From: Jonathan Kim <jonathan.kim@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: <Harish.Kasiviswanathan@amd.com>, Jonathan Kim <jonathan.kim@amd.com>
Subject: [PATCH 2/2] drm/amdkfd: flag per-sdma queue reset supported to user space
Date: Wed, 26 Feb 2025 15:57:34 -0500 [thread overview]
Message-ID: <20250226205734.3108512-2-jonathan.kim@amd.com> (raw)
In-Reply-To: <20250226205734.3108512-1-jonathan.kim@amd.com>
Similar to compute queue reset, flag SDMA queue reset capabilities to
user space for safe testing.
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_topology.c | 5 +++++
drivers/gpu/drm/amd/amdkfd/kfd_topology.h | 1 +
include/uapi/linux/kfd_sysfs.h | 3 +++
3 files changed, 9 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index dbc5595e999a..27e7356eed6f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -519,6 +519,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
dev->gpu->kfd->mec_fw_version);
sysfs_show_32bit_prop(buffer, offs, "capability",
dev->node_props.capability);
+ sysfs_show_32bit_prop(buffer, offs, "capability2",
+ dev->node_props.capability2);
sysfs_show_64bit_prop(buffer, offs, "debug_prop",
dev->node_props.debug_prop);
sysfs_show_32bit_prop(buffer, offs, "sdma_fw_version",
@@ -1981,6 +1983,9 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
if (kfd_dbg_has_ttmps_always_setup(dev->gpu))
dev->node_props.debug_prop |= HSA_DBG_DISPATCH_INFO_ALWAYS_VALID;
+ if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
+ dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
+
if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0)) {
if (KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 3) ||
KFD_GC_VERSION(dev->gpu) == IP_VERSION(9, 4, 4))
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index f06c9db7ddde..3de8ec0043bb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -51,6 +51,7 @@ struct kfd_node_properties {
uint32_t cpu_core_id_base;
uint32_t simd_id_base;
uint32_t capability;
+ uint32_t capability2;
uint64_t debug_prop;
uint32_t max_waves_per_simd;
uint32_t lds_size_in_kb;
diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h
index 859b8e91d4d3..1125fe47959f 100644
--- a/include/uapi/linux/kfd_sysfs.h
+++ b/include/uapi/linux/kfd_sysfs.h
@@ -63,6 +63,9 @@
#define HSA_CAP_PER_QUEUE_RESET_SUPPORTED 0x80000000
#define HSA_CAP_RESERVED 0x000f8000
+#define HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED 0x00000001
+#define HSA_CAP2_RESERVED 0xfffffffe
+
/* debug_prop bits in node properties */
#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK 0x0000000f
#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_SHIFT 0
--
2.34.1
next prev parent reply other threads:[~2025-02-26 20:58 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-26 20:57 [PATCH 1/2] drm/amdkfd: implement per queue sdma reset for gfx 9.4+ Jonathan Kim
2025-02-26 20:57 ` Jonathan Kim [this message]
2025-03-04 16:22 ` [PATCH 2/2] drm/amdkfd: flag per-sdma queue reset supported to user space Kasiviswanathan, Harish
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=20250226205734.3108512-2-jonathan.kim@amd.com \
--to=jonathan.kim@amd.com \
--cc=Harish.Kasiviswanathan@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
/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