[tip:x86/mm] x86/efi: Add 5-level paging support

[tip-bot for Kirill A. Shutemov]

Commit-ID:  e981316f560482c001dede7f5b29259bde0b8afb
Gitweb:     http://git.kernel.org/tip/e981316f560482c001dede7f5b29259bde0b8afb
Author:     Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Fri, 17 Mar 2017 21:55:11 +0300
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 27 Mar 2017 08:56:25 +0200

x86/efi: Add 5-level paging support

Allocate additional page table level and ajdust efi_sync_low_kernel_mappings()
to work with additional page table level.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Reviewed-by: Matt Fleming <matt@xxxxxxxxxxxxxxxxxxx>
Acked-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: linux-arch@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/20170317185515.8636-3-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/platform/efi/efi_64.c | 36 ++++++++++++++++++++++++++----------
 1 file changed, 26 insertions(+), 10 deletions(-)

diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 8544dae..eb64e5b 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;
 }
 
@@ -191,26 +197,36 @@ 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);
-	p4d_efi = p4d_offset(pgd_efi, 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);
-
-	pgd_k = pgd_offset_k(EFI_VA_END);
-	p4d_k = p4d_offset(pgd_k, 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);
 
-	p4d_efi = p4d_offset(pgd_efi, EFI_VA_START);
 	pud_efi = pud_offset(p4d_efi, EFI_VA_START);
-	p4d_k = p4d_offset(pgd_k, EFI_VA_START);
 	pud_k = pud_offset(p4d_k, EFI_VA_START);
 
 	num_entries = PTRS_PER_PUD - pud_index(EFI_VA_START);