From e7e8de5918dd6a07cbddae559600d7765ad6a56e Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Tue, 21 Jan 2014 15:49:26 -0800 Subject: memblock: make memblock_set_node() support different memblock_type [sfr@canb.auug.org.au: fix powerpc build] Signed-off-by: Tang Chen Reviewed-by: Zhang Yanfei Cc: "H. Peter Anvin" Cc: "Rafael J . Wysocki" Cc: Chen Tang Cc: Gong Chen Cc: Ingo Molnar Cc: Jiang Liu Cc: Johannes Weiner Cc: Lai Jiangshan Cc: Larry Woodman Cc: Len Brown Cc: Liu Jiang Cc: Mel Gorman Cc: Michal Nazarewicz Cc: Minchan Kim Cc: Prarit Bhargava Cc: Rik van Riel Cc: Taku Izumi Cc: Tejun Heo Cc: Thomas Gleixner Cc: Thomas Renninger Cc: Toshi Kani Cc: Vasilis Liaskovitis Cc: Wanpeng Li Cc: Wen Congyang Cc: Yasuaki Ishimatsu Cc: Yinghai Lu Signed-off-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/init_32.c | 2 +- arch/x86/mm/init_64.c | 2 +- arch/x86/mm/numa.c | 6 ++++-- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 5bdc5430597..e39504878ae 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -665,7 +665,7 @@ void __init initmem_init(void) high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif - memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0); sparse_memory_present_with_active_regions(0); #ifdef CONFIG_FLATMEM diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 104d56a9245..f35c66c5959 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -643,7 +643,7 @@ kernel_physical_mapping_init(unsigned long start, #ifndef CONFIG_NUMA void __init initmem_init(void) { - memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0); } #endif diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index c85da7bb6b6..82e079a0d36 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -491,7 +491,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) for (i = 0; i < mi->nr_blks; i++) { struct numa_memblk *mb = &mi->blk[i]; - memblock_set_node(mb->start, mb->end - mb->start, mb->nid); + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.memory, mb->nid); } /* @@ -565,7 +566,8 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_possible_map); nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES)); + WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, + MAX_NUMNODES)); numa_reset_distance(); ret = init_func(); -- cgit v1.2.3-70-g09d2 From 05d1d8cb1c7c25b7c7197817b3418524ace61372 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Tue, 21 Jan 2014 15:49:29 -0800 Subject: acpi, numa, mem_hotplug: mark hotpluggable memory in memblock When parsing SRAT, we know that which memory area is hotpluggable. So we invoke function memblock_mark_hotplug() introduced by previous patch to mark hotpluggable memory in memblock. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Tang Chen Reviewed-by: Zhang Yanfei Cc: "H. Peter Anvin" Cc: "Rafael J . Wysocki" Cc: Chen Tang Cc: Gong Chen Cc: Ingo Molnar Cc: Jiang Liu Cc: Johannes Weiner Cc: Lai Jiangshan Cc: Larry Woodman Cc: Len Brown Cc: Liu Jiang Cc: Mel Gorman Cc: Michal Nazarewicz Cc: Minchan Kim Cc: Prarit Bhargava Cc: Rik van Riel Cc: Taku Izumi Cc: Tejun Heo Cc: Thomas Gleixner Cc: Thomas Renninger Cc: Toshi Kani Cc: Vasilis Liaskovitis Cc: Wanpeng Li Cc: Wen Congyang Cc: Yasuaki Ishimatsu Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/numa.c | 2 ++ arch/x86/mm/srat.c | 5 +++++ 2 files changed, 7 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 82e079a0d36..78d6a9e5830 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -568,6 +568,8 @@ static int __init numa_init(int (*init_func)(void)) memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, MAX_NUMNODES)); + /* In case that parsing SRAT failed. */ + WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); numa_reset_distance(); ret = init_func(); diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 266ca912f62..1a25187e151 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -181,6 +181,11 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) (unsigned long long) start, (unsigned long long) end - 1, hotpluggable ? " hotplug" : ""); + /* Mark hotplug range in memblock. */ + if (hotpluggable && memblock_mark_hotplug(start, ma->length)) + pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", + (unsigned long long)start, (unsigned long long)end - 1); + return 0; out_err_bad_srat: bad_srat(); -- cgit v1.2.3-70-g09d2 From a0acda917284183f9b71e2d08b0aa0aea722b321 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Tue, 21 Jan 2014 15:49:32 -0800 Subject: acpi, numa, mem_hotplug: mark all nodes the kernel resides un-hotpluggable At very early time, the kernel have to use some memory such as loading the kernel image. We cannot prevent this anyway. So any node the kernel resides in should be un-hotpluggable. Signed-off-by: Tang Chen Reviewed-by: Zhang Yanfei Cc: "H. Peter Anvin" Cc: "Rafael J . Wysocki" Cc: Chen Tang Cc: Gong Chen Cc: Ingo Molnar Cc: Jiang Liu Cc: Johannes Weiner Cc: Lai Jiangshan Cc: Larry Woodman Cc: Len Brown Cc: Liu Jiang Cc: Mel Gorman Cc: Michal Nazarewicz Cc: Minchan Kim Cc: Prarit Bhargava Cc: Rik van Riel Cc: Taku Izumi Cc: Tejun Heo Cc: Thomas Gleixner Cc: Thomas Renninger Cc: Toshi Kani Cc: Vasilis Liaskovitis Cc: Wanpeng Li Cc: Wen Congyang Cc: Yasuaki Ishimatsu Cc: Yinghai Lu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/numa.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 78d6a9e5830..81b2750f366 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,6 +493,14 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) struct numa_memblk *mb = &mi->blk[i]; memblock_set_node(mb->start, mb->end - mb->start, &memblock.memory, mb->nid); + + /* + * At this time, all memory regions reserved by memblock are + * used by the kernel. Set the nid in memblock.reserved will + * mark out all the nodes the kernel resides in. + */ + memblock_set_node(mb->start, mb->end - mb->start, + &memblock.reserved, mb->nid); } /* @@ -554,6 +562,30 @@ static void __init numa_init_array(void) } } +static void __init numa_clear_kernel_node_hotplug(void) +{ + int i, nid; + nodemask_t numa_kernel_nodes; + unsigned long start, end; + struct memblock_type *type = &memblock.reserved; + + /* Mark all kernel nodes. */ + for (i = 0; i < type->cnt; i++) + node_set(type->regions[i].nid, numa_kernel_nodes); + + /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ + for (i = 0; i < numa_meminfo.nr_blks; i++) { + nid = numa_meminfo.blk[i].nid; + if (!node_isset(nid, numa_kernel_nodes)) + continue; + + start = numa_meminfo.blk[i].start; + end = numa_meminfo.blk[i].end; + + memblock_clear_hotplug(start, end - start); + } +} + static int __init numa_init(int (*init_func)(void)) { int i; @@ -568,6 +600,8 @@ static int __init numa_init(int (*init_func)(void)) memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, MAX_NUMNODES)); + WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, + MAX_NUMNODES)); /* In case that parsing SRAT failed. */ WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); numa_reset_distance(); @@ -605,6 +639,16 @@ static int __init numa_init(int (*init_func)(void)) numa_clear_node(i); } numa_init_array(); + + /* + * At very early time, the kernel have to use some memory such as + * loading the kernel image. We cannot prevent this anyway. So any + * node the kernel resides in should be un-hotpluggable. + * + * And when we come here, numa_init() won't fail. + */ + numa_clear_kernel_node_hotplug(); + return 0; } -- cgit v1.2.3-70-g09d2 From 5b6e529521d35e1bcaa0fe43456d1bbb335cae5d Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Tue, 21 Jan 2014 15:50:03 -0800 Subject: x86: memblock: set current limit to max low memory address The memblock current limit value is used to limit early boot memory allocations below max low memory address by default, as the kernel can access only to the low memory. Hence, set memblock current limit value to the max mapped low memory address instead of max mapped memory address. Signed-off-by: Santosh Shilimkar Cc: Tejun Heo Cc: Grygorii Strashko Cc: Yinghai Lu Cc: "Rafael J. Wysocki" Cc: Arnd Bergmann Cc: Christoph Lameter Cc: Greg Kroah-Hartman Cc: H. Peter Anvin Cc: Johannes Weiner Cc: KAMEZAWA Hiroyuki Cc: Konrad Rzeszutek Wilk Cc: Michal Hocko Cc: Paul Walmsley Cc: Pavel Machek Cc: Russell King Cc: Tony Lindgren Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/page_types.h | 4 ++-- arch/x86/kernel/setup.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index f97fbe3abb6..2f59cce3b38 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -51,9 +51,9 @@ extern int devmem_is_allowed(unsigned long pagenr); extern unsigned long max_low_pfn_mapped; extern unsigned long max_pfn_mapped; -static inline phys_addr_t get_max_mapped(void) +static inline phys_addr_t get_max_low_mapped(void) { - return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT; + return (phys_addr_t)max_low_pfn_mapped << PAGE_SHIFT; } bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 06853e67035..c9675594d7c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); - memblock_set_current_limit(get_max_mapped()); + memblock_set_current_limit(get_max_low_mapped()); dma_contiguous_reserve(0); /* -- cgit v1.2.3-70-g09d2 From 9a28f9dc8d10b619af9a37b1e27c41ada5415629 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Tue, 21 Jan 2014 15:50:53 -0800 Subject: x86/mm: memblock: switch to use NUMA_NO_NODE Update X86 code to use NUMA_NO_NODE instead of MAX_NUMNODES while calling memblock APIs, because memblock API will be changed to use NUMA_NO_NODE and will produce warning during boot otherwise. See: https://lkml.org/lkml/2013/12/9/898 Signed-off-by: Grygorii Strashko Cc: Santosh Shilimkar Cc: Stephen Rothwell Cc: Tejun Heo Cc: Yinghai Lu Acked-by: David Rientjes Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/check.c | 2 +- arch/x86/kernel/e820.c | 2 +- arch/x86/mm/memtest.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index e2dbcb7dabd..83a7995625a 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -91,7 +91,7 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, &start, &end, NULL) { start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), PAGE_SIZE, corruption_check_size); end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 174da5fc5a7..988c00a1f60 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1120,7 +1120,7 @@ void __init memblock_find_dma_reserve(void) nr_pages += end_pfn - start_pfn; } - for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) { + for_each_free_mem_range(u, NUMA_NO_NODE, &start, &end, NULL) { start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); if (start_pfn < end_pfn) diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index 8dabbed409e..1e9da795767 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -74,7 +74,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end) u64 i; phys_addr_t this_start, this_end; - for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) { + for_each_free_mem_range(i, NUMA_NO_NODE, &this_start, &this_end, NULL) { this_start = clamp_t(phys_addr_t, this_start, start, end); this_end = clamp_t(phys_addr_t, this_end, start, end); if (this_start < this_end) { -- cgit v1.2.3-70-g09d2