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

[tip-bot for Kirill A. Shutemov]

Commit-ID:  7f68904182e2f346c11b0acd74048181dc6615bb
Gitweb:     http://git.kernel.org/tip/7f68904182e2f346c11b0acd74048181dc6615bb
Author:     Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
AuthorDate: Fri, 17 Mar 2017 21:55:10 +0300
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Mon, 27 Mar 2017 08:56:13 +0200

x86/kexec: Add 5-level paging support

Handle additional page table level in the kexec code.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
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/20170317185515.8636-2-kirill.shutemov@xxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/include/asm/kexec.h       |  1 +
 arch/x86/kernel/machine_kexec_32.c |  4 +++-
 arch/x86/kernel/machine_kexec_64.c | 14 ++++++++++++--
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 282630e..70ef205 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -164,6 +164,7 @@ struct kimage_arch {
 };
 #else
 struct kimage_arch {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 469b23d..5f43cec 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -103,6 +103,7 @@ static void machine_kexec_page_table_set_one(
 	pgd_t *pgd, pmd_t *pmd, pte_t *pte,
 	unsigned long vaddr, unsigned long paddr)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 
 	pgd += pgd_index(vaddr);
@@ -110,7 +111,8 @@ static void machine_kexec_page_table_set_one(
 	if (!(pgd_val(*pgd) & _PAGE_PRESENT))
 		set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT));
 #endif
-	pud = pud_offset(pgd, vaddr);
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	pmd = pmd_offset(pud, vaddr);
 	if (!(pmd_val(*pmd) & _PAGE_PRESENT))
 		set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 857cdbd..085c3b3 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -36,6 +36,7 @@ static struct kexec_file_ops *kexec_file_loaders[] = {
 
 static void free_transition_pgtable(struct kimage *image)
 {
+	free_page((unsigned long)image->arch.p4d);
 	free_page((unsigned long)image->arch.pud);
 	free_page((unsigned long)image->arch.pmd);
 	free_page((unsigned long)image->arch.pte);
@@ -43,6 +44,7 @@ static void free_transition_pgtable(struct kimage *image)
 
 static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 {
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -53,13 +55,21 @@ static int init_transition_pgtable(struct kimage *image, pgd_t *pgd)
 	paddr = __pa(page_address(image->control_code_page)+PAGE_SIZE);
 	pgd += pgd_index(vaddr);
 	if (!pgd_present(*pgd)) {
+		p4d = (p4d_t *)get_zeroed_page(GFP_KERNEL);
+		if (!p4d)
+			goto err;
+		image->arch.p4d = p4d;
+		set_pgd(pgd, __pgd(__pa(p4d) | _KERNPG_TABLE));
+	}
+	p4d = p4d_offset(pgd, vaddr);
+	if (!p4d_present(*p4d)) {
 		pud = (pud_t *)get_zeroed_page(GFP_KERNEL);
 		if (!pud)
 			goto err;
 		image->arch.pud = pud;
-		set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE));
+		set_p4d(p4d, __p4d(__pa(pud) | _KERNPG_TABLE));
 	}
-	pud = pud_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 	if (!pud_present(*pud)) {
 		pmd = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 		if (!pmd)