From 7cbf319234adaa4518a28c8c523d3330e06638f0 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 25 May 2018 14:47:17 -0700 Subject: mm: fix nr_rotate_swap leak in swapon() error case If swapon() fails after incrementing nr_rotate_swap, we don't decrement it and thus effectively leak it. Make sure we decrement it if we incremented it. Link: http://lkml.kernel.org/r/b6fe6b879f17fa68eee6cbd876f459f6e5e33495.1526491581.git.osandov@fb.com Fixes: 81a0298bdfab ("mm, swap: don't use VMA based swap readahead if HDD is used as swap") Signed-off-by: Omar Sandoval Reviewed-by: Rik van Riel Reviewed-by: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/mm/swapfile.c b/mm/swapfile.c index cc2cf04d9018..78a015fcec3b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3112,6 +3112,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; + bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; @@ -3215,8 +3216,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } - } else + } else { atomic_inc(&nr_rotate_swap); + inced_nr_rotate_swap = true; + } error = swap_cgroup_swapon(p->type, maxpages); if (error) @@ -3307,6 +3310,8 @@ bad_swap: vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); + if (inced_nr_rotate_swap) + atomic_dec(&nr_rotate_swap); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { inode_unlock(inode); -- cgit v1.2.3-55-g7522 From 3373de209cb123462954740f41c324d03ecfb6d0 Mon Sep 17 00:00:00 2001 From: Changwei Ge Date: Fri, 25 May 2018 14:47:20 -0700 Subject: ocfs2: revert "ocfs2/o2hb: check len for bio_add_page() to avoid getting incorrect bio" This reverts commit ba16ddfbeb9d ("ocfs2/o2hb: check len for bio_add_page() to avoid getting incorrect bio"). In my testing, this patch introduces a problem that mkfs can't have slots more than 16 with 4k block size. And the original logic is safe actually with the situation it mentions so revert this commit. Attach test log: (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 0, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 1, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 2, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 3, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 4, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 5, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 6, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 7, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 8, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 9, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 10, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 11, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 12, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 13, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 14, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 15, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:463 page 16, vec_len = 4096, vec_start = 0 (mkfs.ocfs2,27479,2):o2hb_setup_one_bio:471 ERROR: Adding page[16] to bio failed, page ffffea0002d7ed40, len 0, vec_len 4096, vec_start 0,bi_sector 8192 (mkfs.ocfs2,27479,2):o2hb_read_slots:500 ERROR: status = -5 (mkfs.ocfs2,27479,2):o2hb_populate_slot_data:1911 ERROR: status = -5 (mkfs.ocfs2,27479,2):o2hb_region_dev_write:2012 ERROR: status = -5 Link: http://lkml.kernel.org/r/SIXPR06MB0461721F398A5A92FC68C39ED5920@SIXPR06MB0461.apcprd06.prod.outlook.com Signed-off-by: Changwei Ge Cc: Jun Piao Cc: Yiwen Jiang Cc: Joseph Qi Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/cluster/heartbeat.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c index 91a8889abf9b..ea8c551bcd7e 100644 --- a/fs/ocfs2/cluster/heartbeat.c +++ b/fs/ocfs2/cluster/heartbeat.c @@ -570,16 +570,7 @@ static struct bio *o2hb_setup_one_bio(struct o2hb_region *reg, current_page, vec_len, vec_start); len = bio_add_page(bio, page, vec_len, vec_start); - if (len != vec_len) { - mlog(ML_ERROR, "Adding page[%d] to bio failed, " - "page %p, len %d, vec_len %u, vec_start %u, " - "bi_sector %llu\n", current_page, page, len, - vec_len, vec_start, - (unsigned long long)bio->bi_iter.bi_sector); - bio_put(bio); - bio = ERR_PTR(-EIO); - return bio; - } + if (len != vec_len) break; cs += vec_len / (PAGE_SIZE/spp); vec_start = 0; -- cgit v1.2.3-55-g7522 From 7a4deea1aa8bddfed4ef1b35fc2b6732563d8ad5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 25 May 2018 14:47:24 -0700 Subject: idr: fix invalid ptr dereference on item delete If the radix tree underlying the IDR happens to be full and we attempt to remove an id which is larger than any id in the IDR, we will call __radix_tree_delete() with an uninitialised 'slot' pointer, at which point anything could happen. This was easiest to hit with a single entry at id 0 and attempting to remove a non-0 id, but it could have happened with 64 entries and attempting to remove an id >= 64. Roman said: The syzcaller test boils down to opening /dev/kvm, creating an eventfd, and calling a couple of KVM ioctls. None of this requires superuser. And the result is dereferencing an uninitialized pointer which is likely a crash. The specific path caught by syzbot is via KVM_HYPERV_EVENTD ioctl which is new in 4.17. But I guess there are other user-triggerable paths, so cc:stable is probably justified. Matthew added: We have around 250 calls to idr_remove() in the kernel today. Many of them pass an ID which is embedded in the object they're removing, so they're safe. Picking a few likely candidates: drivers/firewire/core-cdev.c looks unsafe; the ID comes from an ioctl. drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c is similar drivers/atm/nicstar.c could be taken down by a handcrafted packet Link: http://lkml.kernel.org/r/20180518175025.GD6361@bombadil.infradead.org Fixes: 0a835c4f090a ("Reimplement IDR and IDA using the radix tree") Reported-by: Debugged-by: Roman Kagan Signed-off-by: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- lib/radix-tree.c | 4 +++- tools/testing/radix-tree/idr-test.c | 7 +++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 43e0cbedc3a0..a9e41aed6de4 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -2034,10 +2034,12 @@ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; - void __rcu **slot; + void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); + if (!slot) + return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 6c645eb77d42..ee820fcc29b0 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -252,6 +252,13 @@ void idr_checks(void) idr_remove(&idr, 3); idr_remove(&idr, 0); + assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == 0); + idr_remove(&idr, 1); + for (i = 1; i < RADIX_TREE_MAP_SIZE; i++) + assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == i); + idr_remove(&idr, 1 << 30); + idr_destroy(&idr); + for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) { struct item *item = item_create(i, 0); assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i); -- cgit v1.2.3-55-g7522 From a73ab244f0dad8fffb3291b905f73e2d3eaa7c00 Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 25 May 2018 14:47:27 -0700 Subject: Revert "ipc/shm: Fix shmat mmap nil-page protection" Patch series "ipc/shm: shmat() fixes around nil-page". These patches fix two issues reported[1] a while back by Joe and Andrea around how shmat(2) behaves with nil-page. The first reverts a commit that it was incorrectly thought that mapping nil-page (address=0) was a no no with MAP_FIXED. This is not the case, with the exception of SHM_REMAP; which is address in the second patch. I chose two patches because it is easier to backport and it explicitly reverts bogus behaviour. Both patches ought to be in -stable and ltp testcases need updated (the added testcase around the cve can be modified to just test for SHM_RND|SHM_REMAP). [1] lkml.kernel.org/r/20180430172152.nfa564pvgpk3ut7p@linux-n805 This patch (of 2): Commit 95e91b831f87 ("ipc/shm: Fix shmat mmap nil-page protection") worked on the idea that we should not be mapping as root addr=0 and MAP_FIXED. However, it was reported that this scenario is in fact valid, thus making the patch both bogus and breaks userspace as well. For example X11's libint10.so relies on shmat(1, SHM_RND) for lowmem initialization[1]. [1] https://cgit.freedesktop.org/xorg/xserver/tree/hw/xfree86/os-support/linux/int10/linux.c#n347 Link: http://lkml.kernel.org/r/20180503203243.15045-2-dave@stgolabs.net Fixes: 95e91b831f87 ("ipc/shm: Fix shmat mmap nil-page protection") Signed-off-by: Davidlohr Bueso Reported-by: Joe Lawrence Reported-by: Andrea Arcangeli Cc: Manfred Spraul Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 3cf48988d68c..930be3aa80cf 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1363,13 +1363,8 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, if (addr) { if (addr & (shmlba - 1)) { - /* - * Round down to the nearest multiple of shmlba. - * For sane do_mmap_pgoff() parameters, avoid - * round downs that trigger nil-page and MAP_FIXED. - */ - if ((shmflg & SHM_RND) && addr >= shmlba) - addr &= ~(shmlba - 1); + if (shmflg & SHM_RND) + addr &= ~(shmlba - 1); /* round down */ else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) -- cgit v1.2.3-55-g7522 From 8f89c007b6dec16a1793cb88de88fcc02117bbbc Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Fri, 25 May 2018 14:47:30 -0700 Subject: ipc/shm: fix shmat() nil address after round-down when remapping shmat()'s SHM_REMAP option forbids passing a nil address for; this is in fact the very first thing we check for. Andrea reported that for SHM_RND|SHM_REMAP cases we can end up bypassing the initial addr check, but we need to check again if the address was rounded down to nil. As of this patch, such cases will return -EINVAL. Link: http://lkml.kernel.org/r/20180503204934.kk63josdu6u53fbd@linux-n805 Signed-off-by: Davidlohr Bueso Reported-by: Andrea Arcangeli Cc: Joe Lawrence Cc: Manfred Spraul Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index 930be3aa80cf..d73269381ec7 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -1363,9 +1363,17 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, if (addr) { if (addr & (shmlba - 1)) { - if (shmflg & SHM_RND) + if (shmflg & SHM_RND) { addr &= ~(shmlba - 1); /* round down */ - else + + /* + * Ensure that the round-down is non-nil + * when remapping. This can happen for + * cases when addr < shmlba. + */ + if (!addr && (shmflg & SHM_REMAP)) + goto out; + } else #ifndef __ARCH_FORCE_SHMLBA if (addr & ~PAGE_MASK) #endif -- cgit v1.2.3-55-g7522 From b9ddff9b85036292f8b6d4ac37e21fc229fedea1 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 25 May 2018 14:47:35 -0700 Subject: MAINTAINERS: change hugetlbfs maintainer and update files The current hugetlbfs maintainer has not been active for more than a few years. I have been been active in this area for more than two years and plan to remain active in the foreseeable future. Also, update the hugetlbfs entry to include linux-mm mail list and additional hugetlbfs related files. hugetlb.c and hugetlb.h are not 100% hugetlbfs, but a majority of their content is hugetlbfs related. Link: http://lkml.kernel.org/r/20180518225236.19079-1-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Naoya Horiguchi Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Acked-by: Michal Hocko Cc: Nadia Yvette Chambers Cc: "Aneesh Kumar K . V" Cc: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index a9ca122957e9..89ead18184a6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6503,9 +6503,15 @@ F: Documentation/networking/hinic.txt F: drivers/net/ethernet/huawei/hinic/ HUGETLB FILESYSTEM -M: Nadia Yvette Chambers +M: Mike Kravetz +L: linux-mm@kvack.org S: Maintained F: fs/hugetlbfs/ +F: mm/hugetlb.c +F: include/linux/hugetlb.h +F: Documentation/admin-guide/mm/hugetlbpage.rst +F: Documentation/vm/hugetlbfs_reserv.rst +F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages HVA ST MEDIA DRIVER M: Jean-Christophe Trotin -- cgit v1.2.3-55-g7522 From 0f901dcbc31f88ae41a2aaa365f7802b5d520a28 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 25 May 2018 14:47:38 -0700 Subject: mm/kasan: don't vfree() nonexistent vm_area KASAN uses different routines to map shadow for hot added memory and memory obtained in boot process. Attempt to offline memory onlined by normal boot process leads to this: Trying to vfree() nonexistent vm area (000000005d3b34b9) WARNING: CPU: 2 PID: 13215 at mm/vmalloc.c:1525 __vunmap+0x147/0x190 Call Trace: kasan_mem_notifier+0xad/0xb9 notifier_call_chain+0x166/0x260 __blocking_notifier_call_chain+0xdb/0x140 __offline_pages+0x96a/0xb10 memory_subsys_offline+0x76/0xc0 device_offline+0xb8/0x120 store_mem_state+0xfa/0x120 kernfs_fop_write+0x1d5/0x320 __vfs_write+0xd4/0x530 vfs_write+0x105/0x340 SyS_write+0xb0/0x140 Obviously we can't call vfree() to free memory that wasn't allocated via vmalloc(). Use find_vm_area() to see if we can call vfree(). Unfortunately it's a bit tricky to properly unmap and free shadow allocated during boot, so we'll have to keep it. If memory will come online again that shadow will be reused. Matthew asked: how can you call vfree() on something that isn't a vmalloc address? vfree() is able to free any address returned by __vmalloc_node_range(). And __vmalloc_node_range() gives you any address you ask. It doesn't have to be an address in [VMALLOC_START, VMALLOC_END] range. That's also how the module_alloc()/module_memfree() works on architectures that have designated area for modules. [aryabinin@virtuozzo.com: improve comments] Link: http://lkml.kernel.org/r/dabee6ab-3a7a-51cd-3b86-5468718e0390@virtuozzo.com [akpm@linux-foundation.org: fix typos, reflow comment] Link: http://lkml.kernel.org/r/20180201163349.8700-1-aryabinin@virtuozzo.com Fixes: fa69b5989bb0 ("mm/kasan: add support for memory hotplug") Signed-off-by: Andrey Ryabinin Reported-by: Paul Menzel Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 61 insertions(+), 2 deletions(-) diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index bc0e68f7dc75..7160028efd12 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -792,6 +792,40 @@ DEFINE_ASAN_SET_SHADOW(f5); DEFINE_ASAN_SET_SHADOW(f8); #ifdef CONFIG_MEMORY_HOTPLUG +static bool shadow_mapped(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + if (pgd_none(*pgd)) + return false; + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) + return false; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + return false; + + /* + * We can't use pud_large() or pud_huge(), the first one is + * arch-specific, the last one depends on HUGETLB_PAGE. So let's abuse + * pud_bad(), if pud is bad then it's bad because it's huge. + */ + if (pud_bad(*pud)) + return true; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + return false; + + if (pmd_bad(*pmd)) + return true; + pte = pte_offset_kernel(pmd, addr); + return !pte_none(*pte); +} + static int __meminit kasan_mem_notifier(struct notifier_block *nb, unsigned long action, void *data) { @@ -813,6 +847,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb, case MEM_GOING_ONLINE: { void *ret; + /* + * If shadow is mapped already than it must have been mapped + * during the boot. This could happen if we onlining previously + * offlined memory. + */ + if (shadow_mapped(shadow_start)) + return NOTIFY_OK; + ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start, shadow_end, GFP_KERNEL, PAGE_KERNEL, VM_NO_GUARD, @@ -824,8 +866,25 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb, kmemleak_ignore(ret); return NOTIFY_OK; } - case MEM_OFFLINE: - vfree((void *)shadow_start); + case MEM_OFFLINE: { + struct vm_struct *vm; + + /* + * shadow_start was either mapped during boot by kasan_init() + * or during memory online by __vmalloc_node_range(). + * In the latter case we can use vfree() to free shadow. + * Non-NULL result of the find_vm_area() will tell us if + * that was the second case. + * + * Currently it's not possible to free shadow mapped + * during boot by kasan_init(). It's because the code + * to do that hasn't been written yet. So we'll just + * leak the memory. + */ + vm = find_vm_area((void *)shadow_start); + if (vm) + vfree((void *)shadow_start); + } } return NOTIFY_OK; -- cgit v1.2.3-55-g7522 From 15c30bc0908514b4a72fadc3995d32313500393a Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 May 2018 14:47:42 -0700 Subject: mm, memory_hotplug: make has_unmovable_pages more robust Oscar has reported: : Due to an unfortunate setting with movablecore, memblocks containing bootmem : memory (pages marked by get_page_bootmem()) ended up marked in zone_movable. : So while trying to remove that memory, the system failed in do_migrate_range : and __offline_pages never returned. : : This can be reproduced by running : qemu-system-x86_64 -m 6G,slots=8,maxmem=8G -numa node,mem=4096M -numa node,mem=2048M : and movablecore=4G kernel command line : : linux kernel: BIOS-provided physical RAM map: : linux kernel: BIOS-e820: [mem 0x0000000000000000-0x000000000009fbff] usable : linux kernel: BIOS-e820: [mem 0x000000000009fc00-0x000000000009ffff] reserved : linux kernel: BIOS-e820: [mem 0x00000000000f0000-0x00000000000fffff] reserved : linux kernel: BIOS-e820: [mem 0x0000000000100000-0x00000000bffdffff] usable : linux kernel: BIOS-e820: [mem 0x00000000bffe0000-0x00000000bfffffff] reserved : linux kernel: BIOS-e820: [mem 0x00000000feffc000-0x00000000feffffff] reserved : linux kernel: BIOS-e820: [mem 0x00000000fffc0000-0x00000000ffffffff] reserved : linux kernel: BIOS-e820: [mem 0x0000000100000000-0x00000001bfffffff] usable : linux kernel: NX (Execute Disable) protection: active : linux kernel: SMBIOS 2.8 present. : linux kernel: DMI: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org : linux kernel: Hypervisor detected: KVM : linux kernel: e820: update [mem 0x00000000-0x00000fff] usable ==> reserved : linux kernel: e820: remove [mem 0x000a0000-0x000fffff] usable : linux kernel: last_pfn = 0x1c0000 max_arch_pfn = 0x400000000 : : linux kernel: SRAT: PXM 0 -> APIC 0x00 -> Node 0 : linux kernel: SRAT: PXM 1 -> APIC 0x01 -> Node 1 : linux kernel: ACPI: SRAT: Node 0 PXM 0 [mem 0x00000000-0x0009ffff] : linux kernel: ACPI: SRAT: Node 0 PXM 0 [mem 0x00100000-0xbfffffff] : linux kernel: ACPI: SRAT: Node 0 PXM 0 [mem 0x100000000-0x13fffffff] : linux kernel: ACPI: SRAT: Node 1 PXM 1 [mem 0x140000000-0x1bfffffff] : linux kernel: ACPI: SRAT: Node 0 PXM 0 [mem 0x1c0000000-0x43fffffff] hotplug : linux kernel: NUMA: Node 0 [mem 0x00000000-0x0009ffff] + [mem 0x00100000-0xbfffffff] -> [mem 0x0 : linux kernel: NUMA: Node 0 [mem 0x00000000-0xbfffffff] + [mem 0x100000000-0x13fffffff] -> [mem 0 : linux kernel: NODE_DATA(0) allocated [mem 0x13ffd6000-0x13fffffff] : linux kernel: NODE_DATA(1) allocated [mem 0x1bffd3000-0x1bfffcfff] : : zoneinfo shows that the zone movable is placed into both numa nodes: : Node 0, zone Movable : pages free 160140 : min 1823 : low 2278 : high 2733 : spanned 262144 : present 262144 : managed 245670 : Node 1, zone Movable : pages free 448427 : min 3827 : low 4783 : high 5739 : spanned 524288 : present 524288 : managed 515766 Note how only Node 0 has a hutplugable memory region which would rule it out from the early memblock allocations (most likely memmap). Node1 will surely contain memmaps on the same node and those would prevent offlining to succeed. So this is arguably a configuration issue. Although one could argue that we should be more clever and rule early allocations from the zone movable. This would be correct but probably not worth the effort considering what a hack movablecore is. Anyway, We could do better for those cases though. We rely on start_isolate_page_range resp. has_unmovable_pages to do their job. The first one isolates the whole range to be offlined so that we do not allocate from it anymore and the later makes sure we are not stumbling over non-migrateable pages. has_unmovable_pages is overly optimistic, however. It doesn't check all the pages if we are withing zone_movable because we rely that those pages will be always migrateable. As it turns out we are still not perfect there. While bootmem pages in zonemovable sound like a clear bug which should be fixed let's remove the optimization for now and warn if we encounter unmovable pages in zone_movable in the meantime. That should help for now at least. Btw. this wasn't a real problem until commit 72b39cfc4d75 ("mm, memory_hotplug: do not fail offlining too early") because we used to have a small number of retries and then failed. This turned out to be too fragile though. Link: http://lkml.kernel.org/r/20180523125555.30039-2-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Oscar Salvador Tested-by: Oscar Salvador Reviewed-by: Pavel Tatashin Cc: Vlastimil Babka Cc: Reza Arbab Cc: Igor Mammedov Cc: Vitaly Kuznetsov Cc: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 511a7124d7f9..22320ea27489 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7598,11 +7598,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unsigned long pfn, iter, found; /* - * For avoiding noise data, lru_add_drain_all() should be called - * If ZONE_MOVABLE, the zone never contains unmovable pages + * TODO we could make this much more efficient by not checking every + * page in the range if we know all of them are in MOVABLE_ZONE and + * that the movable zone guarantees that pages are migratable but + * the later is not the case right now unfortunatelly. E.g. movablecore + * can still lead to having bootmem allocations in zone_movable. */ - if (zone_idx(zone) == ZONE_MOVABLE) - return false; /* * CMA allocations (alloc_contig_range) really need to mark isolate @@ -7623,7 +7624,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, page = pfn_to_page(check); if (PageReserved(page)) - return true; + goto unmovable; /* * Hugepages are not in LRU lists, but they're movable. @@ -7673,9 +7674,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * page at boot. */ if (found > count) - return true; + goto unmovable; } return false; +unmovable: + WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); + return true; } bool is_pageblock_removable_nolock(struct page *page) -- cgit v1.2.3-55-g7522 From 8addc2d00fe171c89b5fcbafe583c2b90574d301 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 25 May 2018 14:47:46 -0700 Subject: mm: do not warn on offline nodes unless the specific node is explicitly requested Oscar has noticed that we splat WARNING: CPU: 0 PID: 64 at ./include/linux/gfp.h:467 vmemmap_alloc_block+0x4e/0xc9 [...] CPU: 0 PID: 64 Comm: kworker/u4:1 Tainted: G W E 4.17.0-rc5-next-20180517-1-default+ #66 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014 Workqueue: kacpi_hotplug acpi_hotplug_work_fn Call Trace: vmemmap_populate+0xf2/0x2ae sparse_mem_map_populate+0x28/0x35 sparse_add_one_section+0x4c/0x187 __add_pages+0xe7/0x1a0 add_pages+0x16/0x70 add_memory_resource+0xa3/0x1d0 add_memory+0xe4/0x110 acpi_memory_device_add+0x134/0x2e0 acpi_bus_attach+0xd9/0x190 acpi_bus_scan+0x37/0x70 acpi_device_hotplug+0x389/0x4e0 acpi_hotplug_work_fn+0x1a/0x30 process_one_work+0x146/0x340 worker_thread+0x47/0x3e0 kthread+0xf5/0x130 ret_from_fork+0x35/0x40 when adding memory to a node that is currently offline. The VM_WARN_ON is just too loud without a good reason. In this particular case we are doing alloc_pages_node(node, GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN, order) so we do not insist on allocating from the given node (it is more a hint) so we can fall back to any other populated node and moreover we explicitly ask to not warn for the allocation failure. Soften the warning only to cases when somebody asks for the given node explicitly by __GFP_THISNODE. Link: http://lkml.kernel.org/r/20180523125555.30039-3-mhocko@kernel.org Signed-off-by: Michal Hocko Reported-by: Oscar Salvador Tested-by: Oscar Salvador Reviewed-by: Pavel Tatashin Cc: Vlastimil Babka Cc: Reza Arbab Cc: Igor Mammedov Cc: Vitaly Kuznetsov Cc: Anshuman Khandual Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 1a4582b44d32..fc5ab85278d5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -464,7 +464,7 @@ static inline struct page * __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) { VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); - VM_WARN_ON(!node_online(nid)); + VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid)); return __alloc_pages(gfp_mask, order, nid); } -- cgit v1.2.3-55-g7522 From 6c04ab0eddc9a38e6c14ae4b6217db1e34436b8c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 25 May 2018 14:47:50 -0700 Subject: proc: fix smaps and meminfo alignment The 4.17-rc /proc/meminfo and /proc//smaps look ugly: single-digit numbers (commonly 0) are misaligned. Remove seq_put_decimal_ull_width()'s leftover optimization for single digits: it's wrong now that num_to_str() takes care of the width. Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1805241554210.1326@eggly.anvils Fixes: d1be35cb6f96 ("proc: add seq_put_decimal_ull_width to speed up /proc/pid/smaps") Signed-off-by: Hugh Dickins Cc: Andrei Vagin Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/fs/seq_file.c b/fs/seq_file.c index c6c27f1f9c98..4cc090b50cc5 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -709,11 +709,6 @@ void seq_put_decimal_ull_width(struct seq_file *m, const char *delimiter, if (m->count + width >= m->size) goto overflow; - if (num < 10) { - m->buf[m->count++] = num + '0'; - return; - } - len = num_to_str(m->buf + m->count, m->size - m->count, num, width); if (!len) goto overflow; -- cgit v1.2.3-55-g7522 From a21558618c5dfc55b6086743a88ce5a9c1588f0a Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Fri, 25 May 2018 14:47:53 -0700 Subject: mm/memory_hotplug: fix leftover use of struct page during hotplug The case of a new numa node got missed in avoiding using the node info from page_struct during hotplug. In this path we have a call to register_mem_sect_under_node (which allows us to specify it is hotplug so don't change the node), via link_mem_sections which unfortunately does not. Fix is to pass check_nid through link_mem_sections as well and disable it in the new numa node path. Note the bug only 'sometimes' manifests depending on what happens to be in the struct page structures - there are lots of them and it only needs to match one of them. The result of the bug is that (with a new memory only node) we never successfully call register_mem_sect_under_node so don't get the memory associated with the node in sysfs and meminfo for the node doesn't report it. It came up whilst testing some arm64 hotplug patches, but appears to be universal. Whilst I'm triggering it by removing then reinserting memory to a node with no other elements (thus making the node disappear then appear again), it appears it would happen on hotplugging memory where there was none before and it doesn't seem to be related the arm64 patches. These patches call __add_pages (where most of the issue was fixed by Pavel's patch). If there is a node at the time of the __add_pages call then all is well as it calls register_mem_sect_under_node from there with check_nid set to false. Without a node that function returns having not done the sysfs related stuff as there is no node to use. This is expected but it is the resulting path that fails... Exact path to the problem is as follows: mm/memory_hotplug.c: add_memory_resource() The node is not online so we enter the 'if (new_node)' twice, on the second such block there is a call to link_mem_sections which calls into drivers/node.c: link_mem_sections() which calls drivers/node.c: register_mem_sect_under_node() which calls get_nid_for_pfn and keeps trying until the output of that matches the expected node (passed all the way down from add_memory_resource) It is effectively the same fix as the one referred to in the fixes tag just in the code path for a new node where the comments point out we have to rerun the link creation because it will have failed in register_new_memory (as there was no node at the time). (actually that comment is wrong now as we don't have register_new_memory any more it got renamed to hotplug_memory_register in Pavel's patch). Link: http://lkml.kernel.org/r/20180504085311.1240-1-Jonathan.Cameron@huawei.com Fixes: fc44f7f9231a ("mm/memory_hotplug: don't read nid from struct page during hotplug") Signed-off-by: Jonathan Cameron Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/node.c | 5 +++-- include/linux/node.h | 8 +++++--- mm/memory_hotplug.c | 2 +- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/base/node.c b/drivers/base/node.c index 7a3a580821e0..a5e821d09656 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -490,7 +490,8 @@ int unregister_mem_sect_under_nodes(struct memory_block *mem_blk, return 0; } -int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) +int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages, + bool check_nid) { unsigned long end_pfn = start_pfn + nr_pages; unsigned long pfn; @@ -514,7 +515,7 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) mem_blk = find_memory_block_hinted(mem_sect, mem_blk); - ret = register_mem_sect_under_node(mem_blk, nid, true); + ret = register_mem_sect_under_node(mem_blk, nid, check_nid); if (!err) err = ret; diff --git a/include/linux/node.h b/include/linux/node.h index 41f171861dcc..6d336e38d155 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -32,9 +32,11 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages); +extern int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool check_nid); #else -static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages) +static inline int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long nr_pages, bool check_nid) { return 0; } @@ -57,7 +59,7 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages); + error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages, true); } return error; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index f74826cdceea..25982467800b 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1158,7 +1158,7 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) * nodes have to go through register_node. * TODO clean up this mess. */ - ret = link_mem_sections(nid, start_pfn, nr_pages); + ret = link_mem_sections(nid, start_pfn, nr_pages, false); register_fail: /* * If sysfs file of new node can't create, cpu on the node -- cgit v1.2.3-55-g7522 From 23d6aef74da86a33fa6bb75f79565e0a16ee97c2 Mon Sep 17 00:00:00 2001 From: Gustavo A. R. Silva Date: Fri, 25 May 2018 14:47:57 -0700 Subject: kernel/sys.c: fix potential Spectre v1 issue `resource' can be controlled by user-space, hence leading to a potential exploitation of the Spectre variant 1 vulnerability. This issue was detected with the help of Smatch: kernel/sys.c:1474 __do_compat_sys_old_getrlimit() warn: potential spectre issue 'get_current()->signal->rlim' (local cap) kernel/sys.c:1455 __do_sys_old_getrlimit() warn: potential spectre issue 'get_current()->signal->rlim' (local cap) Fix this by sanitizing *resource* before using it to index current->signal->rlim Notice that given that speculation windows are large, the policy is to kill the speculation on the first load and not worry if it can be completed with a dependent load/store [1]. [1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2 Link: http://lkml.kernel.org/r/20180515030038.GA11822@embeddedor.com Signed-off-by: Gustavo A. R. Silva Reviewed-by: Andrew Morton Cc: Alexei Starovoitov Cc: Dan Williams Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sys.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/sys.c b/kernel/sys.c index b0eee418ee0d..d1b2b8d934bb 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -71,6 +71,9 @@ #include #include +/* Hardening for Spectre-v1 */ +#include + #include "uid16.h" #ifndef SET_UNALIGN_CTL @@ -1453,6 +1456,7 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); @@ -1472,6 +1476,7 @@ COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); -- cgit v1.2.3-55-g7522 From ae67d58d0546ad3e1ef323d69de6c3708022791f Mon Sep 17 00:00:00 2001 From: Mathieu Malaterre Date: Fri, 25 May 2018 14:48:00 -0700 Subject: init/main.c: include In commit c7753208a94c ("x86, swiotlb: Add memory encryption support") a call to function `mem_encrypt_init' was added. Include prototype defined in header to prevent a warning reported during compilation with W=1: init/main.c:494:20: warning: no previous prototype for `mem_encrypt_init' [-Wmissing-prototypes] Link: http://lkml.kernel.org/r/20180522195533.31415-1-malat@debian.org Signed-off-by: Mathieu Malaterre Reviewed-by: Andrew Morton Acked-by: Steven Rostedt (VMware) Cc: Tom Lendacky Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Kees Cook Cc: Laura Abbott Cc: Dominik Brodowski Cc: Gargi Sharma Cc: Josh Poimboeuf Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- init/main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/init/main.c b/init/main.c index fd37315835b4..3b4ada11ed52 100644 --- a/init/main.c +++ b/init/main.c @@ -91,6 +91,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3-55-g7522 From d41362ed12b6402f0bba044037653f916757c3b2 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Fri, 25 May 2018 14:48:04 -0700 Subject: checkpatch: fix macro argument precedence test checkpatch's macro argument precedence test is broken so fix it. Link: http://lkml.kernel.org/r/5dd900e9197febc1995604bb33c23c136d8b33ce.camel@perches.com Signed-off-by: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- scripts/checkpatch.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index e16d6713f236..2d42eb9cd1a5 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -5041,7 +5041,7 @@ sub process { $tmp_stmt =~ s/\b(typeof|__typeof__|__builtin\w+|typecheck\s*\(\s*$Type\s*,|\#+)\s*\(*\s*$arg\s*\)*\b//g; $tmp_stmt =~ s/\#+\s*$arg\b//g; $tmp_stmt =~ s/\b$arg\s*\#\#//g; - my $use_cnt = $tmp_stmt =~ s/\b$arg\b//g; + my $use_cnt = () = $tmp_stmt =~ /\b$arg\b/g; if ($use_cnt > 1) { CHK("MACRO_ARG_REUSE", "Macro argument reuse '$arg' - possible side-effects?\n" . "$herectx"); -- cgit v1.2.3-55-g7522 From ed1596f9ab958dd156a66c9ff1029d3761c1786a Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 25 May 2018 14:48:08 -0700 Subject: kasan: free allocated shadow memory on MEM_CANCEL_ONLINE We have to free memory again when we cancel onlining, otherwise a later onlining attempt will fail. Link: http://lkml.kernel.org/r/20180522100756.18478-2-david@redhat.com Fixes: fa69b5989bb0 ("mm/kasan: add support for memory hotplug") Signed-off-by: David Hildenbrand Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 7160028efd12..721e00837f00 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -866,6 +866,7 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb, kmemleak_ignore(ret); return NOTIFY_OK; } + case MEM_CANCEL_ONLINE: case MEM_OFFLINE: { struct vm_struct *vm; -- cgit v1.2.3-55-g7522 From 3f1959721558a976aaf9c2024d5bc884e6411bf7 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 25 May 2018 14:48:11 -0700 Subject: kasan: fix memory hotplug during boot Using module_init() is wrong. E.g. ACPI adds and onlines memory before our memory notifier gets registered. This makes sure that ACPI memory detected during boot up will not result in a kernel crash. Easily reproducible with QEMU, just specify a DIMM when starting up. Link: http://lkml.kernel.org/r/20180522100756.18478-3-david@redhat.com Fixes: 786a8959912e ("kasan: disable memory hotplug") Signed-off-by: David Hildenbrand Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/kasan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index 721e00837f00..f185455b3406 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -898,5 +898,5 @@ static int __init kasan_memhotplug_init(void) return 0; } -module_init(kasan_memhotplug_init); +core_initcall(kasan_memhotplug_init); #endif -- cgit v1.2.3-55-g7522