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()
  ...

2 files changed, 33 insertions, 12 deletions

diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index cef39b097649..3481268da3d0 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -68,7 +68,7 @@ pgd_t * __init efi_call_phys_prolog(void)
 	load_cr3(initial_page_table);
 	__flush_tlb_all();
 
-	gdt_descr.address = __pa(get_cpu_gdt_table(0));
+	gdt_descr.address = get_cpu_gdt_paddr(0);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 
@@ -79,7 +79,7 @@ void __init efi_call_phys_epilog(pgd_t *save_pgd)
 {
 	struct desc_ptr gdt_descr;
 
-	gdt_descr.address = (unsigned long)get_cpu_gdt_table(0);
+	gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0);
 	gdt_descr.size = GDT_SIZE - 1;
 	load_gdt(&gdt_descr);
 
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 642a8698ad61..c488625c9712 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -135,6 +135,7 @@ static pgd_t *efi_pgd;
 int __init efi_alloc_page_tables(void)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	gfp_t gfp_mask;
 
@@ -147,15 +148,20 @@ int __init efi_alloc_page_tables(void)
 		return -ENOMEM;
 
 	pgd = efi_pgd + pgd_index(EFI_VA_END);
+	p4d = p4d_alloc(&init_mm, pgd, EFI_VA_END);
+	if (!p4d) {
+		free_page((unsigned long)efi_pgd);
+		return -ENOMEM;
+	}
 
-	pud = pud_alloc_one(NULL, 0);
+	pud = pud_alloc(&init_mm, p4d, EFI_VA_END);
 	if (!pud) {
+		if (CONFIG_PGTABLE_LEVELS > 4)
+			free_page((unsigned long) pgd_page_vaddr(*pgd));
 		free_page((unsigned long)efi_pgd);
 		return -ENOMEM;
 	}
 
-	pgd_populate(NULL, pgd, pud);
-
 	return 0;
 }
 
@@ -166,6 +172,7 @@ void efi_sync_low_kernel_mappings(void)
 {
 	unsigned num_entries;
 	pgd_t *pgd_k, *pgd_efi;
+	p4d_t *p4d_k, *p4d_efi;
 	pud_t *pud_k, *pud_efi;
 
 	if (efi_enabled(EFI_OLD_MEMMAP))
@@ -190,23 +197,37 @@ void efi_sync_low_kernel_mappings(void)
 	memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries);
 
 	/*
+	 * As with PGDs, we share all P4D entries apart from the one entry
+	 * that covers the EFI runtime mapping space.
+	 */
+	BUILD_BUG_ON(p4d_index(EFI_VA_END) != p4d_index(MODULES_END));
+	BUILD_BUG_ON((EFI_VA_START & P4D_MASK) != (EFI_VA_END & P4D_MASK));
+
+	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
+	pgd_k = pgd_offset_k(EFI_VA_END);
+	p4d_efi = p4d_offset(pgd_efi, 0);
+	p4d_k = p4d_offset(pgd_k, 0);
+
+	num_entries = p4d_index(EFI_VA_END);
+	memcpy(p4d_efi, p4d_k, sizeof(p4d_t) * num_entries);
+
+	/*
 	 * We share all the PUD entries apart from those that map the
 	 * EFI regions. Copy around them.
 	 */
 	BUILD_BUG_ON((EFI_VA_START & ~PUD_MASK) != 0);
 	BUILD_BUG_ON((EFI_VA_END & ~PUD_MASK) != 0);
 
-	pgd_efi = efi_pgd + pgd_index(EFI_VA_END);
-	pud_efi = pud_offset(pgd_efi, 0);
-
-	pgd_k = pgd_offset_k(EFI_VA_END);
-	pud_k = pud_offset(pgd_k, 0);
+	p4d_efi = p4d_offset(pgd_efi, EFI_VA_END);
+	p4d_k = p4d_offset(pgd_k, EFI_VA_END);
+	pud_efi = pud_offset(p4d_efi, 0);
+	pud_k = pud_offset(p4d_k, 0);
 
 	num_entries = pud_index(EFI_VA_END);
 	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
 
-	pud_efi = pud_offset(pgd_efi, EFI_VA_START);
-	pud_k = pud_offset(pgd_k, EFI_VA_START);
+	pud_efi = pud_offset(p4d_efi, EFI_VA_START);
+	pud_k = pud_offset(p4d_k, EFI_VA_START);
 
 	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);
 	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);