From: Ramalingam C <ramalingam.c@intel.com>
To: dri-devel <dri-devel@lists.freedesktop.org>,
intel-gfx <intel-gfx@lists.freedesktop.org>
Cc: Daniel Vetter <daniel@ffwll.ch>,
Matthew Auld <matthew.auld@intel.com>,
CQ Tang <cq.tang@intel.com>,
Hellstrom Thomas <thomas.hellstrom@intel.com>,
Ramalingam C <ramalingam.c@intel.com>
Subject: [Intel-gfx] [PATCH 13/14] drm/i915/uapi: document behaviour for DG2 64K support
Date: Mon, 11 Oct 2021 21:41:54 +0530 [thread overview]
Message-ID: <20211011161155.6397-14-ramalingam.c@intel.com> (raw)
In-Reply-To: <20211011161155.6397-1-ramalingam.c@intel.com>
From: Matthew Auld <matthew.auld@intel.com>
On discrete platforms like DG2, we need to support a minimum page size
of 64K when dealing with device local-memory. This is quite tricky for
various reasons, so try to document the new implicit uapi for this.
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
---
include/uapi/drm/i915_drm.h | 61 ++++++++++++++++++++++++++++++++++---
1 file changed, 56 insertions(+), 5 deletions(-)
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index aa2a7eccfb94..d62e8b7ed8b6 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1118,10 +1118,16 @@ struct drm_i915_gem_exec_object2 {
/**
* When the EXEC_OBJECT_PINNED flag is specified this is populated by
* the user with the GTT offset at which this object will be pinned.
+ *
* When the I915_EXEC_NO_RELOC flag is specified this must contain the
* presumed_offset of the object.
+ *
* During execbuffer2 the kernel populates it with the value of the
* current GTT offset of the object, for future presumed_offset writes.
+ *
+ * See struct drm_i915_gem_create_ext for the rules when dealing with
+ * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with
+ * minimum page sizes, like DG2.
*/
__u64 offset;
@@ -3001,11 +3007,56 @@ struct drm_i915_gem_create_ext {
*
* The (page-aligned) allocated size for the object will be returned.
*
- * Note that for some devices we have might have further minimum
- * page-size restrictions(larger than 4K), like for device local-memory.
- * However in general the final size here should always reflect any
- * rounding up, if for example using the I915_GEM_CREATE_EXT_MEMORY_REGIONS
- * extension to place the object in device local-memory.
+ * On discrete platforms, starting from DG2, we have to contend with GTT
+ * page size restrictions when dealing with I915_MEMORY_CLASS_DEVICE
+ * objects. Specifically the hardware only supports 64K or larger GTT
+ * page sizes for such memory. The kernel will already ensure that all
+ * I915_MEMORY_CLASS_DEVICE memory is allocated using 64K or larger page
+ * sizes underneath.
+ *
+ * Note that the returned size here will always reflect any required
+ * rounding up done by the kernel, i.e 4K will now become 64K on devices
+ * such as DG2. The GTT alignment will also need be at least 64K for
+ * such objects.
+ *
+ * Note that due to how the hardware implements 64K GTT page support, we
+ * have some further complications:
+ *
+ * 1.) The entire PDE(which covers a 2M virtual address range), must
+ * contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same
+ * PDE is forbidden by the hardware.
+ *
+ * 2.) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM
+ * objects.
+ *
+ * To handle the above the kernel implements a memory coloring scheme to
+ * prevent userspace from mixing I915_MEMORY_CLASS_DEVICE and
+ * I915_MEMORY_CLASS_SYSTEM objects in the same PDE. If the kernel is
+ * ever unable to evict the required pages for the given PDE(different
+ * color) when inserting the object into the GTT then it will simply
+ * fail the request.
+ *
+ * Since userspace needs to manage the GTT address space themselves,
+ * special care is needed to ensure this doesn't happen. The simplest
+ * scheme is to simply align and round up all I915_MEMORY_CLASS_DEVICE
+ * objects to 2M, which avoids any issues here. At the very least this
+ * is likely needed for objects that can be placed in both
+ * I915_MEMORY_CLASS_DEVICE and I915_MEMORY_CLASS_SYSTEM, to avoid
+ * potential issues when the kernel needs to migrate the object behind
+ * the scenes, since that might also involve evicting other objects.
+ *
+ * To summarise the GTT rules, on platforms like DG2:
+ *
+ * 1.) All objects that can be placed in I915_MEMORY_CLASS_DEVICE must
+ * have 64K alignment. The kernel will reject this otherwise.
+ *
+ * 2.) All I915_MEMORY_CLASS_DEVICE objects must never be placed in
+ * the same PDE with other I915_MEMORY_CLASS_SYSTEM objects. The
+ * kernel will reject this otherwise.
+ *
+ * 3.) Objects that can be placed in both I915_MEMORY_CLASS_DEVICE and
+ * I915_MEMORY_CLASS_SYSTEM should probably be aligned and padded out
+ * to 2M.
*/
__u64 size;
/**
--
2.20.1
next prev parent reply other threads:[~2021-10-11 16:10 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-10-11 16:11 [Intel-gfx] [PATCH 00/14] drm/i915/dg2: Enabling 64k page size and flat ccs Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 01/14] drm/i915: Add has_64k_pages flag Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 02/14] drm/i915/xehpsdv: set min page-size to 64K Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 03/14] drm/i915/xehpsdv: enforce min GTT alignment Ramalingam C
2021-10-13 13:38 ` Daniel Vetter
2021-10-13 14:13 ` Matthew Auld
2021-10-14 13:33 ` Daniel Vetter
2021-10-14 14:21 ` Matthew Auld
2021-10-11 16:11 ` [Intel-gfx] [PATCH 04/14] drm/i915: enforce min page size for scratch Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 05/14] drm/i915/gtt/xehpsdv: move scratch page to system memory Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 06/14] drm/i915/xehpsdv: support 64K GTT pages Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 07/14] drm/i915: Add vm min alignment support Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 08/14] drm/i915/selftests: account for min_alignment in GTT selftests Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 09/14] drm/i915/xehpsdv: implement memory coloring Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 10/14] drm/i915/xehpsdv: Add has_flat_ccs to device info Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 11/14] drm/i915/lmem: Enable lmem for platforms with Flat CCS Ramalingam C
2021-10-11 16:11 ` [Intel-gfx] [PATCH 12/14] drm/i915/gt: Clear compress metadata for Gen12.5 >= platforms Ramalingam C
2021-10-11 16:11 ` Ramalingam C [this message]
2021-10-13 13:46 ` [Intel-gfx] [PATCH 13/14] drm/i915/uapi: document behaviour for DG2 64K support Daniel Vetter
2021-10-11 16:11 ` [Intel-gfx] [PATCH 14/14] Doc/gpu/rfc/i915: i915 DG2 uAPI Ramalingam C
2021-10-11 17:08 ` Tang, CQ
2021-10-12 5:23 ` Lucas De Marchi
2021-10-13 13:50 ` Daniel Vetter
2021-10-11 18:05 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for drm/i915/dg2: Enabling 64k page size and flat ccs Patchwork
2021-10-11 18:06 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-10-11 18:34 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2021-10-13 13:51 ` [Intel-gfx] [PATCH 00/14] " Daniel Vetter
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=20211011161155.6397-14-ramalingam.c@intel.com \
--to=ramalingam.c@intel.com \
--cc=cq.tang@intel.com \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=matthew.auld@intel.com \
--cc=thomas.hellstrom@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox