From: Matthew Auld <matthew.auld@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: dri-devel@lists.freedesktop.org,
"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
"Matthew Brost" <matthew.brost@intel.com>
Subject: [PATCH 5/7] drm/gpusvm: lower get/unmap pages
Date: Thu, 20 Mar 2025 17:30:02 +0000 [thread overview]
Message-ID: <20250320172956.168358-14-matthew.auld@intel.com> (raw)
In-Reply-To: <20250320172956.168358-9-matthew.auld@intel.com>
Lower get/unmap pages to facilitate operating on the lowest level
pieces, without needing a full drm_gpusvm_range structure. In the next
patch we want to extract get/unmap/free to operate on a different range
type.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
---
drivers/gpu/drm/drm_gpusvm.c | 90 ++++++++++++++++++++++--------------
1 file changed, 55 insertions(+), 35 deletions(-)
diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c
index f27731a51f34..2beca5a6dc0a 100644
--- a/drivers/gpu/drm/drm_gpusvm.c
+++ b/drivers/gpu/drm/drm_gpusvm.c
@@ -1323,38 +1323,28 @@ drm_gpusvm_range_pages_valid_unlocked(struct drm_gpusvm *gpusvm,
return pages_valid;
}
-/**
- * drm_gpusvm_range_get_pages() - Get pages for a GPU SVM range
- * @gpusvm: Pointer to the GPU SVM structure
- * @range: Pointer to the GPU SVM range structure
- * @ctx: GPU SVM context
- *
- * This function gets pages for a GPU SVM range and ensures they are mapped for
- * DMA access.
- *
- * Return: 0 on success, negative error code on failure.
- */
-int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
- struct drm_gpusvm_range *range,
- const struct drm_gpusvm_ctx *ctx)
+static int drm_gpusvm_get_pages(struct drm_gpusvm *gpusvm,
+ struct drm_gpusvm_pages *svm_pages,
+ struct mm_struct *mm,
+ struct mmu_interval_notifier *notifier,
+ unsigned long *notifier_seq,
+ unsigned long mm_start,
+ unsigned long mm_end,
+ const struct drm_gpusvm_ctx *ctx)
{
- struct drm_gpusvm_pages *svm_pages = &range->pages;
- struct mmu_interval_notifier *notifier = &range->notifier->notifier;
struct hmm_range hmm_range = {
.default_flags = HMM_PFN_REQ_FAULT | (ctx->read_only ? 0 :
HMM_PFN_REQ_WRITE),
.notifier = notifier,
- .start = drm_gpusvm_range_start(range),
- .end = drm_gpusvm_range_end(range),
+ .start = mm_start,
+ .end = mm_end,
.dev_private_owner = gpusvm->device_private_page_owner,
};
- struct mm_struct *mm = gpusvm->mm;
struct drm_gpusvm_zdd *zdd;
unsigned long timeout =
jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
unsigned long i, j;
- unsigned long npages = npages_in_range(drm_gpusvm_range_start(range),
- drm_gpusvm_range_end(range));
+ unsigned long npages = npages_in_range(mm_start, mm_end);
unsigned long num_dma_mapped;
unsigned int order = 0;
unsigned long *pfns;
@@ -1518,7 +1508,7 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
drm_gpusvm_notifier_unlock(gpusvm);
kvfree(pfns);
set_seqno:
- range->notifier_seq = hmm_range.notifier_seq;
+ *notifier_seq = hmm_range.notifier_seq;
return 0;
@@ -1531,8 +1521,48 @@ int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
goto retry;
return err;
}
+
+/**
+ * drm_gpusvm_range_get_pages() - Get pages for a GPU SVM range
+ * @gpusvm: Pointer to the GPU SVM structure
+ * @range: Pointer to the GPU SVM range structure
+ * @ctx: GPU SVM context
+ *
+ * This function gets pages for a GPU SVM range and ensures they are mapped for
+ * DMA access.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int drm_gpusvm_range_get_pages(struct drm_gpusvm *gpusvm,
+ struct drm_gpusvm_range *range,
+ const struct drm_gpusvm_ctx *ctx)
+{
+ return drm_gpusvm_get_pages(gpusvm, &range->pages, gpusvm->mm,
+ &range->notifier->notifier,
+ &range->notifier_seq,
+ drm_gpusvm_range_start(range),
+ drm_gpusvm_range_end(range), ctx);
+}
EXPORT_SYMBOL_GPL(drm_gpusvm_range_get_pages);
+static void drm_gpusvm_unmap_pages(struct drm_gpusvm *gpusvm,
+ unsigned long mm_start, unsigned long mm_end,
+ struct drm_gpusvm_pages *svm_pages,
+ const struct drm_gpusvm_ctx *ctx)
+{
+ unsigned long npages = npages_in_range(mm_start, mm_end);
+
+ if (ctx->in_notifier)
+ lockdep_assert_held_write(&gpusvm->notifier_lock);
+ else
+ drm_gpusvm_notifier_lock(gpusvm);
+
+ __drm_gpusvm_unmap_pages(gpusvm, svm_pages, npages);
+
+ if (!ctx->in_notifier)
+ drm_gpusvm_notifier_unlock(gpusvm);
+}
+
/**
* drm_gpusvm_range_unmap_pages() - Unmap pages associated with a GPU SVM range
* @gpusvm: Pointer to the GPU SVM structure
@@ -1549,19 +1579,9 @@ void drm_gpusvm_range_unmap_pages(struct drm_gpusvm *gpusvm,
struct drm_gpusvm_range *range,
const struct drm_gpusvm_ctx *ctx)
{
- struct drm_gpusvm_pages *svm_pages = &range->pages;
- unsigned long npages = npages_in_range(drm_gpusvm_range_start(range),
- drm_gpusvm_range_end(range));
-
- if (ctx->in_notifier)
- lockdep_assert_held_write(&gpusvm->notifier_lock);
- else
- drm_gpusvm_notifier_lock(gpusvm);
-
- __drm_gpusvm_unmap_pages(gpusvm, svm_pages, npages);
-
- if (!ctx->in_notifier)
- drm_gpusvm_notifier_unlock(gpusvm);
+ return drm_gpusvm_unmap_pages(gpusvm, drm_gpusvm_range_start(range),
+ drm_gpusvm_range_end(range),
+ &range->pages, ctx);
}
EXPORT_SYMBOL_GPL(drm_gpusvm_range_unmap_pages);
--
2.48.1
next prev parent reply other threads:[~2025-03-20 17:32 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-20 17:29 [PATCH 0/7] Replace xe_hmm with gpusvm Matthew Auld
2025-03-20 17:29 ` [PATCH 1/7] drm/gpusvm: fix hmm_pfn_to_map_order() usage Matthew Auld
2025-03-20 19:52 ` Thomas Hellström
2025-03-20 20:40 ` Matthew Brost
2025-03-21 11:42 ` Matthew Auld
2025-03-20 17:29 ` [PATCH 2/7] drm/gpusvm: use more selective dma dir in get_pages() Matthew Auld
2025-03-20 19:31 ` Thomas Hellström
2025-03-20 19:37 ` Matthew Brost
2025-03-20 17:30 ` [PATCH 3/7] drm/gpusvm: mark pages as dirty Matthew Auld
2025-03-20 19:29 ` Thomas Hellström
2025-03-20 19:33 ` Matthew Brost
2025-03-21 11:37 ` Matthew Auld
2025-03-20 17:30 ` [PATCH 4/7] drm/gpusvm: pull out drm_gpusvm_pages substructure Matthew Auld
2025-03-20 20:43 ` Matthew Brost
2025-03-21 11:53 ` Matthew Auld
2025-03-20 17:30 ` Matthew Auld [this message]
2025-03-20 20:59 ` [PATCH 5/7] drm/gpusvm: lower get/unmap pages Matthew Brost
2025-03-20 17:30 ` [PATCH 6/7] drm/gpusvm: support basic_range Matthew Auld
2025-03-20 21:04 ` Matthew Brost
2025-03-20 17:30 ` [PATCH 7/7] drm/xe/userptr: replace xe_hmm with gpusvm Matthew Auld
2025-03-20 20:52 ` Matthew Brost
2025-03-25 9:50 ` Ghimiray, Himal Prasad
2025-03-20 17:37 ` ✓ CI.Patch_applied: success for Replace " Patchwork
2025-03-20 17:37 ` ✗ CI.checkpatch: warning " Patchwork
2025-03-20 17:38 ` ✗ CI.KUnit: failure " Patchwork
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=20250320172956.168358-14-matthew.auld@intel.com \
--to=matthew.auld@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.brost@intel.com \
--cc=thomas.hellstrom@linux.intel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.