From: Dmitry Osipenko <digetx-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: Thierry Reding
<thierry.reding-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>,
Jonathan Hunter
<jonathanh-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>,
Joerg Roedel <joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
Cc: linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
Robin Murphy <robin.murphy-5wv7dgnIgG8@public.gmane.org>,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Subject: [PATCH v6 05/21] iommu/tegra: gart: Optimize mapping / unmapping performance
Date: Sun, 9 Dec 2018 23:29:34 +0300 [thread overview]
Message-ID: <20181209202950.31486-6-digetx@gmail.com> (raw)
In-Reply-To: <20181209202950.31486-1-digetx-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Currently GART writes one page entry at a time. More optimal would be to
aggregate the writes and flush BUS buffer in the end, this gives map/unmap
10-40% performance boost (depending on size of mapping) in comparison to
flushing after each page entry update.
Signed-off-by: Dmitry Osipenko <digetx-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
Acked-by: Thierry Reding <treding-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org>
---
drivers/iommu/tegra-gart.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/iommu/tegra-gart.c b/drivers/iommu/tegra-gart.c
index 37a76388ff7e..835fea461c59 100644
--- a/drivers/iommu/tegra-gart.c
+++ b/drivers/iommu/tegra-gart.c
@@ -290,7 +290,6 @@ static int gart_iommu_map(struct iommu_domain *domain, unsigned long iova,
}
}
gart_set_pte(gart, iova, GART_PTE(pfn));
- FLUSH_GART_REGS(gart);
spin_unlock_irqrestore(&gart->pte_lock, flags);
return 0;
}
@@ -307,7 +306,6 @@ static size_t gart_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
spin_lock_irqsave(&gart->pte_lock, flags);
gart_set_pte(gart, iova, 0);
- FLUSH_GART_REGS(gart);
spin_unlock_irqrestore(&gart->pte_lock, flags);
return bytes;
}
@@ -373,6 +371,14 @@ static int gart_iommu_of_xlate(struct device *dev,
return 0;
}
+static void gart_iommu_sync(struct iommu_domain *domain)
+{
+ struct gart_domain *gart_domain = to_gart_domain(domain);
+ struct gart_device *gart = gart_domain->gart;
+
+ FLUSH_GART_REGS(gart);
+}
+
static const struct iommu_ops gart_iommu_ops = {
.capable = gart_iommu_capable,
.domain_alloc = gart_iommu_domain_alloc,
@@ -387,6 +393,8 @@ static const struct iommu_ops gart_iommu_ops = {
.iova_to_phys = gart_iommu_iova_to_phys,
.pgsize_bitmap = GART_IOMMU_PGSIZES,
.of_xlate = gart_iommu_of_xlate,
+ .iotlb_sync_map = gart_iommu_sync,
+ .iotlb_sync = gart_iommu_sync,
};
static int tegra_gart_suspend(struct device *dev)
--
2.19.1
next prev parent reply other threads:[~2018-12-09 20:29 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-09 20:29 [PATCH v6 00/21] IOMMU: Tegra GART driver clean up and optimization Dmitry Osipenko
[not found] ` <20181209202950.31486-1-digetx-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-12-09 20:29 ` [PATCH v6 01/21] iommu/tegra: gart: Remove pr_fmt and clean up includes Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 02/21] iommu/tegra: gart: Clean up driver probe errors handling Dmitry Osipenko
2018-12-09 20:29 ` Dmitry Osipenko [this message]
2018-12-09 20:29 ` [PATCH v6 08/21] memory: tegra: Don't invoke Tegra30+ specific memory timing setup on Tegra20 Dmitry Osipenko
2018-12-12 10:02 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 09/21] memory: tegra: Adapt to Tegra20 device-tree binding changes Dmitry Osipenko
[not found] ` <20181209202950.31486-10-digetx-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
2018-12-12 10:05 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 10/21] memory: tegra: Read client ID on GART page fault Dmitry Osipenko
2018-12-12 10:05 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 11/21] memory: tegra: Use of_device_get_match_data() Dmitry Osipenko
2018-12-12 10:05 ` Thierry Reding
2018-12-11 9:53 ` [PATCH v6 00/21] IOMMU: Tegra GART driver clean up and optimization Joerg Roedel
[not found] ` <20181211095317.tv43aaefnsezmic7-zLv9SwRftAIdnm+yROfE0A@public.gmane.org>
2018-12-11 13:22 ` Dmitry Osipenko
2018-12-12 10:24 ` Thierry Reding
2018-12-12 10:43 ` Joerg Roedel
2018-12-12 12:49 ` Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 03/21] iommu/tegra: gart: Ignore devices without IOMMU phandle in DT Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 04/21] iommu: Introduce iotlb_sync_map callback Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 06/21] dt-bindings: memory: tegra: Squash tegra20-gart into tegra20-mc Dmitry Osipenko
2018-12-12 10:02 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 07/21] ARM: dts: tegra20: Update Memory Controller node to the new binding Dmitry Osipenko
2018-12-12 10:02 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 12/21] memory: tegra: Use relaxed versions of readl/writel Dmitry Osipenko
2018-12-12 10:05 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 13/21] iommu/tegra: gart: Integrate with Memory Controller driver Dmitry Osipenko
2018-12-12 10:14 ` Thierry Reding
2018-12-12 13:52 ` Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 14/21] iommu/tegra: gart: Fix spinlock recursion Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 15/21] iommu/tegra: gart: Fix NULL pointer dereference Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 16/21] iommu/tegra: gart: Allow only one active domain at a time Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 17/21] iommu/tegra: gart: Don't use managed resources Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 18/21] iommu/tegra: gart: Prepend error/debug messages with "gart:" Dmitry Osipenko
2018-12-12 10:20 ` Thierry Reding
2018-12-09 20:29 ` [PATCH v6 19/21] iommu/tegra: gart: Don't detach devices from inactive domains Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 20/21] iommu/tegra: gart: Simplify clients-tracking code Dmitry Osipenko
2018-12-09 20:29 ` [PATCH v6 21/21] iommu/tegra: gart: Perform code refactoring Dmitry Osipenko
2018-12-12 10:20 ` Thierry Reding
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=20181209202950.31486-6-digetx@gmail.com \
--to=digetx-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
--cc=devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org \
--cc=jonathanh-DDmLM1+adcrQT0dZR+AlfA@public.gmane.org \
--cc=joro-zLv9SwRftAIdnm+yROfE0A@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-tegra-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=robin.murphy-5wv7dgnIgG8@public.gmane.org \
--cc=thierry.reding-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.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).