while (1) {
 		native_halt();
-		/*
-		 * If NMI wants to wake up CPU0, start CPU0.
-		 */
-		if (wakeup_cpu0())
-			start_cpu0();
+
+		cond_wakeup_cpu0();
 	}
 }
 
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 1b4766fe1de2..eafc4d601f25 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-ccflags-y += -Iarch/x86/kvm
+ccflags-y += -I $(srctree)/arch/x86/kvm
 ccflags-$(CONFIG_KVM_WERROR) += -Werror
 
 ifeq ($(CONFIG_FRAME_POINTER),y)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d75524bc8423..951dae4e7175 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5884,6 +5884,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	struct kvm_mmu_page *sp;
 	unsigned int ratio;
 	LIST_HEAD(invalid_list);
+	bool flush = false;
 	ulong to_zap;
 
 	rcu_idx = srcu_read_lock(&kvm->srcu);
@@ -5905,19 +5906,19 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      lpage_disallowed_link);
 		WARN_ON_ONCE(!sp->lpage_disallowed);
 		if (is_tdp_mmu_page(sp)) {
-			kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
-				sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+			flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 			WARN_ON_ONCE(sp->lpage_disallowed);
 		}
 
 		if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
-			kvm_mmu_commit_zap_page(kvm, &invalid_list);
+			kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
 			cond_resched_rwlock_write(&kvm->mmu_lock);
+			flush = false;
 		}
 	}
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
 
 	write_unlock(&kvm->mmu_lock);
 	srcu_read_unlock(&kvm->srcu, rcu_idx);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 462b1f71c77f..018d82e73e31 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 	list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
 
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield);
+			  gfn_t start, gfn_t end, bool can_yield, bool flush);
 
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 {
@@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
 
 	list_del(&root->link);
 
-	zap_gfn_range(kvm, root, 0, max_gfn, false);
+	zap_gfn_range(kvm, root, 0, max_gfn, false, false);
 
 	free_page((unsigned long)root->spt);
 	kmem_cache_free(mmu_page_header_cache, root);
@@ -668,20 +668,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm,
  * scheduler needs the CPU or there is contention on the MMU lock. If this
  * function cannot yield, it will not release the MMU lock or reschedule and
  * the caller must ensure it does not supply too large a GFN range, or the
- * operation can cause a soft lockup.
+ * operation can cause a soft lockup.  Note, in some use cases a flush may be
+ * required by prior actions.  Ensure the pending flush is performed prior to
+ * yielding.
  */
 static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
-			  gfn_t start, gfn_t end, bool can_yield)
+			  gfn_t start, gfn_t end, bool can_yield, bool flush)
 {
 	struct tdp_iter iter;
-	bool flush_needed = false;
 
 	rcu_read_lock();
 
 	tdp_root_for_each_pte(iter, root, start, end) {
 		if (can_yield &&
-		    tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
-			flush_needed = false;
+		    tdp_mmu_iter_cond_resched(kvm, &iter, flush)) {
+			flush = false;
 			continue;
 		}
 
@@ -699,11 +700,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
 			continue;
 
 		tdp_mmu_set_spte(kvm, &iter, 0);
-		flush_needed = true;
+		flush = true;
 	}
 
 	rcu_read_unlock();
-	return flush_needed;
+	return flush;
 }
 
 /*
@@ -712,13 +713,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
  * SPTEs have been cleared and a TLB flush is needed before releasing the
  * MMU lock.
  */
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield)
 {
 	struct kvm_mmu_page *root;
 	bool flush = false;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root)
-		flush |= zap_gfn_range(kvm, root, start, end, true);
+		flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
 
 	return flush;
 }
@@ -930,7 +932,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm,
 				     struct kvm_mmu_page *root, gfn_t start,
 				     gfn_t end, unsigned long unused)
 {
-	return zap_gfn_range(kvm, root, start, end, false);
+	return zap_gfn_range(kvm, root, start, end, false, false);
 }
 
 int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 3b761c111bff..31096ece9b14 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -8,7 +8,29 @@
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root);
 
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield);
+static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start,
+					     gfn_t end)
+{
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true);
+}
+static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+
+	/*
+	 * Don't allow yielding, as the caller may have a flush pending.  Note,
+	 * if mmu_lock is held for write, zapping will never yield in this case,
+	 * but explicitly disallow it for safety.  The TDP MMU does not yield
+	 * until it has made forward progress (steps sideways), and when zapping
+	 * a single shadow page that it's guaranteed to see (thus the mmu_lock
+	 * requirement), its "step sideways" will always step beyond the bounds
+	 * of the shadow page's gfn range and stop iterating before yielding.
+	 */
+	lockdep_assert_held_write(&kvm->mmu_lock);
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false);
+}
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 35891d9a1099..fb204eaa8bb3 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 	return true;
 }
 
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
+static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	bool vmcb12_lma;
 
+	/*
+	 * FIXME: these should be done after copying the fields,
+	 * to avoid TOC/TOU races.  For these save area checks
+	 * the possible damage is limited since kvm_set_cr0 and
+	 * kvm_set_cr4 handle failure; EFER_SVME is an exception
+	 * so it is force-set later in nested_prepare_vmcb_save.
+	 */
 	if ((vmcb12->save.efer & EFER_SVME) == 0)
 		return false;
 
@@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
 		return false;
 
-	return nested_vmcb_check_controls(&vmcb12->control);
+	return true;
 }
 
 static void load_nested_vmcb_control(struct vcpu_svm *svm,
@@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
 	svm->vmcb->save.idtr = vmcb12->save.idtr;
 	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
-	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+
+	/*
+	 * Force-set EFER_SVME even though it is checked earlier on the
+	 * VMCB12, because the guest can flip the bit between the check
+	 * and now.  Clearing EFER_SVME would call svm_free_nested.
+	 */
+	svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+
 	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
 	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
@@ -468,7 +482,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
 
 
 	svm->nested.vmcb12_gpa = vmcb12_gpa;
-	load_nested_vmcb_control(svm, &vmcb12->control);
 	nested_prepare_vmcb_control(svm);
 	nested_prepare_vmcb_save(svm, vmcb12);
 
@@ -515,7 +528,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 	if (WARN_ON_ONCE(!svm->nested.initialized))
 		return -EINVAL;
 
-	if (!nested_vmcb_checks(svm, vmcb12)) {
+	load_nested_vmcb_control(svm, &vmcb12->control);
+
+	if (!nested_vmcb_check_save(svm, vmcb12) ||
+	    !nested_vmcb_check_controls(&svm->nested.ctl)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_code_hi = 0;
 		vmcb12->control.exit_info_1  = 0;
@@ -1209,6 +1225,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 */
 	if (!(save->cr0 & X86_CR0_PG))
 		goto out_free;
+	if (!(save->efer & EFER_SVME))
+		goto out_free;
 
 	/*
 	 * All checks done, we can enter guest mode.  L1 control fields
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index 035da07500e8..fdf587f19c5f 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr)
 static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 					     enum pmu_type type)
 {
+	struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+
 	switch (msr) {
 	case MSR_F15H_PERF_CTL0:
 	case MSR_F15H_PERF_CTL1:
@@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	case MSR_F15H_PERF_CTL3:
 	case MSR_F15H_PERF_CTL4:
 	case MSR_F15H_PERF_CTL5:
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		fallthrough;
 	case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
 		if (type != PMU_TYPE_EVNTSEL)
 			return NULL;
@@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
 	case MSR_F15H_PERF_CTR3:
 	case MSR_F15H_PERF_CTR4:
 	case MSR_F15H_PERF_CTR5:
+		if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+			return NULL;
+		fallthrough;
 	case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
 		if (type != PMU_TYPE_COUNTER)
 			return NULL;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fe806e894212..eca63625aee4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -271,8 +271,7 @@ static struct kmem_cache *x86_emulator_cache;
  * When called, it means the previous get/set msr reached an invalid msr.
  * Return true if we want to ignore/silent this failed msr access.
  */
-static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
-				  u64 data, bool write)
+static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write)
 {
 	const char *op = write ? "wrmsr" : "rdmsr";
 
@@ -1445,7 +1444,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	if (r == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear the output for simplicity */
 		*data = 0;
-		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+		if (kvm_msr_ignored_check(index, 0, false))
 			r = 0;
 	}
 
@@ -1620,7 +1619,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
 	int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
 
 	if (ret == KVM_MSR_RET_INVALID)
-		if (kvm_msr_ignored_check(vcpu, index, data, true))
+		if (kvm_msr_ignored_check(index, data, true))
 			ret = 0;
 
 	return ret;
@@ -1658,7 +1657,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
 	if (ret == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear *data for simplicity */
 		*data = 0;
-		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+		if (kvm_msr_ignored_check(index, 0, false))
 			ret = 0;
 	}
 
@@ -2329,7 +2328,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	kvm_vcpu_write_tsc_offset(vcpu, offset);
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
-	spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
 	if (!matched) {
 		kvm->arch.nr_vcpus_matched_tsc = 0;
 	} else if (!already_matched) {
@@ -2337,7 +2336,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
 	}
 
 	kvm_track_tsc_matching(vcpu);
-	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
 }
 
 static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2559,13 +2558,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	int i;
 	struct kvm_vcpu *vcpu;
 	struct kvm_arch *ka = &kvm->arch;
+	unsigned long flags;
 
 	kvm_hv_invalidate_tsc_page(kvm);
 
-	spin_lock(&ka->pvclock_gtod_sync_lock);
 	kvm_make_mclock_inprogress_request(kvm);
+
 	/* no guest entries from this point */
+	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	pvclock_update_vm_gtod_copy(kvm);
+	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2573,8 +2575,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 	/* guest entries allowed */
 	kvm_for_each_vcpu(i, vcpu, kvm)
 		kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
 #endif
 }
 
@@ -2582,17 +2582,18 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 {
 	struct kvm_arch *ka = &kvm->arch;
 	struct pvclock_vcpu_time_info hv_clock;
+	unsigned long flags;
 	u64 ret;
 
-	spin_lock(&ka->pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	if (!ka->use_master_clock) {
-		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 		return get_kvmclock_base_ns() + ka->kvmclock_offset;
 	}
 
 	hv_clock.tsc_timestamp = ka->master_cycle_now;
 	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
 	get_cpu();
@@ -2686,13 +2687,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
 	 */
-	spin_lock(&ka->pvclock_gtod_sync_lock);
+	spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 	use_master_clock = ka->use_master_clock;
 	if (use_master_clock) {
 		host_tsc = ka->master_cycle_now;
 		kernel_ns = ka->master_kernel_ns;
 	}
-	spin_unlock(&ka->pvclock_gtod_sync_lock);
+	spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
@@ -5726,6 +5727,7 @@ set_pit2_out:
 	}
 #endif
 	case KVM_SET_CLOCK: {
+		struct kvm_arch *ka = &kvm->arch;
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
@@ -5744,8 +5746,22 @@ set_pit2_out:
 		 * pvclock_update_vm_gtod_copy().
 		 */
 		kvm_gen_update_masterclock(kvm);
-		now_ns = get_kvmclock_ns(kvm);
-		kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
+
+		/*
+		 * This pairs with kvm_guest_time_update(): when masterclock is
+		 * in use, we use master_kernel_ns + kvmclock_offset to set
+		 * unsigned 'system_time' so if we use get_kvmclock_ns() (which
+		 * is slightly ahead) here we risk going negative on unsigned
+		 * 'system_time' when 'user_ns.clock' is very small.
+		 */
+		spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+		if (kvm->arch.use_master_clock)
+			now_ns = ka->master_kernel_ns;
+		else
+			now_ns = get_kvmclock_base_ns();
+		ka->kvmclock_offset = user_ns.clock - now_ns;
+		spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+
 		kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
 		break;
 	}
@@ -7724,6 +7740,7 @@ static void kvm_hyperv_tsc_notifier(void)
 	struct kvm *kvm;
 	struct kvm_vcpu *vcpu;
 	int cpu;
+	unsigned long flags;
 
 	mutex_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
@@ -7739,17 +7756,15 @@ static void kvm_hyperv_tsc_notifier(void)
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		struct kvm_arch *ka = &kvm->arch;
 
-		spin_lock(&ka->pvclock_gtod_sync_lock);
-
+		spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
 		pvclock_update_vm_gtod_copy(kvm);
+		spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 
 		kvm_for_each_vcpu(cpu, vcpu, kvm)
 			kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
-		spin_unlock(&ka->pvclock_gtod_sync_lock);
 	}
 	mutex_unlock(&kvm_lock);
 }
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 39eb04887141..9035e34aa156 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -250,7 +250,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu)
 void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs);
 void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
-void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
 u64 get_kvmclock_ns(struct kvm *kvm);
 
 int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 4b01f7dbaf30..ae78cef79980 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -262,7 +262,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
 	if (pgprot_val(old_prot) == pgprot_val(new_prot))
 		return;
 
-	pa = pfn << page_level_shift(level);
+	pa = pfn << PAGE_SHIFT;
 	size = page_level_size(level);
 
 	/*
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 9eead60f0301..1a467b2a5467 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1689,7 +1689,16 @@ emit_jmp:
 		}
 
 		if (image) {
-			if (unlikely(proglen + ilen > oldproglen)) {
+			/*
+			 * When populating the image, assert that:
+			 *
+			 *  i) We do not write beyond the allocated space, and
+			 * ii) addrs[i] did not change from the prior run, in order
+			 *     to validate assumptions made for computing branch
+			 *     displacements.
+			 */
+			if (unlikely(proglen + ilen > oldproglen ||
+				     proglen + ilen != addrs[i])) {
 				pr_err("bpf_jit: fatal error\n");
 				return -EFAULT;
 			}
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 0a7a2870f111..3da88ded6ee3 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -2469,7 +2469,16 @@ notyet:
 		}
 
 		if (image) {
-			if (unlikely(proglen + ilen > oldproglen)) {
+			/*
+			 * When populating the image, assert that:
+			 *
+			 *  i) We do not write beyond the allocated space, and
+			 * ii) addrs[i] did not change from the prior run, in order
+			 *     to validate assumptions made for computing branch
+			 *     displacements.
+			 */
+			if (unlikely(proglen + ilen > oldproglen ||
+				     proglen + ilen != addrs[i])) {
 				pr_err("bpf_jit: fatal error\n");
 				return -EFAULT;
 			}
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 17d80f751fcb..ac06ca32e9ef 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -98,8 +98,8 @@ EXPORT_SYMBOL_GPL(xen_p2m_size);
 unsigned long xen_max_p2m_pfn __read_mostly;
 EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
 
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
-#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
+#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
 #else
 #define P2M_LIMIT 0
 #endif
@@ -416,9 +416,6 @@ void __init xen_vmalloc_p2m_tree(void)
 	xen_p2m_last_pfn = xen_max_p2m_pfn;
 
 	p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
-	if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC))
-		p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO;
-
 	vm.flags = VM_ALLOC;
 	vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
 			PMD_SIZE * PMDS_PER_MID_PAGE);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 1a3b75652fa4..8bfc10330107 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -59,6 +59,18 @@ static struct {
 } xen_remap_buf __initdata __aligned(PAGE_SIZE);
 static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
 
+/*
+ * The maximum amount of extra memory compared to the base size.  The
+ * main scaling factor is the size of struct page.  At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ *
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO		(10)
+
 static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
 
 static void __init xen_parse_512gb(void)
@@ -778,13 +790,13 @@ char * __init xen_memory_setup(void)
 		extra_pages += max_pages - max_pfn;
 
 	/*
-	 * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO
+	 * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
 	 * factor the base size.
 	 *
 	 * Make sure we have no memory above max_pages, as this area
 	 * isn't handled by the p2m management.
 	 */
-	extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+	extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
 			   extra_pages, max_pages - max_pfn);
 	i = 0;
 	addr = xen_e820_table.entries[0].addr;