aboutsummaryrefslogtreecommitdiffstats
path: root/tools/perf/scripts/python
diff options
context:
space:
mode:
authorChuck Lever <chuck.lever@oracle.com>2020-04-15 17:36:22 -0400
committerChuck Lever <chuck.lever@oracle.com>2020-04-27 10:58:30 -0400
commit0a8e7b7d08466b5fc52f8e96070acc116d82a8bb (patch)
tree5d970e9546b444a329fc41b466ceb0d31ebf4240 /tools/perf/scripts/python
parentSUNRPC: Fix GSS privacy computation of auth->au_ralign (diff)
downloadlinux-0a8e7b7d08466b5fc52f8e96070acc116d82a8bb.tar.gz
linux-0a8e7b7d08466b5fc52f8e96070acc116d82a8bb.zip
SUNRPC: Revert 241b1f419f0e ("SUNRPC: Remove xdr_buf_trim()")
I've noticed that when krb5i or krb5p security is in use, retransmitted requests are missing the server's duplicate reply cache. The computed checksum on the retransmitted request does not match the cached checksum, resulting in the server performing the retransmitted request again instead of returning the cached reply. The assumptions made when removing xdr_buf_trim() were not correct. In the send paths, the upper layer has already set the segment lengths correctly, and shorting the buffer's content is simply a matter of reducing buf->len. xdr_buf_trim() is the right answer in the receive/unwrap path on both the client and the server. The buffer segment lengths have to be shortened one-by-one. On the server side in particular, head.iov_len needs to be updated correctly to enable nfsd_cache_csum() to work correctly. The simple buf->len computation doesn't do that, and that results in checksumming stale data in the buffer. The problem isn't noticed until there's significant instability of the RPC transport. At that point, the reliability of retransmit detection on the server becomes crucial. Fixes: 241b1f419f0e ("SUNRPC: Remove xdr_buf_trim()") Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Diffstat (limited to 'tools/perf/scripts/python')
0 files changed, 0 insertions, 0 deletions
ed/topology.c?id=993f0b0510dad98b4e6e39506834dab0d13fd539&follow=1'>sched/topology: Fix off by one bugPeter Zijlstra1-1/+1 2018-11-03memory_hotplug: cond_resched in __remove_pagesMichal Hocko1-0/+1 2018-11-03bfs: add sanity check at bfs_fill_super()Tetsuo Handa1-3/+6 2018-11-03kernel/sysctl.c: remove duplicated includeMichael Schupikov1-1/+0 2018-11-03kernel/kexec_file.c: remove some duplicated includeszhong jiang1-2/+0 2018-11-03mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmaskMichal Hocko5-77/+40 2018-11-03ocfs2: fix clusters leak in ocfs2_defrag_extent()Larry Chen1-0/+17 2018-11-03ocfs2: dlmglue: clean up timestamp handlingArnd Bergmann1-17/+9 2018-11-03ocfs2: don't put and assigning null to bh allocated outsideChangwei Ge1-18/+59 2018-11-03ocfs2: fix a misuse a of brelse after failing ocfs2_check_dir_entryChangwei Ge1-2/+1 2018-11-03ocfs2: don't use iocb when EIOCBQUEUED returnsChangwei Ge1-2/+2 2018-11-03ocfs2: without quota support, avoid calling quota recoveryGuozhonghua1-17/+34 2018-11-03ocfs2: remove ocfs2_is_o2cb_active()Gang He3-10/+1 2018-11-03mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappingsAndrea Arcangeli1-2/+30 2018-11-03include/linux/notifier.h: SRCU: fix ctagsSam Protsenko1-2/+1 2018-11-03mm: handle no memcg case in memcg_kmem_charge() properlyRoman Gushchin1-1/+1 2018-11-02ARM: dts: stm32: update HASH1 dmas property on stm32mp157cAlexandre Torgue1-1/+1 2018-11-02ARM: orion: avoid VLA in orion_mpp_confArnd Bergmann1-1/+6 2018-11-02iov_iter: Fix 9p virtio breakageMarc Zyngier1-1/+1 2018-11-02cifs: fix signed/unsigned mismatch on aio_read patchSteve French1-6/+11 2018-11-02cifs: don't dereference smb_file_target before null checkColin Ian King1-2/+5 2018-11-02CIFS: Add direct I/O functions to file_operationsLong Li1-6/+4 2018-11-02CIFS: Add support for direct I/O writeLong Li2-41/+164 2018-11-02CIFS: Add support for direct I/O readLong Li3-39/+192 2018-11-02smb3: missing defines and structs for reparse point handlingSteve French2-0/+38 2018-11-02smb3: allow more detailed protocol info on open files for debuggingSteve French4-0/+65 2018-11-02smb3: on kerberos mount if server doesn't specify auth type use krb5Steve French1-2/+4 2018-11-02smb3: add trace point for tree connectionSteve French2-1/+44 2018-11-02cifs: fix spelling mistake, EACCESS -> EACCESColin Ian King2-3/+3 2018-11-02cifs: fix return value for cifs_listxattrRonnie Sahlberg1-5/+6