Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The main x86 MM changes in this cycle were:

   - continued native kernel PCID support preparation patches to the TLB
     flushing code (Andy Lutomirski)

   - various fixes related to 32-bit compat syscall returning address
     over 4Gb in applications, launched from 64-bit binaries - motivated
     by C/R frameworks such as Virtuozzo. (Dmitry Safonov)

   - continued Intel 5-level paging enablement: in particular the
     conversion of x86 GUP to the generic GUP code. (Kirill A. Shutemov)

   - x86/mpx ABI corner case fixes/enhancements (Joerg Roedel)

   - ... plus misc updates, fixes and cleanups"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
  mm, zone_device: Replace {get, put}_zone_device_page() with a single reference to fix pmem crash
  x86/mm: Fix flush_tlb_page() on Xen
  x86/mm: Make flush_tlb_mm_range() more predictable
  x86/mm: Remove flush_tlb() and flush_tlb_current_task()
  x86/vm86/32: Switch to flush_tlb_mm_range() in mark_screen_rdonly()
  x86/mm/64: Fix crash in remove_pagetable()
  Revert "x86/mm/gup: Switch GUP to the generic get_user_page_fast() implementation"
  x86/boot/e820: Remove a redundant self assignment
  x86/mm: Fix dump pagetables for 4 levels of page tables
  x86/mpx, selftests: Only check bounds-vs-shadow when we keep shadow
  x86/mpx: Correctly report do_mpx_bt_fault() failures to user-space
  Revert "x86/mm/numa: Remove numa_nodemask_from_meminfo()"
  x86/espfix: Add support for 5-level paging
  x86/kasan: Extend KASAN to support 5-level paging
  x86/mm: Add basic defines/helpers for CONFIG_X86_5LEVEL=y
  x86/paravirt: Add 5-level support to the paravirt code
  x86/mm: Define virtual memory map for 5-level paging
  x86/asm: Remove __VIRTUAL_MASK_SHIFT==47 assert
  x86/boot: Detect 5-level paging support
  x86/mm/numa: Remove numa_nodemask_from_meminfo()
  ...

3 files changed, 43 insertions, 18 deletions

diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 66ade16c7693..6b05a9219ea2 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -95,7 +95,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 	 * 'pmode_gdt' in wakeup_start.
 	 */
 	ctxt->gdt_desc.size = GDT_SIZE - 1;
-	ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_table(smp_processor_id());
+	ctxt->gdt_desc.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id());
 
 	store_tr(ctxt->tr);
 
@@ -162,7 +162,7 @@ static void fix_processor_context(void)
 	int cpu = smp_processor_id();
 	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
 #ifdef CONFIG_X86_64
-	struct desc_struct *desc = get_cpu_gdt_table(cpu);
+	struct desc_struct *desc = get_cpu_gdt_rw(cpu);
 	tss_desc tss;
 #endif
 	set_tss_desc(cpu, t);	/*
@@ -183,6 +183,9 @@ static void fix_processor_context(void)
 	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
+
+	/* The processor is back on the direct GDT, load back the fixmap */
+	load_fixmap_gdt(cpu);
 }
 
 /**
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index 9f14bd34581d..c35fdb585c68 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -32,6 +32,7 @@ pgd_t *resume_pg_dir;
  */
 static pmd_t *resume_one_md_table_init(pgd_t *pgd)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd_table;
 
@@ -41,11 +42,13 @@ static pmd_t *resume_one_md_table_init(pgd_t *pgd)
 		return NULL;
 
 	set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
 
 	BUG_ON(pmd_table != pmd_offset(pud, 0));
 #else
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	pud = pud_offset(p4d, 0);
 	pmd_table = pmd_offset(pud, 0);
 #endif
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 053801b022dd..6a61194ffd58 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -50,6 +50,7 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 {
 	pmd_t *pmd;
 	pud_t *pud;
+	p4d_t *p4d;
 
 	/*
 	 * The new mapping only has to cover the page containing the image
@@ -64,6 +65,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 	 * the virtual address space after switching over to the original page
 	 * tables used by the image kernel.
 	 */
+
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		p4d = (p4d_t *)get_safe_page(GFP_ATOMIC);
+		if (!p4d)
+			return -ENOMEM;
+	}
+
 	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
 	if (!pud)
 		return -ENOMEM;
@@ -76,8 +84,13 @@ static int set_up_temporary_text_mapping(pgd_t *pgd)
 		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
 	set_pud(pud + pud_index(restore_jump_address),
 		__pud(__pa(pmd) | _KERNPG_TABLE));
-	set_pgd(pgd + pgd_index(restore_jump_address),
-		__pgd(__pa(pud) | _KERNPG_TABLE));
+	if (IS_ENABLED(CONFIG_X86_5LEVEL)) {
+		set_p4d(p4d + p4d_index(restore_jump_address), __p4d(__pa(pud) | _KERNPG_TABLE));
+		set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(p4d) | _KERNPG_TABLE));
+	} else {
+		/* No p4d for 4-level paging: point the pgd to the pud page table */
+		set_pgd(pgd + pgd_index(restore_jump_address), __pgd(__pa(pud) | _KERNPG_TABLE));
+	}
 
 	return 0;
 }
@@ -125,7 +138,10 @@ static int set_up_temporary_mappings(void)
 static int relocate_restore_code(void)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
 
 	relocated_restore_code = get_safe_page(GFP_ATOMIC);
 	if (!relocated_restore_code)
@@ -135,22 +151,25 @@ static int relocate_restore_code(void)
 
 	/* Make the page containing the relocated code executable */
 	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
-	pud = pud_offset(pgd, relocated_restore_code);
+	p4d = p4d_offset(pgd, relocated_restore_code);
+	if (p4d_large(*p4d)) {
+		set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX));
+		goto out;
+	}
+	pud = pud_offset(p4d, relocated_restore_code);
 	if (pud_large(*pud)) {
 		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
-	} else {
-		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
-
-		if (pmd_large(*pmd)) {
-			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
-		} else {
-			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
-
-			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
-		}
+		goto out;
+	}
+	pmd = pmd_offset(pud, relocated_restore_code);
+	if (pmd_large(*pmd)) {
+		set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		goto out;
 	}
+	pte = pte_offset_kernel(pmd, relocated_restore_code);
+	set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+out:
 	__flush_tlb_all();
-
 	return 0;
 }