From e8c24773d6b2cd9bc8b36bd6e60beff599be14be Mon Sep 17 00:00:00 2001 From: Dave Young Date: Thu, 4 Jan 2018 16:17:45 -0800 Subject: mm: check pfn_valid first in zero_resv_unavail With latest kernel I get below bug while testing kdump: BUG: unable to handle kernel paging request at ffffea00034b1040 IP: zero_resv_unavail+0xbd/0x126 PGD 37b98067 P4D 37b98067 PUD 37b97067 PMD 0 Oops: 0002 [#1] SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 4.15.0-rc1+ #316 Hardware name: LENOVO 20ARS1BJ02/20ARS1BJ02, BIOS GJET92WW (2.42 ) 03/03/2017 task: ffffffff81a0e4c0 task.stack: ffffffff81a00000 RIP: 0010:zero_resv_unavail+0xbd/0x126 RSP: 0000:ffffffff81a03d88 EFLAGS: 00010006 RAX: 0000000000000000 RBX: ffffea00034b1040 RCX: 0000000000000010 RDX: 0000000000000000 RSI: 0000000000000092 RDI: ffffea00034b1040 RBP: 00000000000d2c41 R08: 00000000000000c0 R09: 0000000000000a0d R10: 0000000000000002 R11: 0000000000007f01 R12: ffffffff81a03d90 R13: ffffea0000000000 R14: 0000000000000063 R15: 0000000000000062 FS: 0000000000000000(0000) GS:ffffffff81c73000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffea00034b1040 CR3: 0000000037609000 CR4: 00000000000606b0 Call Trace: ? free_area_init_nodes+0x640/0x664 ? zone_sizes_init+0x58/0x72 ? setup_arch+0xb50/0xc6c ? start_kernel+0x64/0x43d ? secondary_startup_64+0xa5/0xb0 Code: c1 e8 0c 48 39 d8 76 27 48 89 de 48 c1 e3 06 48 c7 c7 7a 87 79 81 e8 b0 c0 3e ff 4c 01 eb b9 10 00 00 00 31 c0 48 89 df 49 ff c6 ab eb bc 6a 00 49 c7 c0 f0 93 d1 81 31 d2 83 ce ff 41 54 49 RIP: zero_resv_unavail+0xbd/0x126 RSP: ffffffff81a03d88 CR2: ffffea00034b1040 ---[ end trace f5ba9e8f73c7ee26 ]--- This is introduced by commit a4a3ede2132a ("mm: zero reserved and unavailable struct pages"). The reason is some efi reserved boot ranges is not reported in E820 ram. In my case it is a bgrt buffer: efi: mem00: [Boot Data |RUN| | | | | | | |WB|WT|WC|UC] range=[0x00000000d2c41000-0x00000000d2c85fff] (0MB) Use "add_efi_memmap" can workaround the problem with another fix: http://lkml.kernel.org/r/20171130052327.GA3500@dhcp-128-65.nay.redhat.com In zero_resv_unavail it would be better to check pfn_valid first before zero the page struct. This fixes the problem and potential other similar problems. Also as Pavel Tatashin suggested checks pfn_valid at the beginning of the section. The range is backed by real memory. The memory range is efi "Boot Service Data", that means after ExitBootServices() these ranges can be used as system ram. But some of them need to be reserved, for example the bgrt image address in an acpi table, if the image memory is freed then kexec reboot will fail because kexec inherit same acpi table to initialize the driver. Link: http://lkml.kernel.org/r/20171201095048.GA3084@dhcp-128-65.nay.redhat.com Fixes: a4a3ede2132a ("mm: zero reserved and unavailable struct pages") Signed-off-by: Dave Young Cc: Michal Hocko Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7e5e775e97f4..76c9688b6a0a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6260,6 +6260,8 @@ void __paginginit zero_resv_unavail(void) pgcnt = 0; for_each_resv_unavail_range(i, &start, &end) { for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) + continue; mm_zero_struct_page(pfn_to_page(pfn)); pgcnt++; } -- cgit v1.2.3 From 4d9570158b6260f449e317a5f9ed030c2504a615 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 4 Jan 2018 16:17:49 -0800 Subject: kernel/acct.c: fix the acct->needcheck check in check_free_space() As Tsukada explains, the time_is_before_jiffies(acct->needcheck) check is very wrong, we need time_is_after_jiffies() to make sys_acct() work. Ignoring the overflows, the code should "goto out" if needcheck > jiffies, while currently it checks "needcheck < jiffies" and thus in the likely case check_free_space() does nothing until jiffies overflow. In particular this means that sys_acct() is simply broken, acct_on() sets acct->needcheck = jiffies and expects that check_free_space() should set acct->active = 1 after the free-space check, but this won't happen if jiffies increments in between. This was broken by commit 32dc73086015 ("get rid of timer in kern/acct.c") in 2011, then another (correct) commit 795a2f22a8ea ("acct() should honour the limits from the very beginning") made the problem more visible. Link: http://lkml.kernel.org/r/20171213133940.GA6554@redhat.com Fixes: 32dc73086015 ("get rid of timer in kern/acct.c") Reported-by: TSUKADA Koutaro Suggested-by: TSUKADA Koutaro Signed-off-by: Oleg Nesterov Cc: Al Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/acct.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/acct.c b/kernel/acct.c index d15c0ee4d955..addf7732fb56 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -102,7 +102,7 @@ static int check_free_space(struct bsd_acct_struct *acct) { struct kstatfs sbuf; - if (time_is_before_jiffies(acct->needcheck)) + if (time_is_after_jiffies(acct->needcheck)) goto out; /* May block */ -- cgit v1.2.3 From 4991c09c7c812dba13ea9be79a68b4565bb1fa4e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 4 Jan 2018 16:17:52 -0800 Subject: mm/mprotect: add a cond_resched() inside change_pmd_range() While testing on a large CPU system, detected the following RCU stall many times over the span of the workload. This problem is solved by adding a cond_resched() in the change_pmd_range() function. INFO: rcu_sched detected stalls on CPUs/tasks: 154-....: (670 ticks this GP) idle=022/140000000000000/0 softirq=2825/2825 fqs=612 (detected by 955, t=6002 jiffies, g=4486, c=4485, q=90864) Sending NMI from CPU 955 to CPUs 154: NMI backtrace for cpu 154 CPU: 154 PID: 147071 Comm: workload Not tainted 4.15.0-rc3+ #3 NIP: c0000000000b3f64 LR: c0000000000b33d4 CTR: 000000000000aa18 REGS: 00000000a4b0fb44 TRAP: 0501 Not tainted (4.15.0-rc3+) MSR: 8000000000009033 CR: 22422082 XER: 00000000 CFAR: 00000000006cf8f0 SOFTE: 1 GPR00: 0010000000000000 c00003ef9b1cb8c0 c0000000010cc600 0000000000000000 GPR04: 8e0000018c32b200 40017b3858fd6e00 8e0000018c32b208 40017b3858fd6e00 GPR08: 8e0000018c32b210 40017b3858fd6e00 8e0000018c32b218 40017b3858fd6e00 GPR12: ffffffffffffffff c00000000fb25100 NIP [c0000000000b3f64] plpar_hcall9+0x44/0x7c LR [c0000000000b33d4] pSeries_lpar_flush_hash_range+0x384/0x420 Call Trace: flush_hash_range+0x48/0x100 __flush_tlb_pending+0x44/0xd0 hpte_need_flush+0x408/0x470 change_protection_range+0xaac/0xf10 change_prot_numa+0x30/0xb0 task_numa_work+0x2d0/0x3e0 task_work_run+0x130/0x190 do_notify_resume+0x118/0x120 ret_from_except_lite+0x70/0x74 Instruction dump: 60000000 f8810028 7ca42b78 7cc53378 7ce63b78 7d074378 7d284b78 7d495378 e9410060 e9610068 e9810070 44000022 <7d806378> e9810028 f88c0000 f8ac0008 Link: http://lkml.kernel.org/r/20171214140551.5794-1-khandual@linux.vnet.ibm.com Signed-off-by: Anshuman Khandual Suggested-by: Nicholas Piggin Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mprotect.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/mprotect.c b/mm/mprotect.c index ec39f730a0bf..58b629bb70de 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -166,7 +166,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, next = pmd_addr_end(addr, end); if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd) && pmd_none_or_clear_bad(pmd)) - continue; + goto next; /* invoke the mmu notifier if the pmd is populated */ if (!mni_start) { @@ -188,7 +188,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } /* huge pmd was handled */ - continue; + goto next; } } /* fall through, the trans huge pmd just split */ @@ -196,6 +196,8 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, this_pages = change_pte_range(vma, pmd, addr, next, newprot, dirty_accountable, prot_numa); pages += this_pages; +next: + cond_resched(); } while (pmd++, addr = next, addr != end); if (mni_start) -- cgit v1.2.3 From dc8635b78cd8669c37e230058d18c33af7451ab1 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Thu, 4 Jan 2018 16:17:56 -0800 Subject: kernel/exit.c: export abort() to modules gcc -fisolate-erroneous-paths-dereference can generate calls to abort() from modular code too. [arnd@arndb.de: drop duplicate exports of abort()] Link: http://lkml.kernel.org/r/20180102103311.706364-1-arnd@arndb.de Reported-by: Vineet Gupta Cc: Sudip Mukherjee Cc: Arnd Bergmann Cc: Alexey Brodkin Cc: Russell King Cc: Jose Abreu Signed-off-by: Andrew Morton Signed-off-by: Arnd Bergmann Signed-off-by: Linus Torvalds --- arch/arm/kernel/traps.c | 1 - arch/m32r/kernel/traps.c | 1 - arch/unicore32/kernel/traps.c | 1 - kernel/exit.c | 1 + 4 files changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 5cf04888c581..3e26c6f7a191 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -793,7 +793,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index cb79fba79d43..b88a8dd14933 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -122,7 +122,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { diff --git a/arch/unicore32/kernel/traps.c b/arch/unicore32/kernel/traps.c index 5f25b39f04d4..c4ac6043ebb0 100644 --- a/arch/unicore32/kernel/traps.c +++ b/arch/unicore32/kernel/traps.c @@ -298,7 +298,6 @@ void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } -EXPORT_SYMBOL(abort); void __init trap_init(void) { diff --git a/kernel/exit.c b/kernel/exit.c index df0c91d5606c..995453d9fb55 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1763,3 +1763,4 @@ __weak void abort(void) /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } +EXPORT_SYMBOL(abort); -- cgit v1.2.3 From 152a2d199e1385c6ccef17c24555103b30447c91 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 4 Jan 2018 16:17:59 -0800 Subject: mm/debug.c: provide useful debugging information for VM_BUG With the recent addition of hashed kernel pointers, places which need to produce useful debug output have to specify %px, not %p. This patch fixes all the VM debug to use %px. This is appropriate because it's debug output that the user should never be able to trigger, and kernel developers need to see the actual pointers. Link: http://lkml.kernel.org/r/20171219133236.GE13680@bombadil.infradead.org Signed-off-by: Matthew Wilcox Acked-by: Michal Hocko Cc: "Tobin C. Harding" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/debug.c | 28 ++++++++++++++-------------- 1 file changed, 14 insertions(+), 14 deletions(-) diff --git a/mm/debug.c b/mm/debug.c index d947f3e03b0d..56e2d9125ea5 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -50,7 +50,7 @@ void __dump_page(struct page *page, const char *reason) */ int mapcount = PageSlab(page) ? 0 : page_mapcount(page); - pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx", + pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx", page, page_ref_count(page), mapcount, page->mapping, page_to_pgoff(page)); if (PageCompound(page)) @@ -69,7 +69,7 @@ void __dump_page(struct page *page, const char *reason) #ifdef CONFIG_MEMCG if (page->mem_cgroup) - pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup); + pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup); #endif } @@ -84,10 +84,10 @@ EXPORT_SYMBOL(dump_page); void dump_vma(const struct vm_area_struct *vma) { - pr_emerg("vma %p start %p end %p\n" - "next %p prev %p mm %p\n" - "prot %lx anon_vma %p vm_ops %p\n" - "pgoff %lx file %p private_data %p\n" + pr_emerg("vma %px start %px end %px\n" + "next %px prev %px mm %px\n" + "prot %lx anon_vma %px vm_ops %px\n" + "pgoff %lx file %px private_data %px\n" "flags: %#lx(%pGv)\n", vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next, vma->vm_prev, vma->vm_mm, @@ -100,27 +100,27 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %p mmap %p seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" #ifdef CONFIG_MMU - "get_unmapped_area %p\n" + "get_unmapped_area %px\n" #endif "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" - "pgd %p mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n" + "pgd %px mm_users %d mm_count %d pgtables_bytes %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" "pinned_vm %lx data_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" "start_brk %lx brk %lx start_stack %lx\n" "arg_start %lx arg_end %lx env_start %lx env_end %lx\n" - "binfmt %p flags %lx core_state %p\n" + "binfmt %px flags %lx core_state %px\n" #ifdef CONFIG_AIO - "ioctx_table %p\n" + "ioctx_table %px\n" #endif #ifdef CONFIG_MEMCG - "owner %p " + "owner %px " #endif - "exe_file %p\n" + "exe_file %px\n" #ifdef CONFIG_MMU_NOTIFIER - "mmu_notifier_mm %p\n" + "mmu_notifier_mm %px\n" #endif #ifdef CONFIG_NUMA_BALANCING "numa_next_scan %lu numa_scan_offset %lu numa_scan_seq %d\n" -- cgit v1.2.3 From cdc346b36e1dfec201b24eddb7bdbcff6727db04 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 4 Jan 2018 16:18:02 -0800 Subject: mm/zsmalloc.c: include fs.h `struct file_system_type' and alloc_anon_inode() function are defined in fs.h, include it directly. Link: http://lkml.kernel.org/r/20171219104219.3017-1-sergey.senozhatsky@gmail.com Signed-off-by: Sergey Senozhatsky Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/zsmalloc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 685049a9048d..683c0651098c 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -53,6 +53,7 @@ #include #include #include +#include #define ZSPAGE_MAGIC 0x58 -- cgit v1.2.3 From d09cfbbfa0f761a97687828b5afb27b56cbf2e19 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Thu, 4 Jan 2018 16:18:06 -0800 Subject: mm/sparse.c: wrong allocation for mem_section In commit 83e3c48729d9 ("mm/sparsemem: Allocate mem_section at runtime for CONFIG_SPARSEMEM_EXTREME=y") mem_section is allocated at runtime to save memory. It allocates the first dimension of array with sizeof(struct mem_section). It costs extra memory, should be sizeof(struct mem_section *). Fix it. Link: http://lkml.kernel.org/r/1513932498-20350-1-git-send-email-bhe@redhat.com Fixes: 83e3c48729 ("mm/sparsemem: Allocate mem_section at runtime for CONFIG_SPARSEMEM_EXTREME=y") Signed-off-by: Baoquan He Tested-by: Dave Young Acked-by: Kirill A. Shutemov Cc: Kirill A. Shutemov Cc: Ingo Molnar Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Atsushi Kumagai Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/sparse.c b/mm/sparse.c index 7a5dacaa06e3..2609aba121e8 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -211,7 +211,7 @@ void __init memory_present(int nid, unsigned long start, unsigned long end) if (unlikely(!mem_section)) { unsigned long size, align; - size = sizeof(struct mem_section) * NR_SECTION_ROOTS; + size = sizeof(struct mem_section*) * NR_SECTION_ROOTS; align = 1 << (INTERNODE_CACHE_SHIFT); mem_section = memblock_virt_alloc(size, align); } -- cgit v1.2.3 From 0cbb4b4f4c44f54af268969b18d8deda63aded59 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 4 Jan 2018 16:18:09 -0800 Subject: userfaultfd: clear the vma->vm_userfaultfd_ctx if UFFD_EVENT_FORK fails The previous fix in commit 384632e67e08 ("userfaultfd: non-cooperative: fix fork use after free") corrected the refcounting in case of UFFD_EVENT_FORK failure for the fork userfault paths. That still didn't clear the vma->vm_userfaultfd_ctx of the vmas that were set to point to the aborted new uffd ctx earlier in dup_userfaultfd. Link: http://lkml.kernel.org/r/20171223002505.593-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Reported-by: syzbot Reviewed-by: Mike Rapoport Cc: Eric Biggers Cc: Dmitry Vyukov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/userfaultfd.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index ac9a4e65ca49..41a75f9f23fd 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -570,11 +570,14 @@ out: static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, struct userfaultfd_wait_queue *ewq) { + struct userfaultfd_ctx *release_new_ctx; + if (WARN_ON_ONCE(current->flags & PF_EXITING)) goto out; ewq->ctx = ctx; init_waitqueue_entry(&ewq->wq, current); + release_new_ctx = NULL; spin_lock(&ctx->event_wqh.lock); /* @@ -601,8 +604,7 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, new = (struct userfaultfd_ctx *) (unsigned long) ewq->msg.arg.reserved.reserved1; - - userfaultfd_ctx_put(new); + release_new_ctx = new; } break; } @@ -617,6 +619,20 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, __set_current_state(TASK_RUNNING); spin_unlock(&ctx->event_wqh.lock); + if (release_new_ctx) { + struct vm_area_struct *vma; + struct mm_struct *mm = release_new_ctx->mm; + + /* the various vma->vm_userfaultfd_ctx still points to it */ + down_write(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) + if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) + vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; + up_write(&mm->mmap_sem); + + userfaultfd_ctx_put(release_new_ctx); + } + /* * ctx may go away after this if the userfault pseudo fd is * already released. -- cgit v1.2.3 From 9a0e7120109632910e77295ce6fc512c16cd367b Mon Sep 17 00:00:00 2001 From: Jeffy Chen Date: Thu, 4 Jan 2018 16:18:12 -0800 Subject: mailmap: update Mark Yao's email address Change the previous employers email addresses to the current email address. Link: http://lkml.kernel.org/r/20171229121726.31589-1-jeffy.chen@rock-chips.com Signed-off-by: Jeffy Chen Acked-by: Martin Kepplinger Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .mailmap | 1 + 1 file changed, 1 insertion(+) diff --git a/.mailmap b/.mailmap index 1469ff0d3f4d..e18cab73e209 100644 --- a/.mailmap +++ b/.mailmap @@ -107,6 +107,7 @@ Linus Lüssing Maciej W. Rozycki Marcin Nowakowski Mark Brown +Mark Yao Martin Kepplinger Martin Kepplinger Matthieu CASTET -- cgit v1.2.3