From d84f2f5a755208da3f93e17714631485cb3da11c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 23 Sep 2019 15:35:40 -0700 Subject: drivers/base/node.c: simplify unregister_memory_block_under_nodes() We don't allow to offline memory block devices that belong to multiple numa nodes. Therefore, such devices can never get removed. It is sufficient to process a single node when removing the memory block. No need to iterate over each and every PFN. We already have the nid stored for each memory block. Make sure that the nid always has a sane value. Please note that checking for node_online(nid) is not required. If we would have a memory block belonging to a node that is no longer offline, then we would have a BUG in the node offlining code. Link: http://lkml.kernel.org/r/20190719135244.15242-1-david@redhat.com Signed-off-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: David Hildenbrand Cc: Stephen Rothwell Cc: Pavel Tatashin Cc: Michal Hocko Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 39 +++++++++++++++------------------------ 1 file changed, 15 insertions(+), 24 deletions(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index 75b7e6f6535b..840c95baa1d8 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -759,8 +759,6 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk, int ret, nid = *(int *)arg; unsigned long pfn, sect_start_pfn, sect_end_pfn; - mem_blk->nid = nid; - sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr); sect_end_pfn += PAGES_PER_SECTION - 1; @@ -789,6 +787,13 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk, if (page_nid != nid) continue; } + + /* + * If this memory block spans multiple nodes, we only indicate + * the last processed node. + */ + mem_blk->nid = nid; + ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, &mem_blk->dev.kobj, kobject_name(&mem_blk->dev.kobj)); @@ -804,32 +809,18 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk, } /* - * Unregister memory block device under all nodes that it spans. - * Has to be called with mem_sysfs_mutex held (due to unlinked_nodes). + * Unregister a memory block device under the node it spans. Memory blocks + * with multiple nodes cannot be offlined and therefore also never be removed. */ void unregister_memory_block_under_nodes(struct memory_block *mem_blk) { - unsigned long pfn, sect_start_pfn, sect_end_pfn; - static nodemask_t unlinked_nodes; - - nodes_clear(unlinked_nodes); - sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); - sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr); - for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { - int nid; + if (mem_blk->nid == NUMA_NO_NODE) + return; - nid = get_nid_for_pfn(pfn); - if (nid < 0) - continue; - if (!node_online(nid)) - continue; - if (node_test_and_set(nid, unlinked_nodes)) - continue; - sysfs_remove_link(&node_devices[nid]->dev.kobj, - kobject_name(&mem_blk->dev.kobj)); - sysfs_remove_link(&mem_blk->dev.kobj, - kobject_name(&node_devices[nid]->dev.kobj)); - } + sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj, + kobject_name(&mem_blk->dev.kobj)); + sysfs_remove_link(&mem_blk->dev.kobj, + kobject_name(&node_devices[mem_blk->nid]->dev.kobj)); } int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn) -- cgit v1.2.3 From b6c88d3b9d38f9448e0fcf44847a075ea81d5ca2 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 23 Sep 2019 15:35:49 -0700 Subject: drivers/base/memory.c: don't store end_section_nr in memory blocks Each memory block spans the same amount of sections/pages/bytes. The size is determined before the first memory block is created. No need to store what we can easily calculate - and the calculations even look simpler now. Michal brought up the idea of variable-sized memory blocks. However, if we ever implement something like this, we will need an API compatibility switch and reworks at various places (most code assumes a fixed memory block size). So let's cleanup what we have right now. While at it, fix the variable naming in register_mem_sect_under_node() - we no longer talk about a single section. Link: http://lkml.kernel.org/r/20190809110200.2746-1-david@redhat.com Signed-off-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Pavel Tatashin Cc: Michal Hocko Cc: Dan Williams Cc: Oscar Salvador Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 1 - drivers/base/node.c | 10 +++++----- include/linux/memory.h | 1 - mm/memory_hotplug.c | 2 +- 4 files changed, 6 insertions(+), 8 deletions(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 763154c82eb3..6bea4f3f8040 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -656,7 +656,6 @@ static int init_memory_block(struct memory_block **memory, return -ENOMEM; mem->start_section_nr = block_id * sections_per_block; - mem->end_section_nr = mem->start_section_nr + sections_per_block - 1; mem->state = state; start_pfn = section_nr_to_pfn(mem->start_section_nr); mem->phys_device = arch_get_memory_phys_device(start_pfn); diff --git a/drivers/base/node.c b/drivers/base/node.c index 840c95baa1d8..257449cf061f 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -756,13 +756,13 @@ static int __ref get_nid_for_pfn(unsigned long pfn) static int register_mem_sect_under_node(struct memory_block *mem_blk, void *arg) { + unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE; + unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); + unsigned long end_pfn = start_pfn + memory_block_pfns - 1; int ret, nid = *(int *)arg; - unsigned long pfn, sect_start_pfn, sect_end_pfn; + unsigned long pfn; - sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); - sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr); - sect_end_pfn += PAGES_PER_SECTION - 1; - for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) { + for (pfn = start_pfn; pfn <= end_pfn; pfn++) { int page_nid; /* diff --git a/include/linux/memory.h b/include/linux/memory.h index b3d9df060626..0ebb105eb261 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -25,7 +25,6 @@ struct memory_block { unsigned long start_section_nr; - unsigned long end_section_nr; unsigned long state; /* serialized by the dev->lock */ int section_count; /* serialized by mem_sysfs_mutex */ int online_type; /* for passing data to online routine */ diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 5b8811945bbb..3706a137d880 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1654,7 +1654,7 @@ static int check_memblock_offlined_cb(struct memory_block *mem, void *arg) phys_addr_t beginpa, endpa; beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)); - endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1; + endpa = beginpa + memory_block_size_bytes() - 1; pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n", &beginpa, &endpa); -- cgit v1.2.3 From 60fbf0ab5da1c360e02b7f7d882bf1c0d8f7e32a Mon Sep 17 00:00:00 2001 From: Song Liu Date: Mon, 23 Sep 2019 15:37:54 -0700 Subject: mm,thp: stats for file backed THP In preparation for non-shmem THP, this patch adds a few stats and exposes them in /proc/meminfo, /sys/bus/node/devices//meminfo, and /proc//task//smaps. This patch is mostly a rewrite of Kirill A. Shutemov's earlier version: https://lkml.kernel.org/r/20170126115819.58875-5-kirill.shutemov@linux.intel.com/ Link: http://lkml.kernel.org/r/20190801184244.3169074-5-songliubraving@fb.com Signed-off-by: Song Liu Acked-by: Rik van Riel Acked-by: Kirill A. Shutemov Acked-by: Johannes Weiner Cc: Hillf Danton Cc: Hugh Dickins Cc: William Kucharski Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 6 ++++++ fs/proc/meminfo.c | 4 ++++ fs/proc/task_mmu.c | 4 +++- include/linux/mmzone.h | 2 ++ mm/vmstat.c | 2 ++ 5 files changed, 17 insertions(+), 1 deletion(-) (limited to 'drivers/base/node.c') diff --git a/drivers/base/node.c b/drivers/base/node.c index 257449cf061f..296546ffed6c 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -427,6 +427,8 @@ static ssize_t node_read_meminfo(struct device *dev, "Node %d AnonHugePages: %8lu kB\n" "Node %d ShmemHugePages: %8lu kB\n" "Node %d ShmemPmdMapped: %8lu kB\n" + "Node %d FileHugePages: %8lu kB\n" + "Node %d FilePmdMapped: %8lu kB\n" #endif , nid, K(node_page_state(pgdat, NR_FILE_DIRTY)), @@ -452,6 +454,10 @@ static ssize_t node_read_meminfo(struct device *dev, nid, K(node_page_state(pgdat, NR_SHMEM_THPS) * HPAGE_PMD_NR), nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) * + HPAGE_PMD_NR), + nid, K(node_page_state(pgdat, NR_FILE_THPS) * + HPAGE_PMD_NR), + nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED) * HPAGE_PMD_NR) #endif ); diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 4bd80e68eb03..ac9247371871 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -132,6 +132,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v) global_node_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR); show_val_kb(m, "ShmemPmdMapped: ", global_node_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR); + show_val_kb(m, "FileHugePages: ", + global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR); + show_val_kb(m, "FilePmdMapped: ", + global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); #endif #ifdef CONFIG_CMA diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ea1630465474..9442631fd4af 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -417,6 +417,7 @@ struct mem_size_stats { unsigned long lazyfree; unsigned long anonymous_thp; unsigned long shmem_thp; + unsigned long file_thp; unsigned long swap; unsigned long shared_hugetlb; unsigned long private_hugetlb; @@ -588,7 +589,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, else if (is_zone_device_page(page)) /* pass */; else - VM_BUG_ON_PAGE(1, page); + mss->file_thp += HPAGE_PMD_SIZE; smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else @@ -809,6 +810,7 @@ static void __show_smap(struct seq_file *m, const struct mem_size_stats *mss, SEQ_PUT_DEC(" kB\nLazyFree: ", mss->lazyfree); SEQ_PUT_DEC(" kB\nAnonHugePages: ", mss->anonymous_thp); SEQ_PUT_DEC(" kB\nShmemPmdMapped: ", mss->shmem_thp); + SEQ_PUT_DEC(" kB\nFilePmdMapped: ", mss->file_thp); SEQ_PUT_DEC(" kB\nShared_Hugetlb: ", mss->shared_hugetlb); seq_put_decimal_ull_width(m, " kB\nPrivate_Hugetlb: ", mss->private_hugetlb >> 10, 7); diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3f38c30d2f13..aafb7c38c627 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -235,6 +235,8 @@ enum node_stat_item { NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_SHMEM_THPS, NR_SHMEM_PMDMAPPED, + NR_FILE_THPS, + NR_FILE_PMDMAPPED, NR_ANON_THPS, NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_VMSCAN_WRITE, diff --git a/mm/vmstat.c b/mm/vmstat.c index fd7e16ca6996..6afc892a148a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1158,6 +1158,8 @@ const char * const vmstat_text[] = { "nr_shmem", "nr_shmem_hugepages", "nr_shmem_pmdmapped", + "nr_file_hugepages", + "nr_file_pmdmapped", "nr_anon_transparent_hugepages", "nr_unstable", "nr_vmscan_write", -- cgit v1.2.3