From 595ad9af8584908ea5fb698b836169d05b99f186 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 24 Jan 2013 12:20:09 -0800 Subject: memblock: Add memblock_mem_size() Use it to get mem size under the limit_pfn. to replace local version in x86 reserved_initrd. -v2: remove not needed cast that is pointed out by HPA. Signed-off-by: Yinghai Lu Link: http://lkml.kernel.org/r/1359058816-7615-29-git-send-email-yinghai@kernel.org Signed-off-by: H. Peter Anvin --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/memblock.h') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d452ee191066..f388203db7e8 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -155,6 +155,7 @@ phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr); phys_addr_t memblock_phys_mem_size(void); +phys_addr_t memblock_mem_size(unsigned long limit_pfn); phys_addr_t memblock_start_of_DRAM(void); phys_addr_t memblock_end_of_DRAM(void); void memblock_enforce_memory_limit(phys_addr_t memory_limit); -- cgit v1.2.3 From fb06bc8e5f42f38c011de0e59481f464a82380f6 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:42 -0800 Subject: page_alloc: bootmem limit with movablecore_map Ensure the bootmem will not allocate memory from areas that may be ZONE_MOVABLE. The map info is from movablecore_map boot option. Signed-off-by: Tang Chen Reviewed-by: Wen Congyang Reviewed-by: Lai Jiangshan Tested-by: Lin Feng Cc: Wu Jianguo Cc: Mel Gorman Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/memblock.h') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index f388203db7e8..dfefaf111c0e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,6 +42,7 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; +extern struct movablemem_map movablemem_map; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -- cgit v1.2.3 From f7210e6c4ac795694106c1c5307134d3fc233e88 Mon Sep 17 00:00:00 2001 From: Tang Chen Date: Fri, 22 Feb 2013 16:33:51 -0800 Subject: mm/memblock.c: use CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect movablecore_map in memblock_overlaps_region(). The definition of struct movablecore_map is protected by CONFIG_HAVE_MEMBLOCK_NODE_MAP but its use in memblock_overlaps_region() is not. So add CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect the use of movablecore_map in memblock_overlaps_region(). Signed-off-by: Tang Chen Reported-by: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/memblock.h') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index dfefaf111c0e..3e5ecb2d790e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,7 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -- cgit v1.2.3 From 20e6926dcbafa1b361f1c29d967688be14b6ca4b Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Fri, 1 Mar 2013 14:51:27 -0800 Subject: x86, ACPI, mm: Revert movablemem_map support Tim found: WARNING: at arch/x86/kernel/smpboot.c:324 topology_sane.isra.2+0x6f/0x80() Hardware name: S2600CP sched: CPU #1's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency. smpboot: Booting Node 1, Processors #1 Modules linked in: Pid: 0, comm: swapper/1 Not tainted 3.9.0-0-generic #1 Call Trace: set_cpu_sibling_map+0x279/0x449 start_secondary+0x11d/0x1e5 Don Morris reproduced on a HP z620 workstation, and bisected it to commit e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") It turns out movable_map has some problems, and it breaks several things 1. numa_init is called several times, NOT just for srat. so those nodes_clear(numa_nodes_parsed) memset(&numa_meminfo, 0, sizeof(numa_meminfo)) can not be just removed. Need to consider sequence is: numaq, srat, amd, dummy. and make fall back path working. 2. simply split acpi_numa_init to early_parse_srat. a. that early_parse_srat is NOT called for ia64, so you break ia64. b. for (i = 0; i < MAX_LOCAL_APIC; i++) set_apicid_to_node(i, NUMA_NO_NODE) still left in numa_init. So it will just clear result from early_parse_srat. it should be moved before that.... c. it breaks ACPI_TABLE_OVERIDE...as the acpi table scan is moved early before override from INITRD is settled. 3. that patch TITLE is total misleading, there is NO x86 in the title, but it changes critical x86 code. It caused x86 guys did not pay attention to find the problem early. Those patches really should be routed via tip/x86/mm. 4. after that commit, following range can not use movable ram: a. real_mode code.... well..funny, legacy Node0 [0,1M) could be hot-removed? b. initrd... it will be freed after booting, so it could be on movable... c. crashkernel for kdump...: looks like we can not put kdump kernel above 4G anymore. d. init_mem_mapping: can not put page table high anymore. e. initmem_init: vmemmap can not be high local node anymore. That is not good. If node is hotplugable, the mem related range like page table and vmemmap could be on the that node without problem and should be on that node. We have workaround patch that could fix some problems, but some can not be fixed. So just remove that offending commit and related ones including: f7210e6c4ac7 ("mm/memblock.c: use CONFIG_HAVE_MEMBLOCK_NODE_MAP to protect movablecore_map in memblock_overlaps_region().") 01a178a94e8e ("acpi, memory-hotplug: support getting hotplug info from SRAT") 27168d38fa20 ("acpi, memory-hotplug: extend movablemem_map ranges to the end of node") e8d195525809 ("acpi, memory-hotplug: parse SRAT before memblock is ready") fb06bc8e5f42 ("page_alloc: bootmem limit with movablecore_map") 42f47e27e761 ("page_alloc: make movablemem_map have higher priority") 6981ec31146c ("page_alloc: introduce zone_movable_limit[] to keep movable limit for nodes") 34b71f1e04fc ("page_alloc: add movable_memmap kernel parameter") 4d59a75125d5 ("x86: get pg_data_t's memory from other node") Later we should have patches that will make sure kernel put page table and vmemmap on local node ram instead of push them down to node0. Also need to find way to put other kernel used ram to local node ram. Reported-by: Tim Gardner Reported-by: Don Morris Bisected-by: Don Morris Tested-by: Don Morris Signed-off-by: Yinghai Lu Cc: Tony Luck Cc: Thomas Renninger Cc: Tejun Heo Cc: Tang Chen Cc: Yasuaki Ishimatsu Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/memblock.h') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 3e5ecb2d790e..f388203db7e8 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -42,7 +42,6 @@ struct memblock { extern struct memblock memblock; extern int memblock_debug; -extern struct movablemem_map movablemem_map; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) @@ -61,7 +60,6 @@ int memblock_reserve(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, unsigned long *out_end_pfn, int *out_nid); -- cgit v1.2.3