From 09cbfeaf1a5a67bfb3201e0c83c810cecb2efa5a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 1 Apr 2016 15:29:47 +0300 Subject: mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/ceph/libceph.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index e7975e4681e1..db92a8d4926e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -176,8 +176,8 @@ extern void ceph_put_snap_context(struct ceph_snap_context *sc); */ static inline int calc_pages_for(u64 off, u64 len) { - return ((off+len+PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT) - - (off >> PAGE_CACHE_SHIFT); + return ((off+len+PAGE_SIZE-1) >> PAGE_SHIFT) - + (off >> PAGE_SHIFT); } extern struct kmem_cache *ceph_inode_cachep; -- cgit v1.2.3 From 6c1ea260f89709e0021d2c59f8fd2a104b5b1123 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 11 Apr 2016 19:34:49 +0200 Subject: libceph: make authorizer destruction independent of ceph_auth_client Starting the kernel client with cephx disabled and then enabling cephx and restarting userspace daemons can result in a crash: [262671.478162] BUG: unable to handle kernel paging request at ffffebe000000000 [262671.531460] IP: [] kfree+0x5a/0x130 [262671.584334] PGD 0 [262671.635847] Oops: 0000 [#1] SMP [262672.055841] CPU: 22 PID: 2961272 Comm: kworker/22:2 Not tainted 4.2.0-34-generic #39~14.04.1-Ubuntu [262672.162338] Hardware name: Dell Inc. PowerEdge R720/068CDY, BIOS 2.4.3 07/09/2014 [262672.268937] Workqueue: ceph-msgr con_work [libceph] [262672.322290] task: ffff88081c2d0dc0 ti: ffff880149ae8000 task.ti: ffff880149ae8000 [262672.428330] RIP: 0010:[] [] kfree+0x5a/0x130 [262672.535880] RSP: 0018:ffff880149aeba58 EFLAGS: 00010286 [262672.589486] RAX: 000001e000000000 RBX: 0000000000000012 RCX: ffff8807e7461018 [262672.695980] RDX: 000077ff80000000 RSI: ffff88081af2be04 RDI: 0000000000000012 [262672.803668] RBP: ffff880149aeba78 R08: 0000000000000000 R09: 0000000000000000 [262672.912299] R10: ffffebe000000000 R11: ffff880819a60e78 R12: ffff8800aec8df40 [262673.021769] R13: ffffffffc035f70f R14: ffff8807e5b138e0 R15: ffff880da9785840 [262673.131722] FS: 0000000000000000(0000) GS:ffff88081fac0000(0000) knlGS:0000000000000000 [262673.245377] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [262673.303281] CR2: ffffebe000000000 CR3: 0000000001c0d000 CR4: 00000000001406e0 [262673.417556] Stack: [262673.472943] ffff880149aeba88 ffff88081af2be04 ffff8800aec8df40 ffff88081af2be04 [262673.583767] ffff880149aeba98 ffffffffc035f70f ffff880149aebac8 ffff8800aec8df00 [262673.694546] ffff880149aebac8 ffffffffc035c89e ffff8807e5b138e0 ffff8805b047f800 [262673.805230] Call Trace: [262673.859116] [] ceph_x_destroy_authorizer+0x1f/0x50 [libceph] [262673.968705] [] ceph_auth_destroy_authorizer+0x3e/0x60 [libceph] [262674.078852] [] put_osd+0x45/0x80 [libceph] [262674.134249] [] remove_osd+0xae/0x140 [libceph] [262674.189124] [] __reset_osd+0x103/0x150 [libceph] [262674.243749] [] kick_requests+0x223/0x460 [libceph] [262674.297485] [] ceph_osdc_handle_map+0x282/0x5e0 [libceph] [262674.350813] [] dispatch+0x4e/0x720 [libceph] [262674.403312] [] try_read+0x3d1/0x1090 [libceph] [262674.454712] [] ? dequeue_entity+0x152/0x690 [262674.505096] [] con_work+0xcb/0x1300 [libceph] [262674.555104] [] process_one_work+0x14e/0x3d0 [262674.604072] [] worker_thread+0x11a/0x470 [262674.652187] [] ? rescuer_thread+0x310/0x310 [262674.699022] [] kthread+0xd2/0xf0 [262674.744494] [] ? kthread_create_on_node+0x1c0/0x1c0 [262674.789543] [] ret_from_fork+0x3f/0x70 [262674.834094] [] ? kthread_create_on_node+0x1c0/0x1c0 What happens is the following: (1) new MON session is established (2) old "none" ac is destroyed (3) new "cephx" ac is constructed ... (4) old OSD session (w/ "none" authorizer) is put ceph_auth_destroy_authorizer(ac, osd->o_auth.authorizer) osd->o_auth.authorizer in the "none" case is just a bare pointer into ac, which contains a single static copy for all services. By the time we get to (4), "none" ac, freed in (2), is long gone. On top of that, a new vtable installed in (3) points us at ceph_x_destroy_authorizer(), so we end up trying to destroy a "none" authorizer with a "cephx" destructor operating on invalid memory! To fix this, decouple authorizer destruction from ac and do away with a single static "none" authorizer by making a copy for each OSD or MDS session. Authorizers themselves are independent of ac and so there is no reason for destroy_authorizer() to be an ac op. Make it an op on the authorizer itself by turning ceph_authorizer into a real struct. Fixes: http://tracker.ceph.com/issues/15447 Reported-by: Alan Zhang Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/auth.h | 10 +++++----- include/linux/ceph/osd_client.h | 1 - 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux/ceph') diff --git a/include/linux/ceph/auth.h b/include/linux/ceph/auth.h index 260d78b587c4..1563265d2097 100644 --- a/include/linux/ceph/auth.h +++ b/include/linux/ceph/auth.h @@ -12,9 +12,12 @@ */ struct ceph_auth_client; -struct ceph_authorizer; struct ceph_msg; +struct ceph_authorizer { + void (*destroy)(struct ceph_authorizer *); +}; + struct ceph_auth_handshake { struct ceph_authorizer *authorizer; void *authorizer_buf; @@ -62,8 +65,6 @@ struct ceph_auth_client_ops { struct ceph_auth_handshake *auth); int (*verify_authorizer_reply)(struct ceph_auth_client *ac, struct ceph_authorizer *a, size_t len); - void (*destroy_authorizer)(struct ceph_auth_client *ac, - struct ceph_authorizer *a); void (*invalidate_authorizer)(struct ceph_auth_client *ac, int peer_type); @@ -112,8 +113,7 @@ extern int ceph_auth_is_authenticated(struct ceph_auth_client *ac); extern int ceph_auth_create_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *auth); -extern void ceph_auth_destroy_authorizer(struct ceph_auth_client *ac, - struct ceph_authorizer *a); +void ceph_auth_destroy_authorizer(struct ceph_authorizer *a); extern int ceph_auth_update_authorizer(struct ceph_auth_client *ac, int peer_type, struct ceph_auth_handshake *a); diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4343df806710..cbf460927c42 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -16,7 +16,6 @@ struct ceph_msg; struct ceph_snap_context; struct ceph_osd_request; struct ceph_osd_client; -struct ceph_authorizer; /* * completion callback for async writepages -- cgit v1.2.3