8 files changed, 121 insertions, 125 deletions

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index e6c469b323cc..296d294142c8 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -7,7 +7,6 @@
 #include <linux/sched.h>		/* test_thread_flag(), ...	*/
 #include <linux/sched/task_stack.h>	/* task_stack_*(), ...		*/
 #include <linux/kdebug.h>		/* oops_begin/end, ...		*/
-#include <linux/extable.h>		/* search_exception_tables	*/
 #include <linux/memblock.h>		/* max_low_pfn			*/
 #include <linux/kfence.h>		/* kfence_handle_page_fault	*/
 #include <linux/kprobes.h>		/* NOKPROBE_SYMBOL, ...		*/
@@ -678,7 +677,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code,
 			      ASM_CALL_ARG3,
 			      , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info));
 
-		unreachable();
+		BUG();
 	}
 #endif
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index c6d29f283001..62aa4d66a032 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1080,7 +1080,8 @@ struct execmem_info __init *execmem_arch_setup(void)
 
 	start = MODULES_VADDR + offset;
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) {
+	if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) &&
+	    cpu_feature_enabled(X86_FEATURE_PSE)) {
 		pgprot = PAGE_KERNEL_ROX;
 		flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE;
 	} else {
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 8d29163568a7..38ff7791a9c7 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -593,8 +593,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr,
  * Examine the physical address to determine if it is EFI data. Check
  * it against the boot params structure and EFI tables and memory types.
  */
-static bool memremap_is_efi_data(resource_size_t phys_addr,
-				 unsigned long size)
+static bool memremap_is_efi_data(resource_size_t phys_addr)
 {
 	u64 paddr;
 
@@ -632,42 +631,54 @@ static bool memremap_is_efi_data(resource_size_t phys_addr,
  * Examine the physical address to determine if it is boot data by checking
  * it against the boot params setup_data chain.
  */
-static bool memremap_is_setup_data(resource_size_t phys_addr,
-				   unsigned long size)
+static bool __ref __memremap_is_setup_data(resource_size_t phys_addr, bool early)
 {
+	unsigned int setup_data_sz = sizeof(struct setup_data);
 	struct setup_indirect *indirect;
 	struct setup_data *data;
 	u64 paddr, paddr_next;
 
 	paddr = boot_params.hdr.setup_data;
 	while (paddr) {
-		unsigned int len;
+		unsigned int len, size;
 
 		if (phys_addr == paddr)
 			return true;
 
-		data = memremap(paddr, sizeof(*data),
-				MEMREMAP_WB | MEMREMAP_DEC);
+		if (early)
+			data = early_memremap_decrypted(paddr, setup_data_sz);
+		else
+			data = memremap(paddr, setup_data_sz, MEMREMAP_WB | MEMREMAP_DEC);
 		if (!data) {
-			pr_warn("failed to memremap setup_data entry\n");
+			pr_warn("failed to remap setup_data entry\n");
 			return false;
 		}
 
+		size = setup_data_sz;
+
 		paddr_next = data->next;
 		len = data->len;
 
 		if ((phys_addr > paddr) &&
-		    (phys_addr < (paddr + sizeof(struct setup_data) + len))) {
-			memunmap(data);
+		    (phys_addr < (paddr + setup_data_sz + len))) {
+			if (early)
+				early_memunmap(data, setup_data_sz);
+			else
+				memunmap(data);
 			return true;
 		}
 
 		if (data->type == SETUP_INDIRECT) {
-			memunmap(data);
-			data = memremap(paddr, sizeof(*data) + len,
-					MEMREMAP_WB | MEMREMAP_DEC);
+			size += len;
+			if (early) {
+				early_memunmap(data, setup_data_sz);
+				data = early_memremap_decrypted(paddr, size);
+			} else {
+				memunmap(data);
+				data = memremap(paddr, size, MEMREMAP_WB | MEMREMAP_DEC);
+			}
 			if (!data) {
-				pr_warn("failed to memremap indirect setup_data\n");
+				pr_warn("failed to remap indirect setup_data\n");
 				return false;
 			}
 
@@ -679,7 +690,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr,
 			}
 		}
 
-		memunmap(data);
+		if (early)
+			early_memunmap(data, size);
+		else
+			memunmap(data);
 
 		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
 			return true;
@@ -690,67 +704,14 @@ static bool memremap_is_setup_data(resource_size_t phys_addr,
 	return false;
 }
 
-/*
- * Examine the physical address to determine if it is boot data by checking
- * it against the boot params setup_data chain (early boot version).
- */
-static bool __init early_memremap_is_setup_data(resource_size_t phys_addr,
-						unsigned long size)
+static bool memremap_is_setup_data(resource_size_t phys_addr)
 {
-	struct setup_indirect *indirect;
-	struct setup_data *data;
-	u64 paddr, paddr_next;
-
-	paddr = boot_params.hdr.setup_data;
-	while (paddr) {
-		unsigned int len, size;
-
-		if (phys_addr == paddr)
-			return true;
-
-		data = early_memremap_decrypted(paddr, sizeof(*data));
-		if (!data) {
-			pr_warn("failed to early memremap setup_data entry\n");
-			return false;
-		}
-
-		size = sizeof(*data);
-
-		paddr_next = data->next;
-		len = data->len;
-
-		if ((phys_addr > paddr) &&
-		    (phys_addr < (paddr + sizeof(struct setup_data) + len))) {
-			early_memunmap(data, sizeof(*data));
-			return true;
-		}
-
-		if (data->type == SETUP_INDIRECT) {
-			size += len;
-			early_memunmap(data, sizeof(*data));
-			data = early_memremap_decrypted(paddr, size);
-			if (!data) {
-				pr_warn("failed to early memremap indirect setup_data\n");
-				return false;
-			}
-
-			indirect = (struct setup_indirect *)data->data;
-
-			if (indirect->type != SETUP_INDIRECT) {
-				paddr = indirect->addr;
-				len = indirect->len;
-			}
-		}
-
-		early_memunmap(data, size);
-
-		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))
-			return true;
-
-		paddr = paddr_next;
-	}
+	return __memremap_is_setup_data(phys_addr, false);
+}
 
-	return false;
+static bool __init early_memremap_is_setup_data(resource_size_t phys_addr)
+{
+	return __memremap_is_setup_data(phys_addr, true);
 }
 
 /*
@@ -771,8 +732,8 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size,
 		return false;
 
 	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
-		if (memremap_is_setup_data(phys_addr, size) ||
-		    memremap_is_efi_data(phys_addr, size))
+		if (memremap_is_setup_data(phys_addr) ||
+		    memremap_is_efi_data(phys_addr))
 			return false;
 	}
 
@@ -797,8 +758,8 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
 	encrypted_prot = true;
 
 	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
-		if (early_memremap_is_setup_data(phys_addr, size) ||
-		    memremap_is_efi_data(phys_addr, size))
+		if (early_memremap_is_setup_data(phys_addr) ||
+		    memremap_is_efi_data(phys_addr))
 			encrypted_prot = false;
 	}
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 0a120d85d7bb..95bae74fdab2 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -94,6 +94,8 @@ void __init mem_encrypt_init(void)
 	/* Call into SWIOTLB to update the SWIOTLB DMA buffers */
 	swiotlb_update_mem_attributes();
 
+	snp_secure_tsc_prepare();
+
 	print_mem_encrypt_feature_info();
 }
 
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 774f9677458f..b56c5c073003 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -541,6 +541,9 @@ void __init sme_early_init(void)
 	 * kernel mapped.
 	 */
 	snp_update_svsm_ca();
+
+	if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 95bc50a8541c..ef4514d64c05 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -32,8 +32,6 @@
 #include <asm/pgalloc.h>
 #include <asm/proto.h>
 #include <asm/memtype.h>
-#include <asm/hyperv-tlfs.h>
-#include <asm/mshyperv.h>
 
 #include "../mm_internal.h"
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 5745a354a241..1fef5ad32d5a 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -19,12 +19,23 @@ EXPORT_SYMBOL(physical_mask);
 #endif
 
 #ifndef CONFIG_PARAVIRT
+#ifndef CONFIG_PT_RECLAIM
 static inline
 void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
-	tlb_remove_page(tlb, table);
+	struct ptdesc *ptdesc = (struct ptdesc *)table;
+
+	pagetable_dtor(ptdesc);
+	tlb_remove_page(tlb, ptdesc_page(ptdesc));
 }
-#endif
+#else
+static inline
+void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
+{
+	tlb_remove_table(tlb, table);
+}
+#endif /* !CONFIG_PT_RECLAIM */
+#endif /* !CONFIG_PARAVIRT */
 
 gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
 
@@ -52,15 +63,13 @@ early_param("userpte", setup_userpte);
 
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
-	pagetable_pte_dtor(page_ptdesc(pte));
 	paravirt_release_pte(page_to_pfn(pte));
-	paravirt_tlb_remove_table(tlb, pte);
+	paravirt_tlb_remove_table(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
-	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
 	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
 	/*
 	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
@@ -69,25 +78,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	pagetable_pmd_dtor(ptdesc);
-	paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc));
+	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
-	struct ptdesc *ptdesc = virt_to_ptdesc(pud);
-
-	pagetable_pud_dtor(ptdesc);
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_page(pud));
+	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_page(p4d));
+	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
@@ -222,7 +227,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 		if (pmds[i]) {
 			ptdesc = virt_to_ptdesc(pmds[i]);
 
-			pagetable_pmd_dtor(ptdesc);
+			pagetable_dtor(ptdesc);
 			pagetable_free(ptdesc);
 			mm_dec_nr_pmds(mm);
 		}
@@ -392,15 +397,14 @@ void __init pgtable_cache_init(void)
 				      SLAB_PANIC, NULL);
 }
 
-static inline pgd_t *_pgd_alloc(void)
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
 	/*
 	 * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
-						 PGD_ALLOCATION_ORDER);
+		return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -409,24 +413,23 @@ static inline pgd_t *_pgd_alloc(void)
 	return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
 }
 
-static inline void _pgd_free(pgd_t *pgd)
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	if (!SHARED_KERNEL_PMD)
-		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
+		__pgd_free(mm, pgd);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
 #else
 
-static inline pgd_t *_pgd_alloc(void)
+static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
 {
-	return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
-					 PGD_ALLOCATION_ORDER);
+	return __pgd_alloc(mm, PGD_ALLOCATION_ORDER);
 }
 
-static inline void _pgd_free(pgd_t *pgd)
+static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
-	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
+	__pgd_free(mm, pgd);
 }
 #endif /* CONFIG_X86_PAE */
 
@@ -436,7 +439,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
 	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
 
-	pgd = _pgd_alloc();
+	pgd = _pgd_alloc(mm);
 
 	if (pgd == NULL)
 		goto out;
@@ -479,7 +482,7 @@ out_free_pmds:
 	if (sizeof(pmds) != 0)
 		free_pmds(mm, pmds, PREALLOCATED_PMDS);
 out_free_pgd:
-	_pgd_free(pgd);
+	_pgd_free(mm, pgd);
 out:
 	return NULL;
 }
@@ -489,7 +492,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 	pgd_mop_up_pmds(mm, pgd);
 	pgd_dtor(pgd);
 	paravirt_pgd_free(mm, pgd);
-	_pgd_free(pgd);
+	_pgd_free(mm, pgd);
 }
 
 /*
@@ -856,7 +859,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 
 	free_page((unsigned long)pmd_sv);
 
-	pagetable_pmd_dtor(virt_to_ptdesc(pmd));
+	pagetable_dtor(virt_to_ptdesc(pmd));
 	free_page((unsigned long)pmd);
 
 	return 1;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index a2becb85bea7..6cf881a942bb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -607,18 +607,15 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
 		cond_mitigation(tsk);
 
 		/*
-		 * Stop remote flushes for the previous mm.
-		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
-		 * but the bitmap manipulation can cause cache line contention.
+		 * Leave this CPU in prev's mm_cpumask. Atomic writes to
+		 * mm_cpumask can be expensive under contention. The CPU
+		 * will be removed lazily at TLB flush time.
 		 */
-		if (prev != &init_mm) {
-			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
-						mm_cpumask(prev)));
-			cpumask_clear_cpu(cpu, mm_cpumask(prev));
-		}
+		VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu,
+				mm_cpumask(prev)));
 
 		/* Start receiving IPIs and then read tlb_gen (and LAM below) */
-		if (next != &init_mm)
+		if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
@@ -760,10 +757,13 @@ static void flush_tlb_func(void *info)
 	if (!local) {
 		inc_irq_stat(irq_tlb_count);
 		count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
+	}
 
-		/* Can only happen on remote CPUs */
-		if (f->mm && f->mm != loaded_mm)
-			return;
+	/* The CPU was left in the mm_cpumask of the target mm. Clear it. */
+	if (f->mm && f->mm != loaded_mm) {
+		cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm));
+		trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0);
+		return;
 	}
 
 	if (unlikely(loaded_mm == &init_mm))
@@ -893,9 +893,36 @@ done:
 			nr_invalidate);
 }
 
-static bool tlb_is_not_lazy(int cpu, void *data)
+static bool should_flush_tlb(int cpu, void *data)
+{
+	struct flush_tlb_info *info = data;
+
+	/* Lazy TLB will get flushed at the next context switch. */
+	if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu))
+		return false;
+
+	/* No mm means kernel memory flush. */
+	if (!info->mm)
+		return true;
+
+	/* The target mm is loaded, and the CPU is not lazy. */
+	if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm)
+		return true;
+
+	/* In cpumask, but not the loaded mm? Periodically remove by flushing. */
+	if (info->trim_cpumask)
+		return true;
+
+	return false;
+}
+
+static bool should_trim_cpumask(struct mm_struct *mm)
 {
-	return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu);
+	if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) {
+		WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ);
+		return true;
+	}
+	return false;
 }
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared);
@@ -929,7 +956,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask,
 	if (info->freed_tables)
 		on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true);
 	else
-		on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
+		on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func,
 				(void *)info, 1, cpumask);
 }
 
@@ -980,6 +1007,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
 	info->freed_tables	= freed_tables;
 	info->new_tlb_gen	= new_tlb_gen;
 	info->initiating_cpu	= smp_processor_id();
+	info->trim_cpumask	= 0;
 
 	return info;
 }
@@ -1022,6 +1050,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	 * flush_tlb_func_local() directly in this case.
 	 */
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) {
+		info->trim_cpumask = should_trim_cpumask(mm);
 		flush_tlb_multi(mm_cpumask(mm), info);
 	} else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
 		lockdep_assert_irqs_enabled();