From 4b239f458c229de044d6905c2b0f9fe16ed9e01e Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 17 Dec 2010 16:58:28 -0800 Subject: x86-64, mm: Put early page table high While dubug kdump, found current kernel will have problem with crashkernel=512M. It turns out that initial mapping is to 512M, and later initial mapping to 4G (acutally is 2040M in my platform), will put page table near 512M. then initial mapping to 128g will be near 2g. before this patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x1fffc000-0x1fffffff] [ 0.000000] memblock_x86_reserve_range: [0x1fffc000-0x1fffdfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x7bc01000-0x7bc83fff] [ 0.000000] memblock_x86_reserve_range: [0x7bc01000-0x7bc7efff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] crashkernel reservation failed - No suitable area found. after patch: [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x7f74c000-0x7f74ffff] [ 0.000000] memblock_x86_reserve_range: [0x7f74c000-0x7f74dfff] PGTABLE [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000207fffffff] [ 0.000000] 0100000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x207ff7d000-0x207fffffff] [ 0.000000] memblock_x86_reserve_range: [0x207ff7d000-0x207fffafff] PGTABLE [ 0.000000] RAMDISK: 7bc84000 - 7f745000 [ 0.000000] memblock_x86_reserve_range: [0x17000000-0x36ffffff] CRASH KERNEL [ 0.000000] Reserving 512MB of memory at 368MB for crashkernel (System RAM: 133120MB) It means with the patch, page table for [0, 2g) will need 2g, instead of under 512M, page table for [4g, 128g) will be near 128g, instead of under 2g. That would good, if we have lots of memory above 4g, like 1024g, or 2048g or 16T, will not put related page table under 2g. that would be have chance to fill the under 2g if 1G or 2M page is not used. the code change will use add map_low_page() and update unmap_low_page() for 64bit, and use them to get access the corresponding high memory for page table setting. Signed-off-by: Yinghai Lu LKML-Reference: <4D0C0734.7060900@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/mm/init.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'arch/x86/mm/init.c') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c0e28a13de7d..5863950ebe0c 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -33,7 +33,7 @@ int direct_gbpages static void __init find_early_table_space(unsigned long end, int use_pse, int use_gbpages) { - unsigned long puds, pmds, ptes, tables, start; + unsigned long puds, pmds, ptes, tables, start = 0, good_end = end; phys_addr_t base; puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; @@ -73,12 +73,9 @@ static void __init find_early_table_space(unsigned long end, int use_pse, * need roughly 0.5KB per GB. */ #ifdef CONFIG_X86_32 - start = 0x7000; -#else - start = 0x8000; + good_end = max_pfn_mapped << PAGE_SHIFT; #endif - base = memblock_find_in_range(start, max_pfn_mapped< Date: Mon, 27 Dec 2010 16:48:17 -0800 Subject: x86-64, numa: Put pgtable to local node memory Introduce init_memory_mapping_high(), and use it with 64bit. It will go with every memory segment above 4g to create page table to the memory range itself. before this patch all page tables was on one node. with this patch, one RED-PEN is killed debug out for 8 sockets system after patch [ 0.000000] initial memory mapped : 0 - 20000000 [ 0.000000] init_memory_mapping: [0x00000000000000-0x0000007f74ffff] [ 0.000000] 0000000000 - 007f600000 page 2M [ 0.000000] 007f600000 - 007f750000 page 4k [ 0.000000] kernel direct mapping tables up to 7f750000 @ [0x7f74c000-0x7f74ffff] [ 0.000000] RAMDISK: 7bc84000 - 7f745000 .... [ 0.000000] Adding active range (0, 0x10, 0x95) 0 entries of 3200 used [ 0.000000] Adding active range (0, 0x100, 0x7f750) 1 entries of 3200 used [ 0.000000] Adding active range (0, 0x100000, 0x1080000) 2 entries of 3200 used [ 0.000000] Adding active range (1, 0x1080000, 0x2080000) 3 entries of 3200 used [ 0.000000] Adding active range (2, 0x2080000, 0x3080000) 4 entries of 3200 used [ 0.000000] Adding active range (3, 0x3080000, 0x4080000) 5 entries of 3200 used [ 0.000000] Adding active range (4, 0x4080000, 0x5080000) 6 entries of 3200 used [ 0.000000] Adding active range (5, 0x5080000, 0x6080000) 7 entries of 3200 used [ 0.000000] Adding active range (6, 0x6080000, 0x7080000) 8 entries of 3200 used [ 0.000000] Adding active range (7, 0x7080000, 0x8080000) 9 entries of 3200 used [ 0.000000] init_memory_mapping: [0x00000100000000-0x0000107fffffff] [ 0.000000] 0100000000 - 1080000000 page 2M [ 0.000000] kernel direct mapping tables up to 1080000000 @ [0x107ffbd000-0x107fffffff] [ 0.000000] memblock_x86_reserve_range: [0x107ffc2000-0x107fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00001080000000-0x0000207fffffff] [ 0.000000] 1080000000 - 2080000000 page 2M [ 0.000000] kernel direct mapping tables up to 2080000000 @ [0x207ff7d000-0x207fffffff] [ 0.000000] memblock_x86_reserve_range: [0x207ffc0000-0x207fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00002080000000-0x0000307fffffff] [ 0.000000] 2080000000 - 3080000000 page 2M [ 0.000000] kernel direct mapping tables up to 3080000000 @ [0x307ff3d000-0x307fffffff] [ 0.000000] memblock_x86_reserve_range: [0x307ffc0000-0x307fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00003080000000-0x0000407fffffff] [ 0.000000] 3080000000 - 4080000000 page 2M [ 0.000000] kernel direct mapping tables up to 4080000000 @ [0x407fefd000-0x407fffffff] [ 0.000000] memblock_x86_reserve_range: [0x407ffc0000-0x407fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00004080000000-0x0000507fffffff] [ 0.000000] 4080000000 - 5080000000 page 2M [ 0.000000] kernel direct mapping tables up to 5080000000 @ [0x507febd000-0x507fffffff] [ 0.000000] memblock_x86_reserve_range: [0x507ffc0000-0x507fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00005080000000-0x0000607fffffff] [ 0.000000] 5080000000 - 6080000000 page 2M [ 0.000000] kernel direct mapping tables up to 6080000000 @ [0x607fe7d000-0x607fffffff] [ 0.000000] memblock_x86_reserve_range: [0x607ffc0000-0x607fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00006080000000-0x0000707fffffff] [ 0.000000] 6080000000 - 7080000000 page 2M [ 0.000000] kernel direct mapping tables up to 7080000000 @ [0x707fe3d000-0x707fffffff] [ 0.000000] memblock_x86_reserve_range: [0x707ffc0000-0x707fffffff] PGTABLE [ 0.000000] init_memory_mapping: [0x00007080000000-0x0000807fffffff] [ 0.000000] 7080000000 - 8080000000 page 2M [ 0.000000] kernel direct mapping tables up to 8080000000 @ [0x807fdfc000-0x807fffffff] [ 0.000000] memblock_x86_reserve_range: [0x807ffbf000-0x807fffffff] PGTABLE [ 0.000000] Initmem setup node 0 [0000000000000000-000000107fffffff] [ 0.000000] NODE_DATA [0x0000107ffbd000-0x0000107ffc1fff] [ 0.000000] Initmem setup node 1 [0000001080000000-000000207fffffff] [ 0.000000] NODE_DATA [0x0000207ffbb000-0x0000207ffbffff] [ 0.000000] Initmem setup node 2 [0000002080000000-000000307fffffff] [ 0.000000] NODE_DATA [0x0000307ffbb000-0x0000307ffbffff] [ 0.000000] Initmem setup node 3 [0000003080000000-000000407fffffff] [ 0.000000] NODE_DATA [0x0000407ffbb000-0x0000407ffbffff] [ 0.000000] Initmem setup node 4 [0000004080000000-000000507fffffff] [ 0.000000] NODE_DATA [0x0000507ffbb000-0x0000507ffbffff] [ 0.000000] Initmem setup node 5 [0000005080000000-000000607fffffff] [ 0.000000] NODE_DATA [0x0000607ffbb000-0x0000607ffbffff] [ 0.000000] Initmem setup node 6 [0000006080000000-000000707fffffff] [ 0.000000] NODE_DATA [0x0000707ffbb000-0x0000707ffbffff] [ 0.000000] Initmem setup node 7 [0000007080000000-000000807fffffff] [ 0.000000] NODE_DATA [0x0000807ffba000-0x0000807ffbefff] Signed-off-by: Yinghai Lu LKML-Reference: <4D1933D1.9020609@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/mm/init.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) (limited to 'arch/x86/mm/init.c') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 5863950ebe0c..fa6fe756d912 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -65,16 +65,10 @@ static void __init find_early_table_space(unsigned long end, int use_pse, #ifdef CONFIG_X86_32 /* for fixmap */ tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE); -#endif - /* - * RED-PEN putting page tables only on node 0 could - * cause a hotspot and fill up ZONE_DMA. The page tables - * need roughly 0.5KB per GB. - */ -#ifdef CONFIG_X86_32 good_end = max_pfn_mapped << PAGE_SHIFT; #endif + base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); if (base == MEMBLOCK_ERROR) panic("Cannot find space for the kernel page tables"); -- cgit v1.2.3 From f005fe12b90c5b9fe180a09209a893e09affa8aa Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 27 Dec 2010 16:48:32 -0800 Subject: x86-64: Move out cleanup higmap [_brk_end, _end) out of init_memory_mapping() It is not related to init_memory_mapping(), and init_memory_mapping() is getting more bigger. So make it as seperated function and call it from reserve_brk() and that is point when _brk_end is concluded. Signed-off-by: Yinghai Lu LKML-Reference: <4D1933E0.7090305@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/mm/init.c | 19 ------------------- 1 file changed, 19 deletions(-) (limited to 'arch/x86/mm/init.c') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index fa6fe756d912..35ee75d9061a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -270,25 +270,6 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, load_cr3(swapper_pg_dir); #endif -#ifdef CONFIG_X86_64 - if (!after_bootmem && !start) { - pud_t *pud; - pmd_t *pmd; - - mmu_cr4_features = read_cr4(); - - /* - * _brk_end cannot change anymore, but it and _end may be - * located on different 2M pages. cleanup_highmap(), however, - * can only consider _end when it runs, so destroy any - * mappings beyond _brk_end here. - */ - pud = pud_offset(pgd_offset_k(_brk_end), _brk_end); - pmd = pmd_offset(pud, _brk_end - 1); - while (++pmd <= pmd_offset(pud, (unsigned long)_end - 1)) - pmd_clear(pmd); - } -#endif __flush_tlb_all(); if (!after_bootmem && e820_table_end > e820_table_start) -- cgit v1.2.3 From d1b19426b04787e48f2689923e28d37b488969b0 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Feb 2011 14:46:24 +0100 Subject: x86: Rename e820_table_* to pgt_buf_* e820_table_{start|end|top}, which are used to buffer page table allocation during early boot, are now derived from memblock and don't have much to do with e820. Change the names so that they reflect what they're used for. This patch doesn't introduce any behavior change. -v2: Ingo found that earlier patch "x86: Use early pre-allocated page table buffer top-down" caused crash on 32bit and needed to be dropped. This patch was updated to reflect the change. -tj: Updated commit description. Signed-off-by: Yinghai Lu Signed-off-by: Tejun Heo --- arch/x86/mm/init.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'arch/x86/mm/init.c') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index b8054e087ead..286d289b039b 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -18,9 +18,9 @@ DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -unsigned long __initdata e820_table_start; -unsigned long __meminitdata e820_table_end; -unsigned long __meminitdata e820_table_top; +unsigned long __initdata pgt_buf_start; +unsigned long __meminitdata pgt_buf_end; +unsigned long __meminitdata pgt_buf_top; int after_bootmem; @@ -73,12 +73,12 @@ static void __init find_early_table_space(unsigned long end, int use_pse, if (base == MEMBLOCK_ERROR) panic("Cannot find space for the kernel page tables"); - e820_table_start = base >> PAGE_SHIFT; - e820_table_end = e820_table_start; - e820_table_top = e820_table_start + (tables >> PAGE_SHIFT); + pgt_buf_start = base >> PAGE_SHIFT; + pgt_buf_end = pgt_buf_start; + pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT); printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n", - end, e820_table_start << PAGE_SHIFT, e820_table_top << PAGE_SHIFT); + end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT); } struct map_range { @@ -272,9 +272,9 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, __flush_tlb_all(); - if (!after_bootmem && e820_table_end > e820_table_start) - memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT, - e820_table_end << PAGE_SHIFT, "PGTABLE"); + if (!after_bootmem && pgt_buf_end > pgt_buf_start) + memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT, + pgt_buf_end << PAGE_SHIFT, "PGTABLE"); if (!after_bootmem) early_memtest(start, end); -- cgit v1.2.3