All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yinghai Lu <yinghai@kernel.org>
To: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@elte.hu>,
	"H. Peter Anvin" <hpa@zytor.com>, Jacob Shin <jacob.shin@amd.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	Stefano Stabellini <stefano.stabellini@eu.citrix.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	linux-kernel@vger.kernel.org, Yinghai Lu <yinghai@kernel.org>
Subject: [PATCH 01/46] x86, mm: Add global page_size_mask and probe one time only
Date: Mon, 12 Nov 2012 13:17:57 -0800	[thread overview]
Message-ID: <1352755122-25660-2-git-send-email-yinghai@kernel.org> (raw)
In-Reply-To: <1352755122-25660-1-git-send-email-yinghai@kernel.org>

Now we pass around use_gbpages and use_pse for calculating page table size,
Later we will need to call init_memory_mapping for every ram range one by one,
that mean those calculation will be done several times.

Those information are the same for all ram range and could be stored in
page_size_mask and could be probed it one time only.

Move that probing code out of init_memory_mapping into separated function
probe_page_size_mask(), and call it before all init_memory_mapping.

Suggested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
---
 arch/x86/include/asm/pgtable.h |    1 +
 arch/x86/kernel/setup.c        |    1 +
 arch/x86/mm/init.c             |   55 ++++++++++++++++++---------------------
 3 files changed, 27 insertions(+), 30 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a1f780d..98ac76d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -602,6 +602,7 @@ static inline int pgd_none(pgd_t pgd)
 #ifndef __ASSEMBLY__
 
 extern int direct_gbpages;
+void probe_page_size_mask(void);
 
 /* local pte updates need not use xchg for locking */
 static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ca45696..01fb5f9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -913,6 +913,7 @@ void __init setup_arch(char **cmdline_p)
 	setup_real_mode();
 
 	init_gbpages();
+	probe_page_size_mask();
 
 	/* max_pfn_mapped is updated here */
 	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index d7aea41..aa5b0da 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -35,6 +35,7 @@ struct map_range {
 	unsigned page_size_mask;
 };
 
+static int page_size_mask;
 /*
  * First calculate space needed for kernel direct mapping page tables to cover
  * mr[0].start to mr[nr_range - 1].end, while accounting for possible 2M and 1GB
@@ -94,6 +95,30 @@ static void __init find_early_table_space(struct map_range *mr, int nr_range)
 		(pgt_buf_top << PAGE_SHIFT) - 1);
 }
 
+void probe_page_size_mask(void)
+{
+#if !defined(CONFIG_DEBUG_PAGEALLOC) && !defined(CONFIG_KMEMCHECK)
+	/*
+	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
+	 * This will simplify cpa(), which otherwise needs to support splitting
+	 * large pages into small in interrupt context, etc.
+	 */
+	if (direct_gbpages)
+		page_size_mask |= 1 << PG_LEVEL_1G;
+	if (cpu_has_pse)
+		page_size_mask |= 1 << PG_LEVEL_2M;
+#endif
+
+	/* Enable PSE if available */
+	if (cpu_has_pse)
+		set_in_cr4(X86_CR4_PSE);
+
+	/* Enable PGE if available */
+	if (cpu_has_pge) {
+		set_in_cr4(X86_CR4_PGE);
+		__supported_pte_mask |= _PAGE_GLOBAL;
+	}
+}
 void __init native_pagetable_reserve(u64 start, u64 end)
 {
 	memblock_reserve(start, end - start);
@@ -129,45 +154,15 @@ static int __meminit save_mr(struct map_range *mr, int nr_range,
 unsigned long __init_refok init_memory_mapping(unsigned long start,
 					       unsigned long end)
 {
-	unsigned long page_size_mask = 0;
 	unsigned long start_pfn, end_pfn;
 	unsigned long ret = 0;
 	unsigned long pos;
-
 	struct map_range mr[NR_RANGE_MR];
 	int nr_range, i;
-	int use_pse, use_gbpages;
 
 	printk(KERN_INFO "init_memory_mapping: [mem %#010lx-%#010lx]\n",
 	       start, end - 1);
 
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
-	/*
-	 * For CONFIG_DEBUG_PAGEALLOC, identity mapping will use small pages.
-	 * This will simplify cpa(), which otherwise needs to support splitting
-	 * large pages into small in interrupt context, etc.
-	 */
-	use_pse = use_gbpages = 0;
-#else
-	use_pse = cpu_has_pse;
-	use_gbpages = direct_gbpages;
-#endif
-
-	/* Enable PSE if available */
-	if (cpu_has_pse)
-		set_in_cr4(X86_CR4_PSE);
-
-	/* Enable PGE if available */
-	if (cpu_has_pge) {
-		set_in_cr4(X86_CR4_PGE);
-		__supported_pte_mask |= _PAGE_GLOBAL;
-	}
-
-	if (use_gbpages)
-		page_size_mask |= 1 << PG_LEVEL_1G;
-	if (use_pse)
-		page_size_mask |= 1 << PG_LEVEL_2M;
-
 	memset(mr, 0, sizeof(mr));
 	nr_range = 0;
 
-- 
1.7.7


  reply	other threads:[~2012-11-12 21:20 UTC|newest]

Thread overview: 115+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-10-09 23:58 [PATCH -v3 0/7] x86: Use BRK to pre mapping page table to make xen happy Yinghai Lu
2012-10-09 23:58 ` [PATCH 1/7] x86, mm: align start address to correct big page size Yinghai Lu
2012-10-09 23:58 ` [PATCH 2/7] x86, mm: Use big page size for small memory range Yinghai Lu
2012-10-09 23:58 ` [PATCH 3/7] x86, mm: Don't clear page table if next range is ram Yinghai Lu
2012-10-09 23:58 ` [PATCH 4/7] x86, mm: only keep initial mapping for ram Yinghai Lu
2012-10-10 13:48   ` Konrad Rzeszutek Wilk
2012-10-10 14:59     ` Yinghai Lu
2012-10-09 23:58 ` [PATCH 5/7] x86, mm: Break down init_all_memory_mapping Yinghai Lu
2012-10-10 13:55   ` Konrad Rzeszutek Wilk
2012-10-10 15:42     ` Yinghai Lu
2012-10-09 23:58 ` [PATCH 6/7] x86, mm: setup page table from top-down Yinghai Lu
2012-10-10  1:53   ` Yinghai Lu
2012-10-10 16:38   ` Stefano Stabellini
2012-10-10 17:07     ` Yinghai Lu
2012-10-10 17:26       ` Stefano Stabellini
2012-10-10 17:38         ` Yinghai Lu
2012-11-16 17:14           ` H. Peter Anvin
2012-11-16 17:16             ` Yinghai Lu
2012-10-09 23:58 ` [PATCH 7/7] x86, mm: Remove early_memremap workaround for page table accessing Yinghai Lu
2012-10-10 13:47 ` [PATCH -v3 0/7] x86: Use BRK to pre mapping page table to make xen happy Konrad Rzeszutek Wilk
2012-10-10 14:55   ` Yinghai Lu
2012-10-10 16:40 ` Stefano Stabellini
2012-10-11  6:13   ` Yinghai Lu
2012-10-11 23:04     ` Yinghai Lu
2012-10-18 16:17     ` Stefano Stabellini
2012-10-18 16:26       ` Jacob Shin
2012-10-18 16:57         ` Stefano Stabellini
2012-10-18 20:36           ` Yinghai Lu
2012-10-18 20:40         ` Yinghai Lu
2012-10-18 21:57           ` Jacob Shin
2012-10-18 20:43       ` Yinghai Lu
2012-10-30 13:44     ` Konrad Rzeszutek Wilk
2012-10-30 14:47       ` Yinghai Lu
2012-11-03 21:35         ` Yinghai Lu
2012-11-03 21:37           ` H. Peter Anvin
2012-11-05 20:25             ` Yinghai Lu
2012-11-05 20:27               ` [PATCH 39/42] x86, mm: kill numa_free_all_bootmem() Yinghai Lu
2012-11-05 20:27                 ` [PATCH 40/42] x86, mm: kill numa_64.h Yinghai Lu
2012-11-05 20:27                 ` [PATCH 41/42] sparc, mm: Remove calling of free_all_bootmem_node() Yinghai Lu
2012-11-05 20:27                   ` Yinghai Lu
2012-11-06 17:44                   ` David Miller
2012-11-06 17:44                     ` David Miller
2012-11-05 20:27                 ` [PATCH 42/42] mm: Kill NO_BOOTMEM version free_all_bootmem_node() Yinghai Lu
2012-11-07 16:11               ` [PATCH -v3 0/7] x86: Use BRK to pre mapping page table to make xen happy Konrad Rzeszutek Wilk
2012-11-08  1:40                 ` Konrad Rzeszutek Wilk
2012-11-08  4:06                   ` Yinghai Lu
2012-11-09 20:31                     ` Yinghai Lu
2012-11-12 19:30           ` Konrad Rzeszutek Wilk
2012-11-12 21:17             ` [PATCH v7 00/46] x86, mm: map ram from top-down with BRK and memblock Yinghai Lu
2012-11-12 21:17               ` Yinghai Lu [this message]
2012-11-12 21:17               ` [PATCH 02/46] x86, mm: Split out split_mem_range from init_memory_mapping Yinghai Lu
2012-11-13  5:51                 ` Yasuaki Ishimatsu
2012-11-13  6:20                   ` Yinghai Lu
2012-11-13  7:03                     ` snakky.zhang
2012-11-13 18:34                       ` Yinghai Lu
2012-11-12 21:17               ` [PATCH 03/46] x86, mm: Move down find_early_table_space() Yinghai Lu
2012-11-12 21:18               ` [PATCH 04/46] x86, mm: Move init_memory_mapping calling out of setup.c Yinghai Lu
2012-11-12 21:18               ` [PATCH 05/46] x86, mm: Revert back good_end setting for 64bit Yinghai Lu
2012-11-12 21:18               ` [PATCH 06/46] x86, mm: Change find_early_table_space() paramters Yinghai Lu
2012-11-12 21:18               ` [PATCH 07/46] x86, mm: Find early page table buffer together Yinghai Lu
2012-11-12 21:18               ` [PATCH 08/46] x86, mm: Separate out calculate_table_space_size() Yinghai Lu
2012-11-12 21:18               ` [PATCH 09/46] x86, mm: Set memblock initial limit to 1M Yinghai Lu
2012-11-12 21:18               ` [PATCH 10/46] x86, mm: if kernel .text .data .bss are not marked as E820_RAM, complain and fix Yinghai Lu
2012-11-12 21:18               ` [PATCH 11/46] x86, mm: Fixup code testing if a pfn is direct mapped Yinghai Lu
2012-11-12 21:18               ` [PATCH 12/46] x86, mm: use pfn_range_is_mapped() with CPA Yinghai Lu
2012-11-12 21:18               ` [PATCH 13/46] x86, mm: use pfn_range_is_mapped() with gart Yinghai Lu
2012-11-12 21:18               ` [PATCH 14/46] x86, mm: use pfn_range_is_mapped() with reserve_initrd Yinghai Lu
2012-11-12 21:18               ` [PATCH 15/46] x86, mm: Only direct map addresses that are marked as E820_RAM Yinghai Lu
2012-11-12 21:18               ` [PATCH 16/46] x86, mm: relocate initrd under all mem for 64bit Yinghai Lu
2012-11-12 21:18               ` [PATCH 17/46] x86, mm: Align start address to correct big page size Yinghai Lu
2012-11-12 21:18               ` [PATCH 18/46] x86, mm: Use big page size for small memory range Yinghai Lu
2012-11-12 21:18               ` [PATCH 19/46] x86, mm: Don't clear page table if range is ram Yinghai Lu
2012-11-12 21:18               ` [PATCH 20/46] x86, mm: Break down init_all_memory_mapping Yinghai Lu
2012-11-12 21:18               ` [PATCH 21/46] x86, mm: setup page table in top-down Yinghai Lu
2012-11-13 17:26                 ` Stefano Stabellini
2012-11-13 19:59                   ` Yinghai Lu
2012-11-13 20:01                     ` H. Peter Anvin
2012-11-13 20:36                       ` Yinghai Lu
2012-11-15 19:28                         ` Yinghai Lu
2012-11-12 21:18               ` [PATCH 22/46] x86, mm: Remove early_memremap workaround for page table accessing on 64bit Yinghai Lu
2012-11-13 16:52                 ` Stefano Stabellini
2012-11-12 21:18               ` [PATCH 23/46] x86, mm: Remove parameter in alloc_low_page for 64bit Yinghai Lu
2012-11-13 17:40                 ` Stefano Stabellini
2012-11-12 21:18               ` [PATCH 24/46] x86, mm: Merge alloc_low_page between 64bit and 32bit Yinghai Lu
2012-11-12 21:18               ` [PATCH 25/46] x86, mm: Move min_pfn_mapped back to mm/init.c Yinghai Lu
2012-11-12 21:18               ` [PATCH 26/46] x86, mm, Xen: Remove mapping_pagetable_reserve() Yinghai Lu
2012-11-13 16:36                 ` Stefano Stabellini
2012-11-13 18:51                   ` Yinghai Lu
2012-11-14 11:19                     ` Stefano Stabellini
2012-11-12 21:18               ` [PATCH 27/46] x86, mm: Add alloc_low_pages(num) Yinghai Lu
2012-11-13 16:37                 ` Stefano Stabellini
2012-11-13 18:53                   ` Yinghai Lu
2012-11-12 21:18               ` [PATCH 28/46] x86, mm: Add pointer about Xen mmu requirement for alloc_low_pages Yinghai Lu
2012-11-13 16:38                 ` Stefano Stabellini
2012-11-13 17:56                   ` H. Peter Anvin
2012-11-13 18:58                     ` Yinghai Lu
2012-11-12 21:18               ` [PATCH 29/46] x86, mm: only call early_ioremap_page_table_range_init() once Yinghai Lu
2012-11-12 21:18               ` [PATCH 30/46] x86, mm: Move back pgt_buf_* to mm/init.c Yinghai Lu
2012-11-12 21:18               ` [PATCH 31/46] x86, mm: Move init_gbpages() out of setup.c Yinghai Lu
2012-11-12 21:18               ` [PATCH 32/46] x86, mm: change low/hignmem_pfn_init to static on 32bit Yinghai Lu
2012-11-12 21:18               ` [PATCH 33/46] x86, mm: Move function declaration into mm_internal.h Yinghai Lu
2012-11-12 21:18               ` [PATCH 34/46] x86, mm: Add check before clear pte above max_low_pfn on 32bit Yinghai Lu
2012-11-12 21:18               ` [PATCH 35/46] x86, mm: use round_up/down in split_mem_range() Yinghai Lu
2012-11-12 21:18               ` [PATCH 36/46] x86, mm: use PFN_DOWN " Yinghai Lu
2012-11-12 21:18               ` [PATCH 37/46] x86, mm: use pfn instead of pos in split_mem_range Yinghai Lu
2012-11-12 21:18               ` [PATCH 38/46] x86, mm: use limit_pfn for end pfn Yinghai Lu
2012-11-12 21:18               ` [PATCH 39/46] x86, mm: Unifying after_bootmem for 32bit and 64bit Yinghai Lu
2012-11-12 21:18               ` [PATCH 40/46] x86, mm: Move after_bootmem to mm_internel.h Yinghai Lu
2012-11-12 21:18               ` [PATCH 41/46] x86, mm: Use clamp_t() in init_range_memory_mapping Yinghai Lu
2012-11-12 21:18               ` [PATCH 42/46] x86, mm: kill numa_free_all_bootmem() Yinghai Lu
2012-11-12 21:18               ` [PATCH 43/46] x86, mm: kill numa_64.h Yinghai Lu
2012-11-12 21:18               ` [PATCH 44/46] sparc, mm: Remove calling of free_all_bootmem_node() Yinghai Lu
2012-11-12 21:18                 ` Yinghai Lu
2012-11-12 21:18               ` [PATCH 45/46] mm: Kill NO_BOOTMEM version free_all_bootmem_node() Yinghai Lu
2012-11-12 21:18               ` [PATCH 46/46] x86, mm: Let "memmap=" take more entries one time Yinghai Lu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1352755122-25660-2-git-send-email-yinghai@kernel.org \
    --to=yinghai@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=hpa@zytor.com \
    --cc=jacob.shin@amd.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=stefano.stabellini@eu.citrix.com \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.