From 27811d8cabe56e0c3622251b049086f49face4ff Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:07 -0800 Subject: x86: Move range related operation to one file We have almost the same code for mtrr cleanup and amd_bus checkup, and this code will also be used in replacing bootmem with early_res, so try to move them together and reuse it from different parts. Also rename update_range to subtract_range as that is what the function is actually doing. -v2: update comments as Christoph requested Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-4-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- include/linux/range.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/range.h (limited to 'include') diff --git a/include/linux/range.h b/include/linux/range.h new file mode 100644 index 000000000000..0789f1412e1f --- /dev/null +++ b/include/linux/range.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_RANGE_H +#define _LINUX_RANGE_H + +struct range { + u64 start; + u64 end; +}; + +int add_range(struct range *range, int az, int nr_range, + u64 start, u64 end); + + +int add_range_with_merge(struct range *range, int az, int nr_range, + u64 start, u64 end); + +void subtract_range(struct range *range, int az, u64 start, u64 end); + +int clean_sort_range(struct range *range, int az); + +void sort_range(struct range *range, int nr_range); + +#endif -- cgit v1.2.2 From 9ad3f2c7c69659c343843393944d739fec1f2e73 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:11 -0800 Subject: x86/pci: Add cap_resource() Prepare for 32bit pci root bus -v2: hpa said we should compare with (resource_size_t)~0 -v3: according to Linus to use MAX_RESOURCE instead. also need need to put related patches together -v4: according to Andrew, use min in cap_resource() Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-8-git-send-email-yinghai@kernel.org> Acked-by: Jesse Barnes Signed-off-by: H. Peter Anvin --- include/linux/range.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/range.h b/include/linux/range.h index 0789f1412e1f..bd184a5db791 100644 --- a/include/linux/range.h +++ b/include/linux/range.h @@ -19,4 +19,12 @@ int clean_sort_range(struct range *range, int az); void sort_range(struct range *range, int nr_range); +#define MAX_RESOURCE ((resource_size_t)~0) +static inline resource_size_t cap_resource(u64 val) +{ + if (val > MAX_RESOURCE) + return MAX_RESOURCE; + + return val; +} #endif -- cgit v1.2.2 From 08677214e318297f228237be0042aac754f48f1d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:20 -0800 Subject: x86: Make 64 bit use early_res instead of bootmem before slab Finally we can use early_res to replace bootmem for x86_64 now. Still can use CONFIG_NO_BOOTMEM to enable it or not. -v2: fix 32bit compiling about MAX_DMA32_PFN -v3: folded bug fix from LKML message below Signed-off-by: Yinghai Lu LKML-Reference: <4B747239.4070907@kernel.org> Signed-off-by: H. Peter Anvin --- include/linux/bootmem.h | 7 +++++++ include/linux/mm.h | 5 +++++ include/linux/mmzone.h | 2 ++ 3 files changed, 14 insertions(+) (limited to 'include') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b10ec49ee2dd..266ab9291232 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -23,6 +23,7 @@ extern unsigned long max_pfn; extern unsigned long saved_max_pfn; #endif +#ifndef CONFIG_NO_BOOTMEM /* * node_bootmem_map is a map pointer - the bits represent all physical * memory pages (including holes) on the node. @@ -37,6 +38,7 @@ typedef struct bootmem_data { } bootmem_data_t; extern bootmem_data_t bootmem_node_data[]; +#endif extern unsigned long bootmem_bootmap_pages(unsigned long); @@ -46,6 +48,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat, unsigned long endpfn); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); +unsigned long free_all_memory_core_early(int nodeid); extern unsigned long free_all_bootmem_node(pg_data_t *pgdat); extern unsigned long free_all_bootmem(void); @@ -84,6 +87,10 @@ extern void *__alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal); +void *__alloc_bootmem_node_high(pg_data_t *pgdat, + unsigned long size, + unsigned long align, + unsigned long goal); extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, unsigned long align, diff --git a/include/linux/mm.h b/include/linux/mm.h index 8b2fa8593c61..f2c5b3cee8a1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -12,6 +12,7 @@ #include #include #include +#include struct mempolicy; struct anon_vma; @@ -1049,6 +1050,10 @@ extern void get_pfn_range_for_nid(unsigned int nid, extern unsigned long find_min_pfn_with_active_regions(void); extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); +int add_from_early_node_map(struct range *range, int az, + int nr_range, int nid); +void *__alloc_memory_core_early(int nodeid, u64 size, u64 align, + u64 goal, u64 limit); typedef int (*work_fn_t)(unsigned long, unsigned long, void *); extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data); extern void sparse_memory_present_with_active_regions(int nid); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 30fe668c2542..eae8387b6007 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -620,7 +620,9 @@ typedef struct pglist_data { struct page_cgroup *node_page_cgroup; #endif #endif +#ifndef CONFIG_NO_BOOTMEM struct bootmem_data *bdata; +#endif #ifdef CONFIG_MEMORY_HOTPLUG /* * Must be held any time you expect node_start_pfn, node_present_pages -- cgit v1.2.2 From 9bdac914240759457175ac0d6529a37d2820bc4d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:22 -0800 Subject: sparsemem: Put mem map for one node together. Add vmemmap_alloc_block_buf for mem map only. It will fallback to the old way if it cannot get a block that big. Before this patch, when a node have 128g ram installed, memmap are split into two parts or more. [ 0.000000] [ffffea0000000000-ffffea003fffffff] PMD -> [ffff880100600000-ffff88013e9fffff] on node 1 [ 0.000000] [ffffea0040000000-ffffea006fffffff] PMD -> [ffff88013ec00000-ffff88016ebfffff] on node 1 [ 0.000000] [ffffea0070000000-ffffea007fffffff] PMD -> [ffff882000600000-ffff8820105fffff] on node 0 [ 0.000000] [ffffea0080000000-ffffea00bfffffff] PMD -> [ffff882010800000-ffff8820507fffff] on node 0 [ 0.000000] [ffffea00c0000000-ffffea00dfffffff] PMD -> [ffff882050a00000-ffff8820709fffff] on node 0 [ 0.000000] [ffffea00e0000000-ffffea00ffffffff] PMD -> [ffff884000600000-ffff8840205fffff] on node 2 [ 0.000000] [ffffea0100000000-ffffea013fffffff] PMD -> [ffff884020800000-ffff8840607fffff] on node 2 [ 0.000000] [ffffea0140000000-ffffea014fffffff] PMD -> [ffff884060a00000-ffff8840709fffff] on node 2 [ 0.000000] [ffffea0150000000-ffffea017fffffff] PMD -> [ffff886000600000-ffff8860305fffff] on node 3 [ 0.000000] [ffffea0180000000-ffffea01bfffffff] PMD -> [ffff886030800000-ffff8860707fffff] on node 3 [ 0.000000] [ffffea01c0000000-ffffea01ffffffff] PMD -> [ffff888000600000-ffff8880405fffff] on node 4 [ 0.000000] [ffffea0200000000-ffffea022fffffff] PMD -> [ffff888040800000-ffff8880707fffff] on node 4 [ 0.000000] [ffffea0230000000-ffffea023fffffff] PMD -> [ffff88a000600000-ffff88a0105fffff] on node 5 [ 0.000000] [ffffea0240000000-ffffea027fffffff] PMD -> [ffff88a010800000-ffff88a0507fffff] on node 5 [ 0.000000] [ffffea0280000000-ffffea029fffffff] PMD -> [ffff88a050a00000-ffff88a0709fffff] on node 5 [ 0.000000] [ffffea02a0000000-ffffea02bfffffff] PMD -> [ffff88c000600000-ffff88c0205fffff] on node 6 [ 0.000000] [ffffea02c0000000-ffffea02ffffffff] PMD -> [ffff88c020800000-ffff88c0607fffff] on node 6 [ 0.000000] [ffffea0300000000-ffffea030fffffff] PMD -> [ffff88c060a00000-ffff88c0709fffff] on node 6 [ 0.000000] [ffffea0310000000-ffffea033fffffff] PMD -> [ffff88e000600000-ffff88e0305fffff] on node 7 [ 0.000000] [ffffea0340000000-ffffea037fffffff] PMD -> [ffff88e030800000-ffff88e0707fffff] on node 7 after patch will get [ 0.000000] [ffffea0000000000-ffffea006fffffff] PMD -> [ffff880100200000-ffff88016e5fffff] on node 0 [ 0.000000] [ffffea0070000000-ffffea00dfffffff] PMD -> [ffff882000200000-ffff8820701fffff] on node 1 [ 0.000000] [ffffea00e0000000-ffffea014fffffff] PMD -> [ffff884000200000-ffff8840701fffff] on node 2 [ 0.000000] [ffffea0150000000-ffffea01bfffffff] PMD -> [ffff886000200000-ffff8860701fffff] on node 3 [ 0.000000] [ffffea01c0000000-ffffea022fffffff] PMD -> [ffff888000200000-ffff8880701fffff] on node 4 [ 0.000000] [ffffea0230000000-ffffea029fffffff] PMD -> [ffff88a000200000-ffff88a0701fffff] on node 5 [ 0.000000] [ffffea02a0000000-ffffea030fffffff] PMD -> [ffff88c000200000-ffff88c0701fffff] on node 6 [ 0.000000] [ffffea0310000000-ffffea037fffffff] PMD -> [ffff88e000200000-ffff88e0701fffff] on node 7 -v2: change buf to vmemmap_buf instead according to Ingo also add CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER according to Ingo -v3: according to Andrew, use sizeof(name) instead of hard coded 15 Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-19-git-send-email-yinghai@kernel.org> Cc: Christoph Lameter Acked-by: Christoph Lameter Signed-off-by: H. Peter Anvin --- include/linux/mm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index f2c5b3cee8a1..f6002e5dc187 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1326,12 +1326,19 @@ extern int randomize_va_space; const char * arch_vma_name(struct vm_area_struct *vma); void print_vma_addr(char *prefix, unsigned long rip); +void sparse_mem_maps_populate_node(struct page **map_map, + unsigned long pnum_begin, + unsigned long pnum_end, + unsigned long map_count, + int nodeid); + struct page *sparse_mem_map_populate(unsigned long pnum, int nid); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); void *vmemmap_alloc_block(unsigned long size, int node); +void *vmemmap_alloc_block_buf(unsigned long size, int node); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); int vmemmap_populate_basepages(struct page *start_page, unsigned long pages, int node); -- cgit v1.2.2 From 9b3be9f99203d9a400e8547f0e80f1d8f8e5738c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:29 -0800 Subject: Move round_up/down to kernel.h ... in preparation of moving early_res to kernel/. Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-26-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- include/linux/kernel.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 328bca609b9b..d45e372fad81 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -44,6 +44,16 @@ extern const char linux_proc_banner[]; #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) +/* + * This looks more complex than it should be. But we need to + * get the type for the ~ right in round_down (it needs to be + * as wide as the result!), and we want to evaluate the macro + * arguments just once each. + */ +#define __round_mask(x, y) ((__typeof__(x))((y)-1)) +#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) +#define round_down(x, y) ((x) & ~__round_mask(x, y)) + #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) #define DIV_ROUND_UP(n,d) (((n) + (d) - 1) / (d)) #define roundup(x, y) ((((x) + ((y) - 1)) / (y)) * (y)) -- cgit v1.2.2 From 580e0ad21d6d6f932461d24b47041e3dd499c23f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 16 Feb 2010 18:40:35 -0800 Subject: core: Move early_res from arch/x86 to kernel/ This makes the range reservation feature available to other architectures. -v2: add get_max_mapped, max_pfn_mapped only defined in x86... to fix PPC compiling -v3: according to hpa, add CONFIG_HAVE_EARLY_RES -v4: fix typo about EARLY_RES in config Signed-off-by: Yinghai Lu LKML-Reference: <4B7B5723.4070009@kernel.org> Signed-off-by: H. Peter Anvin --- include/linux/early_res.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 include/linux/early_res.h (limited to 'include') diff --git a/include/linux/early_res.h b/include/linux/early_res.h new file mode 100644 index 000000000000..50f7663bb8b1 --- /dev/null +++ b/include/linux/early_res.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_EARLY_RES_H +#define _LINUX_EARLY_RES_H +#ifdef __KERNEL__ + +extern void reserve_early(u64 start, u64 end, char *name); +extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); +extern void free_early(u64 start, u64 end); +extern void early_res_to_bootmem(u64 start, u64 end); + +void reserve_early_without_check(u64 start, u64 end, char *name); +u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, + u64 size, u64 align); +u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start, + u64 *sizep, u64 align); +u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align); +u64 get_max_mapped(void); +#include +int get_free_all_memory_range(struct range **rangep, int nodeid); + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_EARLY_RES_H */ -- cgit v1.2.2 From fb90ef93df654f2678933efbbf864adac0ae490e Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 24 Feb 2010 18:36:53 -0800 Subject: early_res: Add free_early_partial() To free partial areas in pcpu_setup... Reported-by: Peter Zijlstra Signed-off-by: Yinghai Lu Cc: Tejun Heo Cc: Christoph Lameter Cc: Stephen Rothwell Cc: Linus Torvalds Cc: Jesse Barnes Cc: Pekka Enberg LKML-Reference: <4B85E245.5030001@kernel.org> Signed-off-by: Ingo Molnar --- include/linux/early_res.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/early_res.h b/include/linux/early_res.h index 50f7663bb8b1..29c09f57a13c 100644 --- a/include/linux/early_res.h +++ b/include/linux/early_res.h @@ -5,6 +5,7 @@ extern void reserve_early(u64 start, u64 end, char *name); extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); extern void free_early(u64 start, u64 end); +void free_early_partial(u64 start, u64 end); extern void early_res_to_bootmem(u64 start, u64 end); void reserve_early_without_check(u64 start, u64 end, char *name); -- cgit v1.2.2