Linux IOMMU Development
 help / color / mirror / Atom feed
From: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
To: <linux-kernel@vger.kernel.org>, <iommu@lists.linux.dev>
Cc: <joro@8bytes.org>, <joao.m.martins@oracle.com>,
	<alejandro.j.jimenez@oracle.com>, <boris.ostrovsky@oracle.com>,
	<jon.grimm@amd.com>, <santosh.shukla@amd.com>,
	<vasant.hegde@amd.com>, <kishon.vijayabraham@amd.com>,
	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Subject: [PATCH v2 5/5] iommu/amd: Improving Interrupt Remapping Table Invalidation
Date: Thu, 18 May 2023 20:55:29 -0400	[thread overview]
Message-ID: <20230519005529.28171-6-suravee.suthikulpanit@amd.com> (raw)
In-Reply-To: <20230519005529.28171-1-suravee.suthikulpanit@amd.com>

Invalidating Interrupt Remapping Table (IRT) requires, the AMD IOMMU driver
to issue INVALIDATE_INTERRUPT_TABLE and COMPLETION_WAIT commands.
Currently, the driver issues the two commands separately, which requires
calling raw_spin_lock_irqsave() twice. In addition, the COMPLETION_WAIT
could potentially be interleaved with other commands causing delay of
the COMPLETION_WAIT command.

Therefore, combine issuing of the two commands in one spin-lock, and
changing struct amd_iommu.cmd_sem_val to use atomic64 to minimize
locking.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
---
 drivers/iommu/amd/amd_iommu_types.h |  2 +-
 drivers/iommu/amd/init.c            |  2 +-
 drivers/iommu/amd/iommu.c           | 27 ++++++++++++++++++++++-----
 3 files changed, 24 insertions(+), 7 deletions(-)

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 486a052e37ca..2fa65da2a9a5 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -744,7 +744,7 @@ struct amd_iommu {
 
 	u32 flags;
 	volatile u64 *cmd_sem;
-	u64 cmd_sem_val;
+	atomic64_t cmd_sem_val;
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index fc0392d706db..16737819f79a 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -1750,7 +1750,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h,
 	iommu->pci_seg = pci_seg;
 
 	raw_spin_lock_init(&iommu->lock);
-	iommu->cmd_sem_val = 0;
+	atomic64_set(&iommu->cmd_sem_val, 0);
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 51c2b018433d..57ae4a8072d3 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1182,11 +1182,11 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	if (!iommu->need_sync)
 		return 0;
 
-	raw_spin_lock_irqsave(&iommu->lock, flags);
-
-	data = ++iommu->cmd_sem_val;
+	data = atomic64_add_return(1, &iommu->cmd_sem_val);
 	build_completion_wait(&cmd, iommu, data);
 
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+
 	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_unlock;
@@ -1284,11 +1284,28 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 
 static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
 {
+	int ret;
+	u64 data;
+	unsigned long flags;
+	struct iommu_cmd cmd, cmd2;
+
 	if (iommu->irtcachedis_enabled)
 		return;
 
-	iommu_flush_irt(iommu, devid);
-	iommu_completion_wait(iommu);
+	build_inv_irt(&cmd, devid);
+	data = atomic64_add_return(1, &iommu->cmd_sem_val);
+	build_completion_wait(&cmd2, iommu, data);
+
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	if (ret)
+		goto out;
+	ret = __iommu_queue_command_sync(iommu, &cmd2, false);
+	if (ret)
+		goto out;
+	wait_on_sem(iommu, data);
+out:
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
 void iommu_flush_all_caches(struct amd_iommu *iommu)
-- 
2.31.1


  parent reply	other threads:[~2023-05-19  0:56 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-05-19  0:55 [PATCH v2 0/5] iommu/amd: AVIC Interrupt Remapping Improvements Suravee Suthikulpanit
2023-05-19  0:55 ` [PATCH v2 1/5] iommu/amd: Switch amd_iommu_update_ga() to use modify_irte_ga() Suravee Suthikulpanit
2023-05-23  0:02   ` Jerry Snitselaar
2023-05-19  0:55 ` [PATCH v2 2/5] iommu/amd: Remove the unused struct amd_ir_data.ref Suravee Suthikulpanit
2023-05-23  0:03   ` Jerry Snitselaar
2023-05-19  0:55 ` [PATCH v2 3/5] iommu/amd: Introduce Disable IRTE Caching Support Suravee Suthikulpanit
2023-05-22 17:02   ` Alejandro Jimenez
2023-05-23  0:10   ` Jerry Snitselaar
2023-05-19  0:55 ` [PATCH v2 4/5] iommu/amd: Do not Invalidate IRT when disable IRTE caching Suravee Suthikulpanit
2023-05-23  0:17   ` jsnitsel
2023-05-23  3:38     ` Suthikulpanit, Suravee
2023-05-23  6:32       ` Joerg Roedel
2023-05-19  0:55 ` Suravee Suthikulpanit [this message]
2023-05-23  0:22   ` [PATCH v2 5/5] iommu/amd: Improving Interrupt Remapping Table Invalidation Jerry Snitselaar

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=20230519005529.28171-6-suravee.suthikulpanit@amd.com \
    --to=suravee.suthikulpanit@amd.com \
    --cc=alejandro.j.jimenez@oracle.com \
    --cc=boris.ostrovsky@oracle.com \
    --cc=iommu@lists.linux.dev \
    --cc=joao.m.martins@oracle.com \
    --cc=jon.grimm@amd.com \
    --cc=joro@8bytes.org \
    --cc=kishon.vijayabraham@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=santosh.shukla@amd.com \
    --cc=vasant.hegde@amd.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