x86/mm: Add support for gbpages to kernel_ident_mapping_init()

Kernel identity mappings on x86-64 kernels are created in two
ways: by the early x86 boot code, or by kernel_ident_mapping_init().

Native kernels (which is the dominant usecase) use the former,
but the kexec and the hibernation code uses kernel_ident_mapping_init().

There's a subtle difference between these two ways of how identity
mappings are created, the current kernel_ident_mapping_init() code
creates identity mappings always using 2MB page(PMD level) - while
the native kernel boot path also utilizes gbpages where available.

This difference is suboptimal both for performance and for memory
usage: kernel_ident_mapping_init() needs to allocate pages for the
page tables when creating the new identity mappings.

This patch adds 1GB page(PUD level) support to kernel_ident_mapping_init()
to address these concerns.

The primary advantage would be better TLB coverage/performance,
because we'd utilize 1GB TLBs instead of 2MB ones.

It is also useful for machines with large number of memory to
save paging structure allocations(around 4MB/TB using 2MB page)
when setting identity mappings for all the memory, after using
1GB page it will consume only 8KB/TB.

( Note that this change alone does not activate gbpages in kexec,
  we are doing that in a separate patch. )

Signed-off-by: Xunlei Pang <xlpang@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: akpm@linux-foundation.org
Cc: kexec@lists.infradead.org
Link: http://lkml.kernel.org/r/1493862171-8799-1-git-send-email-xlpang@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

5 files changed, 18 insertions, 5 deletions

diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index 56589d0a804b..1d78f1739087 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -70,7 +70,7 @@ static unsigned long level4p;
  * Due to relocation, pointers must be assigned at run time not build time.
  */
 static struct x86_mapping_info mapping_info = {
-	.pmd_flag       = __PAGE_KERNEL_LARGE_EXEC,
+	.page_flag       = __PAGE_KERNEL_LARGE_EXEC,
 };
 
 /* Locates and clears a region for a new top level page table. */
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 737da62bfeb0..474eb8c66fee 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -4,8 +4,9 @@
 struct x86_mapping_info {
 	void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
 	void *context;			 /* context for alloc_pgt_page */
-	unsigned long pmd_flag;		 /* page flag for PMD entry */
+	unsigned long page_flag;	 /* page flag for PMD or PUD entry */
 	unsigned long offset;		 /* ident mapping offset */
+	bool direct_gbpages;		 /* PUD level 1GB page support */
 };
 
 int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page,
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 085c3b300d32..1d4f2b076545 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -113,7 +113,7 @@ static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
 	struct x86_mapping_info info = {
 		.alloc_pgt_page	= alloc_pgt_page,
 		.context	= image,
-		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
 	};
 	unsigned long mstart, mend;
 	pgd_t *level4p;
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
index 04210a29dd60..adab1595f4bd 100644
--- a/arch/x86/mm/ident_map.c
+++ b/arch/x86/mm/ident_map.c
@@ -13,7 +13,7 @@ static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page,
 		if (pmd_present(*pmd))
 			continue;
 
-		set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag));
+		set_pmd(pmd, __pmd((addr - info->offset) | info->page_flag));
 	}
 }
 
@@ -30,6 +30,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 		if (next > end)
 			next = end;
 
+		if (info->direct_gbpages) {
+			pud_t pudval;
+
+			if (pud_present(*pud))
+				continue;
+
+			addr &= PUD_MASK;
+			pudval = __pud((addr - info->offset) | info->page_flag);
+			set_pud(pud, pudval);
+			continue;
+		}
+
 		if (pud_present(*pud)) {
 			pmd = pmd_offset(pud, 0);
 			ident_pmd_init(info, pmd, addr, next);
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 6a61194ffd58..a6e21fee22ea 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -104,7 +104,7 @@ static int set_up_temporary_mappings(void)
 {
 	struct x86_mapping_info info = {
 		.alloc_pgt_page	= alloc_pgt_page,
-		.pmd_flag	= __PAGE_KERNEL_LARGE_EXEC,
+		.page_flag	= __PAGE_KERNEL_LARGE_EXEC,
 		.offset		= __PAGE_OFFSET,
 	};
 	unsigned long mstart, mend;