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 --- .../blockdev/drbd/DRBD-8.3-data-packets.svg | 588 +++++++++++++++++++++ .../blockdev/drbd/DRBD-data-packets.svg | 459 ++++++++++++++++ .../admin-guide/blockdev/drbd/conn-states-8.dot | 18 + .../blockdev/drbd/data-structure-v9.rst | 42 ++ .../admin-guide/blockdev/drbd/disk-states-8.dot | 16 + .../drbd/drbd-connection-state-overview.dot | 85 +++ .../admin-guide/blockdev/drbd/figures.rst | 30 ++ Documentation/admin-guide/blockdev/drbd/index.rst | 19 + .../admin-guide/blockdev/drbd/peer-states-8.dot | 8 + 9 files changed, 1265 insertions(+) create mode 100644 Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg create mode 100644 Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg create mode 100644 Documentation/admin-guide/blockdev/drbd/conn-states-8.dot create mode 100644 Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst create mode 100644 Documentation/admin-guide/blockdev/drbd/disk-states-8.dot create mode 100644 Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot create mode 100644 Documentation/admin-guide/blockdev/drbd/figures.rst create mode 100644 Documentation/admin-guide/blockdev/drbd/index.rst create mode 100644 Documentation/admin-guide/blockdev/drbd/peer-states-8.dot (limited to 'Documentation/admin-guide/blockdev/drbd') diff --git a/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg b/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg new file mode 100644 index 000000000..f87cfa0dc --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/DRBD-8.3-data-packets.svg @@ -0,0 +1,588 @@ + + + + + + Master slide + + + + + + + + + + RSDataReply + + + + + + + CsumRSRequest + + + + w_make_resync_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_csum_rs_req() + + + receive_RSDataReply() + + + drbd_endio_write_sec() + + + e_end_resync_block() + + + + + + WriteAck + + + + got_BlockAck() + + + Checksum based Resync, case not in sync + + + DRBD-8.3 data flow + + + w_e_send_csum() + + + + + + + + RSIsInSync + + + + + + + CsumRSRequest + + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_csum_rs_req() + + + got_IsInSync() + + + Checksum based Resync, case in sync + + + + + + + + + + OVReply + + + + + + + OVRequest + + + + receive_OVRequest() + + + drbd_endio_read_sec() + + + w_e_end_ov_req() + + + receive_OVReply() + + + drbd_endio_read_sec() + + + w_e_end_ov_reply() + + + + + + OVResult + + + + got_OVResult() + + + Online verify + + + w_make_ov_request() + + + + + + + + drbd_endio_read_sec() + + + w_make_resync_request() + + + w_e_send_csum() + + + + + drbd_endio_read_sec() + + + + + + rs_begin_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_complete_io() + + + rs_complete_io() + + diff --git a/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg b/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg new file mode 100644 index 000000000..48a1e2165 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/DRBD-data-packets.svg @@ -0,0 +1,459 @@ + + + + + + Master slide + + + + + + + + + RSDataReply + + + + + RSDataRequest + + + w_make_resync_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_rsdata_req() + + + receive_RSDataReply() + + + drbd_endio_write_sec() + + + e_end_resync_block() + + + + + WriteAck + + + got_BlockAck() + + + Resync blocks, 4-32K + + + + + + + WriteAck + + + + + Data + + + drbd_make_request() + + + receive_Data() + + + drbd_endio_write_sec() + + + e_end_block() + + + got_BlockAck() + + + Regular mirrored write, 512-32K + + + w_send_dblock() + + + + + drbd_endio_write_pri() + + + + + + + DataReply + + + + + DataRequest + + + drbd_make_request() + + + receive_DataRequest() + + + drbd_endio_read_sec() + + + w_e_end_data_req() + + + Drawing + + receive_DataReply() + + + + Diskless read, 512-32K + + + w_send_read_req() + + + DRBD 8 data flow + + + + + + al_begin_io() + + + al_complete_io() + + + rs_begin_io() + + + rs_complete_io() + + + rs_begin_io() + + + rs_complete_io() + + diff --git a/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot b/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot new file mode 100644 index 000000000..025e8cf5e --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/conn-states-8.dot @@ -0,0 +1,18 @@ +digraph conn_states { + StandAllone -> WFConnection [ label = "ioctl_set_net()" ] + WFConnection -> Unconnected [ label = "unable to bind()" ] + WFConnection -> WFReportParams [ label = "in connect() after accept" ] + WFReportParams -> StandAllone [ label = "checks in receive_param()" ] + WFReportParams -> Connected [ label = "in receive_param()" ] + WFReportParams -> WFBitMapS [ label = "sync_handshake()" ] + WFReportParams -> WFBitMapT [ label = "sync_handshake()" ] + WFBitMapS -> SyncSource [ label = "receive_bitmap()" ] + WFBitMapT -> SyncTarget [ label = "receive_bitmap()" ] + SyncSource -> Connected + SyncTarget -> Connected + SyncSource -> PausedSyncS + SyncTarget -> PausedSyncT + PausedSyncS -> SyncSource + PausedSyncT -> SyncTarget + Connected -> WFConnection [ label = "* on network error" ] +} diff --git a/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst b/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst new file mode 100644 index 000000000..66036b901 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/data-structure-v9.rst @@ -0,0 +1,42 @@ +================================ +kernel data structure for DRBD-9 +================================ + +This describes the in kernel data structure for DRBD-9. Starting with +Linux v3.14 we are reorganizing DRBD to use this data structure. + +Basic Data Structure +==================== + +A node has a number of DRBD resources. Each such resource has a number of +devices (aka volumes) and connections to other nodes ("peer nodes"). Each DRBD +device is represented by a block device locally. + +The DRBD objects are interconnected to form a matrix as depicted below; a +drbd_peer_device object sits at each intersection between a drbd_device and a +drbd_connection:: + + /--------------+---------------+.....+---------------\ + | resource | device | | device | + +--------------+---------------+.....+---------------+ + | connection | peer_device | | peer_device | + +--------------+---------------+.....+---------------+ + : : : : : + : : : : : + +--------------+---------------+.....+---------------+ + | connection | peer_device | | peer_device | + \--------------+---------------+.....+---------------/ + +In this table, horizontally, devices can be accessed from resources by their +volume number. Likewise, peer_devices can be accessed from connections by +their volume number. Objects in the vertical direction are connected by double +linked lists. There are back pointers from peer_devices to their connections a +devices, and from connections and devices to their resource. + +All resources are in the drbd_resources double-linked list. In addition, all +devices can be accessed by their minor device number via the drbd_devices idr. + +The drbd_resource, drbd_connection, and drbd_device objects are reference +counted. The peer_device objects only serve to establish the links between +devices and connections; their lifetime is determined by the lifetime of the +device and connection which they reference. diff --git a/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot b/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot new file mode 100644 index 000000000..d06cfb46f --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/disk-states-8.dot @@ -0,0 +1,16 @@ +digraph disk_states { + Diskless -> Inconsistent [ label = "ioctl_set_disk()" ] + Diskless -> Consistent [ label = "ioctl_set_disk()" ] + Diskless -> Outdated [ label = "ioctl_set_disk()" ] + Consistent -> Outdated [ label = "receive_param()" ] + Consistent -> UpToDate [ label = "receive_param()" ] + Consistent -> Inconsistent [ label = "start resync" ] + Outdated -> Inconsistent [ label = "start resync" ] + UpToDate -> Inconsistent [ label = "ioctl_replicate" ] + Inconsistent -> UpToDate [ label = "resync completed" ] + Consistent -> Failed [ label = "io completion error" ] + Outdated -> Failed [ label = "io completion error" ] + UpToDate -> Failed [ label = "io completion error" ] + Inconsistent -> Failed [ label = "io completion error" ] + Failed -> Diskless [ label = "sending notify to peer" ] +} diff --git a/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot b/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot new file mode 100644 index 000000000..6d9cf0a7b --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/drbd-connection-state-overview.dot @@ -0,0 +1,85 @@ +// vim: set sw=2 sts=2 : +digraph { + rankdir=BT + bgcolor=white + + node [shape=plaintext] + node [fontcolor=black] + + StandAlone [ style=filled,fillcolor=gray,label=StandAlone ] + + node [fontcolor=lightgray] + + Unconnected [ label=Unconnected ] + + CommTrouble [ shape=record, + label="{communication loss|{Timeout|BrokenPipe|NetworkFailure}}" ] + + node [fontcolor=gray] + + subgraph cluster_try_connect { + label="try to connect, handshake" + rank=max + WFConnection [ label=WFConnection ] + WFReportParams [ label=WFReportParams ] + } + + TearDown [ label=TearDown ] + + Connected [ label=Connected,style=filled,fillcolor=green,fontcolor=black ] + + node [fontcolor=lightblue] + + StartingSyncS [ label=StartingSyncS ] + StartingSyncT [ label=StartingSyncT ] + + subgraph cluster_bitmap_exchange { + node [fontcolor=red] + fontcolor=red + label="new application (WRITE?) requests blocked\lwhile bitmap is exchanged" + + WFBitMapT [ label=WFBitMapT ] + WFSyncUUID [ label=WFSyncUUID ] + WFBitMapS [ label=WFBitMapS ] + } + + node [fontcolor=blue] + + cluster_resync [ shape=record,label="{resynchronisation process running\l'concurrent' application requests allowed|{{PausedSyncT\nSyncTarget}|{PausedSyncS\nSyncSource}}}" ] + + node [shape=box,fontcolor=black] + + // drbdadm [label="drbdadm connect"] + // handshake [label="drbd_connect()\ndrbd_do_handshake\ndrbd_sync_handshake() etc."] + // comm_error [label="communication trouble"] + + // + // edges + // -------------------------------------- + + StandAlone -> Unconnected [ label="drbdadm connect" ] + Unconnected -> StandAlone [ label="drbdadm disconnect\lor serious communication trouble" ] + Unconnected -> WFConnection [ label="receiver thread is started" ] + WFConnection -> WFReportParams [ headlabel="accept()\land/or \lconnect()\l" ] + + WFReportParams -> StandAlone [ label="during handshake\lpeers do not agree\labout something essential" ] + WFReportParams -> Connected [ label="data identical\lno sync needed",color=green,fontcolor=green ] + + WFReportParams -> WFBitMapS + WFReportParams -> WFBitMapT + WFBitMapT -> WFSyncUUID [minlen=0.1,constraint=false] + + WFBitMapS -> cluster_resync:S + WFSyncUUID -> cluster_resync:T + + edge [color=green] + cluster_resync:any -> Connected [ label="resnyc done",fontcolor=green ] + + edge [color=red] + WFReportParams -> CommTrouble + Connected -> CommTrouble + cluster_resync:any -> CommTrouble + edge [color=black] + CommTrouble -> Unconnected [label="receiver thread is stopped" ] + +} diff --git a/Documentation/admin-guide/blockdev/drbd/figures.rst b/Documentation/admin-guide/blockdev/drbd/figures.rst new file mode 100644 index 000000000..9f73253ea --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/figures.rst @@ -0,0 +1,30 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. The here included files are intended to help understand the implementation + +Data flows that Relate some functions, and write packets +======================================================== + +.. kernel-figure:: DRBD-8.3-data-packets.svg + :alt: DRBD-8.3-data-packets.svg + :align: center + +.. kernel-figure:: DRBD-data-packets.svg + :alt: DRBD-data-packets.svg + :align: center + + +Sub graphs of DRBD's state transitions +====================================== + +.. kernel-figure:: conn-states-8.dot + :alt: conn-states-8.dot + :align: center + +.. kernel-figure:: disk-states-8.dot + :alt: disk-states-8.dot + :align: center + +.. kernel-figure:: peer-states-8.dot + :alt: peer-states-8.dot + :align: center diff --git a/Documentation/admin-guide/blockdev/drbd/index.rst b/Documentation/admin-guide/blockdev/drbd/index.rst new file mode 100644 index 000000000..561fd1e35 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/index.rst @@ -0,0 +1,19 @@ +========================================== +Distributed Replicated Block Device - DRBD +========================================== + +Description +=========== + + DRBD is a shared-nothing, synchronously replicated block device. It + is designed to serve as a building block for high availability + clusters and in this context, is a "drop-in" replacement for shared + storage. Simplistically, you could see it as a network RAID 1. + + Please visit https://www.drbd.org to find out more. + +.. toctree:: + :maxdepth: 1 + + data-structure-v9 + figures diff --git a/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot new file mode 100644 index 000000000..6dc395495 --- /dev/null +++ b/Documentation/admin-guide/blockdev/drbd/peer-states-8.dot @@ -0,0 +1,8 @@ +digraph peer_states { + Secondary -> Primary [ label = "recv state packet" ] + Primary -> Secondary [ label = "recv state packet" ] + Primary -> Unknown [ label = "connection lost" ] + Secondary -> Unknown [ label = "connection lost" ] + Unknown -> Primary [ label = "connected" ] + Unknown -> Secondary [ label = "connected" ] +} -- cgit v1.3.1