From: Alex Deucher <alexander.deucher@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: Mukul Joshi <mukul.joshi@amd.com>,
Felix Kuehling <felix.kuehling@amd.com>,
Alex Deucher <alexander.deucher@amd.com>
Subject: [PATCH 48/95] drm/amdgpu: Add connection state management
Date: Fri, 21 Aug 2026 15:34:11 -0400 [thread overview]
Message-ID: <20260821193458.808626-49-alexander.deucher@amd.com> (raw)
In-Reply-To: <20260821193458.808626-1-alexander.deucher@amd.com>
From: Mukul Joshi <mukul.joshi@amd.com>
Add functions for managing connection state between GPUs
before import/export of ualink handles occurs.
These functions handle the lifecycle of connections between
GPUs,including handling GPU resets, in the NPA-based memory
sharing model.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c | 226 +++++++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h | 13 +-
2 files changed, 238 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c
index 34c69de06e48d..9ef67d10aa963 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c
@@ -32,6 +32,9 @@
#include <linux/string.h>
static void deactivate_accelerator(struct amdgpu_device *adev);
+static int amdgpu_ualink_remote_interrupt(struct amdgpu_device *adev,
+ u32 remote_accel_id, u32 dw0, u32 dw1,
+ u32 dw2, u32 dw3);
static const struct drm_client_funcs ualink_client_funcs = {
.unregister = drm_client_release,
@@ -1206,6 +1209,229 @@ static void amdgpu_generate_ualink_handle(struct amdgpu_device *adev,
handle->handle_hi, handle->handle_lo);
}
+static int amdgpu_ualink_send_hello_ack_msg(struct amdgpu_device *adev,
+ u32 remote_acc_id)
+{
+ dev_dbg(adev->dev, "SEND HELLO-ACK: HELLO-ACK message to remote AccId:%u\n",
+ remote_acc_id);
+ return amdgpu_ualink_remote_interrupt(adev, remote_acc_id,
+ AMDGPU_UALINK_HELLO_ACK_MSG,
+ 0, 0, 0);
+}
+
+static int amdgpu_ualink_send_hello_msg(struct amdgpu_device *adev,
+ u32 remote_acc_id)
+{
+ u32 dw0;
+
+ dw0 = AMDGPU_UALINK_HELLO_MSG;
+ dw0 |= (remote_acc_id << AMDGPU_UALINK_HELLO_MSG_RECV_ACCID_SHIFT);
+ dw0 |= (adev->ualink.info->ppod.accel_id <<
+ AMDGPU_UALINK_HELLO_MSG_SENDER_ACCID_SHIFT);
+
+ dev_dbg(adev->dev, "SEND HELLO: HELLO message to remote AccId:%u\n",
+ remote_acc_id);
+ return amdgpu_ualink_remote_interrupt(adev, remote_acc_id, dw0, 0,
+ 0, 0);
+}
+
+static u32 amdgpu_ualink_check_conn_ready(struct amdgpu_device *adev,
+ u32 remote_acc_id, u32 gen_count)
+{
+ struct amdgpu_ualink_connection *conn_state;
+ u32 current_gen_count = 0;
+
+ conn_state = &adev->ualink.conn_state[remote_acc_id];
+
+ /* Check if the connection is established. */
+ mutex_lock(&conn_state->lock);
+ if ((conn_state->state == AMDGPU_UALINK_CONN_ESTABLISHED) &&
+ (!gen_count || conn_state->generation_count == gen_count))
+ current_gen_count = conn_state->generation_count;
+ mutex_unlock(&conn_state->lock);
+
+ return current_gen_count;
+}
+
+static void amdgpu_ualink_process_hello_ack_msg(struct amdgpu_device *adev,
+ u32 sender_acc_id)
+{
+ struct amdgpu_ualink_connection *conn_state;
+
+ if (sender_acc_id >= AMDGPU_UALINK_ACCEL_MAX) {
+ dev_err(adev->dev,
+ "HELLO-ACK: sender AccId out of range:%u\n",
+ sender_acc_id);
+ return;
+ }
+
+ conn_state = &adev->ualink.conn_state[sender_acc_id];
+
+ /* If we are in IN_PROGRESS state, then transition the connection
+ * state to established and signal that the HELLO ACK is received.
+ * Otherwise, ignore the HELLO ACK.
+ */
+ mutex_lock(&conn_state->lock);
+
+ if (conn_state->state == AMDGPU_UALINK_CONN_IN_PROGRESS) {
+ conn_state->state = AMDGPU_UALINK_CONN_ESTABLISHED;
+ conn_state->generation_count++;
+ complete(&conn_state->hello_done);
+ } else {
+ dev_dbg(adev->dev,
+ "HELLO-ACK: already connected, ignoring from AccId:%u\n",
+ sender_acc_id);
+ }
+ mutex_unlock(&conn_state->lock);
+}
+
+static void amdgpu_ualink_process_hello_msg(struct amdgpu_device *adev,
+ u32 receiver_acc_id,
+ u32 sender_acc_id,
+ u32 src_acc_id)
+{
+ struct amdgpu_ualink_connection *conn_state;
+ int r;
+
+ if (receiver_acc_id != adev->ualink.info->ppod.accel_id) {
+ dev_err(adev->dev,
+ "HELLO: receiver AccId mismatch got:%u self:%u\n",
+ receiver_acc_id, adev->ualink.info->ppod.accel_id);
+ return;
+ }
+
+ /* src_acc_id is the AccId received in IH cookie. Confirm it
+ * matches with the sender AccId.
+ */
+ if (sender_acc_id != src_acc_id) {
+ dev_err(adev->dev,
+ "HELLO: sender AccId mismatch sender:%u IH cookie:%u\n",
+ sender_acc_id, src_acc_id);
+ return;
+ }
+
+ if (sender_acc_id >= AMDGPU_UALINK_ACCEL_MAX) {
+ dev_err(adev->dev,
+ "HELLO: sender AccId out of range:%u\n",
+ sender_acc_id);
+ return;
+ }
+
+ conn_state = &adev->ualink.conn_state[sender_acc_id];
+
+ /* Check if connection is already established. If yes, then receiving HELLO msg
+ * triggers a reset handling scenario.
+ * If the connection is not ready, and we receive a HELLO msg, then
+ * transition the state to PENDING.
+ * Otherwise, leave it IN_PROGRESS.
+ */
+ mutex_lock(&conn_state->lock);
+ if (conn_state->state != AMDGPU_UALINK_CONN_ESTABLISHED) {
+ if (conn_state->state == AMDGPU_UALINK_CONN_NOT_READY)
+ conn_state->state = AMDGPU_UALINK_CONN_PENDING;
+ /* otherwise, leave it IN_PROGRESS to signal the completion below */
+ mutex_unlock(&conn_state->lock);
+ } else {
+ /* Set the connection state back to In Progress and revoke
+ * all exports and release all imports corresponding to the
+ * sender GPU. Added in later patches.
+ */
+ conn_state->state = AMDGPU_UALINK_CONN_PENDING;
+ mutex_unlock(&conn_state->lock);
+ }
+
+ r = amdgpu_ualink_send_hello_ack_msg(adev, sender_acc_id);
+ if (r)
+ dev_err(adev->dev, "HELLO-ACK: send failed to remote AccId:%u\n",
+ sender_acc_id);
+
+ mutex_lock(&conn_state->lock);
+ if (r) {
+ conn_state->state = AMDGPU_UALINK_CONN_NOT_READY;
+ } else {
+ /* If we are in IN_PROGRESS state and we receivied the HELLO message,
+ * upon receiving the HELLO message, transition the state to ESTABLISHED
+ * and signal the completion.
+ */
+ if (conn_state->state == AMDGPU_UALINK_CONN_IN_PROGRESS)
+ complete(&conn_state->hello_done);
+ conn_state->state = AMDGPU_UALINK_CONN_ESTABLISHED;
+ conn_state->generation_count++;
+ }
+ mutex_unlock(&conn_state->lock);
+}
+
+static int amdgpu_ualink_setup_connection(struct amdgpu_device *adev,
+ u32 remote_acc_id)
+{
+ struct amdgpu_ualink_connection *conn_state;
+ int r;
+
+ conn_state = &adev->ualink.conn_state[remote_acc_id];
+
+ /* Connection state management goes through different states.
+ * The states are:
+ * - NOT_READY: The connection is not ready.
+ * - IN_PROGRESS: GPU sent HELLO message and is waiting for the HELLO_ACK.
+ * - PENDING: GPU received HELLO message and is in the process of sending
+ * the HELLO_ACK.
+ * - ESTABLISHED: The connection is established.
+ */
+
+ /* Grab the lock and check if connection establishment was
+ * already done by another thread.
+ */
+ mutex_lock(&conn_state->lock);
+ if (conn_state->state == AMDGPU_UALINK_CONN_ESTABLISHED) {
+ r = 0;
+ goto out;
+ } else if (conn_state->state == AMDGPU_UALINK_CONN_IN_PROGRESS ||
+ conn_state->state == AMDGPU_UALINK_CONN_PENDING) {
+ r = -EAGAIN;
+ goto out;
+ }
+
+ conn_state->state = AMDGPU_UALINK_CONN_IN_PROGRESS;
+ mutex_unlock(&conn_state->lock);
+
+ /* Send HELLO message */
+ r = amdgpu_ualink_send_hello_msg(adev, remote_acc_id);
+ if (r) {
+ dev_warn(adev->dev,
+ "HELLO: Send failed to remote AccId:%u\n",
+ remote_acc_id);
+ goto reset_state;
+ }
+
+ /* Wait for the HELLO_ACK to come back */
+ /* complete(conn_state->hello_done) should be called from the IRQ
+ * handler when the HELLO_ACK is received.
+ */
+ r = wait_for_completion_interruptible_timeout(&conn_state->hello_done,
+ msecs_to_jiffies(AMDGPU_UALINK_RESP_TIMEOUT));
+ if (r == -ERESTARTSYS) {
+ dev_err_ratelimited(adev->dev,
+ "HELLO-ACK: interrupted by signal\n");
+ goto reset_state;
+ } else if (r == 0) {
+ dev_warn(adev->dev,
+ "HELLO-ACK: Timeout from remote AccId:%u\n",
+ remote_acc_id);
+ r = -ETIMEDOUT;
+ goto reset_state;
+ }
+
+ return 0;
+
+reset_state:
+ mutex_lock(&conn_state->lock);
+ conn_state->state = AMDGPU_UALINK_CONN_NOT_READY;
+out:
+ mutex_unlock(&conn_state->lock);
+
+ return r;
+}
+
static void amdgpu_ualink_exp_cleanup_worker(struct work_struct *work)
{
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h
index cf9522e4f8a74..c8c37d4ee4b48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h
@@ -31,12 +31,23 @@
#define AMDGPU_UALINK_LOCAL_ACCELS_MAX 8
#define AMDGPU_UALINK_STATIONS_MAX 64
+#define AMDGPU_UALINK_RESP_TIMEOUT 5000 /* 5s timeout */
+
#define AMDGPU_UALINK_HANDLE_ACCID_MASK GENMASK_ULL(9, 0)
+#define AMDGPU_UALINK_HELLO_MSG_RECV_ACCID_SHIFT 10
+#define AMDGPU_UALINK_HELLO_MSG_SENDER_ACCID_SHIFT 20
+
+enum AMDGPU_UALINK_PROTOCOL_MESSAGES {
+ AMDGPU_UALINK_HELLO_MSG = 1,
+ AMDGPU_UALINK_HELLO_ACK_MSG = 2,
+ AMDGPU_UALINK_MAX_PROTOCOL_MSG
+};
enum amdgpu_ualink_conn_state {
AMDGPU_UALINK_CONN_NOT_READY = 0,
AMDGPU_UALINK_CONN_IN_PROGRESS = 1,
- AMDGPU_UALINK_CONN_ESTABLISHED = 2
+ AMDGPU_UALINK_CONN_PENDING = 2,
+ AMDGPU_UALINK_CONN_ESTABLISHED = 3
};
enum amdgpu_ualink_type {
--
2.55.0
next prev parent reply other threads:[~2026-08-21 19:51 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-08-21 19:33 [PATCH 00/95] Add UALink instrastructure series 1 Alex Deucher
2026-08-21 19:33 ` [PATCH 01/95] drm/amdgpu: Add psp ualink command interfaces Alex Deucher
2026-08-21 19:33 ` [PATCH 02/95] drm/amdgpu: Fetch asp ualink interface version Alex Deucher
2026-08-21 19:33 ` [PATCH 03/95] drm/amdgpu: Add sysfs API for UALink information Alex Deucher
2026-08-21 19:33 ` [PATCH 04/95] drm/amdgpu: Add sysfs API for UALink physical pod setup Alex Deucher
2026-08-21 19:33 ` [PATCH 05/95] drm/amdgpu: Add sysfs API for UALink virtual pod config Alex Deucher
2026-08-21 19:33 ` [PATCH 06/95] drm/amdgpu: Add sysfs API for UALink station configuration Alex Deucher
2026-08-21 19:33 ` [PATCH 07/95] drm/amdgpu: Add UALink manager core infrastructure Alex Deucher
2026-08-21 19:33 ` [PATCH 08/95] drm/amdgpu: Implement PSP cmd UAL_GET_CONFIG Alex Deucher
2026-08-21 19:33 ` [PATCH 09/95] drm/amdgpu: Query initial UALink config from PSP Alex Deucher
2026-08-21 19:33 ` [PATCH 10/95] drm/amdgpu: Implement PSP cmd UAL_SET_PPOD_CONFIG Alex Deucher
2026-08-21 19:33 ` [PATCH 11/95] drm/amdgpu: Set physical pod configuration to PSP Alex Deucher
2026-08-21 19:33 ` [PATCH 12/95] drm/amdgpu: Implement PSP cmd UAL_SET_VPOD_CONFIG Alex Deucher
2026-08-21 19:33 ` [PATCH 13/95] drm/amdgpu: Set virtual pod configuration to PSP Alex Deucher
2026-08-21 19:33 ` [PATCH 14/95] drm/amdgpu: Implement PSP cmd UAL_SET_STATION_CONFIG Alex Deucher
2026-08-21 19:33 ` [PATCH 15/95] drm/amdgpu: Set UALink station config to PSP Alex Deucher
2026-08-21 19:33 ` [PATCH 16/95] drm/amdgpu: Implement PSP cmd UAL_SET_NPA_CONFIG Alex Deucher
2026-08-21 19:33 ` [PATCH 17/95] drm/amdgpu: Enable/disable NPA address translation using PSP Alex Deucher
2026-08-21 19:33 ` [PATCH 18/95] drm/amdgpu: Add helper function to check psp xgmi ta Alex Deucher
2026-08-21 19:33 ` [PATCH 19/95] drm/amdgpu: add handler for nHT error Alex Deucher
2026-08-21 19:33 ` [PATCH 20/95] drm/amdgpu: Add ual_config_state to ual_get_config Alex Deucher
2026-08-21 19:33 ` [PATCH 21/95] drm/amdgpu: extend PSP command polling sleep range Alex Deucher
2026-08-21 19:33 ` [PATCH 22/95] drm/amdgpu: Fix NULL pointer issue during ualink init Alex Deucher
2026-08-21 19:33 ` [PATCH 23/95] drm/amdgpu: Add a new NPA Address space Alex Deucher
2026-08-21 19:33 ` [PATCH 24/95] drm/amdgpu: Add address allocator for NPA addresses Alex Deucher
2026-08-21 19:33 ` [PATCH 25/95] drm/amdgpu: Initialize VM for NPA addr management Alex Deucher
2026-08-21 19:33 ` [PATCH 26/95] drm/amdgpu: Rework VMID reservation logic Alex Deucher
2026-08-21 19:33 ` [PATCH 27/95] drm/amdgpu: Reserve VMID for NPA VM Alex Deucher
2026-08-21 19:33 ` [PATCH 28/95] drm/amdgpu: Use reserved " Alex Deucher
2026-08-21 19:33 ` [PATCH 29/95] drm/amdgpu: Enable UALink Manager when pod becomes active Alex Deucher
2026-08-21 19:33 ` [PATCH 30/95] drm/amdgpu: Fix UALink vPod double-activation Alex Deucher
2026-08-21 19:33 ` [PATCH 31/95] drm/amdgpu: Add UALink remote state structures and API declarations Alex Deucher
2026-08-21 19:33 ` [PATCH 32/95] drm/amdgpu: Add UALink NPA address layout helpers Alex Deucher
2026-08-21 19:33 ` [PATCH 33/95] drm/amdgpu: Add UALink NPA address computation for ring buffers Alex Deucher
2026-08-21 19:33 ` [PATCH 34/95] drm/amdgpu: Add UALink NPA VM mapping " Alex Deucher
2026-08-21 19:33 ` [PATCH 35/95] drm/amdgpu: Add UALink SDMA scheduler entities Alex Deucher
2026-08-21 19:33 ` [PATCH 36/95] drm/amdgpu: Add UALink GART helpers for NPA address access Alex Deucher
2026-08-21 19:34 ` [PATCH 37/95] drm/amdgpu: Add UALink ring buffer allocation and firmware init Alex Deucher
2026-08-21 19:34 ` [PATCH 38/95] drm/amdgpu: Add UALink remote command packets and SDMA dispatch Alex Deucher
2026-08-21 19:34 ` [PATCH 39/95] drm/amdgpu: Add UALink firmware writeback address configuration Alex Deucher
2026-08-21 19:34 ` [PATCH 40/95] drm/amdgpu: Add UALink cross-GPU TLB shootdown and remote interrupt Alex Deucher
2026-08-21 19:34 ` [PATCH 41/95] drm/amdgpu: Add UALink software init, teardown, and reset Alex Deucher
2026-08-21 19:34 ` [PATCH 42/95] drm/amdgpu: Add UALink IH ring and enable interrupt Alex Deucher
2026-08-21 19:34 ` [PATCH 43/95] drm/amdgpu: UALink use LSDMA to send remote interrupt command Alex Deucher
2026-08-21 19:34 ` [PATCH 44/95] drm/amdgpu: Create a drm client for UALink NPA BOs Alex Deucher
2026-08-21 19:34 ` [PATCH 45/95] drm/amdgpu: Control NPA DMA-buf importing Alex Deucher
2026-08-21 19:34 ` [PATCH 46/95] drm/amdgpu: Add ualink handle to BOs Alex Deucher
2026-08-21 19:34 ` [PATCH 47/95] drm/amdgpu: Implement UALink handle export Alex Deucher
2026-08-21 19:34 ` Alex Deucher [this message]
2026-08-21 19:34 ` [PATCH 49/95] drm/amdgpu: Implement UALink handle import ioctl Alex Deucher
2026-08-21 19:34 ` [PATCH 50/95] drm/amdgpu: Implement mechanism to revoke exported memory Alex Deucher
2026-08-21 19:34 ` [PATCH 51/95] drm/amdgpu: lock UALink import invalidation via drm_exec Alex Deucher
2026-08-21 19:34 ` [PATCH 52/95] drm/amdgpu: Cleanup exported UALink handles Alex Deucher
2026-08-21 19:34 ` [PATCH 53/95] drm/amdgpu: Cleanup imported " Alex Deucher
2026-08-21 19:34 ` [PATCH 54/95] drm/amdgpu: Handle connection reset Alex Deucher
2026-08-21 19:34 ` [PATCH 55/95] drm/amdgpu: Setup PTE mappings for NPA addresses Alex Deucher
2026-08-21 19:34 ` [PATCH 56/95] drm/amdgpu: Add handling for remote interrupts Alex Deucher
2026-08-21 19:34 ` [PATCH 57/95] drm/amdgpu: Send TLB shootdown on exported memory unmap Alex Deucher
2026-08-21 19:34 ` [PATCH 58/95] drm/amdgpu: Handle local GPUs in UALink import Alex Deucher
2026-08-21 19:34 ` [PATCH 59/95] drm/amdgpu: Add debugfs to drop UALink protocol messages Alex Deucher
2026-08-21 19:34 ` [PATCH 60/95] drm/amdgpu: Temporarily disable sending remote TLB shootdowns Alex Deucher
2026-08-21 19:34 ` [PATCH 61/95] drm/amdgpu: Temporarily Flush TLB on NPA mapping always Alex Deucher
2026-08-21 19:34 ` [PATCH 62/95] drm/amdgpu: log remote memory MTYPE for GC 12.1.0 Alex Deucher
2026-08-21 19:34 ` [PATCH 63/95] drm/amdgpu: Prevent double-free of drm_exec Alex Deucher
2026-08-21 19:34 ` [PATCH 64/95] drm/amdgpu: fix NPA-RELEASE race in UALink exporter cleanup Alex Deucher
2026-08-21 19:34 ` [PATCH 65/95] drm/amdgpu: initialize UALink importer node list head Alex Deucher
2026-08-21 19:34 ` [PATCH 66/95] drm/amdgpu: Fix initialization flags for UALink XAs Alex Deucher
2026-08-21 19:34 ` [PATCH 67/95] drm/amdgpu: fix dma_buf leak in UALink exporter cleanup Alex Deucher
2026-08-21 19:34 ` [PATCH 68/95] drm/amdgpu: Increase UALink soft ring size Alex Deucher
2026-08-21 19:34 ` [PATCH 69/95] drm/amdgpu: Fix uninitialized fence in UALink NPA unmap Alex Deucher
2026-08-21 19:34 ` [PATCH 70/95] drm/amdgpu: Use vm->last_update fence in UALink NPA unmap paths Alex Deucher
2026-08-21 19:34 ` [PATCH 71/95] drm/amdgpu: Pin page tables in NPA VMs Alex Deucher
2026-08-21 19:34 ` [PATCH 72/95] drm/amdgpu: Initialize NPA PT/PDs to noretry Alex Deucher
2026-08-21 19:34 ` [PATCH 73/95] drm/amdgpu: always use MTYPE_UC for remote memory on GFX 12.1 Alex Deucher
2026-08-21 19:34 ` [PATCH 74/95] drm/amdkfd: program compute MQD coherent_aql_mtype " Alex Deucher
2026-08-21 19:34 ` [PATCH 75/95] drm/amdgpu: Separate out ualink init sequences Alex Deucher
2026-08-21 19:34 ` [PATCH 76/95] drm/amdgpu: Add ualink as separate ip block Alex Deucher
2026-08-21 19:34 ` [PATCH 77/95] drm/admgpu: Seggregate ualink nht messaging Alex Deucher
2026-08-21 19:34 ` [PATCH 78/95] drm/amdgpu: Assign accel state based on ASP config Alex Deucher
2026-08-21 19:34 ` [PATCH 79/95] drm/amdgpu: Drop duplicate vpod check functions Alex Deucher
2026-08-21 19:34 ` [PATCH 80/95] drm/amdgpu: Add support to send ASP completion Alex Deucher
2026-08-21 19:34 ` [PATCH 81/95] drm/amdgpu: Add handlers for ualink notifications Alex Deucher
2026-08-21 19:34 ` [PATCH 82/95] drm/amdgpu: Improve ualink state transitions Alex Deucher
2026-08-21 19:34 ` [PATCH 83/95] drm/amdgpu: Use uniform logic for inband/sideband Alex Deucher
2026-08-21 19:34 ` [PATCH 84/95] drm/amdgpu: Fix GART and SDMA entity leak on vPod reconfiguration Alex Deucher
2026-08-21 19:34 ` [PATCH 85/95] drm/amdgpu: Add UALink diagnostic logging for vpod commit/activation Alex Deucher
2026-08-21 19:34 ` [PATCH 86/95] drm/amdgpu: Handle UALink vPod reconfiguration while ACTIVE Alex Deucher
2026-08-21 19:34 ` [PATCH 87/95] drm/amdgpu: Add name for ualink ip block Alex Deucher
2026-08-21 19:34 ` [PATCH 88/95] drm/amdgpu: Cleanup UALink XA entries on manager stop Alex Deucher
2026-08-21 19:34 ` [PATCH 89/95] drm/amdgpu: Move ualink ip version related changes Alex Deucher
2026-08-21 19:34 ` [PATCH 90/95] drm/amdgpu: Add hw_fini for ualink Alex Deucher
2026-08-21 19:34 ` [PATCH 91/95] drm/amdgpu: Expose ualink info under each xcp Alex Deucher
2026-08-21 19:34 ` [PATCH 92/95] drm/amdgpu: Handle concurrent UALINK handle import race Alex Deucher
2026-08-21 19:34 ` [PATCH 93/95] drm/amdgpu: create UALink NPA import BO directly in the NPA domain Alex Deucher
2026-08-21 19:34 ` [PATCH 94/95] drm/amdgpu: add mtype_remote module parameter Alex Deucher
2026-08-21 19:34 ` [PATCH 95/95] drm/amdgpu: Honor mtype overrides for NPA remote memory Alex Deucher
2026-08-25 14:45 ` [PATCH 00/95] Add UALink instrastructure series 1 Philip Yang
-- strict thread matches above, loose matches on Subject: below --
2026-08-31 18:26 [PATCH V2 00/95] Add UALink infrastructure " Alex Deucher
2026-08-31 18:27 ` [PATCH 48/95] drm/amdgpu: Add connection state management Alex Deucher
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=20260821193458.808626-49-alexander.deucher@amd.com \
--to=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=felix.kuehling@amd.com \
--cc=mukul.joshi@amd.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