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

[tip-bot for Kirill A. Shutemov]

Commit-ID:  06c830a48346643e195801460dfe16d96ba4dff5
Gitweb:     http://git.kernel.org/tip/06c830a48346643e195801460dfe16d96ba4dff5
Author:     Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Mon, 13 Mar 2017 17:33:09 +0300
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 14 Mar 2017 08:45:09 +0100

x86/power: Add 5-level paging support

set_up_temporary_text_mapping() and relocate_restore_code() require
adjustments to handle additional page table level.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
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: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: linux-arch@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
Link: http://lkml.kernel.org/r/20170313143309.16020-7-kirill.shutemov@xxxxxxxxxxxxxxx
[ Minor readability edits. ]
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/power/hibernate_64.c | 47 ++++++++++++++++++++++++++++++-------------
 1 file changed, 33 insertions(+), 14 deletions(-)

diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index ded2e82..2a9f993 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -49,6 +49,7 @@ 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
@@ -63,6 +64,13 @@ 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;
@@ -75,8 +83,13 @@ 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;
 }
@@ -124,7 +137,10 @@ 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)
@@ -134,22 +150,25 @@ 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;
 }