From 630dc25e43dacfb5af94cd41532e77c47ec1caff Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 5 Dec 2022 16:08:57 +0100 Subject: mm/swap: fix SWP_PFN_BITS with CONFIG_PHYS_ADDR_T_64BIT on 32bit We use "unsigned long" to store a PFN in the kernel and phys_addr_t to store a physical address. On a 64bit system, both are 64bit wide. However, on a 32bit system, the latter might be 64bit wide. This is, for example, the case on x86 with PAE: phys_addr_t and PTEs are 64bit wide, while "unsigned long" only spans 32bit. The current definition of SWP_PFN_BITS without MAX_PHYSMEM_BITS misses that case, and assumes that the maximum PFN is limited by an 32bit phys_addr_t. This implies, that SWP_PFN_BITS will currently only be able to cover 4 GiB - 1 on any 32bit system with 4k page size, which is wrong. Let's rely on the number of bits in phys_addr_t instead, but make sure to not exceed the maximum swap offset, to not make the BUILD_BUG_ON() in is_pfn_swap_entry() unhappy. Note that swp_entry_t is effectively an unsigned long and the maximum swap offset shares that value with the swap type. For example, on an 8 GiB x86 PAE system with a kernel config based on Debian 11.5 (-> CONFIG_FLATMEM=y, CONFIG_X86_PAE=y), we will currently fail removing migration entries (remove_migration_ptes()), because mm/page_vma_mapped.c:check_pte() will fail to identify a PFN match as swp_offset_pfn() wrongly masks off PFN bits. For example, split_huge_page_to_list()->...->remap_page() will leave migration entries in place and continue to unlock the page. Later, when we stumble over these migration entries (e.g., via /proc/self/pagemap), pfn_swap_entry_to_page() will BUG_ON() because these migration entries shouldn't exist anymore and the page was unlocked. [ 33.067591] kernel BUG at include/linux/swapops.h:497! [ 33.067597] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI [ 33.067602] CPU: 3 PID: 742 Comm: cow Tainted: G E 6.1.0-rc8+ #16 [ 33.067605] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014 [ 33.067606] EIP: pagemap_pmd_range+0x644/0x650 [ 33.067612] Code: 00 00 00 00 66 90 89 ce b9 00 f0 ff ff e9 ff fb ff ff 89 d8 31 db e8 48 c6 52 00 e9 23 fb ff ff e8 61 83 56 00 e9 b6 fe ff ff <0f> 0b bf 00 f0 ff ff e9 38 fa ff ff 3e 8d 74 26 00 55 89 e5 57 31 [ 33.067615] EAX: ee394000 EBX: 00000002 ECX: ee394000 EDX: 00000000 [ 33.067617] ESI: c1b0ded4 EDI: 00024a00 EBP: c1b0ddb4 ESP: c1b0dd68 [ 33.067619] DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068 EFLAGS: 00010246 [ 33.067624] CR0: 80050033 CR2: b7a00000 CR3: 01bbbd20 CR4: 00350ef0 [ 33.067625] Call Trace: [ 33.067628] ? madvise_free_pte_range+0x720/0x720 [ 33.067632] ? smaps_pte_range+0x4b0/0x4b0 [ 33.067634] walk_pgd_range+0x325/0x720 [ 33.067637] ? mt_find+0x1d6/0x3a0 [ 33.067641] ? mt_find+0x1d6/0x3a0 [ 33.067643] __walk_page_range+0x164/0x170 [ 33.067646] walk_page_range+0xf9/0x170 [ 33.067648] ? __kmem_cache_alloc_node+0x2a8/0x340 [ 33.067653] pagemap_read+0x124/0x280 [ 33.067658] ? default_llseek+0x101/0x160 [ 33.067662] ? smaps_account+0x1d0/0x1d0 [ 33.067664] vfs_read+0x90/0x290 [ 33.067667] ? do_madvise.part.0+0x24b/0x390 [ 33.067669] ? debug_smp_processor_id+0x12/0x20 [ 33.067673] ksys_pread64+0x58/0x90 [ 33.067675] __ia32_sys_ia32_pread64+0x1b/0x20 [ 33.067680] __do_fast_syscall_32+0x4c/0xc0 [ 33.067683] do_fast_syscall_32+0x29/0x60 [ 33.067686] do_SYSENTER_32+0x15/0x20 [ 33.067689] entry_SYSENTER_32+0x98/0xf1 Decrease the indentation level of SWP_PFN_BITS and SWP_PFN_MASK to keep it readable and consistent. [david@redhat.com: rely on sizeof(phys_addr_t) and min_t() instead] Link: https://lkml.kernel.org/r/20221206105737.69478-1-david@redhat.com [david@redhat.com: use "int" for comparison, as we're only comparing numbers < 64] Link: https://lkml.kernel.org/r/1f157500-2676-7cef-a84e-9224ed64e540@redhat.com Link: https://lkml.kernel.org/r/20221205150857.167583-1-david@redhat.com Fixes: 0d206b5d2e0d ("mm/swap: add swp_offset_pfn() to fetch PFN from swap entry") Signed-off-by: David Hildenbrand Acked-by: Peter Xu Reviewed-by: Yang Shi Cc: Hugh Dickins Cc: Andrea Arcangeli Signed-off-by: Andrew Morton --- include/linux/swapops.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 86b95ccb81bb..b07b277d6a16 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -33,11 +33,13 @@ * can use the extra bits to store other information besides PFN. */ #ifdef MAX_PHYSMEM_BITS -#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) #else /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#define SWP_PFN_BITS min_t(int, \ + sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \ + SWP_TYPE_SHIFT) #endif /* MAX_PHYSMEM_BITS */ -#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) /** * Migration swap entry specific bitfield definitions. Layout: -- cgit v1.2.3 From 4a7ba45b1a435e7097ca0f79a847d0949d0eb088 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 7 Dec 2022 16:53:15 -1000 Subject: memcg: fix possible use-after-free in memcg_write_event_control() memcg_write_event_control() accesses the dentry->d_name of the specified control fd to route the write call. As a cgroup interface file can't be renamed, it's safe to access d_name as long as the specified file is a regular cgroup file. Also, as these cgroup interface files can't be removed before the directory, it's safe to access the parent too. Prior to 347c4a874710 ("memcg: remove cgroup_event->cft"), there was a call to __file_cft() which verified that the specified file is a regular cgroupfs file before further accesses. The cftype pointer returned from __file_cft() was no longer necessary and the commit inadvertently dropped the file type check with it allowing any file to slip through. With the invarients broken, the d_name and parent accesses can now race against renames and removals of arbitrary files and cause use-after-free's. Fix the bug by resurrecting the file type check in __file_cft(). Now that cgroupfs is implemented through kernfs, checking the file operations needs to go through a layer of indirection. Instead, let's check the superblock and dentry type. Link: https://lkml.kernel.org/r/Y5FRm/cfcKPGzWwl@slm.duckdns.org Fixes: 347c4a874710 ("memcg: remove cgroup_event->cft") Signed-off-by: Tejun Heo Reported-by: Jann Horn Acked-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Linus Torvalds Cc: Michal Hocko Cc: Muchun Song Cc: Shakeel Butt Cc: [3.14+] Signed-off-by: Andrew Morton --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup-internal.h | 1 - mm/memcontrol.c | 15 +++++++++++++-- 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 528bd44b59e2..2b7d077de7ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -68,6 +68,7 @@ struct css_task_iter { struct list_head iters_node; /* css_set->task_iters */ }; +extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index fd4020835ec6..367b0a42ada9 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -167,7 +167,6 @@ struct cgroup_mgctx { extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; -extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a1a35c12635e..266a1ab05434 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4832,6 +4832,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, unsigned int efd, cfd; struct fd efile; struct fd cfile; + struct dentry *cdentry; const char *name; char *endp; int ret; @@ -4885,6 +4886,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, if (ret < 0) goto out_put_cfile; + /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + /* * Determine the event callbacks and set them in @event. This used * to be done via struct cftype but cgroup core no longer knows @@ -4893,7 +4904,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_path.dentry->d_name.name; + name = cdentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4917,7 +4928,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) -- cgit v1.2.3