DPDK patches and discussions
 help / color / mirror / Atom feed
From: Yipeng Wang <yipeng1.wang@intel.com>
To: pablo.de.lara.guarch@intel.com
Cc: dev@dpdk.org, yipeng1.wang@intel.com, bruce.richardson@intel.com,
	honnappa.nagarahalli@arm.com, vguvva@caviumnetworks.com,
	brijesh.s.singh@gmail.com
Subject: [dpdk-dev] [PATCH v4 2/8] hash: fix a multi-writer race condition
Date: Mon,  9 Jul 2018 03:44:57 -0700	[thread overview]
Message-ID: <1531133103-437316-3-git-send-email-yipeng1.wang@intel.com> (raw)
In-Reply-To: <1531133103-437316-1-git-send-email-yipeng1.wang@intel.com>

Current multi-writer implementation uses Intel TSX to
protect the cuckoo path moving but not the cuckoo
path searching. After searching, we need to verify again if
the same empty slot still exists at the begining of the TSX
region. Otherwise another writer could occupy the empty slot
before the TSX region. Current code does not verify.

Fixes: be856325cba3 ("hash: add scalable multi-writer insertion with Intel TSX")
Cc: stable@dpdk.org

Signed-off-by: Yipeng Wang <yipeng1.wang@intel.com>
Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com>
---
 lib/librte_hash/rte_cuckoo_hash_x86.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lib/librte_hash/rte_cuckoo_hash_x86.h b/lib/librte_hash/rte_cuckoo_hash_x86.h
index 2c5b017..981d7bd 100644
--- a/lib/librte_hash/rte_cuckoo_hash_x86.h
+++ b/lib/librte_hash/rte_cuckoo_hash_x86.h
@@ -66,6 +66,9 @@ rte_hash_cuckoo_move_insert_mw_tm(const struct rte_hash *h,
 	while (try < RTE_HASH_TSX_MAX_RETRY) {
 		status = rte_xbegin();
 		if (likely(status == RTE_XBEGIN_STARTED)) {
+			/* In case empty slot was gone before entering TSX */
+			if (curr_bkt->key_idx[curr_slot] != EMPTY_SLOT)
+				rte_xabort(RTE_XABORT_CUCKOO_PATH_INVALIDED);
 			while (likely(curr_node->prev != NULL)) {
 				prev_node = curr_node->prev;
 				prev_bkt = prev_node->bkt;
-- 
2.7.4

  parent reply	other threads:[~2018-07-09 17:52 UTC|newest]

Thread overview: 65+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-08 10:51 [dpdk-dev] [PATCH v1 0/3] Add read-write concurrency to rte_hash library Yipeng Wang
2018-06-08 10:51 ` [dpdk-dev] [PATCH v1 1/3] hash: add read and write concurrency support Yipeng Wang
2018-06-26 14:59   ` De Lara Guarch, Pablo
2018-06-08 10:51 ` [dpdk-dev] [PATCH v1 2/3] test: add test case for read write concurrency Yipeng Wang
2018-06-26 15:48   ` De Lara Guarch, Pablo
2018-06-08 10:51 ` [dpdk-dev] [PATCH v1 3/3] hash: add new API function to query the key count Yipeng Wang
2018-06-26 16:11   ` De Lara Guarch, Pablo
2018-06-29 12:24 ` [dpdk-dev] [PATCH v2 0/6] Add read-write concurrency to rte_hash library Yipeng Wang
2018-06-29 12:24   ` [dpdk-dev] [PATCH v2 1/6] hash: make duplicated code into functions Yipeng Wang
2018-07-06 10:04     ` De Lara Guarch, Pablo
2018-06-29 12:24   ` [dpdk-dev] [PATCH v2 2/6] hash: add read and write concurrency support Yipeng Wang
2018-07-06 17:11     ` De Lara Guarch, Pablo
2018-06-29 12:24   ` [dpdk-dev] [PATCH v2 3/6] test: add tests in hash table perf test Yipeng Wang
2018-07-06 17:17     ` De Lara Guarch, Pablo
2018-06-29 12:24   ` [dpdk-dev] [PATCH v2 4/6] test: add test case for read write concurrency Yipeng Wang
2018-07-06 17:31     ` De Lara Guarch, Pablo
2018-06-29 12:24   ` [dpdk-dev] [PATCH v2 5/6] hash: fix to have more accurate key slot size Yipeng Wang
2018-07-06 17:32     ` De Lara Guarch, Pablo
2018-06-29 12:24   ` [dpdk-dev] [PATCH v2 6/6] hash: add new API function to query the key count Yipeng Wang
2018-07-06 17:36     ` De Lara Guarch, Pablo
2018-07-06 19:46 ` [dpdk-dev] [PATCH v3 0/8] Add read-write concurrency to rte_hash library Yipeng Wang
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 1/8] hash: fix multiwriter lock memory allocation Yipeng Wang
2018-07-09 11:26     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 2/8] hash: fix a multi-writer bug Yipeng Wang
2018-07-09 14:16     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 3/8] hash: fix to have more accurate key slot size Yipeng Wang
2018-07-09 14:20     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 4/8] hash: make duplicated code into functions Yipeng Wang
2018-07-09 14:25     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 5/8] hash: add read and write concurrency support Yipeng Wang
2018-07-09 14:28     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 6/8] test: add tests in hash table perf test Yipeng Wang
2018-07-09 15:33     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 7/8] test: add test case for read write concurrency Yipeng Wang
2018-07-09 16:24     ` De Lara Guarch, Pablo
2018-07-06 19:46   ` [dpdk-dev] [PATCH v3 8/8] hash: add new API function to query the key count Yipeng Wang
2018-07-09 16:22     ` De Lara Guarch, Pablo
2018-07-09 10:44 ` [dpdk-dev] [PATCH v4 0/8] Add read-write concurrency to rte_hash library Yipeng Wang
2018-07-09 10:44   ` [dpdk-dev] [PATCH v4 1/8] hash: fix multiwriter lock memory allocation Yipeng Wang
2018-07-09 10:44   ` Yipeng Wang [this message]
2018-07-09 10:44   ` [dpdk-dev] [PATCH v4 3/8] hash: fix key slot size accuracy Yipeng Wang
2018-07-09 10:44   ` [dpdk-dev] [PATCH v4 4/8] hash: make duplicated code into functions Yipeng Wang
2018-07-09 10:45   ` [dpdk-dev] [PATCH v4 5/8] hash: add read and write concurrency support Yipeng Wang
2018-07-09 10:45   ` [dpdk-dev] [PATCH v4 6/8] test: add tests in hash table perf test Yipeng Wang
2018-07-09 10:45   ` [dpdk-dev] [PATCH v4 7/8] test: add test case for read write concurrency Yipeng Wang
2018-07-09 10:45   ` [dpdk-dev] [PATCH v4 8/8] hash: add new API function to query the key count Yipeng Wang
2018-07-10 18:00   ` [dpdk-dev] [PATCH v4 0/8] Add read-write concurrency to rte_hash library Honnappa Nagarahalli
2018-07-12  1:31     ` Wang, Yipeng1
2018-07-12  2:36       ` Honnappa Nagarahalli
2018-07-13  1:47         ` Wang, Yipeng1
2018-07-10 16:59 ` [dpdk-dev] [PATCH v5 " Yipeng Wang
2018-07-10 16:59   ` [dpdk-dev] [PATCH v5 1/8] hash: fix multiwriter lock memory allocation Yipeng Wang
2018-07-10 16:59   ` [dpdk-dev] [PATCH v5 2/8] hash: fix a multi-writer race condition Yipeng Wang
2018-07-10 16:59   ` [dpdk-dev] [PATCH v5 3/8] hash: fix key slot size accuracy Yipeng Wang
2018-07-10 16:59   ` [dpdk-dev] [PATCH v5 4/8] hash: make duplicated code into functions Yipeng Wang
2018-07-10 16:59   ` [dpdk-dev] [PATCH v5 5/8] hash: add read and write concurrency support Yipeng Wang
2018-07-11 20:49     ` Stephen Hemminger
2018-07-12  1:22       ` Wang, Yipeng1
2018-07-12 20:30         ` Thomas Monjalon
2018-07-13  1:55           ` Wang, Yipeng1
2018-08-17 12:51             ` ASM
2018-07-10 16:59   ` [dpdk-dev] [PATCH v5 6/8] test: add tests in hash table perf test Yipeng Wang
2018-07-10 17:00   ` [dpdk-dev] [PATCH v5 7/8] test: add test case for read write concurrency Yipeng Wang
2018-07-10 17:00   ` [dpdk-dev] [PATCH v5 8/8] hash: add new API function to query the key count Yipeng Wang
2018-07-12 21:03   ` [dpdk-dev] [PATCH v5 0/8] Add read-write concurrency to rte_hash library Thomas Monjalon

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1531133103-437316-3-git-send-email-yipeng1.wang@intel.com \
    --to=yipeng1.wang@intel.com \
    --cc=brijesh.s.singh@gmail.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=honnappa.nagarahalli@arm.com \
    --cc=pablo.de.lara.guarch@intel.com \
    --cc=vguvva@caviumnetworks.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).