public inbox for linux-kernel@vger.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>,
	Andrew Morton <akpm@linux-foundation.org>,
	Tejun Heo <tj@kernel.org>, Thomas Renninger <trenn@suse.de>,
	Tang Chen <tangchen@cn.fujitsu.com>
Cc: linux-kernel@vger.kernel.org, Yinghai Lu <yinghai@kernel.org>,
	Pekka Enberg <penberg@kernel.org>,
	Jacob Shin <jacob.shin@amd.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Subject: [PATCH v4 21/22] x86, mm: Make init_mem_mapping be able to be called several times
Date: Thu, 11 Apr 2013 17:56:07 -0700	[thread overview]
Message-ID: <1365728168-32067-22-git-send-email-yinghai@kernel.org> (raw)
In-Reply-To: <1365728168-32067-1-git-send-email-yinghai@kernel.org>

Prepare to put page table on local nodes.

Move calling of init_mem_mapping to early_initmem_init.

Rework alloc_low_pages to alloc page table in following order:
	BRK, local node, low range

Still only load_cr3 one time, otherwise we would break xen 64bit again.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Jacob Shin <jacob.shin@amd.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
---
 arch/x86/include/asm/pgtable.h |  2 +-
 arch/x86/kernel/setup.c        |  1 -
 arch/x86/mm/init.c             | 88 ++++++++++++++++++++++++++----------------
 arch/x86/mm/numa.c             | 24 ++++++++++++
 4 files changed, 79 insertions(+), 36 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1e67223..868687c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -621,7 +621,7 @@ static inline int pgd_none(pgd_t pgd)
 #ifndef __ASSEMBLY__
 
 extern int direct_gbpages;
-void init_mem_mapping(void);
+void init_mem_mapping(unsigned long begin, unsigned long end);
 void early_alloc_pgt_buf(void);
 
 /* local pte updates need not use xchg for locking */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 6ef3fa2..67ef4bc 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1105,7 +1105,6 @@ void __init setup_arch(char **cmdline_p)
 	acpi_boot_table_init();
 	early_acpi_boot_init();
 	early_initmem_init();
-	init_mem_mapping();
 	memblock.current_limit = get_max_mapped();
 	early_trap_pf_init();
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 2754e45..8a03283 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -24,7 +24,10 @@ static unsigned long __initdata pgt_buf_start;
 static unsigned long __initdata pgt_buf_end;
 static unsigned long __initdata pgt_buf_top;
 
-static unsigned long min_pfn_mapped;
+static unsigned long low_min_pfn_mapped;
+static unsigned long low_max_pfn_mapped;
+static unsigned long local_min_pfn_mapped;
+static unsigned long local_max_pfn_mapped;
 
 static bool __initdata can_use_brk_pgt = true;
 
@@ -52,10 +55,17 @@ __ref void *alloc_low_pages(unsigned int num)
 
 	if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) {
 		unsigned long ret;
-		if (min_pfn_mapped >= max_pfn_mapped)
-			panic("alloc_low_page: ran out of memory");
-		ret = memblock_find_in_range(min_pfn_mapped << PAGE_SHIFT,
-					max_pfn_mapped << PAGE_SHIFT,
+		if (local_min_pfn_mapped >= local_max_pfn_mapped) {
+			if (low_min_pfn_mapped >= low_max_pfn_mapped)
+				panic("alloc_low_page: ran out of memory");
+			ret = memblock_find_in_range(
+					low_min_pfn_mapped << PAGE_SHIFT,
+					low_max_pfn_mapped << PAGE_SHIFT,
+					PAGE_SIZE * num , PAGE_SIZE);
+		} else
+			ret = memblock_find_in_range(
+					local_min_pfn_mapped << PAGE_SHIFT,
+					local_max_pfn_mapped << PAGE_SHIFT,
 					PAGE_SIZE * num , PAGE_SIZE);
 		if (!ret)
 			panic("alloc_low_page: can not alloc memory");
@@ -402,60 +412,75 @@ static unsigned long __init get_new_step_size(unsigned long step_size)
 	return  step_size;
 }
 
-void __init init_mem_mapping(void)
+void __init init_mem_mapping(unsigned long begin, unsigned long end)
 {
-	unsigned long end, real_end, start, last_start;
+	unsigned long real_end, start, last_start;
 	unsigned long step_size;
 	unsigned long addr;
 	unsigned long mapped_ram_size = 0;
 	unsigned long new_mapped_ram_size;
+	bool is_low = false;
+
+	if (!begin) {
+		probe_page_size_mask();
+		/* the ISA range is always mapped regardless of memory holes */
+		init_memory_mapping(0, ISA_END_ADDRESS);
+		begin = ISA_END_ADDRESS;
+		is_low = true;
+	}
 
-	probe_page_size_mask();
-
-#ifdef CONFIG_X86_64
-	end = max_pfn << PAGE_SHIFT;
-#else
-	end = max_low_pfn << PAGE_SHIFT;
-#endif
-
-	/* the ISA range is always mapped regardless of memory holes */
-	init_memory_mapping(0, ISA_END_ADDRESS);
+	if (begin >= end)
+		return;
 
 	/* xen has big range in reserved near end of ram, skip it at first.*/
-	addr = memblock_find_in_range(ISA_END_ADDRESS, end, PMD_SIZE, PMD_SIZE);
+	addr = memblock_find_in_range(begin, end, PMD_SIZE, PMD_SIZE);
 	real_end = addr + PMD_SIZE;
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
 	step_size = PMD_SIZE;
-	max_pfn_mapped = 0; /* will get exact value next */
-	min_pfn_mapped = real_end >> PAGE_SHIFT;
+	local_max_pfn_mapped = begin >> PAGE_SHIFT;
+	local_min_pfn_mapped = real_end >> PAGE_SHIFT;
 	last_start = start = real_end;
-	while (last_start > ISA_END_ADDRESS) {
+	while (last_start > begin) {
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
-			if (start < ISA_END_ADDRESS)
-				start = ISA_END_ADDRESS;
+			if (start < begin)
+				start = begin;
 		} else
-			start = ISA_END_ADDRESS;
+			start = begin;
 		new_mapped_ram_size = init_range_memory_mapping(start,
 							last_start);
+		if ((last_start >> PAGE_SHIFT) > local_max_pfn_mapped)
+			local_max_pfn_mapped = last_start >> PAGE_SHIFT;
+		local_min_pfn_mapped = start >> PAGE_SHIFT;
 		last_start = start;
-		min_pfn_mapped = last_start >> PAGE_SHIFT;
 		/* only increase step_size after big range get mapped */
 		if (new_mapped_ram_size > mapped_ram_size)
 			step_size = get_new_step_size(step_size);
 		mapped_ram_size += new_mapped_ram_size;
 	}
 
-	if (real_end < end)
+	if (real_end < end) {
 		init_range_memory_mapping(real_end, end);
+		if ((end >> PAGE_SHIFT) > local_max_pfn_mapped)
+			local_max_pfn_mapped = end >> PAGE_SHIFT;
+	}
 
+	if (is_low) {
+		low_min_pfn_mapped = local_min_pfn_mapped;
+		low_max_pfn_mapped = local_max_pfn_mapped;
+	}
+}
+
+#ifndef CONFIG_NUMA
+void __init early_initmem_init(void)
+{
 #ifdef CONFIG_X86_64
-	if (max_pfn > max_low_pfn) {
-		/* can we preseve max_low_pfn ?*/
+	init_mem_mapping(0, max_pfn << PAGE_SHIFT);
+	if (max_pfn > max_low_pfn)
 		max_low_pfn = max_pfn;
-	}
 #else
+	init_mem_mapping(0, max_low_pfn << PAGE_SHIFT);
 	early_ioremap_page_table_range_init();
 #endif
 
@@ -464,11 +489,6 @@ void __init init_mem_mapping(void)
 
 	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
 }
-
-#ifndef CONFIG_NUMA
-void __init early_initmem_init(void)
-{
-}
 #endif
 
 /*
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index c2d4653..d3eb0c9 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -17,8 +17,10 @@
 #include <asm/dma.h>
 #include <asm/acpi.h>
 #include <asm/amd_nb.h>
+#include <asm/tlbflush.h>
 
 #include "numa_internal.h"
+#include "mm_internal.h"
 
 int __initdata numa_off;
 nodemask_t numa_nodes_parsed __initdata;
@@ -668,9 +670,31 @@ static void __init early_x86_numa_init(void)
 	numa_init(dummy_numa_init);
 }
 
+#ifdef CONFIG_X86_64
+static void __init early_x86_numa_init_mapping(void)
+{
+	init_mem_mapping(0, max_pfn << PAGE_SHIFT);
+	if (max_pfn > max_low_pfn)
+		max_low_pfn = max_pfn;
+}
+#else
+static void __init early_x86_numa_init_mapping(void)
+{
+	init_mem_mapping(0, max_low_pfn << PAGE_SHIFT);
+	early_ioremap_page_table_range_init();
+}
+#endif
+
 void __init early_initmem_init(void)
 {
 	early_x86_numa_init();
+
+	early_x86_numa_init_mapping();
+
+	load_cr3(swapper_pg_dir);
+	__flush_tlb_all();
+
+	early_memtest(0, max_pfn_mapped<<PAGE_SHIFT);
 }
 
 void __init x86_numa_init(void)
-- 
1.8.1.4


  parent reply	other threads:[~2013-04-12  0:57 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-04-12  0:55 [PATCH v4 00/22] x86, ACPI, numa: Parse numa info early Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 01/22] x86: Change get_ramdisk_image() to global Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 02/22] x86, microcode: Use common get_ramdisk_image() Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 03/22] x86, ACPI, mm: Kill max_low_pfn_mapped Yinghai Lu
2013-06-05  8:36   ` Tang Chen
2013-04-12  0:55 ` [PATCH v4 04/22] x86, ACPI: Search buffer above 4G in second try for acpi override tables Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 05/22] x86, ACPI: Increase override tables number limit Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 06/22] x86, ACPI: Split acpi_initrd_override to find/copy two functions Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 07/22] x86, ACPI: Store override acpi tables phys addr in cpio files info array Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 08/22] x86, ACPI: Make acpi_initrd_override_find work with 32bit flat mode Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 09/22] x86, ACPI: Find acpi tables in initrd early from head_32.S/head64.c Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 10/22] x86, mm, numa: Move two functions calling on successful path later Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 11/22] x86, mm, numa: Call numa_meminfo_cover_memory() checking early Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 12/22] x86, mm, numa: Move node_map_pfn alignment() to x86 Yinghai Lu
2013-04-12  0:55 ` [PATCH v4 13/22] x86, mm, numa: Use numa_meminfo to check node_map_pfn alignment Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 14/22] x86, mm, numa: Set memblock nid later Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 15/22] x86, mm, numa: Move node_possible_map setting later Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 16/22] x86, mm, numa: Move emulation handling down Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 17/22] x86, ACPI, numa, ia64: split SLIT handling out Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 18/22] x86, mm, numa: Add early_initmem_init() stub Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 19/22] x86, mm: Parse numa info early Yinghai Lu
2013-04-12  0:56 ` [PATCH v4 20/22] x86, mm: Add comments for step_size shift Yinghai Lu
2013-04-12  0:56 ` Yinghai Lu [this message]
2013-04-12  0:56 ` [PATCH v4 22/22] x86, mm, numa: Put pagetable on local node ram for 64bit Yinghai Lu
2013-04-26  8:58 ` [PATCH v4 00/22] x86, ACPI, numa: Parse numa info early Tang Chen
2013-04-30  7:21 ` Tang Chen
2013-05-06  9:49   ` Tang Chen
2013-05-09  8:54   ` Tang Chen
2013-05-09 18:24     ` Yinghai Lu
2013-05-13  2:59       ` Tang Chen
2013-05-14  9:06         ` Tang Chen
2013-05-22  5:14       ` Tang Chen
2013-05-22  5:18         ` H. Peter Anvin
2013-06-03  6:01           ` Tang Chen
  -- strict thread matches above, loose matches on Subject: below --
2013-04-12  1:05 [PATCH v4 21/22] x86, mm: Make init_mem_mapping be able to be called several times Konrad Wilk
2013-04-12  2:04 ` Yinghai Lu
2013-04-12  2:20   ` H. Peter Anvin

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=1365728168-32067-22-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=penberg@kernel.org \
    --cc=tangchen@cn.fujitsu.com \
    --cc=tglx@linutronix.de \
    --cc=tj@kernel.org \
    --cc=trenn@suse.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox