From: Sasha Levin <sashal@kernel.org>
To: stable@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Shaul Triebitz <shaul.triebitz@intel.com>,
Luca Coelho <luciano.coelho@intel.com>,
Sasha Levin <sashal@kernel.org>
Subject: [PATCH AUTOSEL 4.9 13/48] iwlwifi: pcie: avoid empty free RB queue
Date: Wed, 31 Oct 2018 19:10:19 -0400 [thread overview]
Message-ID: <20181031231054.29333-13-sashal@kernel.org> (raw)
In-Reply-To: <20181031231054.29333-1-sashal@kernel.org>
From: Shaul Triebitz <shaul.triebitz@intel.com>
[ Upstream commit 868a1e863f95183f00809363fefba6d4f5bcd116 ]
If all free RB queues are empty, the driver will never restock the
free RB queue. That's because the restocking happens in the Rx flow,
and if the free queue is empty there will be no Rx.
Although there's a background worker (a.k.a. allocator) allocating
memory for RBs so that the Rx handler can restock them, the worker may
run only after the free queue has become empty (and then it is too
late for restocking as explained above).
There is a solution for that called 'emergency': If the number of used
RB's reaches half the amount of all RB's, the Rx handler will not wait
for the allocator but immediately allocate memory for the used RB's
and restock the free queue.
But, since the used RB's is per queue, it may happen that the used
RB's are spread between the queues such that the emergency check will
fail for each of the queues
(and still run out of RBs, causing the above symptom).
To fix it, move to emergency mode if the sum of *all* used RBs (for
all Rx queues) reaches half the amount of all RB's
Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 32 +++++++++++++-------
1 file changed, 21 insertions(+), 11 deletions(-)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 996a928142ad..e58a50d31d96 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1030,6 +1030,14 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
kfree(trans_pcie->rxq);
}
+static void iwl_pcie_rx_move_to_allocator(struct iwl_rxq *rxq,
+ struct iwl_rb_allocator *rba)
+{
+ spin_lock(&rba->lock);
+ list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
+ spin_unlock(&rba->lock);
+}
+
/*
* iwl_pcie_rx_reuse_rbd - Recycle used RBDs
*
@@ -1061,9 +1069,7 @@ static void iwl_pcie_rx_reuse_rbd(struct iwl_trans *trans,
if ((rxq->used_count % RX_CLAIM_REQ_ALLOC) == RX_POST_REQ_ALLOC) {
/* Move the 2 RBDs to the allocator ownership.
Allocator has another 6 from pool for the request completion*/
- spin_lock(&rba->lock);
- list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
- spin_unlock(&rba->lock);
+ iwl_pcie_rx_move_to_allocator(rxq, rba);
atomic_inc(&rba->req_pending);
queue_work(rba->alloc_wq, &rba->rx_alloc);
@@ -1233,10 +1239,18 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue)
IWL_DEBUG_RX(trans, "Q %d: HW = SW = %d\n", rxq->id, r);
while (i != r) {
+ struct iwl_rb_allocator *rba = &trans_pcie->rba;
struct iwl_rx_mem_buffer *rxb;
-
- if (unlikely(rxq->used_count == rxq->queue_size / 2))
+ /* number of RBDs still waiting for page allocation */
+ u32 rb_pending_alloc =
+ atomic_read(&trans_pcie->rba.req_pending) *
+ RX_CLAIM_REQ_ALLOC;
+
+ if (unlikely(rb_pending_alloc >= rxq->queue_size / 2 &&
+ !emergency)) {
+ iwl_pcie_rx_move_to_allocator(rxq, rba);
emergency = true;
+ }
if (trans->cfg->mq_rx_supported) {
/*
@@ -1279,17 +1293,13 @@ static void iwl_pcie_rx_handle(struct iwl_trans *trans, int queue)
iwl_pcie_rx_allocator_get(trans, rxq);
if (rxq->used_count % RX_CLAIM_REQ_ALLOC == 0 && !emergency) {
- struct iwl_rb_allocator *rba = &trans_pcie->rba;
-
/* Add the remaining empty RBDs for allocator use */
- spin_lock(&rba->lock);
- list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
- spin_unlock(&rba->lock);
+ iwl_pcie_rx_move_to_allocator(rxq, rba);
} else if (emergency) {
count++;
if (count == 8) {
count = 0;
- if (rxq->used_count < rxq->queue_size / 3)
+ if (rb_pending_alloc < rxq->queue_size / 3)
emergency = false;
rxq->read = i;
--
2.17.1
next prev parent reply other threads:[~2018-10-31 23:20 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-31 23:10 [PATCH AUTOSEL 4.9 01/48] net: ethernet: ti: cpsw: unsync mcast entries while switch promisc mode Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 02/48] locking/lockdep: Fix debug_locks off performance problem Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 03/48] ataflop: fix error handling during setup Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 04/48] swim: fix cleanup on setup error Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 05/48] tun: Consistently configure generic netdev params via rtnetlink Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 06/48] s390/sthyi: Fix machine name validity indication Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 07/48] hwmon: (pwm-fan) Set fan speed to 0 on suspend Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 08/48] perf tools: Free temporary 'sys' string in read_event_files() Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 09/48] perf tools: Cleanup trace-event-info 'tdata' leak Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 10/48] perf strbuf: Match va_{add,copy} with va_end Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 11/48] cpupower: Fix coredump on VMWare Sasha Levin
2018-11-12 10:31 ` Rafael David Tinoco
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 12/48] mmc: sdhci-pci-o2micro: Add quirk for O2 Micro dev 0x8620 rev 0x01 Sasha Levin
2018-10-31 23:10 ` Sasha Levin [this message]
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 14/48] x86/olpc: Indicate that legacy PC XO-1 platform should not register RTC Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 15/48] cpufreq: dt: Try freeing static OPPs only if we have added them Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 16/48] regulator: fixed: Default enable high on DT regulators Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 17/48] Bluetooth: btbcm: Add entry for BCM4335C0 UART bluetooth Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 18/48] x86: boot: Fix EFI stub alignment Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 19/48] pinctrl: qcom: spmi-mpp: Fix err handling of pmic_mpp_set_mux Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 20/48] brcmfmac: fix for proper support of 160MHz bandwidth Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 21/48] kprobes: Return error if we fail to reuse kprobe instead of BUG_ON() Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 22/48] ACPI / LPSS: Add alternative ACPI HIDs for Cherry Trail DMA controllers Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 23/48] pinctrl: qcom: spmi-mpp: Fix drive strength setting Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 24/48] pinctrl: spmi-mpp: Fix pmic_mpp_config_get() to be compliant Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 25/48] pinctrl: ssbi-gpio: Fix pm8xxx_pin_config_get() " Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 26/48] ixgbevf: VF2VF TCP RSS Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 27/48] ath10k: schedule hardware restart if WMI command times out Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 28/48] cgroup, netclassid: add a preemption point to write_classid Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 29/48] scsi: esp_scsi: Track residual for PIO transfers Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 30/48] scsi: megaraid_sas: fix a missing-check bug Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 31/48] RDMA/core: Do not expose unsupported counters Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 32/48] IB/ipoib: Clear IPCB before icmp_send Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 33/48] tpm: suppress transmit cmd error logs when TPM 1.2 is disabled/deactivated Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 34/48] Drivers: hv: kvp: Fix two "this statement may fall through" warnings Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 35/48] VMCI: Resource wildcard match fixed Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 36/48] usb: gadget: udc: atmel: handle at91sam9rl PMC Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 37/48] ext4: fix argument checking in EXT4_IOC_MOVE_EXT Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 38/48] MD: fix invalid stored role for a disk Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 39/48] PCI/MSI: Warn and return error if driver enables MSI/MSI-X twice Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 40/48] coresight: etb10: Fix handling of perf mode Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 41/48] crypto: caam - fix implicit casts in endianness helpers Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 42/48] usb: chipidea: Prevent unbalanced IRQ disable Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 43/48] driver/dma/ioat: Call del_timer_sync() without holding prep_lock Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 44/48] uio: ensure class is registered before devices Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 45/48] scsi: lpfc: Correct soft lockup when running mds diagnostics Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 46/48] signal: Always deliver the kernel's SIGKILL and SIGSTOP to a pid namespace init Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 47/48] dmaengine: dma-jz4780: Return error if not probed from DT Sasha Levin
2018-10-31 23:10 ` [PATCH AUTOSEL 4.9 48/48] ALSA: hda: Check the non-cached stream buffers more explicitly Sasha Levin
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=20181031231054.29333-13-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luciano.coelho@intel.com \
--cc=shaul.triebitz@intel.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®