From: eric.auger@linaro.org (Eric Auger)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH v7 3/7] vfio/type1: specialize remove_dma and replay according to type
Date: Tue, 19 Apr 2016 17:24:43 +0000 [thread overview]
Message-ID: <1461086687-2658-4-git-send-email-eric.auger@linaro.org> (raw)
In-Reply-To: <1461086687-2658-1-git-send-email-eric.auger@linaro.org>
Before allowing the end-user to create VFIO_IOVA_RESERVED dma slots,
let's implement the expected behavior for removal and replay. As opposed
to user dma slots, the physical pages bound to reserved IOVA do not need
to be pinned/unpinned. Also we currently handle a single reserved iova
domain. Any attempt to remove the single reserved dma slot ends up
deleting the underlying iova domain for each iommu domain.
Signed-off-by: Eric Auger <eric.auger@linaro.org>
---
drivers/vfio/vfio_iommu_type1.c | 17 ++++++++++++++++-
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 2d769d4..93c17d9 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -36,6 +36,7 @@
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/workqueue.h>
+#include <linux/dma-reserved-iommu.h>
#define DRIVER_VERSION "0.2"
#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
@@ -445,9 +446,20 @@ static void vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma)
vfio_lock_acct(-unlocked);
}
+static void vfio_destroy_reserved(struct vfio_iommu *iommu)
+{
+ struct vfio_domain *d;
+
+ list_for_each_entry(d, &iommu->domain_list, next)
+ iommu_free_reserved_iova_domain(d->domain);
+}
+
static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
{
- vfio_unmap_unpin(iommu, dma);
+ if (likely(dma->type == VFIO_IOVA_USER))
+ vfio_unmap_unpin(iommu, dma);
+ else
+ vfio_destroy_reserved(iommu);
vfio_unlink_dma(iommu, dma);
kfree(dma);
}
@@ -727,6 +739,9 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
dma = rb_entry(n, struct vfio_dma, node);
iova = dma->iova;
+ if (dma->type == VFIO_IOVA_RESERVED)
+ continue;
+
while (iova < dma->iova + dma->size) {
phys_addr_t phys = iommu_iova_to_phys(d->domain, iova);
size_t size;
--
1.9.1
next prev parent reply other threads:[~2016-04-19 17:24 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-04-19 17:24 [PATCH v7 0/7] KVM PCIe/MSI passthrough on ARM/ARM64: kernel part 3/3: vfio changes Eric Auger
2016-04-19 17:24 ` [PATCH v7 1/7] vfio: introduce a vfio_dma type field Eric Auger
2016-04-19 17:24 ` [PATCH v7 2/7] vfio/type1: vfio_find_dma accepting a type argument Eric Auger
2016-04-19 17:24 ` Eric Auger [this message]
2016-04-20 3:05 ` [PATCH v7 3/7] vfio/type1: specialize remove_dma and replay according to type kbuild test robot
2016-04-19 17:24 ` [PATCH v7 4/7] vfio: allow reserved iova registration Eric Auger
2016-04-19 17:24 ` [PATCH v7 5/7] vfio/type1: also check IRQ remapping capability at msi domain Eric Auger
2016-04-19 17:24 ` [PATCH v7 6/7] iommu/arm-smmu: do not advertise IOMMU_CAP_INTR_REMAP Eric Auger
2016-04-22 11:16 ` Robin Murphy
2016-04-22 11:39 ` Eric Auger
2016-04-22 15:40 ` Robin Murphy
2016-04-19 17:24 ` [PATCH v7 7/7] vfio/type1: return MSI mapping requirements with VFIO_IOMMU_GET_INFO Eric Auger
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=1461086687-2658-4-git-send-email-eric.auger@linaro.org \
--to=eric.auger@linaro.org \
--cc=linux-arm-kernel@lists.infradead.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).