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,
	Mitko Haralanov <mitko.haralanov@intel.com>,
	Mike Marciniszyn <mike.marciniszyn@intel.com>,
	"Michael J. Ruhl" <michael.j.ruhl@intel.com>,
	Dennis Dalessandro <dennis.dalessandro@intel.com>,
	Jason Gunthorpe <jgg@mellanox.com>,
	Sasha Levin <sashal@kernel.org>
Subject: [PATCH 4.19 03/67] IB/hfi1: Remove race conditions in user_sdma send path
Date: Thu, 20 Dec 2018 10:18:15 +0100	[thread overview]
Message-ID: <20181220085903.702233696@linuxfoundation.org> (raw)
In-Reply-To: <20181220085903.562090333@linuxfoundation.org>

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

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

commit 28a9a9e83ceae2cee25b9af9ad20d53aaa9ab951 upstream

Packet queue state is over used to determine SDMA descriptor
availablitity and packet queue request state.

cpu 0  ret = user_sdma_send_pkts(req, pcount);
cpu 0  if (atomic_read(&pq->n_reqs))
cpu 1  IRQ user_sdma_txreq_cb calls pq_update() (state to _INACTIVE)
cpu 0        xchg(&pq->state, SDMA_PKT_Q_ACTIVE);

At this point pq->n_reqs == 0 and pq->state is incorrectly
SDMA_PKT_Q_ACTIVE.  The close path will hang waiting for the state
to return to _INACTIVE.

This can also change the state from _DEFERRED to _ACTIVE.  However,
this is a mostly benign race.

Remove the racy code path.

Use n_reqs to determine if a packet queue is active or not.

Cc: <stable@vger.kernel.org> # 4.19.x
Reviewed-by: Mitko Haralanov <mitko.haralanov@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/hw/hfi1/user_sdma.c | 24 ++++++++++--------------
 drivers/infiniband/hw/hfi1/user_sdma.h |  9 +++++----
 2 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index 39134dd305f5..51831bfbf90f 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -187,7 +187,6 @@ int hfi1_user_sdma_alloc_queues(struct hfi1_ctxtdata *uctxt,
 	pq->ctxt = uctxt->ctxt;
 	pq->subctxt = fd->subctxt;
 	pq->n_max_reqs = hfi1_sdma_comp_ring_size;
-	pq->state = SDMA_PKT_Q_INACTIVE;
 	atomic_set(&pq->n_reqs, 0);
 	init_waitqueue_head(&pq->wait);
 	atomic_set(&pq->n_locked, 0);
@@ -276,7 +275,7 @@ int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
 		/* Wait until all requests have been freed. */
 		wait_event_interruptible(
 			pq->wait,
-			(READ_ONCE(pq->state) == SDMA_PKT_Q_INACTIVE));
+			!atomic_read(&pq->n_reqs));
 		kfree(pq->reqs);
 		kfree(pq->req_in_use);
 		kmem_cache_destroy(pq->txreq_cache);
@@ -312,6 +311,13 @@ static u8 dlid_to_selector(u16 dlid)
 	return mapping[hash];
 }
 
+/**
+ * hfi1_user_sdma_process_request() - Process and start a user sdma request
+ * @fd: valid file descriptor
+ * @iovec: array of io vectors to process
+ * @dim: overall iovec array size
+ * @count: number of io vector array entries processed
+ */
 int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 				   struct iovec *iovec, unsigned long dim,
 				   unsigned long *count)
@@ -560,20 +566,12 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd,
 		req->ahg_idx = sdma_ahg_alloc(req->sde);
 
 	set_comp_state(pq, cq, info.comp_idx, QUEUED, 0);
+	pq->state = SDMA_PKT_Q_ACTIVE;
 	/* Send the first N packets in the request to buy us some time */
 	ret = user_sdma_send_pkts(req, pcount);
 	if (unlikely(ret < 0 && ret != -EBUSY))
 		goto free_req;
 
-	/*
-	 * It is possible that the SDMA engine would have processed all the
-	 * submitted packets by the time we get here. Therefore, only set
-	 * packet queue state to ACTIVE if there are still uncompleted
-	 * requests.
-	 */
-	if (atomic_read(&pq->n_reqs))
-		xchg(&pq->state, SDMA_PKT_Q_ACTIVE);
-
 	/*
 	 * This is a somewhat blocking send implementation.
 	 * The driver will block the caller until all packets of the
@@ -1409,10 +1407,8 @@ static void user_sdma_txreq_cb(struct sdma_txreq *txreq, int status)
 
 static inline void pq_update(struct hfi1_user_sdma_pkt_q *pq)
 {
-	if (atomic_dec_and_test(&pq->n_reqs)) {
-		xchg(&pq->state, SDMA_PKT_Q_INACTIVE);
+	if (atomic_dec_and_test(&pq->n_reqs))
 		wake_up(&pq->wait);
-	}
 }
 
 static void user_sdma_free_request(struct user_sdma_request *req, bool unpin)
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.h b/drivers/infiniband/hw/hfi1/user_sdma.h
index 0ae06456c868..91c343f91776 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.h
+++ b/drivers/infiniband/hw/hfi1/user_sdma.h
@@ -105,9 +105,10 @@ static inline int ahg_header_set(u32 *arr, int idx, size_t array_size,
 #define TXREQ_FLAGS_REQ_ACK   BIT(0)      /* Set the ACK bit in the header */
 #define TXREQ_FLAGS_REQ_DISABLE_SH BIT(1) /* Disable header suppression */
 
-#define SDMA_PKT_Q_INACTIVE BIT(0)
-#define SDMA_PKT_Q_ACTIVE   BIT(1)
-#define SDMA_PKT_Q_DEFERRED BIT(2)
+enum pkt_q_sdma_state {
+	SDMA_PKT_Q_ACTIVE,
+	SDMA_PKT_Q_DEFERRED,
+};
 
 /*
  * Maximum retry attempts to submit a TX request
@@ -133,7 +134,7 @@ struct hfi1_user_sdma_pkt_q {
 	struct user_sdma_request *reqs;
 	unsigned long *req_in_use;
 	struct iowait busy;
-	unsigned state;
+	enum pkt_q_sdma_state state;
 	wait_queue_head_t wait;
 	unsigned long unpinned;
 	struct mmu_rb_handler *handler;
-- 
2.19.1




  parent reply	other threads:[~2018-12-20  9:34 UTC|newest]

Thread overview: 76+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-12-20  9:18 [PATCH 4.19 00/67] 4.19.12-stable review Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 01/67] locking/qspinlock: Re-order code Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 02/67] locking/qspinlock, x86: Provide liveness guarantee Greg Kroah-Hartman
2018-12-20  9:18 ` Greg Kroah-Hartman [this message]
2018-12-20  9:18 ` [PATCH 4.19 04/67] mac80211_hwsim: fix module init error paths for netlink Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 05/67] Input: hyper-v - fix wakeup from suspend-to-idle Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 06/67] i2c: rcar: check bus state before reinitializing Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 07/67] scsi: libiscsi: Fix NULL pointer dereference in iscsi_eh_session_reset Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 08/67] scsi: vmw_pscsi: Rearrange code to avoid multiple calls to free_irq during unload Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 09/67] tools/bpf: fix two test_btf unit test cases Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 10/67] tools/bpf: add addition type tests to test_btf Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 11/67] net: ethernet: ave: Replace NET_IP_ALIGN with AVE_FRAME_HEADROOM Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 12/67] drm/amd/display: Fix 6x4K displays light-up on Vega20 (v2) Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 13/67] x86/earlyprintk/efi: Fix infinite loop on some screen widths Greg Kroah-Hartman
2018-12-20  9:18   ` Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 14/67] drm/msm: Fix task dump in gpu recovery Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 15/67] drm/msm/gpu: Fix a couple memory leaks in debugfs Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 16/67] drm/msm: fix handling of cmdstream offset Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 17/67] drm/msm/dsi: configure VCO rate for 10nm PLL driver Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 18/67] drm/msm: Grab a vblank reference when waiting for commit_done Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 19/67] drm/ttm: fix LRU handling in ttm_buffer_object_transfer Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 20/67] drm/amdgpu: wait for IB test on first device open Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 21/67] ARC: io.h: Implement reads{x}()/writes{x}() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 22/67] net: stmmac: Move debugfs init/exit to ->probe()/->remove() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 23/67] net: aquantia: fix rx checksum offload bits Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 24/67] bonding: fix 802.3ad state sent to partner when unbinding slave Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 25/67] bpf: Fix verifier log string check for bad alignment Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 26/67] liquidio: read sc->iq_no before release sc Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 27/67] nfs: dont dirty kernel pages read by direct-io Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 28/67] SUNRPC: Fix a potential race in xprt_connect() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 29/67] sbus: char: add of_node_put() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 30/67] drivers/sbus/char: " Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 31/67] drivers/tty: add missing of_node_put() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 32/67] ide: pmac: add of_node_put() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 33/67] drm/msm/hdmi: Enable HPD after HDMI IRQ is set up Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 34/67] drm/msm: dpu: Dont set legacy plane->crtc pointer Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 35/67] drm/msm: dpu: Fix "WARNING: invalid free of devm_ allocated data" Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 36/67] drm/msm: Fix error return checking Greg Kroah-Hartman
2018-12-20  9:18   ` Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 37/67] drm/amd/powerplay: issue pre-display settings for display change event Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 38/67] clk: mvebu: Off by one bugs in cp110_of_clk_get() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 39/67] clk: mmp: Off by one in mmp_clk_add() Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 40/67] Input: synaptics - enable SMBus for HP 15-ay000 Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 41/67] Input: omap-keypad - fix keyboard debounce configuration Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 42/67] libata: whitelist all SAMSUNG MZ7KM* solid-state disks Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 43/67] macvlan: return correct error value Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 44/67] mv88e6060: disable hardware level MAC learning Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 45/67] net/mlx4_en: Fix build break when CONFIG_INET is off Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 46/67] bpf: check pending signals while verifying programs Greg Kroah-Hartman
2018-12-20  9:18 ` [PATCH 4.19 47/67] ARM: 8814/1: mm: improve/fix ARM v7_dma_inv_range() unaligned address handling Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 48/67] ARM: 8815/1: V7M: align v7m_dma_inv_range() with v7 counterpart Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 49/67] ARM: 8816/1: dma-mapping: fix potential uninitialized return Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 50/67] ethernet: fman: fix wrong of_node_put() in probe function Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 51/67] thermal: armada: fix legacy validity test sense Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 52/67] net: mvpp2: fix detection of 10G SFP modules Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 53/67] net: mvpp2: fix phylink handling of invalid PHY modes Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 54/67] drm/amdgpu/vcn: Update vcn.cur_state during suspend Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 55/67] tools/testing/nvdimm: Align test resources to 128M Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 56/67] acpi/nfit: Fix user-initiated ARS to be "ARS-long" rather than "ARS-short" Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 57/67] drm/ast: Fix connector leak during driver unload Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 58/67] cifs: In Kconfig CONFIG_CIFS_POSIX needs depends on legacy (insecure cifs) Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 59/67] vhost/vsock: fix reset orphans race with close timeout Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 60/67] mlxsw: spectrum_switchdev: Fix VLAN device deletion via ioctl Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 61/67] i2c: axxia: properly handle master timeout Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 62/67] i2c: scmi: Fix probe error on devices with an empty SMB0001 ACPI device node Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 63/67] i2c: uniphier: fix violation of tLOW requirement for Fast-mode Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 64/67] i2c: uniphier-f: " Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 65/67] nvme: validate controller state before rescheduling keep alive Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 66/67] nvmet-rdma: fix response use after free Greg Kroah-Hartman
2018-12-20  9:19 ` [PATCH 4.19 67/67] Btrfs: fix missing delayed iputs on unmount Greg Kroah-Hartman
2018-12-20 15:03 ` [PATCH 4.19 00/67] 4.19.12-stable review Naresh Kamboju
2018-12-21  7:10   ` Greg Kroah-Hartman
2018-12-20 18:29 ` Guenter Roeck
2018-12-21  7:10   ` Greg Kroah-Hartman
2018-12-20 22:48 ` shuah
2018-12-21  7:09   ` Greg Kroah-Hartman

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=20181220085903.702233696@linuxfoundation.org \
    --to=gregkh@linuxfoundation.org \
    --cc=dennis.dalessandro@intel.com \
    --cc=jgg@mellanox.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=michael.j.ruhl@intel.com \
    --cc=mike.marciniszyn@intel.com \
    --cc=mitko.haralanov@intel.com \
    --cc=sashal@kernel.org \
    --cc=stable@vger.kernel.org \
    /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.