5 files changed, 33 insertions, 228 deletions

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 69309cd56fdf..ea9010113f69 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -249,10 +249,22 @@ static void note_wx(struct pg_state *st, unsigned long addr)
 		  (void *)st->start_address);
 }
 
-static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
+static void effective_prot(struct ptdump_state *pt_st, int level, u64 val)
 {
-	return (prot1 & prot2 & (_PAGE_USER | _PAGE_RW)) |
-	       ((prot1 | prot2) & _PAGE_NX);
+	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
+	pgprotval_t prot = val & PTE_FLAGS_MASK;
+	pgprotval_t effective;
+
+	if (level > 0) {
+		pgprotval_t higher_prot = st->prot_levels[level - 1];
+
+		effective = (higher_prot & prot & (_PAGE_USER | _PAGE_RW)) |
+			    ((higher_prot | prot) & _PAGE_NX);
+	} else {
+		effective = prot;
+	}
+
+	st->prot_levels[level] = effective;
 }
 
 /*
@@ -261,7 +273,7 @@ static inline pgprotval_t effective_prot(pgprotval_t prot1, pgprotval_t prot2)
  * print what we collected so far.
  */
 static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
-		      unsigned long val)
+		      u64 val)
 {
 	struct pg_state *st = container_of(pt_st, struct pg_state, ptdump);
 	pgprotval_t new_prot, new_eff;
@@ -270,16 +282,10 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
 	struct seq_file *m = st->seq;
 
 	new_prot = val & PTE_FLAGS_MASK;
-
-	if (level > 0) {
-		new_eff = effective_prot(st->prot_levels[level - 1],
-					 new_prot);
-	} else {
-		new_eff = new_prot;
-	}
-
-	if (level >= 0)
-		st->prot_levels[level] = new_eff;
+	if (!val)
+		new_eff = 0;
+	else
+		new_eff = st->prot_levels[level];
 
 	/*
 	 * If we have a "break" in the series, we need to flush the state that
@@ -374,6 +380,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m,
 	struct pg_state st = {
 		.ptdump = {
 			.note_page	= note_page,
+			.effective_prot = effective_prot,
 			.range		= ptdump_ranges
 		},
 		.level = -1,
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index a51df516b87b..dffe8e4d3140 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -190,16 +190,13 @@ static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 	return pmd_k;
 }
 
-static void vmalloc_sync(void)
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
 {
-	unsigned long address;
-
-	if (SHARED_KERNEL_PMD)
-		return;
+	unsigned long addr;
 
-	for (address = VMALLOC_START & PMD_MASK;
-	     address >= TASK_SIZE_MAX && address < VMALLOC_END;
-	     address += PMD_SIZE) {
+	for (addr = start & PMD_MASK;
+	     addr >= TASK_SIZE_MAX && addr < VMALLOC_END;
+	     addr += PMD_SIZE) {
 		struct page *page;
 
 		spin_lock(&pgd_lock);
@@ -210,61 +207,13 @@ static void vmalloc_sync(void)
 			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
 
 			spin_lock(pgt_lock);
-			vmalloc_sync_one(page_address(page), address);
+			vmalloc_sync_one(page_address(page), addr);
 			spin_unlock(pgt_lock);
 		}
 		spin_unlock(&pgd_lock);
 	}
 }
 
-void vmalloc_sync_mappings(void)
-{
-	vmalloc_sync();
-}
-
-void vmalloc_sync_unmappings(void)
-{
-	vmalloc_sync();
-}
-
-/*
- * 32-bit:
- *
- *   Handle a fault on the vmalloc or module mapping area
- */
-static noinline int vmalloc_fault(unsigned long address)
-{
-	unsigned long pgd_paddr;
-	pmd_t *pmd_k;
-	pte_t *pte_k;
-
-	/* Make sure we are in vmalloc area: */
-	if (!(address >= VMALLOC_START && address < VMALLOC_END))
-		return -1;
-
-	/*
-	 * Synchronize this task's top level page-table
-	 * with the 'reference' page table.
-	 *
-	 * Do _not_ use "current" here. We might be inside
-	 * an interrupt in the middle of a task switch..
-	 */
-	pgd_paddr = read_cr3_pa();
-	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
-	if (!pmd_k)
-		return -1;
-
-	if (pmd_large(*pmd_k))
-		return 0;
-
-	pte_k = pte_offset_kernel(pmd_k, address);
-	if (!pte_present(*pte_k))
-		return -1;
-
-	return 0;
-}
-NOKPROBE_SYMBOL(vmalloc_fault);
-
 /*
  * Did it hit the DOS screen memory VA from vm86 mode?
  */
@@ -329,96 +278,6 @@ out:
 
 #else /* CONFIG_X86_64: */
 
-void vmalloc_sync_mappings(void)
-{
-	/*
-	 * 64-bit mappings might allocate new p4d/pud pages
-	 * that need to be propagated to all tasks' PGDs.
-	 */
-	sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
-}
-
-void vmalloc_sync_unmappings(void)
-{
-	/*
-	 * Unmappings never allocate or free p4d/pud pages.
-	 * No work is required here.
-	 */
-}
-
-/*
- * 64-bit:
- *
- *   Handle a fault on the vmalloc area
- */
-static noinline int vmalloc_fault(unsigned long address)
-{
-	pgd_t *pgd, *pgd_k;
-	p4d_t *p4d, *p4d_k;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	/* Make sure we are in vmalloc area: */
-	if (!(address >= VMALLOC_START && address < VMALLOC_END))
-		return -1;
-
-	/*
-	 * Copy kernel mappings over when needed. This can also
-	 * happen within a race in page table update. In the later
-	 * case just flush:
-	 */
-	pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(address);
-	pgd_k = pgd_offset_k(address);
-	if (pgd_none(*pgd_k))
-		return -1;
-
-	if (pgtable_l5_enabled()) {
-		if (pgd_none(*pgd)) {
-			set_pgd(pgd, *pgd_k);
-			arch_flush_lazy_mmu_mode();
-		} else {
-			BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_k));
-		}
-	}
-
-	/* With 4-level paging, copying happens on the p4d level. */
-	p4d = p4d_offset(pgd, address);
-	p4d_k = p4d_offset(pgd_k, address);
-	if (p4d_none(*p4d_k))
-		return -1;
-
-	if (p4d_none(*p4d) && !pgtable_l5_enabled()) {
-		set_p4d(p4d, *p4d_k);
-		arch_flush_lazy_mmu_mode();
-	} else {
-		BUG_ON(p4d_pfn(*p4d) != p4d_pfn(*p4d_k));
-	}
-
-	BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4);
-
-	pud = pud_offset(p4d, address);
-	if (pud_none(*pud))
-		return -1;
-
-	if (pud_large(*pud))
-		return 0;
-
-	pmd = pmd_offset(pud, address);
-	if (pmd_none(*pmd))
-		return -1;
-
-	if (pmd_large(*pmd))
-		return 0;
-
-	pte = pte_offset_kernel(pmd, address);
-	if (!pte_present(*pte))
-		return -1;
-
-	return 0;
-}
-NOKPROBE_SYMBOL(vmalloc_fault);
-
 #ifdef CONFIG_CPU_SUP_AMD
 static const char errata93_warning[] =
 KERN_ERR 
@@ -1257,29 +1116,6 @@ do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code,
 	 */
 	WARN_ON_ONCE(hw_error_code & X86_PF_PK);
 
-	/*
-	 * We can fault-in kernel-space virtual memory on-demand. The
-	 * 'reference' page table is init_mm.pgd.
-	 *
-	 * NOTE! We MUST NOT take any locks for this case. We may
-	 * be in an interrupt or a critical region, and should
-	 * only copy the information from the master page table,
-	 * nothing more.
-	 *
-	 * Before doing this on-demand faulting, ensure that the
-	 * fault is not any of the following:
-	 * 1. A fault on a PTE with a reserved bit set.
-	 * 2. A fault caused by a user-mode access.  (Do not demand-
-	 *    fault kernel memory due to user-mode accesses).
-	 * 3. A fault caused by a page-level protection violation.
-	 *    (A demand fault would be on a non-present page which
-	 *     would have X86_PF_PROT==0).
-	 */
-	if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) {
-		if (vmalloc_fault(address) >= 0)
-			return;
-	}
-
 	/* Was the fault spurious, caused by lazy TLB invalidation? */
 	if (spurious_kernel_fault(hw_error_code, address))
 		return;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 8b5f73f5e207..96274a90c5ff 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -218,6 +218,11 @@ void sync_global_pgds(unsigned long start, unsigned long end)
 		sync_global_pgds_l4(start, end);
 }
 
+void arch_sync_kernel_mappings(unsigned long start, unsigned long end)
+{
+	sync_global_pgds(start, end);
+}
+
 /*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 843aa10a4cb6..da0fb17a1a36 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -448,13 +448,7 @@ static void __init pti_clone_user_shared(void)
 		 * the sp1 and sp2 slots.
 		 *
 		 * This is done for all possible CPUs during boot to ensure
-		 * that it's propagated to all mms.  If we were to add one of
-		 * these mappings during CPU hotplug, we would need to take
-		 * some measure to make sure that every mm that subsequently
-		 * ran on that CPU would have the relevant PGD entry in its
-		 * pagetables.  The usual vmalloc_fault() mechanism would not
-		 * work for page faults taken in entry_SYSCALL_64 before RSP
-		 * is set up.
+		 * that it's propagated to all mms.
 		 */
 
 		unsigned long va = (unsigned long)&per_cpu(cpu_tss_rw, cpu);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 66f96f21a7b6..f3fe261e5936 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -161,34 +161,6 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	local_irq_restore(flags);
 }
 
-static void sync_current_stack_to_mm(struct mm_struct *mm)
-{
-	unsigned long sp = current_stack_pointer;
-	pgd_t *pgd = pgd_offset(mm, sp);
-
-	if (pgtable_l5_enabled()) {
-		if (unlikely(pgd_none(*pgd))) {
-			pgd_t *pgd_ref = pgd_offset_k(sp);
-
-			set_pgd(pgd, *pgd_ref);
-		}
-	} else {
-		/*
-		 * "pgd" is faked.  The top level entries are "p4d"s, so sync
-		 * the p4d.  This compiles to approximately the same code as
-		 * the 5-level case.
-		 */
-		p4d_t *p4d = p4d_offset(pgd, sp);
-
-		if (unlikely(p4d_none(*p4d))) {
-			pgd_t *pgd_ref = pgd_offset_k(sp);
-			p4d_t *p4d_ref = p4d_offset(pgd_ref, sp);
-
-			set_p4d(p4d, *p4d_ref);
-		}
-	}
-}
-
 static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next)
 {
 	unsigned long next_tif = task_thread_info(next)->flags;
@@ -377,15 +349,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		 */
 		cond_ibpb(tsk);
 
-		if (IS_ENABLED(CONFIG_VMAP_STACK)) {
-			/*
-			 * If our current stack is in vmalloc space and isn't
-			 * mapped in the new pgd, we'll double-fault.  Forcibly
-			 * map it.
-			 */
-			sync_current_stack_to_mm(next);
-		}
-
 		/*
 		 * Stop remote flushes for the previous mm.
 		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,