From: Matthew Auld <matthew.auld@intel.com>
To: intel-xe@lists.freedesktop.org
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Subject: [Intel-xe] [PATCH v2 07/14] drm/xe/buddy: remove the virtualized start
Date: Tue, 28 Feb 2023 10:41:30 +0000 [thread overview]
Message-ID: <20230228104137.80965-8-matthew.auld@intel.com> (raw)
In-Reply-To: <20230228104137.80965-1-matthew.auld@intel.com>
Hopefully not needed anymore. We can add a .compatible() hook once we
need to differentiate between mappable and non-mappable vram. If the
allocation is not contiguous then the start value is kind of
meaningless, so rather just mark as invalid.
In upstream, TTM wants to eventually remove the ttm_resource.start
usage.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
---
drivers/gpu/drm/xe/xe_bo.c | 6 ++++++
drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 29 ++++++++++++++--------------
2 files changed, 20 insertions(+), 15 deletions(-)
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 2bfd3f6f2e9a..7b331314064c 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -662,6 +662,12 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
void *new_addr = gt->mem.vram.mapping +
(new_mem->start << PAGE_SHIFT);
+ if (XE_WARN_ON(new_mem->start == XE_BO_INVALID_OFFSET)) {
+ ret = -EINVAL;
+ xe_device_mem_access_put(xe);
+ goto out;
+ }
+
XE_BUG_ON(new_mem->start !=
bo->placements->fpfn);
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index 643365b18bc7..e3ac8c6d3978 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -54,7 +54,6 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
struct xe_ttm_vram_mgr_resource *vres;
u64 size, remaining_size, lpfn, fpfn;
struct drm_buddy *mm = &mgr->mm;
- struct drm_buddy_block *block;
unsigned long pages_per_block;
int r;
@@ -186,24 +185,24 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
list_splice_tail(trim_list, &vres->blocks);
}
- vres->base.start = 0;
- list_for_each_entry(block, &vres->blocks, link) {
- unsigned long start;
+ if (!(vres->base.placement & TTM_PL_FLAG_CONTIGUOUS) &&
+ xe_is_vram_mgr_blocks_contiguous(mm, &vres->blocks))
+ vres->base.placement |= TTM_PL_FLAG_CONTIGUOUS;
- start = drm_buddy_block_offset(block) +
- drm_buddy_block_size(mm, block);
- start >>= PAGE_SHIFT;
+ /*
+ * For some kernel objects we still rely on the start when io mapping
+ * the object.
+ */
+ if (vres->base.placement & TTM_PL_FLAG_CONTIGUOUS) {
+ struct drm_buddy_block *block = list_first_entry(&vres->blocks,
+ typeof(*block),
+ link);
- if (start > PFN_UP(vres->base.size))
- start -= PFN_UP(vres->base.size);
- else
- start = 0;
- vres->base.start = max(vres->base.start, start);
+ vres->base.start = drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ } else {
+ vres->base.start = XE_BO_INVALID_OFFSET;
}
- if (xe_is_vram_mgr_blocks_contiguous(mm, &vres->blocks))
- vres->base.placement |= TTM_PL_FLAG_CONTIGUOUS;
-
*res = &vres->base;
return 0;
--
2.39.2
next prev parent reply other threads:[~2023-02-28 10:42 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-28 10:41 [Intel-xe] [PATCH v2 00/14] small-bar support Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 01/14] drm/xe/display: fix IS_ALDERLAKE_P() Matthew Auld
2023-02-28 14:09 ` Maarten Lankhorst
2023-02-28 17:57 ` Matt Roper
2023-02-28 18:54 ` Lucas De Marchi
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 02/14] drm/xe/display: fix bo leak when unloading module Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 03/14] drm/xe: prefer xe_bo_create_pin_map() Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 04/14] drm/xe/bo: explicitly reject zero sized BO Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 05/14] drm/xe/mmio: s/lmem/vram/ Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 06/14] drm/xe/vram: start tracking the io_size Matthew Auld
2023-02-28 10:41 ` Matthew Auld [this message]
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 08/14] drm/xe/buddy: add visible tracking Matthew Auld
2023-02-28 14:24 ` Maarten Lankhorst
2023-02-28 15:05 ` Matthew Auld
2023-02-28 20:26 ` Maarten Lankhorst
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 09/14] drm/xe/buddy: add compatible and intersects hooks Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 10/14] drm/xe/bo: support tiered vram allocation for small-bar Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 11/14] drm/xe/migrate: retain CCS aux state for vram -> vram Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 12/14] drm/xe/display: annotate CC buffers with NEEDS_CPU_ACCESS Matthew Auld
2023-02-28 14:48 ` Maarten Lankhorst
2023-02-28 15:20 ` Matthew Auld
2023-03-02 11:51 ` Maarten Lankhorst
2023-03-03 12:12 ` Matthew Auld
2023-03-03 12:58 ` Maarten Lankhorst
2023-02-28 15:22 ` Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 13/14] drm/xe/uapi: add the userspace bits for small-bar Matthew Auld
2023-02-28 10:41 ` [Intel-xe] [PATCH v2 14/14] drm/xe: fully turn on small-bar support Matthew Auld
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=20230228104137.80965-8-matthew.auld@intel.com \
--to=matthew.auld@intel.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=lucas.demarchi@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.