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>
Subject: [PATCH 07/10] mm/hmm: add an helper function that fault pages and map them to a device
Date: Tue, 29 Jan 2019 11:54:25 -0500 [thread overview]
Message-ID: <20190129165428.3931-8-jglisse@redhat.com> (raw)
In-Reply-To: <20190129165428.3931-1-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.
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>
---
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 4263f8fb32e5..fc3630d0bbfd 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -502,6 +502,15 @@ 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 0a4ff31e9d7a..9cd68334a759 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>
@@ -985,6 +986,157 @@ 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:[~2019-01-29 16:54 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-29 16:54 [PATCH 00/10] HMM updates for 5.1 jglisse
2019-01-29 16:54 ` [PATCH 01/10] mm/hmm: use reference counting for HMM struct jglisse
2019-02-20 23:47 ` John Hubbard
2019-02-20 23:59 ` Jerome Glisse
2019-02-21 0:06 ` John Hubbard
2019-02-21 0:15 ` Jerome Glisse
2019-02-21 0:32 ` John Hubbard
2019-02-21 0:37 ` Jerome Glisse
2019-02-21 0:42 ` John Hubbard
2019-01-29 16:54 ` [PATCH 02/10] mm/hmm: do not erase snapshot when a range is invalidated jglisse
2019-02-20 23:58 ` John Hubbard
2019-01-29 16:54 ` [PATCH 03/10] mm/hmm: improve and rename hmm_vma_get_pfns() to hmm_range_snapshot() jglisse
2019-02-21 0:25 ` John Hubbard
2019-02-21 0:28 ` Jerome Glisse
2019-01-29 16:54 ` [PATCH 04/10] mm/hmm: improve and rename hmm_vma_fault() to hmm_range_fault() jglisse
2019-01-29 16:54 ` [PATCH 05/10] mm/hmm: improve driver API to work and wait over a range jglisse
2019-01-29 16:54 ` [PATCH 06/10] mm/hmm: add default fault flags to avoid the need to pre-fill pfns arrays jglisse
2019-01-29 16:54 ` jglisse [this message]
2019-03-18 20:21 ` [PATCH 07/10] mm/hmm: add an helper function that fault pages and map them to a device Dan Williams
2019-03-18 20:41 ` Jerome Glisse
2019-03-18 21:30 ` Dan Williams
2019-03-18 22:15 ` Jerome Glisse
2019-03-19 3:29 ` Dan Williams
2019-03-19 13:30 ` Jerome Glisse
2019-03-19 8:44 ` Ira Weiny
2019-03-19 17:10 ` Jerome Glisse
2019-03-19 14:10 ` Ira Weiny
2019-01-29 16:54 ` [PATCH 08/10] mm/hmm: support hugetlbfs (snap shoting, faulting and DMA mapping) jglisse
2019-01-29 16:54 ` [PATCH 09/10] mm/hmm: allow to mirror vma of a file on a DAX backed filesystem jglisse
2019-01-29 18:41 ` Dan Williams
2019-01-29 19:31 ` Jerome Glisse
2019-01-29 20:51 ` Dan Williams
2019-01-29 21:21 ` Jerome Glisse
2019-01-30 2:32 ` Dan Williams
2019-01-30 3:03 ` Jerome Glisse
2019-01-30 17:25 ` Dan Williams
2019-01-30 18:36 ` Jerome Glisse
2019-01-31 3:28 ` Dan Williams
2019-01-31 4:16 ` Jerome Glisse
2019-01-31 5:44 ` Dan Williams
2019-03-05 22:16 ` Andrew Morton
2019-03-06 4:20 ` Dan Williams
2019-03-06 15:51 ` Jerome Glisse
2019-03-06 15:57 ` Dan Williams
2019-03-06 16:03 ` Jerome Glisse
2019-03-06 16:06 ` Dan Williams
2019-03-07 17:46 ` Andrew Morton
2019-03-07 18:56 ` Jerome Glisse
2019-03-12 3:13 ` Dan Williams
2019-03-12 15:25 ` Jerome Glisse
2019-03-12 16:06 ` Dan Williams
2019-03-12 19:06 ` Jerome Glisse
2019-03-12 19:30 ` Dan Williams
2019-03-12 20:34 ` Dave Chinner
2019-03-13 1:06 ` Dan Williams
2019-03-12 21:52 ` Andrew Morton
2019-03-13 0:10 ` Jerome Glisse
2019-03-13 0:46 ` Dan Williams
2019-03-13 1:00 ` Jerome Glisse
2019-03-13 16:06 ` Andrew Morton
2019-03-13 18:39 ` Jerome Glisse
2019-03-06 15:49 ` Jerome Glisse
2019-03-06 22:18 ` Andrew Morton
2019-03-07 0:36 ` Jerome Glisse
2019-01-29 16:54 ` [PATCH 10/10] mm/hmm: add helpers for driver to safely take the mmap_sem jglisse
2019-02-20 21:59 ` John Hubbard
2019-02-20 22:19 ` Jerome Glisse
2019-02-20 22:40 ` John Hubbard
2019-02-20 23:09 ` Jerome Glisse
2019-02-20 23:17 ` [PATCH 00/10] HMM updates for 5.1 John Hubbard
2019-02-20 23:36 ` Jerome Glisse
2019-02-22 23:31 ` Ralph Campbell
2019-03-13 1:27 ` Jerome Glisse
2019-03-13 16:10 ` Andrew Morton
2019-03-13 18:01 ` Jason Gunthorpe
2019-03-13 18:33 ` Jerome Glisse
2019-03-18 17:00 ` Kuehling, Felix
2019-03-18 17:04 ` Jerome Glisse
2019-03-18 18:30 ` Dan Williams
2019-03-18 18:54 ` Jerome Glisse
2019-03-18 19:18 ` Dan Williams
2019-03-18 19:28 ` Jerome Glisse
2019-03-18 19:36 ` Dan Williams
2019-03-19 16:40 ` Andrew Morton
2019-03-19 16:58 ` Jerome Glisse
2019-03-19 17:12 ` Andrew Morton
2019-03-19 17:18 ` Jerome Glisse
2019-03-19 17:33 ` Dan Williams
2019-03-19 17:45 ` Jerome Glisse
2019-03-19 18:42 ` Dan Williams
2019-03-19 19:05 ` Jerome Glisse
2019-03-19 19:13 ` Dan Williams
2019-03-19 14:18 ` Ira Weiny
2019-03-19 22:24 ` Jerome Glisse
2019-03-19 19:18 ` Jerome Glisse
2019-03-19 20:25 ` Jerome Glisse
2019-03-19 21:51 ` Stephen Rothwell
2019-03-19 18:51 ` Deucher, Alexander
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=20190129165428.3931-8-jglisse@redhat.com \
--to=jglisse@redhat.com \
--cc=akpm@linux-foundation.org \
--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).