diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-10-19 06:53:59 -0400 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-10-19 06:53:59 -0400 |
commit | 998d75510e373aab5644d777d3b058312d550159 (patch) | |
tree | bb25edb328e4c4b4447c0a704c854c5d0b52dce3 | |
parent | d418d070057c45fd6f21567278f95452bfe690d1 (diff) | |
parent | 585d730d41120926e3f79a601edad3930fa28366 (diff) |
Merge branch 'akpm' (patches from Andrew)
Merge misc fixes from Andrew Morton:
"Rather a lot of fixes, almost all affecting mm/"
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (26 commits)
scripts/gdb: fix debugging modules on s390
kernel/events/uprobes.c: only do FOLL_SPLIT_PMD for uprobe register
mm/thp: allow dropping THP from page cache
mm/vmscan.c: support removing arbitrary sized pages from mapping
mm/thp: fix node page state in split_huge_page_to_list()
proc/meminfo: fix output alignment
mm/init-mm.c: include <linux/mman.h> for vm_committed_as_batch
mm/filemap.c: include <linux/ramfs.h> for generic_file_vm_ops definition
mm: include <linux/huge_mm.h> for is_vma_temporary_stack
zram: fix race between backing_dev_show and backing_dev_store
mm/memcontrol: update lruvec counters in mem_cgroup_move_account
ocfs2: fix panic due to ocfs2_wq is null
hugetlbfs: don't access uninitialized memmaps in pfn_range_valid_gigantic()
mm: memblock: do not enforce current limit for memblock_phys* family
mm: memcg: get number of pages on the LRU list in memcgroup base on lru_zone_size
mm/gup: fix a misnamed "write" argument, and a related bug
mm/gup_benchmark: add a missing "w" to getopt string
ocfs2: fix error handling in ocfs2_setattr()
mm: memcg/slab: fix panic in __free_slab() caused by premature memcg pointer release
mm/memunmap: don't access uninitialized memmap in memunmap_pages()
...
-rw-r--r-- | drivers/base/memory.c | 3 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 5 | ||||
-rw-r--r-- | fs/ocfs2/file.c | 2 | ||||
-rw-r--r-- | fs/ocfs2/journal.c | 3 | ||||
-rw-r--r-- | fs/ocfs2/localalloc.c | 3 | ||||
-rw-r--r-- | fs/proc/meminfo.c | 4 | ||||
-rw-r--r-- | fs/proc/page.c | 28 | ||||
-rw-r--r-- | kernel/events/uprobes.c | 13 | ||||
-rw-r--r-- | mm/filemap.c | 1 | ||||
-rw-r--r-- | mm/gup.c | 14 | ||||
-rw-r--r-- | mm/huge_memory.c | 9 | ||||
-rw-r--r-- | mm/hugetlb.c | 5 | ||||
-rw-r--r-- | mm/init-mm.c | 1 | ||||
-rw-r--r-- | mm/memblock.c | 6 | ||||
-rw-r--r-- | mm/memcontrol.c | 18 | ||||
-rw-r--r-- | mm/memory-failure.c | 14 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 72 | ||||
-rw-r--r-- | mm/memremap.c | 11 | ||||
-rw-r--r-- | mm/page_owner.c | 5 | ||||
-rw-r--r-- | mm/rmap.c | 1 | ||||
-rw-r--r-- | mm/slab_common.c | 9 | ||||
-rw-r--r-- | mm/truncate.c | 12 | ||||
-rw-r--r-- | mm/vmscan.c | 14 | ||||
-rw-r--r-- | scripts/gdb/linux/dmesg.py | 16 | ||||
-rw-r--r-- | scripts/gdb/linux/symbols.py | 8 | ||||
-rw-r--r-- | scripts/gdb/linux/utils.py | 25 | ||||
-rw-r--r-- | tools/testing/selftests/vm/gup_benchmark.c | 2 |
27 files changed, 165 insertions, 139 deletions
diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 6bea4f3f8040..55907c27075b 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -540,6 +540,9 @@ static ssize_t soft_offline_page_store(struct device *dev, pfn >>= PAGE_SHIFT; if (!pfn_valid(pfn)) return -ENXIO; + /* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ + if (!pfn_to_online_page(pfn)) + return -EIO; ret = soft_offline_page(pfn_to_page(pfn), 0); return ret == 0 ? count : ret; } diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d58a359a6622..4285e75e52c3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -413,13 +413,14 @@ static void reset_bdev(struct zram *zram) static ssize_t backing_dev_show(struct device *dev, struct device_attribute *attr, char *buf) { + struct file *file; struct zram *zram = dev_to_zram(dev); - struct file *file = zram->backing_dev; char *p; ssize_t ret; down_read(&zram->init_lock); - if (!zram->backing_dev) { + file = zram->backing_dev; + if (!file) { memcpy(buf, "none\n", 5); up_read(&zram->init_lock); return 5; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 2e982db3e1ae..53939bf9d7d2 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1230,6 +1230,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) transfer_to[USRQUOTA] = dqget(sb, make_kqid_uid(attr->ia_uid)); if (IS_ERR(transfer_to[USRQUOTA])) { status = PTR_ERR(transfer_to[USRQUOTA]); + transfer_to[USRQUOTA] = NULL; goto bail_unlock; } } @@ -1239,6 +1240,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) transfer_to[GRPQUOTA] = dqget(sb, make_kqid_gid(attr->ia_gid)); if (IS_ERR(transfer_to[GRPQUOTA])) { status = PTR_ERR(transfer_to[GRPQUOTA]); + transfer_to[GRPQUOTA] = NULL; goto bail_unlock; } } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index 930e3d388579..699a560efbb0 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -217,7 +217,8 @@ void ocfs2_recovery_exit(struct ocfs2_super *osb) /* At this point, we know that no more recovery threads can be * launched, so wait for any recovery completion work to * complete. */ - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); /* * Now that recovery is shut down, and the osb is about to be diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 158e5af767fd..720e9f94957e 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -377,7 +377,8 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb) struct ocfs2_dinode *alloc = NULL; cancel_delayed_work(&osb->la_enable_wq); - flush_workqueue(osb->ocfs2_wq); + if (osb->ocfs2_wq) + flush_workqueue(osb->ocfs2_wq); if (osb->local_alloc_state == OCFS2_LA_UNUSED) goto out; diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index ac9247371871..8c1f1bb1a5ce 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -132,9 +132,9 @@ 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: ", + show_val_kb(m, "FileHugePages: ", global_node_page_state(NR_FILE_THPS) * HPAGE_PMD_NR); - show_val_kb(m, "FilePmdMapped: ", + show_val_kb(m, "FilePmdMapped: ", global_node_page_state(NR_FILE_PMDMAPPED) * HPAGE_PMD_NR); #endif diff --git a/fs/proc/page.c b/fs/proc/page.c index 544d1ee15aee..7c952ee732e6 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -42,10 +42,12 @@ static ssize_t kpagecount_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); + if (!ppage || PageSlab(ppage) || page_has_type(ppage)) pcount = 0; else @@ -216,10 +218,11 @@ static ssize_t kpageflags_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (put_user(stable_page_flags(ppage), out)) { ret = -EFAULT; @@ -261,10 +264,11 @@ static ssize_t kpagecgroup_read(struct file *file, char __user *buf, return -EINVAL; while (count > 0) { - if (pfn_valid(pfn)) - ppage = pfn_to_page(pfn); - else - ppage = NULL; + /* + * TODO: ZONE_DEVICE support requires to identify + * memmaps that were actually initialized. + */ + ppage = pfn_to_online_page(pfn); if (ppage) ino = page_cgroup_ino(ppage); diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 94d38a39d72e..c74761004ee5 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -474,14 +474,17 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; bool orig_page_huge = false; + unsigned int gup_flags = FOLL_FORCE; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); retry: + if (is_register) + gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ - ret = get_user_pages_remote(NULL, mm, vaddr, 1, - FOLL_FORCE | FOLL_SPLIT_PMD, &old_page, &vma, NULL); + ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags, + &old_page, &vma, NULL); if (ret <= 0) return ret; @@ -489,6 +492,12 @@ retry: if (ret <= 0) goto put_old; + if (WARN(!is_register && PageCompound(old_page), + "uprobe unregister should never work on compound page\n")) { + ret = -EINVAL; + goto put_old; + } + /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); diff --git a/mm/filemap.c b/mm/filemap.c index 1146fcfa3215..85b7d087eb45 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -40,6 +40,7 @@ #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> +#include <linux/ramfs.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1973,7 +1973,8 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, } static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { unsigned long pte_end; struct page *head, *page; @@ -1986,7 +1987,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, pte = READ_ONCE(*ptep); - if (!pte_access_permitted(pte, write)) + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; /* hugepages are never "special" */ @@ -2023,7 +2024,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, } static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, int write, + unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { pte_t *ptep; @@ -2033,7 +2034,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) + if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) return 0; } while (ptep++, addr = next, addr != end); @@ -2041,7 +2042,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, } #else static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, int write, + unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; @@ -2049,7 +2050,8 @@ static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, #endif /* CONFIG_ARCH_HAS_HUGEPD */ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { struct page *head, *page; int refs; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c5cb6dcd6c69..13cc93785006 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2789,8 +2789,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ds_queue->split_queue_len--; list_del(page_deferred_list(head)); } - if (mapping) - __dec_node_page_state(page, NR_SHMEM_THPS); + if (mapping) { + if (PageSwapBacked(page)) + __dec_node_page_state(page, NR_SHMEM_THPS); + else + __dec_node_page_state(page, NR_FILE_THPS); + } + spin_unlock(&ds_queue->split_queue_lock); __split_huge_page(page, list, end, flags); if (PageSwapCache(head)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ef37c85423a5..b45a95363a84 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1084,11 +1084,10 @@ static bool pfn_range_valid_gigantic(struct zone *z, struct page *page; for (i = start_pfn; i < end_pfn; i++) { - if (!pfn_valid(i)) + page = pfn_to_online_page(i); + if (!page) return false; - page = pfn_to_page(i); - if (page_zone(page) != z) return false; diff --git a/mm/init-mm.c b/mm/init-mm.c index fb1e15028ef0..19603302a77f 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -5,6 +5,7 @@ #include <linux/spinlock.h> #include <linux/list.h> #include <linux/cpumask.h> +#include <linux/mman.h> #include <linux/atomic.h> #include <linux/user_namespace.h> diff --git a/mm/memblock.c b/mm/memblock.c index 7d4f61ae666a..c4b16cae2bc9 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1356,9 +1356,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, align = SMP_CACHE_BYTES; } - if (end > memblock.current_limit) - end = memblock.current_limit; - again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); @@ -1469,6 +1466,9 @@ static void * __init memblock_alloc_internal( if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); + if (max_addr > memblock.current_limit) + max_addr = memblock.current_limit; + alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid); /* retry allocation without lower limit */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bdac56009a38..363106578876 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5420,6 +5420,8 @@ static int mem_cgroup_move_account(struct page *page, struct mem_cgroup *from, struct mem_cgroup *to) { + struct lruvec *from_vec, *to_vec; + struct pglist_data *pgdat; unsigned long flags; unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; @@ -5443,11 +5445,15 @@ static int mem_cgroup_move_account(struct page *page, anon = PageAnon(page); + pgdat = page_pgdat(page); + from_vec = mem_cgroup_lruvec(pgdat, from); + to_vec = mem_cgroup_lruvec(pgdat, to); + spin_lock_irqsave(&from->move_lock, flags); if (!anon && page_mapped(page)) { - __mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages); - __mod_memcg_state(to, NR_FILE_MAPPED, nr_pages); + __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } /* @@ -5459,14 +5465,14 @@ static int mem_cgroup_move_account(struct page *page, struct address_space *mapping = page_mapping(page); if (mapping_cap_account_dirty(mapping)) { - __mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages); - __mod_memcg_state(to, NR_FILE_DIRTY, nr_pages); + __mod_lruvec_state(from_vec, NR_FILE_DIRTY, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_DIRTY, nr_pages); } } if (PageWriteback(page)) { - __mod_memcg_state(from, NR_WRITEBACK, -nr_pages); - __mod_memcg_state(to, NR_WRITEBACK, nr_pages); + __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); + __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 0ae72b6acee7..3151c87dff73 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1257,17 +1257,19 @@ int memory_failure(unsigned long pfn, int flags) if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); - if (!pfn_valid(pfn)) { + p = pfn_to_online_page(pfn); + if (!p) { + if (pfn_valid(pfn)) { + pgmap = get_dev_pagemap(pfn, NULL); + if (pgmap) + return memory_failure_dev_pagemap(pfn, flags, + pgmap); + } pr_err("Memory failure: %#lx: memory outside kernel control\n", pfn); return -ENXIO; } - pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, pgmap); - - p = pfn_to_page(pfn); if (PageHuge(p)) return memory_failure_hugetlb(pfn, flags); if (TestSetPageHWPoison(p)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b1be791f772d..df570e5c71cc 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -436,67 +436,25 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, zone_span_writeunlock(zone); } -static void shrink_pgdat_span(struct pglist_data *pgdat, - unsigned long start_pfn, unsigned long end_pfn) +static void update_pgdat_span(struct pglist_data *pgdat) { - unsigned long pgdat_start_pfn = pgdat->node_start_pfn; - unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */ - unsigned long pgdat_end_pfn = p; - unsigned long pfn; - int nid = pgdat->node_id; - - if (pgdat_start_pfn == start_pfn) { - /* - * If the section is smallest section in the pgdat, it need - * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. - * In this case, we find second smallest valid mem_section - * for shrinking zone. - */ - pfn = find_smallest_section_pfn(nid, NULL, end_pfn, - pgdat_end_pfn); - if (pfn) { - pgdat->node_start_pfn = pfn; - pgdat->node_spanned_pages = pgdat_end_pfn - pfn; - } - } else if (pgdat_end_pfn == end_pfn) { - /* - * If the section is biggest section in the pgdat, it need - * shrink pgdat->node_spanned_pages. - * In this case, we find second biggest valid mem_section for - * shrinking zone. - */ - pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, - start_pfn); - if (pfn) - pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; - } - - /* - * If the section is not biggest or smallest mem_section in the pgdat, - * it only creates a hole in the pgdat. So in this case, we need not - * change the pgdat. - * But perhaps, the pgdat has only hole data. Thus it check the pgdat - * has only hole or not. - */ - pfn = pgdat_start_pfn; - for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) - continue; - - if (pfn_to_nid(pfn) != nid) - continue; + unsigned long node_start_pfn = 0, node_end_pfn = 0; + struct zone *zone; - /* Skip range to be removed */ - if (pfn >= start_pfn && pfn < end_pfn) - continue; + for (zone = pgdat->node_zones; + zone < pgdat->node_zones + MAX_NR_ZONES; zone++) { + unsigned long zone_end_pfn = zone->zone_start_pfn + + zone->spanned_pages; - /* If we find valid section, we have nothing to do */ - return; + /* No need to lock the zones, they can't change. */ + if (zone_end_pfn > node_end_pfn) + node_end_pfn = zone_end_pfn; + if (zone->zone_start_pfn < node_start_pfn) + node_start_pfn = zone->zone_start_pfn; } - /* The pgdat has no valid section */ - pgdat->node_start_pfn = 0; - pgdat->node_spanned_pages = 0; + pgdat->node_start_pfn = node_start_pfn; + pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } static void __remove_zone(struct zone *zone, unsigned long start_pfn, @@ -507,7 +465,7 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); - shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); + update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); } diff --git a/mm/memremap.c b/mm/memremap.c index 68204912cc0a..03ccbdfeb697 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -103,6 +103,7 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) void memunmap_pages(struct dev_pagemap *pgmap) { struct resource *res = &pgmap->res; + struct page *first_page; unsigned long pfn; int nid; @@ -111,14 +112,16 @@ void memunmap_pages(struct dev_pagemap *pgmap) put_page(pfn_to_page(pfn)); dev_pagemap_cleanup(pgmap); + /* make sure to access a memmap that was actually initialized */ + first_page = pfn_to_page(pfn_first(pgmap)); + /* pages are dead and unused, undo the arch mapping */ - nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start))); + nid = page_to_nid(first_page); mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - pfn = PHYS_PFN(res->start); - __remove_pages(page_zone(pfn_to_page(pfn)), pfn, - PHYS_PFN(resource_size(res)), NULL); + __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), pgmap_altmap(pgmap)); diff --git a/mm/page_owner.c b/mm/page_owner.c index e327bcd0380e..18ecde9f45b2 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -271,7 +271,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { - if (!pfn_valid(pfn)) { + page = pfn_to_online_page(pfn); + if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } @@ -279,13 +280,13 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); - page = pfn_to_page(pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { if (!pfn_valid_within(pfn)) continue; + /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) diff --git a/mm/rmap.c b/mm/rmap.c index d9a23bb773bf..0c7b2a9400d4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -61,6 +61,7 @@ #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> +#include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> diff --git a/mm/slab_common.c b/mm/slab_common.c index c29f03adca91..f9fb27b4c843 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -178,10 +178,13 @@ static int init_memcg_params(struct kmem_cache *s, static void destroy_memcg_params(struct kmem_cache *s) { - if (is_root_cache(s)) + if (is_root_cache(s)) { kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); - else + } else { + mem_cgroup_put(s->memcg_params.memcg); + WRITE_ONCE(s->memcg_params.memcg, NULL); percpu_ref_exit(&s->memcg_params.refcnt); + } } static void free_memcg_params(struct rcu_head *rcu) @@ -253,8 +256,6 @@ static void memcg_unlink_cache(struct kmem_cache *s) } else { list_del(&s->memcg_params.children_node); list_del(&s->memcg_params.kmem_caches_node); - mem_cgroup_put(s->memcg_params.memcg); - WRITE_ONCE(s->memcg_params.memcg, NULL); } } #else diff --git a/mm/truncate.c b/mm/truncate.c index 8563339041f6..dd9ebc1da356 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -592,6 +592,16 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, unlock_page(page); continue; } + + /* Take a pin outside pagevec */ + get_page(page); + + /* + * Drop extra pins before trying to invalidate + * the huge page. + */ + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); } ret = invalidate_inode_page(page); @@ -602,6 +612,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ if (!ret) deactivate_file_page(page); + if (PageTransHuge(page)) + put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); diff --git a/mm/vmscan.c b/mm/vmscan.c index c6659bb758a4..ee4eecc7e1c2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -351,12 +351,13 @@ unsigned long zone_reclaimable_pages(struct zone *zone) */ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { - unsigned long lru_size; + unsigned long lru_size = 0; int zid; - if (!mem_cgroup_disabled()) - lru_size = lruvec_page_state_local(lruvec, NR_LRU_BASE + lru); - else + if (!mem_cgroup_disabled()) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) + lru_size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); + } else lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) { @@ -932,10 +933,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under the i_pages lock, then this ordering is not required. */ - if (unlikely(PageTransHuge(page)) && PageSwapCache(page)) - refcount = 1 + HPAGE_PMD_NR; - else - refcount = 2; + refcount = 1 + compound_nr(page); if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ diff --git a/scripts/gdb/linux/dmesg.py b/scripts/gdb/linux/dmesg.py index 6d2e09a2ad2f..2fa7bb83885f 100644 --- a/scripts/gdb/linux/dmesg.py +++ b/scripts/gdb/linux/dmesg.py @@ -16,6 +16,8 @@ import sys from linux import utils +printk_log_type = utils.CachedType("struct printk_log") + class LxDmesg(gdb.Command): """Print Linux kernel log buffer.""" @@ -42,9 +44,14 @@ class LxDmesg(gdb.Command): b = utils.read_memoryview(inf, log_buf_addr, log_next_idx) log_buf = a.tobytes() + b.tobytes() + length_offset = printk_log_type.get_type()['len'].bitpos // 8 + text_len_offset = printk_log_type.get_type()['text_len'].bitpos // 8 + time_stamp_offset = printk_log_type.get_type()['ts_nsec'].bitpos // 8 + text_offset = printk_log_type.get_type().sizeof + pos = 0 while pos < log_buf.__len__(): - length = utils.read_u16(log_buf[pos + 8:pos + 10]) + length = utils.read_u16(log_buf, pos + length_offset) if length == 0: if log_buf_2nd_half == -1: gdb.write("Corrupted log buffer!\n") @@ -52,10 +59,11 @@ class LxDmesg(gdb.Command): pos = log_buf_2nd_half continue - text_len = utils.read_u16(log_buf[pos + 10:pos + 12]) - text = log_buf[pos + 16:pos + 16 + text_len].decode( + text_len = utils.read_u16(log_buf, pos + text_len_offset) + text_start = pos + text_offset + text = log_buf[text_start:text_start + text_len].decode( encoding='utf8', errors='replace') - time_stamp = utils.read_u64(log_buf[pos:pos + 8]) + time_stamp = utils.read_u64(log_buf, pos + time_stamp_offset) for line in text.splitlines(): msg = u"[{time:12.6f}] {line}\n".format( diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py index 34e40e96dee2..7b7c2fafbc68 100644 --- a/scripts/gdb/linux/symbols.py +++ b/scripts/gdb/linux/symbols.py @@ -15,7 +15,7 @@ import gdb import os import re -from linux import modules +from linux import modules, utils if hasattr(gdb, 'Breakpoint'): @@ -116,6 +116,12 @@ lx-symbols command.""" module_file = self._get_module_file(module_name) if module_file: + if utils.is_target_arch('s390'): + # Module text is preceded by PLT stubs on s390. + module_arch = module['arch'] + plt_offset = int(module_arch['plt_offset']) + plt_size = int(module_arch['plt_size']) + module_addr = hex(int(module_addr, 0) + plt_offset + plt_size) gdb.write("loading @{addr}: {filename}\n".format( addr=module_addr, filename=module_file)) cmdline = "add-symbol-file {filename} {addr}{sections}".format( diff --git a/scripts/gdb/linux/utils.py b/scripts/gdb/linux/utils.py index bc67126118c4..ea94221dbd39 100644 --- a/scripts/gdb/linux/utils.py +++ b/scripts/gdb/linux/utils.py @@ -92,15 +92,16 @@ def read_memoryview(inf, start, length): return memoryview(inf.read_memory(start, length)) -def read_u16(buffer): +def read_u16(buffer, offset): + buffer_val = buffer[offset:offset + 2] value = [0, 0] - if type(buffer[0]) is str: - value[0] = ord(buffer[0]) - value[1] = ord(buffer[1]) + if type(buffer_val[0]) is str: + value[0] = ord(buffer_val[0]) + value[1] = ord(buffer_val[1]) else: - value[0] = buffer[0] - value[1] = buffer[1] + value[0] = buffer_val[0] + value[1] = buffer_val[1] if get_target_endianness() == LITTLE_ENDIAN: return value[0] + (value[1] << 8) @@ -108,18 +109,18 @@ def read_u16(buffer): return value[1] + (value[0] << 8) -def read_u32(buffer): +def read_u32(buffer, offset): if get_target_endianness() == LITTLE_ENDIAN: - return read_u16(buffer[0:2]) + (read_u16(buffer[2:4]) << 16) + return read_u16(buffer, offset) + (read_u16(buffer, offset + 2) << 16) else: - return read_u16(buffer[2:4]) + (read_u16(buffer[0:2]) << 16) + return read_u16(buffer, offset + 2) + (read_u16(buffer, offset) << 16) -def read_u64(buffer): +def read_u64(buffer, offset): if get_target_endianness() == LITTLE_ENDIAN: - return read_u32(buffer[0:4]) + (read_u32(buffer[4:8]) << 32) + return read_u32(buffer, offset) + (read_u32(buffer, offset + 4) << 32) else: - return read_u32(buffer[4:8]) + (read_u32(buffer[0:4]) << 32) + retu |