Skip to contentSkip to conversation

Add UALink infrastructure series 2

PATCH Superseded Alex Deucher 1 participant 4 messages Aug 24

Subsystems (4)
lore
Share & tools
lore

Alex Deucher

author maintainer
#0 lore raw

v2 cover Add UALink infrastructure series 2

This adds the core infrastructure for supporting UALink (Ultra Accelerator Link) connected scale up pods. I've split this into two series, one to add the core infrastructure, and one to expose the new IOCTL interface and add the documentation to avoid spamming the larger audience with the implemenation defails. This is the second series.

The first series can be found here:
https://lists.freedesktop.org/archives/amd-gfx/2026-August/151200.html

Both series can be accessed via this git branch:
https://gitlab.freedesktop.org/agd5f/linux/-/commits/ualink?ref_type=heads

This implements UALoE (UALink over Ethernet). An overview of the complete solution can be found here:
https://www.amd.com/en/products/rackscale-solutions/helios.html

Overview

Connected GPUs in a pod can directly access the remove memory on another GPU over UALink. Unlike RMDA, there is no copy involved; it is direct loads/stores over the fabric. Shared memory can only be accessed by a remote GPU if the memory was exported and the importer has been authorized. For the memory to be shared, it must be part of a unified physical address space shared between nodes. This address space is called NPA (Nework Physical Address) space. This address space is partitioned between the GPUs so that each GPU has it's own segment of the address space in which to export its memory. Each GPU maintains a dedicated set of page tables for their NPA space similar to GPUVM.

Exported memory is pinned. This is similar to how dma-bufs in VRAM are pinned for P2P access. Remote TLB shootdowns from the exporter are used when the exported memory is freed in order to remove access by remote GPUs.

To access remote memory, the driver can map NPA addresses into its per process GPUVM page tables just like local memory. Applications use opaque handles to represent remote memory. GPUs in a pod communicate with eachother directly to exchange NPA addresses between importers and exporters. If a node goes offline or is reset, their peers will clean up any remaining refrences that are lost when that happens.

User interface

Export Memory

To export memory, a handle must be created for an allocation that can be shared with another node in the pod. To do this the exporter calls the GEM UALink IOCTL with the GEM handle to the buffer it wants to export. The IOCTL returns a unique handle which can be shared with the remote host.

Import Memory

To import the memory, the handle from the remote node must be converted from a unique handle to a local GEM object which represents the local reference to the NPA space on the importer. If the memory has already been imported, it just returns a new reference to the existing object. If not, the importer queries the exporter to get the NPA address. Once it has that the importer can create a dma-buf to represent the NPA space used by the allocation and that is returned to the application.

Proposed Userspace
https://github.com/ROCm/rocm-systems/blob/35959f8e1260c7cee3e51a740e320be3856ee4ff/projects/rocr-runtime/libhsakmt/src/memory.c#L971
https://github.com/ROCm/rocm-systems/blob/35959f8e1260c7cee3e51a740e320be3856ee4ff/projects/rocr-runtime/libhsakmt/src/memory.c#L1036

V2: Update the documentation per Felix' feedback. Clarify that exported memory is pinned.

Alex Deucher (1):
Documentation: add initial UALink Documentation

Mukul Joshi (2):
drm/gem: Add callback for when handle count goes to 0 drm/amdgpu: Add ioctl infra for exporting/importing UALink handles

 Documentation/gpu/amdgpu/index.rst         |  1 +
 Documentation/gpu/amdgpu/ualink.rst        | 75 ++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c    |  9 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c | 44 +++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h |  2 +
 drivers/gpu/drm/drm_gem.c                  |  5 +-
 include/drm/drm_gem.h                      | 11 ++++
 include/uapi/drm/amdgpu_drm.h              | 30 +++++++++
 9 files changed, 178 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/gpu/amdgpu/ualink.rst
Signature · 1 line
2.55.0
author maintainer
#1 lore raw

PATCH v2 1/3 drm/gem: Add callback for when handle count goes to 0

From: Mukul Joshi <[email protected]>

Add an optional callback for driver-specific cleanup when the GEM handle of an object is freed. This will be used by AMDGPU to enable freeing of memory exported to other nodes in a UALink pod once all user mode references are gone.

The callback is called outside the object_name_lock and before releasing the reference count on the GEM object

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c |  9 +++++++++
 drivers/gpu/drm/drm_gem.c               |  5 ++++-
 include/drm/drm_gem.h                   | 11 +++++++++++
 3 files changed, 24 insertions(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +9 -0
index f754a4a3a1c22..0d579517c03ce 100644
@@ -386,6 +386,14 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str
 	return drm_gem_ttm_mmap(obj, vma);
 }
 
+static void amdgpu_gem_object_handle_free(struct drm_gem_object *gobj)
+{
+	struct amdgpu_bo *aobj = gem_to_amdgpu_bo(gobj);
+
+	amdgpu_ualink_revoke_exported_memory(aobj);
+
+}
+
 const struct drm_gem_object_funcs amdgpu_gem_object_funcs = {
 	.free = amdgpu_gem_object_free,
 	.open = amdgpu_gem_object_open,
@@ -395,6 +403,7 @@ const struct drm_gem_object_funcs amdgpu_gem_object_funcs = {
 	.vunmap = drm_gem_ttm_vunmap,
 	.mmap = amdgpu_gem_object_mmap,
 	.vm_ops = &amdgpu_gem_vm_ops,
+	.handle_free = amdgpu_gem_object_handle_free
 };
 
 static bool amdgpu_gem_are_domains_valid(u32 domains)
drivers/gpu/drm/drm_gem.c +4 -1
index e3ed684ddcf29..6a86bd2a0343e 100644
@@ -354,8 +354,11 @@ void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj)
 	}
 	mutex_unlock(&dev->object_name_lock);
 
-	if (final)
+	if (final) {
+		if (obj->funcs->handle_free)
+			obj->funcs->handle_free(obj);
 		drm_gem_object_put(obj);
+	}
 }
 
 /*
include/drm/drm_gem.h +11 -0
index 8a704f6a65c15..95d8ae6f85df7 100644
@@ -227,6 +227,17 @@ struct drm_gem_object_funcs {
 	 */
 	size_t (*rss)(struct drm_gem_object *obj);
 
+	/**
+	 * @handle_free:
+	 *
+	 * This callback is called when the GEM handle count goes down to 0.
+	 * It is currently used by AMDGPU driver to release their exported BO
+	 * handles.
+	 *
+	 * This callback is optional.
+	 */
+	void (*handle_free)(struct drm_gem_object *obj);
+
 	/**
 	 * @vm_ops:
 	 *
Signature · 1 line
2.55.0
author maintainer
#2 lore raw

PATCH v2 2/3 drm/amdgpu: Add ioctl infra for exporting/importing UALink handles

In reply to Alex Deucher

From: Mukul Joshi <[email protected]>

Add the ioctl infrastructure to support exporting and importing BOs to facilitate NPA based memory sharing across GPUs in a rack scale setup.

Proposed userspace:
https://github.com/ROCm/rocm-systems/blob/35959f8e1260c7cee3e51a740e320be3856ee4ff/projects/rocr-runtime/libhsakmt/src/memory.c#L971
https://github.com/ROCm/rocm-systems/blob/35959f8e1260c7cee3e51a740e320be3856ee4ff/projects/rocr-runtime/libhsakmt/src/memory.c#L1036

v2: Move the ioctl wire-up to the end of the series.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |  2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c | 44 ++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h |  2 +
 include/uapi/drm/amdgpu_drm.h              | 30 +++++++++++++++
 4 files changed, 78 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +2 -0
index 04b21e456fbc0..25430ff39a6c0 100644
@@ -54,6 +54,7 @@
 #include "amdgpu_userq.h"
 #include "amdgpu_userq_fence.h"
 #include "../amdxcp/amdgpu_xcp_drv.h"
+#include "amdgpu_ualink.h"
 
 /*
  * KMS wrapper.
@@ -3119,6 +3120,7 @@ const struct drm_ioctl_desc amdgpu_ioctls_kms[] = {
 	DRM_IOCTL_DEF_DRV(AMDGPU_USERQ_WAIT, amdgpu_userq_wait_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_GEM_LIST_HANDLES, amdgpu_gem_list_handles_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
 	DRM_IOCTL_DEF_DRV(AMDGPU_PROC_OPTIONS, amdgpu_proc_options_ioctl, DRM_AUTH|DRM_RENDER_ALLOW),
+	DRM_IOCTL_DEF_DRV(AMDGPU_UALINK_HANDLE, amdgpu_gem_ualink_handle_ioctl, DRM_AUTH|DRM_RENDER_ALLOW)
 };
 
 static const struct drm_driver amdgpu_kms_driver = {
drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.c +44 -0

50 lines not on this page · raw message

drivers/gpu/drm/amd/amdgpu/amdgpu_ualink.h +2 -0
index 63710b484c6a5..9908d3a277172 100644
@@ -409,6 +409,8 @@ int amdgpu_ualink_export_handle(struct drm_device *dev, struct drm_file *filp,
 int amdgpu_ualink_import_handle(struct drm_device *dev,
 				const struct amdgpu_ualink_handle *ualink_handle,
 				int *fd_out);
+int amdgpu_gem_ualink_handle_ioctl(struct drm_device *dev, void *data,
+				   struct drm_file *filp);
 void amdgpu_ualink_revoke_exported_memory(struct amdgpu_bo *bo);
 
 int ualink_ip_hw_init(struct amdgpu_ip_block *ip_block);
include/uapi/drm/amdgpu_drm.h +30 -0
index d6d5402a1e789..0e8115673d8d2 100644
@@ -59,6 +59,7 @@ extern "C" {
 #define DRM_AMDGPU_USERQ_WAIT		0x18
 #define DRM_AMDGPU_GEM_LIST_HANDLES	0x19
 #define DRM_AMDGPU_PROC_OPTIONS		0x1A
+#define DRM_AMDGPU_UALINK_HANDLE	0x1B
 
 #define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
 #define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
@@ -81,6 +82,7 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_USERQ_WAIT	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_WAIT, struct drm_amdgpu_userq_wait)
 #define DRM_IOCTL_AMDGPU_GEM_LIST_HANDLES DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_LIST_HANDLES, struct drm_amdgpu_gem_list_handles)
 #define DRM_IOCTL_AMDGPU_PROC_OPTIONS	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_PROC_OPTIONS, struct drm_amdgpu_proc_options)
+#define DRM_IOCTL_AMDGPU_UALINK_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_UALINK_HANDLE, union drm_amdgpu_ualink_handle)
 
 /**
  * DOC: memory domains
@@ -1705,6 +1707,34 @@ struct drm_amdgpu_proc_options {
 	} kfd_sigbus_delay;
 };
 
+#define DRM_AMDGPU_UALINK_HANDLE_OP_EXPORT		0
+#define DRM_AMDGPU_UALINK_HANDLE_OP_IMPORT		1
+
+struct drm_amdgpu_ualink_handle_in {
+	/* Export or import */
+	__u32 op;
+	/* For future use, no flags defined so far */
+	__u32 flags;
+	union {
+		/* GEM handle of the BO to export */
+		__u32 gem_handle;
+		/* UALink handle to import */
+		__u64 import_ualink_handle[2];
+	};
+};
+
+union drm_amdgpu_ualink_handle_out {
+	/* Exported UALink handle */
+	__u64 export_ualink_handle[2];
+	/** DMABuf representing the imported UALink handle */
+	__u32 import_dmabuf_handle;
+};
+
+union drm_amdgpu_ualink_handle {
+	struct drm_amdgpu_ualink_handle_in in;
+	union drm_amdgpu_ualink_handle_out out;
+};
+
 #if defined(__cplusplus)
 }
 #endif
Signature · 1 line
2.55.0
author maintainer
#3 lore raw

PATCH v2 3/3 Documentation: add initial UALink Documentation

In reply to Alex Deucher

Document the details of UALink on the GPU.

v2: add updates from Felix

---
 Documentation/gpu/amdgpu/index.rst  |  1 +
 Documentation/gpu/amdgpu/ualink.rst | 75 +++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)
 create mode 100644 Documentation/gpu/amdgpu/ualink.rst
Documentation/gpu/amdgpu/index.rst +1 -0
index b2ab182236efb..ba2ee73278672 100644
@@ -23,4 +23,5 @@ Next (GCN), Radeon DNA (RDNA), and Compute DNA (CDNA) architectures.
    debugfs
    process-isolation
    amdgpu-glossary
+   ualink
    ptl
Documentation/gpu/amdgpu/ualink.rst new file +75 -0

75 lines not on this page · raw message

Signature · 1 line
2.55.0