From: Will Deacon <will@kernel.org>
To: John Garry <john.garry@huawei.com>
Cc: trivial@kernel.org, maz@kernel.org, linux-kernel@vger.kernel.org,
linuxarm@huawei.com, iommu@lists.linux-foundation.org,
robin.murphy@arm.com, linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH 0/4] iommu/arm-smmu-v3: Improve cmdq lock efficiency
Date: Thu, 16 Jul 2020 11:19:41 +0100 [thread overview]
Message-ID: <20200716101940.GA7036@willie-the-truck> (raw)
In-Reply-To: <1592846920-45338-1-git-send-email-john.garry@huawei.com>
On Tue, Jun 23, 2020 at 01:28:36AM +0800, John Garry wrote:
> As mentioned in [0], the CPU may consume many cycles processing
> arm_smmu_cmdq_issue_cmdlist(). One issue we find is the cmpxchg() loop to
> get space on the queue takes approx 25% of the cycles for this function.
>
> This series removes that cmpxchg().
How about something much simpler like the diff below?
Will
--->8
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index f578677a5c41..705d99ec8219 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -560,6 +560,7 @@ struct arm_smmu_cmdq {
atomic_long_t *valid_map;
atomic_t owner_prod;
atomic_t lock;
+ spinlock_t slock;
};
struct arm_smmu_cmdq_batch {
@@ -1378,7 +1379,7 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
u64 cmd_sync[CMDQ_ENT_DWORDS];
u32 prod;
unsigned long flags;
- bool owner;
+ bool owner, cas_failed = false;
struct arm_smmu_cmdq *cmdq = &smmu->cmdq;
struct arm_smmu_ll_queue llq = {
.max_n_shift = cmdq->q.llq.max_n_shift,
@@ -1387,27 +1388,35 @@ static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu,
/* 1. Allocate some space in the queue */
local_irq_save(flags);
- llq.val = READ_ONCE(cmdq->q.llq.val);
do {
u64 old;
+ llq.val = READ_ONCE(cmdq->q.llq.val);
- while (!queue_has_space(&llq, n + sync)) {
+ if (queue_has_space(&llq, n + sync))
+ goto try_cas;
+
+ if (cas_failed)
+ spin_unlock(&cmdq->slock);
+
+ do {
local_irq_restore(flags);
if (arm_smmu_cmdq_poll_until_not_full(smmu, &llq))
dev_err_ratelimited(smmu->dev, "CMDQ timeout\n");
local_irq_save(flags);
- }
+ } while (!queue_has_space(&llq, n + sync));
+try_cas:
head.cons = llq.cons;
head.prod = queue_inc_prod_n(&llq, n + sync) |
CMDQ_PROD_OWNED_FLAG;
old = cmpxchg_relaxed(&cmdq->q.llq.val, llq.val, head.val);
- if (old == llq.val)
- break;
+ cas_failed = old != llq.val;
+
+ if (cas_failed)
+ spin_lock(&cmdq->slock);
+ } while (cas_failed);
- llq.val = old;
- } while (1);
owner = !(llq.prod & CMDQ_PROD_OWNED_FLAG);
head.prod &= ~CMDQ_PROD_OWNED_FLAG;
llq.prod &= ~CMDQ_PROD_OWNED_FLAG;
@@ -3192,6 +3201,7 @@ static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
atomic_set(&cmdq->owner_prod, 0);
atomic_set(&cmdq->lock, 0);
+ spin_lock_init(&cmdq->slock);
bitmap = (atomic_long_t *)bitmap_zalloc(nents, GFP_KERNEL);
if (!bitmap) {
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2020-07-16 10:19 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-22 17:28 [PATCH 0/4] iommu/arm-smmu-v3: Improve cmdq lock efficiency John Garry
2020-06-22 17:28 ` [PATCH 1/4] iommu/arm-smmu-v3: Fix trivial typo John Garry
2020-06-22 17:28 ` [PATCH 2/4] iommu/arm-smmu-v3: Calculate bits for prod and owner John Garry
2020-06-22 17:28 ` [PATCH 3/4] iommu/arm-smmu-v3: Always issue a CMD_SYNC per batch John Garry
2020-06-22 17:28 ` [PATCH 4/4] iommu/arm-smmu-v3: Remove cmpxchg() in arm_smmu_cmdq_issue_cmdlist() John Garry
2020-06-23 1:07 ` kernel test robot
2020-06-23 9:21 ` John Garry
2020-06-23 9:35 ` Rikard Falkeborn
2020-06-23 10:19 ` John Garry
2020-06-23 13:55 ` Rikard Falkeborn
2020-06-26 10:05 ` John Garry
2020-06-23 16:22 ` Robin Murphy
2020-06-24 8:15 ` John Garry
2020-07-16 10:20 ` Will Deacon
2020-07-16 10:26 ` John Garry
2020-07-08 13:00 ` [PATCH 0/4] iommu/arm-smmu-v3: Improve cmdq lock efficiency John Garry
2020-07-16 10:19 ` Will Deacon [this message]
2020-07-16 10:22 ` Will Deacon
2020-07-16 10:28 ` Will Deacon
2020-07-16 10:56 ` John Garry
2020-07-16 11:22 ` Robin Murphy
2020-07-16 11:30 ` John Garry
2020-07-16 11:32 ` Will Deacon
2020-07-16 16:50 ` John Garry
2020-07-16 13:31 ` John Garry
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=20200716101940.GA7036@willie-the-truck \
--to=will@kernel.org \
--cc=iommu@lists.linux-foundation.org \
--cc=john.garry@huawei.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxarm@huawei.com \
--cc=maz@kernel.org \
--cc=robin.murphy@arm.com \
--cc=trivial@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;
as well as URLs for NNTP newsgroup(s).