All of lore.kernel.org
 help / color / mirror / Atom feed
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	stable@vger.kernel.org, Alex Vesker <valex@mellanox.com>,
	Saeed Mahameed <saeedm@mellanox.com>
Subject: [PATCH 4.4 23/31] net/mlx5: Fix command interface race in polling mode
Date: Fri, 20 Jul 2018 14:13:53 +0200	[thread overview]
Message-ID: <20180720121340.992365177@linuxfoundation.org> (raw)
In-Reply-To: <20180720121340.158484922@linuxfoundation.org>

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Alex Vesker <valex@mellanox.com>

[ Upstream commit d412c31dae053bf30a1bc15582a9990df297a660 ]

The command interface can work in two modes: Events and Polling.
In the general case, each time we invoke a command, a work is
queued to handle it.

When working in events, the interrupt handler completes the
command execution. On the other hand, when working in polling
mode, the work itself completes it.

Due to a bug in the work handler, a command could have been
completed by the interrupt handler, while the work handler
hasn't finished yet, causing the it to complete once again
if the command interface mode was changed from Events to
polling after the interrupt handler was called.

mlx5_unload_one()
        mlx5_stop_eqs()
                // Destroy the EQ before cmd EQ
                ...cmd_work_handler()
                        write_doorbell()
                        --> EVENT_TYPE_CMD
                                mlx5_cmd_comp_handler() // First free
                                        free_ent(cmd, ent->idx)
                                        complete(&ent->done)

        <-- mlx5_stop_eqs //cmd was complete
                // move to polling before destroying the last cmd EQ
                mlx5_cmd_use_polling()
                        cmd->mode = POLL;

                --> cmd_work_handler (continues)
                        if (cmd->mode == POLL)
                                mlx5_cmd_comp_handler() // Double free

The solution is to store the cmd->mode before writing the doorbell.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -643,6 +643,7 @@ static void cmd_work_handler(struct work
 	struct semaphore *sem;
 	unsigned long flags;
 	int alloc_ret;
+	int cmd_mode;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
@@ -688,6 +689,7 @@ static void cmd_work_handler(struct work
 	set_signature(ent, !cmd->checksum_disabled);
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
+	cmd_mode = cmd->mode;
 
 	/* ring doorbell after the descriptor is valid */
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
@@ -695,7 +697,7 @@ static void cmd_work_handler(struct work
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
 	mmiowb();
 	/* if not in polling don't use ent after this point */
-	if (cmd->mode == CMD_MODE_POLLING) {
+	if (cmd_mode == CMD_MODE_POLLING) {
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();



  parent reply	other threads:[~2018-07-20 12:27 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-20 12:13 [PATCH 4.4 00/31] 4.4.143-stable review Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 01/31] compiler, clang: suppress warning for unused static inline functions Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 02/31] compiler, clang: properly override inline for clang Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 03/31] compiler, clang: always inline when CONFIG_OPTIMIZE_INLINING is disabled Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 04/31] compiler-gcc.h: Add __attribute__((gnu_inline)) to all inline declarations Greg Kroah-Hartman
2018-07-20 12:13   ` Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 05/31] x86/asm: Add _ASM_ARG* constants for argument registers to <asm/asm.h> Greg Kroah-Hartman
2018-07-20 12:13 ` Greg Kroah-Hartman
2018-07-20 12:13   ` Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 06/31] Revert "sit: reload iphdr in ipip6_rcv" Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 07/31] ocfs2: subsystem.su_mutex is required while accessing the item->ci_parent Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 08/31] bcm63xx_enet: correct clock usage Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 09/31] bcm63xx_enet: do not write to random DMA channel on BCM6345 Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 10/31] crypto: crypto4xx - remove bad list_del Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 11/31] crypto: crypto4xx - fix crypto4xx_build_pdr, crypto4xx_build_sdr leak Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 12/31] atm: zatm: Fix potential Spectre v1 Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 13/31] net: dccp: avoid crash in ccid3_hc_rx_send_feedback() Greg Kroah-Hartman
2018-07-20 12:13   ` Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 14/31] net: dccp: switch rx_tstamp_last_feedback to monotonic clock Greg Kroah-Hartman
2018-07-20 12:13   ` Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 15/31] net/mlx5: Fix incorrect raw command length parsing Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 16/31] net: sungem: fix rx checksum support Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 17/31] qed: Limit msix vectors in kdump kernel to the minimum required count Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 18/31] r8152: napi hangup fix after disconnect Greg Kroah-Hartman
2018-07-20 12:13   ` [4.4,18/31] " Greg Kroah-Hartman
2018-08-24 16:38   ` [PATCH 4.4 18/31] " Ben Hutchings
2018-08-24 16:38     ` [4.4,18/31] " Ben Hutchings
2018-08-25  7:43     ` [PATCH 4.4 18/31] " Jiri Slaby
2018-08-25  7:43       ` [4.4,18/31] " Jiri Slaby
2018-09-12 18:54       ` [PATCH 4.4 18/31] " Ben Hutchings
2018-09-12 18:54         ` [4.4,18/31] " Ben Hutchings
2018-07-20 12:13 ` [PATCH 4.4 19/31] tcp: fix Fast Open key endianness Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 21/31] vhost_net: validate sock before trying to put its fd Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 22/31] net_sched: blackhole: tell upper qdisc about dropped packets Greg Kroah-Hartman
2018-07-20 12:13 ` Greg Kroah-Hartman [this message]
2018-07-20 12:13 ` [PATCH 4.4 24/31] net: cxgb3_main: fix potential Spectre v1 Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 25/31] rtlwifi: rtl8821ae: fix firmware is not ready to run Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 26/31] MIPS: Call dump_stack() from show_regs() Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 27/31] MIPS: Use async IPIs for arch_trigger_cpumask_backtrace() Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 28/31] netfilter: ebtables: reject non-bridge targets Greg Kroah-Hartman
2018-07-20 12:13 ` [PATCH 4.4 29/31] KEYS: DNS: fix parsing multiple options Greg Kroah-Hartman
2018-07-20 12:14 ` [PATCH 4.4 30/31] rds: avoid unenecessary cong_update in loop transport Greg Kroah-Hartman
2018-07-20 12:14 ` [PATCH 4.4 31/31] net/nfc: Avoid stalls when nfc_alloc_send_skb() returned NULL Greg Kroah-Hartman
2018-07-20 13:34 ` [PATCH 4.4 00/31] 4.4.143-stable review Nathan Chancellor
2018-07-21  7:38 ` Naresh Kamboju
2018-07-21 13:39 ` Guenter Roeck

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=20180720121340.992365177@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=saeedm@mellanox.com \
    --cc=stable@vger.kernel.org \
    --cc=valex@mellanox.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.