From: jglisse@redhat.com
To: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Ralph Campbell" <rcampbell@nvidia.com>,
"John Hubbard" <jhubbard@nvidia.com>,
"Dan Williams" <dan.j.williams@intel.com>
Subject: [PATCH v2 11/11] mm/hmm: add an helper function that fault pages and map them to a device v2
Date: Mon, 25 Mar 2019 10:40:11 -0400 [thread overview]
Message-ID: <20190325144011.10560-12-jglisse@redhat.com> (raw)
In-Reply-To: <20190325144011.10560-1-jglisse@redhat.com>
From: Jérôme Glisse <jglisse@redhat.com>
This is a all in one helper that fault pages in a range and map them to
a device so that every single device driver do not have to re-implement
this common pattern.
This is taken from ODP RDMA in preparation of ODP RDMA convertion. It
will be use by nouveau and other drivers.
Changes since v1:
- improved commit message
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Dan Williams <dan.j.williams@intel.com>
---
include/linux/hmm.h | 9 +++
mm/hmm.c | 152 ++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 161 insertions(+)
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 5f9deaeb9d77..7aadf18b29cb 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -568,6 +568,15 @@ int hmm_range_register(struct hmm_range *range,
void hmm_range_unregister(struct hmm_range *range);
long hmm_range_snapshot(struct hmm_range *range);
long hmm_range_fault(struct hmm_range *range, bool block);
+long hmm_range_dma_map(struct hmm_range *range,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool block);
+long hmm_range_dma_unmap(struct hmm_range *range,
+ struct vm_area_struct *vma,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool dirty);
/*
* HMM_RANGE_DEFAULT_TIMEOUT - default timeout (ms) when waiting for a range
diff --git a/mm/hmm.c b/mm/hmm.c
index ce33151c6832..fd143251b157 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -30,6 +30,7 @@
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/jump_label.h>
+#include <linux/dma-mapping.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>
@@ -1163,6 +1164,157 @@ long hmm_range_fault(struct hmm_range *range, bool block)
return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
EXPORT_SYMBOL(hmm_range_fault);
+
+/*
+ * hmm_range_dma_map() - hmm_range_fault() and dma map page all in one.
+ * @range: range being faulted
+ * @device: device against to dma map page to
+ * @daddrs: dma address of mapped pages
+ * @block: allow blocking on fault (if true it sleeps and do not drop mmap_sem)
+ * Returns: number of pages mapped on success, -EAGAIN if mmap_sem have been
+ * drop and you need to try again, some other error value otherwise
+ *
+ * Note same usage pattern as hmm_range_fault().
+ */
+long hmm_range_dma_map(struct hmm_range *range,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool block)
+{
+ unsigned long i, npages, mapped;
+ long ret;
+
+ ret = hmm_range_fault(range, block);
+ if (ret <= 0)
+ return ret ? ret : -EBUSY;
+
+ npages = (range->end - range->start) >> PAGE_SHIFT;
+ for (i = 0, mapped = 0; i < npages; ++i) {
+ enum dma_data_direction dir = DMA_FROM_DEVICE;
+ struct page *page;
+
+ /*
+ * FIXME need to update DMA API to provide invalid DMA address
+ * value instead of a function to test dma address value. This
+ * would remove lot of dumb code duplicated accross many arch.
+ *
+ * For now setting it to 0 here is good enough as the pfns[]
+ * value is what is use to check what is valid and what isn't.
+ */
+ daddrs[i] = 0;
+
+ page = hmm_pfn_to_page(range, range->pfns[i]);
+ if (page == NULL)
+ continue;
+
+ /* Check if range is being invalidated */
+ if (!range->valid) {
+ ret = -EBUSY;
+ goto unmap;
+ }
+
+ /* If it is read and write than map bi-directional. */
+ if (range->pfns[i] & range->values[HMM_PFN_WRITE])
+ dir = DMA_BIDIRECTIONAL;
+
+ daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
+ if (dma_mapping_error(device, daddrs[i])) {
+ ret = -EFAULT;
+ goto unmap;
+ }
+
+ mapped++;
+ }
+
+ return mapped;
+
+unmap:
+ for (npages = i, i = 0; (i < npages) && mapped; ++i) {
+ enum dma_data_direction dir = DMA_FROM_DEVICE;
+ struct page *page;
+
+ page = hmm_pfn_to_page(range, range->pfns[i]);
+ if (page == NULL)
+ continue;
+
+ if (dma_mapping_error(device, daddrs[i]))
+ continue;
+
+ /* If it is read and write than map bi-directional. */
+ if (range->pfns[i] & range->values[HMM_PFN_WRITE])
+ dir = DMA_BIDIRECTIONAL;
+
+ dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
+ mapped--;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL(hmm_range_dma_map);
+
+/*
+ * hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
+ * @range: range being unmapped
+ * @vma: the vma against which the range (optional)
+ * @device: device against which dma map was done
+ * @daddrs: dma address of mapped pages
+ * @dirty: dirty page if it had the write flag set
+ * Returns: number of page unmapped on success, -EINVAL otherwise
+ *
+ * Note that caller MUST abide by mmu notifier or use HMM mirror and abide
+ * to the sync_cpu_device_pagetables() callback so that it is safe here to
+ * call set_page_dirty(). Caller must also take appropriate locks to avoid
+ * concurrent mmu notifier or sync_cpu_device_pagetables() to make progress.
+ */
+long hmm_range_dma_unmap(struct hmm_range *range,
+ struct vm_area_struct *vma,
+ struct device *device,
+ dma_addr_t *daddrs,
+ bool dirty)
+{
+ unsigned long i, npages;
+ long cpages = 0;
+
+ /* Sanity check. */
+ if (range->end <= range->start)
+ return -EINVAL;
+ if (!daddrs)
+ return -EINVAL;
+ if (!range->pfns)
+ return -EINVAL;
+
+ npages = (range->end - range->start) >> PAGE_SHIFT;
+ for (i = 0; i < npages; ++i) {
+ enum dma_data_direction dir = DMA_FROM_DEVICE;
+ struct page *page;
+
+ page = hmm_pfn_to_page(range, range->pfns[i]);
+ if (page == NULL)
+ continue;
+
+ /* If it is read and write than map bi-directional. */
+ if (range->pfns[i] & range->values[HMM_PFN_WRITE]) {
+ dir = DMA_BIDIRECTIONAL;
+
+ /*
+ * See comments in function description on why it is
+ * safe here to call set_page_dirty()
+ */
+ if (dirty)
+ set_page_dirty(page);
+ }
+
+ /* Unmap and clear pfns/dma address */
+ dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
+ range->pfns[i] = range->values[HMM_PFN_NONE];
+ /* FIXME see comments in hmm_vma_dma_map() */
+ daddrs[i] = 0;
+ cpages++;
+ }
+
+ return cpages;
+}
+EXPORT_SYMBOL(hmm_range_dma_unmap);
#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */
--
2.17.2
next prev parent reply other threads:[~2019-03-25 14:40 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-03-25 14:40 [PATCH v2 00/11] Improve HMM driver API v2 jglisse
2019-03-25 14:40 ` [PATCH v2 01/11] mm/hmm: select mmu notifier when selecting HMM jglisse
2019-03-28 20:33 ` John Hubbard
2019-03-29 21:15 ` Jerome Glisse
2019-03-29 21:42 ` John Hubbard
2019-03-25 14:40 ` [PATCH v2 02/11] mm/hmm: use reference counting for HMM struct v2 jglisse
2019-03-28 11:07 ` Ira Weiny
2019-03-28 19:11 ` Jerome Glisse
2019-03-28 20:43 ` John Hubbard
2019-03-28 21:21 ` Jerome Glisse
2019-03-29 0:39 ` John Hubbard
2019-03-28 16:57 ` Ira Weiny
2019-03-29 1:00 ` Jerome Glisse
2019-03-29 1:18 ` John Hubbard
2019-03-29 1:50 ` Jerome Glisse
2019-03-28 18:21 ` Ira Weiny
2019-03-29 2:25 ` Jerome Glisse
2019-03-29 20:07 ` John Hubbard
2019-03-29 2:11 ` John Hubbard
2019-03-29 2:22 ` Jerome Glisse
2019-03-25 14:40 ` [PATCH v2 03/11] mm/hmm: do not erase snapshot when a range is invalidated jglisse
2019-03-25 14:40 ` [PATCH v2 04/11] mm/hmm: improve and rename hmm_vma_get_pfns() to hmm_range_snapshot() v2 jglisse
2019-03-28 13:30 ` Ira Weiny
2019-03-25 14:40 ` [PATCH v2 05/11] mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault() v2 jglisse
2019-03-28 13:43 ` Ira Weiny
2019-03-28 22:03 ` Jerome Glisse
2019-03-25 14:40 ` [PATCH v2 06/11] mm/hmm: improve driver API to work and wait over a range v2 jglisse
2019-03-28 13:11 ` Ira Weiny
2019-03-28 21:39 ` Jerome Glisse
2019-03-28 16:12 ` Ira Weiny
2019-03-29 0:56 ` Jerome Glisse
2019-03-28 18:49 ` Ira Weiny
2019-03-25 14:40 ` [PATCH v2 07/11] mm/hmm: add default fault flags to avoid the need to pre-fill pfns arrays jglisse
2019-03-28 21:59 ` John Hubbard
2019-03-28 22:12 ` Jerome Glisse
2019-03-28 22:19 ` John Hubbard
2019-03-28 22:31 ` Jerome Glisse
2019-03-28 22:40 ` John Hubbard
2019-03-28 23:21 ` Jerome Glisse
2019-03-28 23:28 ` John Hubbard
2019-03-28 16:42 ` Ira Weiny
2019-03-29 1:17 ` Jerome Glisse
2019-03-29 1:30 ` John Hubbard
2019-03-29 1:42 ` Jerome Glisse
2019-03-29 1:59 ` Jerome Glisse
2019-03-29 2:05 ` John Hubbard
2019-03-29 2:12 ` Jerome Glisse
2019-03-28 23:43 ` Jerome Glisse
2019-03-25 14:40 ` [PATCH v2 08/11] mm/hmm: mirror hugetlbfs (snapshoting, faulting and DMA mapping) v2 jglisse
2019-03-28 16:53 ` Ira Weiny
2019-03-25 14:40 ` [PATCH v2 09/11] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem v2 jglisse
2019-03-28 18:04 ` Ira Weiny
2019-03-29 2:17 ` Jerome Glisse
2019-03-25 14:40 ` [PATCH v2 10/11] mm/hmm: add helpers for driver to safely take the mmap_sem v2 jglisse
2019-03-28 20:54 ` John Hubbard
2019-03-28 21:30 ` Jerome Glisse
2019-03-28 21:41 ` John Hubbard
2019-03-28 22:08 ` Jerome Glisse
2019-03-28 22:25 ` John Hubbard
2019-03-28 22:40 ` Jerome Glisse
2019-03-28 22:43 ` John Hubbard
2019-03-28 23:05 ` Jerome Glisse
2019-03-28 23:20 ` John Hubbard
2019-03-28 23:24 ` Jerome Glisse
2019-03-28 23:34 ` John Hubbard
2019-03-28 18:44 ` Ira Weiny
2019-03-25 14:40 ` jglisse [this message]
2019-04-01 11:59 ` [PATCH v2 11/11] mm/hmm: add an helper function that fault pages and map them to a device v2 Souptick Joarder
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=20190325144011.10560-12-jglisse@redhat.com \
--to=jglisse@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=rcampbell@nvidia.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;
as well as URLs for NNTP newsgroup(s).