From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions When using eBPF to probe CS CALL instructions within a function, a crash can be triggered. The eBPF tool probes offset 257 of the __hrtimer_run_queues() function: <__hrtimer_run_queues+249>: nopl 0x0(%rax,%rax,1) <__hrtimer_run_queues+254>: mov %r14,%rdi <__hrtimer_run_queues+257>: cs call <__x86_indirect_thunk_r12> <__hrtimer_run_queues+263>: mov %eax,%r12d <__hrtimer_run_queues+266>: xchg %ax,%ax <__hrtimer_run_queues+268>: mov %r13,%rdi Which triggers this crash: BUG: unable to handle page fault for address: 00000000000f41c9 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP NOPTI CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P RIP: 0010:__hrtimer_run_queues+0x106/0x230 Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is at the 6th byte of the above CS CALL instruction. Since the CS CALL instruction occupies 6 bytes, the exception occurred in the middle of that call instruction. The root cause is that when using eBPF tools to probe in the middle of a function, a kprobe with INT3 is used as the underlying implementation. During single-step emulation of the original CALL instruction, int3_emulate_call() assumes that the probed CALL instruction is 5 bytes long. However, the actual CS-prefixed CALL instruction occupies 6 bytes, so it constructs an incorrect exception return address. When the CPU returns from the kprobe handler, the next instruction to be executed is at the address of the last byte of that CS CALL instruction. Coincidentally, starting from that address, the CPU fetches and decodes a completely different instruction, which ultimately triggers a kernel crash. Fix the issue by using the actual instruction length obtained from the instruction decoder when constructing the exception return address, rather than relying on the hardcoded CALL_INSN_SIZE macro. [ mingo: Refined the changelog ] Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step") Suggested-by: Masami Hiramatsu (Google) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- Documentation/filesystems/ceph.rst | 227 +++++++++++++++++++++++++++++++++++++ 1 file changed, 227 insertions(+) create mode 100644 Documentation/filesystems/ceph.rst (limited to 'Documentation/filesystems/ceph.rst') diff --git a/Documentation/filesystems/ceph.rst b/Documentation/filesystems/ceph.rst new file mode 100644 index 000000000..ee2ca0c0c --- /dev/null +++ b/Documentation/filesystems/ceph.rst @@ -0,0 +1,227 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================ +Ceph Distributed File System +============================ + +Ceph is a distributed network file system designed to provide good +performance, reliability, and scalability. + +Basic features include: + + * POSIX semantics + * Seamless scaling from 1 to many thousands of nodes + * High availability and reliability. No single point of failure. + * N-way replication of data across storage nodes + * Fast recovery from node failures + * Automatic rebalancing of data on node addition/removal + * Easy deployment: most FS components are userspace daemons + +Also, + + * Flexible snapshots (on any directory) + * Recursive accounting (nested files, directories, bytes) + +In contrast to cluster filesystems like GFS, OCFS2, and GPFS that rely +on symmetric access by all clients to shared block devices, Ceph +separates data and metadata management into independent server +clusters, similar to Lustre. Unlike Lustre, however, metadata and +storage nodes run entirely as user space daemons. File data is striped +across storage nodes in large chunks to distribute workload and +facilitate high throughputs. When storage nodes fail, data is +re-replicated in a distributed fashion by the storage nodes themselves +(with some minimal coordination from a cluster monitor), making the +system extremely efficient and scalable. + +Metadata servers effectively form a large, consistent, distributed +in-memory cache above the file namespace that is extremely scalable, +dynamically redistributes metadata in response to workload changes, +and can tolerate arbitrary (well, non-Byzantine) node failures. The +metadata server takes a somewhat unconventional approach to metadata +storage to significantly improve performance for common workloads. In +particular, inodes with only a single link are embedded in +directories, allowing entire directories of dentries and inodes to be +loaded into its cache with a single I/O operation. The contents of +extremely large directories can be fragmented and managed by +independent metadata servers, allowing scalable concurrent access. + +The system offers automatic data rebalancing/migration when scaling +from a small cluster of just a few nodes to many hundreds, without +requiring an administrator carve the data set into static volumes or +go through the tedious process of migrating data between servers. +When the file system approaches full, new nodes can be easily added +and things will "just work." + +Ceph includes flexible snapshot mechanism that allows a user to create +a snapshot on any subdirectory (and its nested contents) in the +system. Snapshot creation and deletion are as simple as 'mkdir +.snap/foo' and 'rmdir .snap/foo'. + +Snapshot names have two limitations: + +* They can not start with an underscore ('_'), as these names are reserved + for internal usage by the MDS. +* They can not exceed 240 characters in size. This is because the MDS makes + use of long snapshot names internally, which follow the format: + `__`. Since filenames in general can't have + more than 255 characters, and `` takes 13 characters, the long + snapshot names can take as much as 255 - 1 - 1 - 13 = 240. + +Ceph also provides some recursive accounting on directories for nested files +and bytes. You can run the commands:: + + getfattr -n ceph.dir.rfiles /some/dir + getfattr -n ceph.dir.rbytes /some/dir + +to get the total number of nested files and their combined size, respectively. +This makes the identification of large disk space consumers relatively quick, +as no 'du' or similar recursive scan of the file system is required. + +Finally, Ceph also allows quotas to be set on any directory in the system. +The quota can restrict the number of bytes or the number of files stored +beneath that point in the directory hierarchy. Quotas can be set using +extended attributes 'ceph.quota.max_files' and 'ceph.quota.max_bytes', eg:: + + setfattr -n ceph.quota.max_bytes -v 100000000 /some/dir + getfattr -n ceph.quota.max_bytes /some/dir + +A limitation of the current quotas implementation is that it relies on the +cooperation of the client mounting the file system to stop writers when a +limit is reached. A modified or adversarial client cannot be prevented +from writing as much data as it needs. + +Mount Syntax +============ + +The basic mount syntax is:: + + # mount -t ceph user@fsid.fs_name=/[subdir] mnt -o mon_addr=monip1[:port][/monip2[:port]] + +You only need to specify a single monitor, as the client will get the +full list when it connects. (However, if the monitor you specify +happens to be down, the mount won't succeed.) The port can be left +off if the monitor is using the default. So if the monitor is at +1.2.3.4:: + + # mount -t ceph cephuser@07fe3187-00d9-42a3-814b-72a4d5e7d5be.cephfs=/ /mnt/ceph -o mon_addr=1.2.3.4 + +is sufficient. If /sbin/mount.ceph is installed, a hostname can be +used instead of an IP address and the cluster FSID can be left out +(as the mount helper will fill it in by reading the ceph configuration +file):: + + # mount -t ceph cephuser@cephfs=/ /mnt/ceph -o mon_addr=mon-addr + +Multiple monitor addresses can be passed by separating each address with a slash (`/`):: + + # mount -t ceph cephuser@cephfs=/ /mnt/ceph -o mon_addr=192.168.1.100/192.168.1.101 + +When using the mount helper, monitor address can be read from ceph +configuration file if available. Note that, the cluster FSID (passed as part +of the device string) is validated by checking it with the FSID reported by +the monitor. + +Mount Options +============= + + mon_addr=ip_address[:port][/ip_address[:port]] + Monitor address to the cluster. This is used to bootstrap the + connection to the cluster. Once connection is established, the + monitor addresses in the monitor map are followed. + + fsid=cluster-id + FSID of the cluster (from `ceph fsid` command). + + ip=A.B.C.D[:N] + Specify the IP and/or port the client should bind to locally. + There is normally not much reason to do this. If the IP is not + specified, the client's IP address is determined by looking at the + address its connection to the monitor originates from. + + wsize=X + Specify the maximum write size in bytes. Default: 64 MB. + + rsize=X + Specify the maximum read size in bytes. Default: 64 MB. + + rasize=X + Specify the maximum readahead size in bytes. Default: 8 MB. + + mount_timeout=X + Specify the timeout value for mount (in seconds), in the case + of a non-responsive Ceph file system. The default is 60 + seconds. + + caps_max=X + Specify the maximum number of caps to hold. Unused caps are released + when number of caps exceeds the limit. The default is 0 (no limit) + + rbytes + When stat() is called on a directory, set st_size to 'rbytes', + the summation of file sizes over all files nested beneath that + directory. This is the default. + + norbytes + When stat() is called on a directory, set st_size to the + number of entries in that directory. + + nocrc + Disable CRC32C calculation for data writes. If set, the storage node + must rely on TCP's error correction to detect data corruption + in the data payload. + + dcache + Use the dcache contents to perform negative lookups and + readdir when the client has the entire directory contents in + its cache. (This does not change correctness; the client uses + cached metadata only when a lease or capability ensures it is + valid.) + + nodcache + Do not use the dcache as above. This avoids a significant amount of + complex code, sacrificing performance without affecting correctness, + and is useful for tracking down bugs. + + noasyncreaddir + Do not use the dcache as above for readdir. + + noquotadf + Report overall filesystem usage in statfs instead of using the root + directory quota. + + nocopyfrom + Don't use the RADOS 'copy-from' operation to perform remote object + copies. Currently, it's only used in copy_file_range, which will revert + to the default VFS implementation if this option is used. + + nearfull_sync + Force written data to stable storage when the cluster or file data pool is + marked NEARFULL. This restores the legacy client-side backpressure + behavior. By default, CephFS writes are not forced synchronous solely + because of NEARFULL. + + recover_session= + Set auto reconnect mode in the case where the client is blocklisted. The + available modes are "no" and "clean". The default is "no". + + * no: never attempt to reconnect when client detects that it has been + blocklisted. Operations will generally fail after being blocklisted. + + * clean: client reconnects to the ceph cluster automatically when it + detects that it has been blocklisted. During reconnect, client drops + dirty data/metadata, invalidates page caches and writable file handles. + After reconnect, file locks become stale because the MDS loses track + of them. If an inode contains any stale file locks, read/write on the + inode is not allowed until applications release all stale file locks. + +More Information +================ + +For more information on Ceph, see the home page at + https://ceph.com/ + +The Linux kernel client source tree is available at + - https://github.com/ceph/ceph-client.git + +and the source for the full system is at + https://github.com/ceph/ceph.git -- cgit v1.3.1