[PATCH libdrm 1/5] new syncobj extension v2

[PATCH libdrm 1/5] new syncobj extension v2

[Christian König]

From: Chunming Zhou <david1.zhou@amd.com>

v2: drop not implemented IOCTLs and flags

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 include/drm/drm.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/include/drm/drm.h b/include/drm/drm.h
index 85c685a2..34f1e3f9 100644
--- a/include/drm/drm.h
+++ b/include/drm/drm.h
@@ -731,6 +731,7 @@ struct drm_syncobj_handle {
 
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
 #define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2)
 struct drm_syncobj_wait {
 	__u64 handles;
 	/* absolute timeout */
@@ -741,12 +742,32 @@ struct drm_syncobj_wait {
 	__u32 pad;
 };
 
+struct drm_syncobj_timeline_wait {
+        __u64 handles;
+        /* wait on specific timeline point for every handles*/
+        __u64 points;
+        /* absolute timeout */
+        __s64 timeout_nsec;
+        __u32 count_handles;
+        __u32 flags;
+        __u32 first_signaled; /* only valid when not waiting all */
+        __u32 pad;
+};
+
 struct drm_syncobj_array {
 	__u64 handles;
 	__u32 count_handles;
 	__u32 pad;
 };
 
+struct drm_syncobj_timeline_query {
+        __u64 handles;
+        /* points are timeline syncobjs payloads returned by query ioctl */
+        __u64 points;
+        __u32 count_handles;
+        __u32 pad;
+};
+
 /* Query current scanout sequence number */
 struct drm_crtc_get_sequence {
 	__u32 crtc_id;		/* requested crtc_id */
@@ -903,6 +924,10 @@ extern "C" {
 #define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
 #define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
 
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
+#define DRM_IOCTL_SYNCOBJ_QUERY         DRM_IOWR(0xCB, struct drm_syncobj_timeline_query)
+
+
 /**
  * Device specific ioctls should only be in their respective headers
  * The device specific ioctl range is from 0x40 to 0x9f.
-- 
2.14.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH libdrm 2/5] addr cs chunk for syncobj timeline

[Christian König]

From: Chunming Zhou <david1.zhou@amd.com>

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
---
 include/drm/amdgpu_drm.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/drm/amdgpu_drm.h b/include/drm/amdgpu_drm.h
index 1ceec56d..a3c067dd 100644
--- a/include/drm/amdgpu_drm.h
+++ b/include/drm/amdgpu_drm.h
@@ -517,6 +517,8 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
 #define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
+#define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT    0x07
+#define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL  0x08
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
@@ -592,6 +594,13 @@ struct drm_amdgpu_cs_chunk_sem {
 	__u32 handle;
 };
 
+struct drm_amdgpu_cs_chunk_syncobj {
+	__u32 handle;
+	__u32 flags;
+	__u64 point;
+};
+
+
 #define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ	0
 #define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD	1
 #define AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD	2
-- 
2.14.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH libdrm 3/5] add timeline wait/query ioctl v2

[Christian König]

From: Chunming Zhou <david1.zhou@amd.com>

v2: drop export/import

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
---
 xf86drm.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 xf86drm.h |  8 ++++++++
 2 files changed, 52 insertions(+)

diff --git a/xf86drm.c b/xf86drm.c
index 71ad54ba..afa2f466 100644
--- a/xf86drm.c
+++ b/xf86drm.c
@@ -4277,3 +4277,47 @@ drm_public int drmSyncobjSignal(int fd, const uint32_t *handles,
     ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_SIGNAL, &args);
     return ret;
 }
+
+drm_public int drmSyncobjTimelineWait(int fd, uint32_t *handles, uint64_t *points,
+				      unsigned num_handles,
+				      int64_t timeout_nsec, unsigned flags,
+				      uint32_t *first_signaled)
+{
+    struct drm_syncobj_timeline_wait args;
+    int ret;
+
+    memclear(args);
+    args.handles = (uintptr_t)handles;
+    args.points = (uint64_t)(uintptr_t)points;
+    args.timeout_nsec = timeout_nsec;
+    args.count_handles = num_handles;
+    args.flags = flags;
+
+    ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, &args);
+    if (ret < 0)
+        return -errno;
+
+    if (first_signaled)
+        *first_signaled = args.first_signaled;
+    return ret;
+}
+
+
+drm_public int drmSyncobjQuery(int fd, uint32_t *handles, uint64_t *points,
+			       uint32_t handle_count)
+{
+    struct drm_syncobj_timeline_query args;
+    int ret;
+
+    memclear(args);
+    args.handles = (uintptr_t)handles;
+    args.points = (uint64_t)(uintptr_t)points;
+    args.count_handles = handle_count;
+
+    ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_QUERY, &args);
+    if (ret)
+        return ret;
+    return 0;
+}
+
+
diff --git a/xf86drm.h b/xf86drm.h
index 7773d71a..2dae1694 100644
--- a/xf86drm.h
+++ b/xf86drm.h
@@ -870,11 +870,19 @@ extern int drmSyncobjFDToHandle(int fd, int obj_fd, uint32_t *handle);
 
 extern int drmSyncobjImportSyncFile(int fd, uint32_t handle, int sync_file_fd);
 extern int drmSyncobjExportSyncFile(int fd, uint32_t handle, int *sync_file_fd);
+extern int drmSyncobjImportSyncFile2(int fd, uint32_t handle, uint64_t point, int sync_file_fd);
+extern int drmSyncobjExportSyncFile2(int fd, uint32_t handle, uint64_t point, int *sync_file_fd);
 extern int drmSyncobjWait(int fd, uint32_t *handles, unsigned num_handles,
 			  int64_t timeout_nsec, unsigned flags,
 			  uint32_t *first_signaled);
 extern int drmSyncobjReset(int fd, const uint32_t *handles, uint32_t handle_count);
 extern int drmSyncobjSignal(int fd, const uint32_t *handles, uint32_t handle_count);
+extern int drmSyncobjTimelineWait(int fd, uint32_t *handles, uint64_t *points,
+				  unsigned num_handles,
+				  int64_t timeout_nsec, unsigned flags,
+				  uint32_t *first_signaled);
+extern int drmSyncobjQuery(int fd, uint32_t *handles, uint64_t *points,
+			   uint32_t handle_count);
 
 #if defined(__cplusplus)
 }
-- 
2.14.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH libdrm 4/5] wrap syncobj timeline query/wait APIs for amdgpu v3

[Christian König]

From: Chunming Zhou <david1.zhou@amd.com>

v2: symbos are stored in lexical order.
v3: drop export/import and extra query indirection

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 amdgpu/amdgpu-symbol-check |  2 ++
 amdgpu/amdgpu.h            | 39 +++++++++++++++++++++++++++++++++++++++
 amdgpu/amdgpu_cs.c         | 23 +++++++++++++++++++++++
 3 files changed, 64 insertions(+)

diff --git a/amdgpu/amdgpu-symbol-check b/amdgpu/amdgpu-symbol-check
index 6f5e0f95..4553736f 100755
--- a/amdgpu/amdgpu-symbol-check
+++ b/amdgpu/amdgpu-symbol-check
@@ -49,8 +49,10 @@ amdgpu_cs_submit
 amdgpu_cs_submit_raw
 amdgpu_cs_syncobj_export_sync_file
 amdgpu_cs_syncobj_import_sync_file
+amdgpu_cs_syncobj_query
 amdgpu_cs_syncobj_reset
 amdgpu_cs_syncobj_signal
+amdgpu_cs_syncobj_timeline_wait
 amdgpu_cs_syncobj_wait
 amdgpu_cs_wait_fences
 amdgpu_cs_wait_semaphore
diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
index dc51659a..330658a0 100644
--- a/amdgpu/amdgpu.h
+++ b/amdgpu/amdgpu.h
@@ -1489,6 +1489,45 @@ int amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
 			   int64_t timeout_nsec, unsigned flags,
 			   uint32_t *first_signaled);
 
+/**
+ *  Wait for one or all sync objects on their points to signal.
+ *
+ * \param   dev	    - \c [in] self-explanatory
+ * \param   handles - \c [in] array of sync object handles
+ * \param   points - \c [in] array of sync points to wait
+ * \param   num_handles - \c [in] self-explanatory
+ * \param   timeout_nsec - \c [in] self-explanatory
+ * \param   flags   - \c [in] a bitmask of DRM_SYNCOBJ_WAIT_FLAGS_*
+ * \param   first_signaled - \c [in] self-explanatory
+ *
+ * \return   0 on success\n
+ *          -ETIME - Timeout
+ *          <0 - Negative POSIX Error code
+ *
+ */
+int amdgpu_cs_syncobj_timeline_wait(amdgpu_device_handle dev,
+				    uint32_t *handles, uint64_t *points,
+				    unsigned num_handles,
+				    int64_t timeout_nsec, unsigned flags,
+				    uint32_t *first_signaled);
+/**
+ *  Query sync objects payloads.
+ *
+ * \param   dev	    - \c [in] self-explanatory
+ * \param   handles - \c [in] array of sync object handles
+ * \param   points - \c [out] array of sync points returned, which presents
+ * syncobj payload.
+ * \param   num_handles - \c [in] self-explanatory
+ *
+ * \return   0 on success\n
+ *          -ETIME - Timeout
+ *          <0 - Negative POSIX Error code
+ *
+ */
+int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
+			    uint32_t *handles, uint64_t *points,
+			    unsigned num_handles);
+
 /**
  *  Export kernel sync object to shareable fd.
  *
diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
index 3b8231aa..e4a547c6 100644
--- a/amdgpu/amdgpu_cs.c
+++ b/amdgpu/amdgpu_cs.c
@@ -661,6 +661,29 @@ drm_public int amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
 			      flags, first_signaled);
 }
 
+drm_public int amdgpu_cs_syncobj_timeline_wait(amdgpu_device_handle dev,
+					       uint32_t *handles, uint64_t *points,
+					       unsigned num_handles,
+					       int64_t timeout_nsec, unsigned flags,
+					       uint32_t *first_signaled)
+{
+	if (NULL == dev)
+		return -EINVAL;
+
+	return drmSyncobjTimelineWait(dev->fd, handles, points, num_handles,
+				      timeout_nsec, flags, first_signaled);
+}
+
+drm_public int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
+				       uint32_t *handles, uint64_t *points,
+				       unsigned num_handles)
+{
+	if (NULL == dev)
+		return -EINVAL;
+
+	return drmSyncobjQuery(dev->fd, handles, points, num_handles);
+}
+
 drm_public int amdgpu_cs_export_syncobj(amdgpu_device_handle dev,
 					uint32_t handle,
 					int *shared_fd)
-- 
2.14.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

[PATCH libdrm 5/5] add syncobj timeline tests v2

[Christian König]

From: Chunming Zhou <david1.zhou@amd.com>

v2: drop DRM_SYNCOBJ_CREATE_TYPE_TIMELINE, fix timeout calculation,
    fix some warnings

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
---
 tests/amdgpu/Makefile.am     |   3 +-
 tests/amdgpu/amdgpu_test.c   |  12 ++
 tests/amdgpu/amdgpu_test.h   |  21 ++++
 tests/amdgpu/meson.build     |   2 +-
 tests/amdgpu/syncobj_tests.c | 266 +++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 302 insertions(+), 2 deletions(-)
 create mode 100644 tests/amdgpu/syncobj_tests.c

diff --git a/tests/amdgpu/Makefile.am b/tests/amdgpu/Makefile.am
index 447ff217..d3fbe2bb 100644
--- a/tests/amdgpu/Makefile.am
+++ b/tests/amdgpu/Makefile.am
@@ -33,4 +33,5 @@ amdgpu_test_SOURCES = \
 	vcn_tests.c \
 	uve_ib.h \
 	deadlock_tests.c \
-	vm_tests.c
+	vm_tests.c \
+	syncobj_tests.c
diff --git a/tests/amdgpu/amdgpu_test.c b/tests/amdgpu/amdgpu_test.c
index ebf44098..ff1448f3 100644
--- a/tests/amdgpu/amdgpu_test.c
+++ b/tests/amdgpu/amdgpu_test.c
@@ -56,6 +56,7 @@
 #define UVD_ENC_TESTS_STR "UVD ENC Tests"
 #define DEADLOCK_TESTS_STR "Deadlock Tests"
 #define VM_TESTS_STR "VM Tests"
+#define SYNCOBJ_TIMELINE_TESTS_STR "SYNCOBJ TIMELINE Tests"
 
 /**
  *  Open handles for amdgpu devices
@@ -116,6 +117,12 @@ static CU_SuiteInfo suites[] = {
 		.pCleanupFunc = suite_vm_tests_clean,
 		.pTests = vm_tests,
 	},
+	{
+		.pName = SYNCOBJ_TIMELINE_TESTS_STR,
+		.pInitFunc = suite_syncobj_timeline_tests_init,
+		.pCleanupFunc = suite_syncobj_timeline_tests_clean,
+		.pTests = syncobj_timeline_tests,
+	},
 
 	CU_SUITE_INFO_NULL,
 };
@@ -165,6 +172,11 @@ static Suites_Active_Status suites_active_stat[] = {
 			.pName = VM_TESTS_STR,
 			.pActive = suite_vm_tests_enable,
 		},
+		{
+			.pName = SYNCOBJ_TIMELINE_TESTS_STR,
+			.pActive = suite_syncobj_timeline_tests_enable,
+		},
+
 };
 
 
diff --git a/tests/amdgpu/amdgpu_test.h b/tests/amdgpu/amdgpu_test.h
index af81eea8..24d64b64 100644
--- a/tests/amdgpu/amdgpu_test.h
+++ b/tests/amdgpu/amdgpu_test.h
@@ -194,6 +194,27 @@ CU_BOOL suite_vm_tests_enable(void);
  */
 extern CU_TestInfo vm_tests[];
 
+/**
+ * Initialize syncobj timeline test suite
+ */
+int suite_syncobj_timeline_tests_init();
+
+/**
+ * Deinitialize syncobj timeline test suite
+ */
+int suite_syncobj_timeline_tests_clean();
+
+/**
+ * Decide if the suite is enabled by default or not.
+ */
+CU_BOOL suite_syncobj_timeline_tests_enable(void);
+
+/**
+ * Tests in syncobj timeline test suite
+ */
+extern CU_TestInfo syncobj_timeline_tests[];
+
+
 /**
  * Helper functions
  */
diff --git a/tests/amdgpu/meson.build b/tests/amdgpu/meson.build
index 4c1237c6..3ceec715 100644
--- a/tests/amdgpu/meson.build
+++ b/tests/amdgpu/meson.build
@@ -24,7 +24,7 @@ if dep_cunit.found()
     files(
       'amdgpu_test.c', 'basic_tests.c', 'bo_tests.c', 'cs_tests.c',
       'vce_tests.c', 'uvd_enc_tests.c', 'vcn_tests.c', 'deadlock_tests.c',
-      'vm_tests.c',
+      'vm_tests.c', 'syncobj_tests.c',
     ),
     dependencies : [dep_cunit, dep_threads],
     include_directories : [inc_root, inc_drm, include_directories('../../amdgpu')],
diff --git a/tests/amdgpu/syncobj_tests.c b/tests/amdgpu/syncobj_tests.c
new file mode 100644
index 00000000..cbe9394c
--- /dev/null
+++ b/tests/amdgpu/syncobj_tests.c
@@ -0,0 +1,266 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+*/
+
+#include "CUnit/Basic.h"
+
+#include "amdgpu_test.h"
+#include "amdgpu_drm.h"
+#include "amdgpu_internal.h"
+#include <pthread.h>
+
+static  amdgpu_device_handle device_handle;
+static  uint32_t  major_version;
+static  uint32_t  minor_version;
+
+static void amdgpu_syncobj_timeline_test(void);
+
+CU_BOOL suite_syncobj_timeline_tests_enable(void)
+{
+	return CU_TRUE;
+}
+
+int suite_syncobj_timeline_tests_init(void)
+{
+	int r;
+
+	r = amdgpu_device_initialize(drm_amdgpu[0], &major_version,
+				   &minor_version, &device_handle);
+
+	if (r) {
+		if ((r == -EACCES) && (errno == EACCES))
+			printf("\n\nError:%s. "
+				"Hint:Try to run this test program as root.",
+				strerror(errno));
+		return CUE_SINIT_FAILED;
+	}
+
+	return CUE_SUCCESS;
+}
+
+int suite_syncobj_timeline_tests_clean(void)
+{
+	int r = amdgpu_device_deinitialize(device_handle);
+
+	if (r == 0)
+		return CUE_SUCCESS;
+	else
+		return CUE_SCLEAN_FAILED;
+}
+
+
+CU_TestInfo syncobj_timeline_tests[] = {
+	{ "syncobj timeline test",  amdgpu_syncobj_timeline_test },
+	CU_TEST_INFO_NULL,
+};
+
+#define GFX_COMPUTE_NOP  0xffff1000
+#define SDMA_NOP  0x0
+static int syncobj_command_submission_helper(uint32_t syncobj_handle, bool
+					     wait_or_signal, uint64_t point)
+{
+	amdgpu_context_handle context_handle;
+	amdgpu_bo_handle ib_result_handle;
+	void *ib_result_cpu;
+	uint64_t ib_result_mc_address;
+	struct drm_amdgpu_cs_chunk chunks[2];
+	struct drm_amdgpu_cs_chunk_data chunk_data;
+	struct drm_amdgpu_cs_chunk_syncobj syncobj_data;
+	struct amdgpu_cs_fence fence_status;
+	amdgpu_bo_list_handle bo_list;
+	amdgpu_va_handle va_handle;
+	uint32_t expired, flags;
+	int i, r;
+	uint64_t seq_no;
+	static uint32_t *ptr;
+
+	r = amdgpu_cs_ctx_create(device_handle, &context_handle);
+	CU_ASSERT_EQUAL(r, 0);
+
+	r = amdgpu_bo_alloc_and_map(device_handle, 4096, 4096,
+				    AMDGPU_GEM_DOMAIN_GTT, 0,
+				    &ib_result_handle, &ib_result_cpu,
+				    &ib_result_mc_address, &va_handle);
+	CU_ASSERT_EQUAL(r, 0);
+
+	r = amdgpu_get_bo_list(device_handle, ib_result_handle, NULL,
+			       &bo_list);
+	CU_ASSERT_EQUAL(r, 0);
+
+	ptr = ib_result_cpu;
+
+	for (i = 0; i < 16; ++i)
+		ptr[i] = wait_or_signal ? GFX_COMPUTE_NOP: SDMA_NOP;
+
+	chunks[0].chunk_id = AMDGPU_CHUNK_ID_IB;
+	chunks[0].length_dw = sizeof(struct drm_amdgpu_cs_chunk_ib) / 4;
+	chunks[0].chunk_data = (uint64_t)(uintptr_t)&chunk_data;
+	chunk_data.ib_data._pad = 0;
+	chunk_data.ib_data.va_start = ib_result_mc_address;
+	chunk_data.ib_data.ib_bytes = 16 * 4;
+	chunk_data.ib_data.ip_type = wait_or_signal ? AMDGPU_HW_IP_GFX :
+		AMDGPU_HW_IP_DMA;
+	chunk_data.ib_data.ip_instance = 0;
+	chunk_data.ib_data.ring = 0;
+	chunk_data.ib_data.flags = 0;
+
+	chunks[1].chunk_id = wait_or_signal ?
+		AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT :
+		AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL;
+	chunks[1].length_dw = sizeof(struct drm_amdgpu_cs_chunk_syncobj) / 4;
+	chunks[1].chunk_data = (uint64_t)(uintptr_t)&syncobj_data;
+	syncobj_data.handle = syncobj_handle;
+	syncobj_data.point = point;
+	syncobj_data.flags = DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT;
+
+	r = amdgpu_cs_submit_raw(device_handle,
+				 context_handle,
+				 bo_list,
+				 2,
+				 chunks,
+				 &seq_no);
+	CU_ASSERT_EQUAL(r, 0);
+
+
+	memset(&fence_status, 0, sizeof(struct amdgpu_cs_fence));
+	fence_status.context = context_handle;
+	fence_status.ip_type = wait_or_signal ? AMDGPU_HW_IP_GFX:
+		AMDGPU_HW_IP_DMA;
+	fence_status.ip_instance = 0;
+	fence_status.ring = 0;
+	fence_status.fence = seq_no;
+
+	r = amdgpu_cs_query_fence_status(&fence_status,
+			AMDGPU_TIMEOUT_INFINITE,0, &expired);
+	CU_ASSERT_EQUAL(r, 0);
+
+	r = amdgpu_bo_list_destroy(bo_list);
+	CU_ASSERT_EQUAL(r, 0);
+
+	r = amdgpu_bo_unmap_and_free(ib_result_handle, va_handle,
+				     ib_result_mc_address, 4096);
+	CU_ASSERT_EQUAL(r, 0);
+
+	r = amdgpu_cs_ctx_free(context_handle);
+	CU_ASSERT_EQUAL(r, 0);
+
+	return r;
+}
+
+struct syncobj_point {
+	uint32_t syncobj_handle;
+	uint64_t point;
+};
+
+static void *syncobj_wait(void *data)
+{
+	struct syncobj_point *sp = (struct syncobj_point *)data;
+	int r;
+
+	r = syncobj_command_submission_helper(sp->syncobj_handle, true,
+					      sp->point);
+	CU_ASSERT_EQUAL(r, 0);
+
+	return (void *)(long)r;
+}
+
+static void *syncobj_signal(void *data)
+{
+	struct syncobj_point *sp = (struct syncobj_point *)data;
+	int r;
+
+	r = syncobj_command_submission_helper(sp->syncobj_handle, false,
+					      sp->point);
+	CU_ASSERT_EQUAL(r, 0);
+
+	return (void *)(long)r;
+}
+
+static void amdgpu_syncobj_timeline_test(void)
+{
+	static pthread_t wait_thread;
+	static pthread_t signal_thread;
+	static pthread_t c_thread;
+	struct syncobj_point sp1, sp2, sp3;
+	uint32_t syncobj_handle;
+	uint64_t payload;
+	uint64_t wait_point;
+	uint64_t timeout;
+	struct timespec tp;
+	int r;
+	void *tmp;
+
+	r =  amdgpu_cs_create_syncobj2(device_handle, 0, &syncobj_handle);
+	CU_ASSERT_EQUAL(r, 0);
+
+	// wait on point 5
+	sp1.syncobj_handle = syncobj_handle;
+	sp1.point = 5;
+	r = pthread_create(&wait_thread, NULL, syncobj_wait, &sp1);
+	CU_ASSERT_EQUAL(r, 0);
+
+	// signal on point 10
+	sp2.syncobj_handle = syncobj_handle;
+	sp2.point = 10;
+	r = pthread_create(&signal_thread, NULL, syncobj_signal, &sp2);
+	CU_ASSERT_EQUAL(r, 0);
+
+	r = pthread_join(wait_thread, &tmp);
+	CU_ASSERT_EQUAL(r, 0);
+	CU_ASSERT_EQUAL(tmp, 0);
+
+	r = pthread_join(signal_thread, &tmp);
+	CU_ASSERT_EQUAL(r, 0);
+	CU_ASSERT_EQUAL(tmp, 0);
+
+	//query timeline payload
+	r = amdgpu_cs_syncobj_query(device_handle, &syncobj_handle,
+				    &payload, 1);
+	CU_ASSERT_EQUAL(r, 0);
+	CU_ASSERT_EQUAL(payload, 10);
+
+	//signal on point 16
+	sp3.syncobj_handle = syncobj_handle;
+	sp3.point = 16;
+	r = pthread_create(&c_thread, NULL, syncobj_signal, &sp3);
+	CU_ASSERT_EQUAL(r, 0);
+	//CPU wait on point 16
+	wait_point = 16;
+	timeout = 0;
+	clock_gettime(CLOCK_MONOTONIC, &tp);
+	timeout = tp.tv_sec * 1000000000ULL + tp.tv_nsec;
+	timeout += 0x10000000000; //10s
+	r = amdgpu_cs_syncobj_timeline_wait(device_handle, &syncobj_handle,
+					    &wait_point, 1, timeout,
+					    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL |
+					    DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT,
+					    NULL);
+
+	CU_ASSERT_EQUAL(r, 0);
+	r = pthread_join(c_thread, &tmp);
+	CU_ASSERT_EQUAL(r, 0);
+	CU_ASSERT_EQUAL(tmp, 0);
+
+	r = amdgpu_cs_destroy_syncobj(device_handle, syncobj_handle);
+	CU_ASSERT_EQUAL(r, 0);
+
+}
-- 
2.14.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH libdrm 3/5] add timeline wait/query ioctl v2

[zhoucm1]

On 2018年11月28日 22:50, Christian König wrote:
> From: Chunming Zhou <david1.zhou@amd.com>
>
> v2: drop export/import
>
> Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
> ---
>   xf86drm.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
>   xf86drm.h |  8 ++++++++
>   2 files changed, 52 insertions(+)
>
> diff --git a/xf86drm.c b/xf86drm.c
> index 71ad54ba..afa2f466 100644
> --- a/xf86drm.c
> +++ b/xf86drm.c
> @@ -4277,3 +4277,47 @@ drm_public int drmSyncobjSignal(int fd, const uint32_t *handles,
>       ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_SIGNAL, &args);
>       return ret;
>   }
> +
> +drm_public int drmSyncobjTimelineWait(int fd, uint32_t *handles, uint64_t *points,
> +				      unsigned num_handles,
> +				      int64_t timeout_nsec, unsigned flags,
> +				      uint32_t *first_signaled)
> +{
> +    struct drm_syncobj_timeline_wait args;
> +    int ret;
> +
> +    memclear(args);
> +    args.handles = (uintptr_t)handles;
> +    args.points = (uint64_t)(uintptr_t)points;
> +    args.timeout_nsec = timeout_nsec;
> +    args.count_handles = num_handles;
> +    args.flags = flags;
> +
> +    ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, &args);
> +    if (ret < 0)
> +        return -errno;
> +
> +    if (first_signaled)
> +        *first_signaled = args.first_signaled;
> +    return ret;
> +}
> +
> +
> +drm_public int drmSyncobjQuery(int fd, uint32_t *handles, uint64_t *points,
We should change 'uint64_t *point' to 'uint64_t **points', otherwise, 
userspace always needs a copy to their own variable.

-David
> +			       uint32_t handle_count)
> +{
> +    struct drm_syncobj_timeline_query args;
> +    int ret;
> +
> +    memclear(args);
> +    args.handles = (uintptr_t)handles;
> +    args.points = (uint64_t)(uintptr_t)points;
> +    args.count_handles = handle_count;
> +
> +    ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_QUERY, &args);
> +    if (ret)
> +        return ret;
> +    return 0;
> +}
> +
> +
> diff --git a/xf86drm.h b/xf86drm.h
> index 7773d71a..2dae1694 100644
> --- a/xf86drm.h
> +++ b/xf86drm.h
> @@ -870,11 +870,19 @@ extern int drmSyncobjFDToHandle(int fd, int obj_fd, uint32_t *handle);
>   
>   extern int drmSyncobjImportSyncFile(int fd, uint32_t handle, int sync_file_fd);
>   extern int drmSyncobjExportSyncFile(int fd, uint32_t handle, int *sync_file_fd);
> +extern int drmSyncobjImportSyncFile2(int fd, uint32_t handle, uint64_t point, int sync_file_fd);
> +extern int drmSyncobjExportSyncFile2(int fd, uint32_t handle, uint64_t point, int *sync_file_fd);
>   extern int drmSyncobjWait(int fd, uint32_t *handles, unsigned num_handles,
>   			  int64_t timeout_nsec, unsigned flags,
>   			  uint32_t *first_signaled);
>   extern int drmSyncobjReset(int fd, const uint32_t *handles, uint32_t handle_count);
>   extern int drmSyncobjSignal(int fd, const uint32_t *handles, uint32_t handle_count);
> +extern int drmSyncobjTimelineWait(int fd, uint32_t *handles, uint64_t *points,
> +				  unsigned num_handles,
> +				  int64_t timeout_nsec, unsigned flags,
> +				  uint32_t *first_signaled);
> +extern int drmSyncobjQuery(int fd, uint32_t *handles, uint64_t *points,
> +			   uint32_t handle_count);
>   
>   #if defined(__cplusplus)
>   }

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH libdrm 3/5] add timeline wait/query ioctl v2

[Christian König]

Am 29.11.18 um 10:28 schrieb zhoucm1:
>
>
> On 2018年11月28日 22:50, Christian König wrote:
>> From: Chunming Zhou <david1.zhou@amd.com>
>>
>> v2: drop export/import
>>
>> Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
>> ---
>>   xf86drm.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
>>   xf86drm.h |  8 ++++++++
>>   2 files changed, 52 insertions(+)
>>
>> diff --git a/xf86drm.c b/xf86drm.c
>> index 71ad54ba..afa2f466 100644
>> --- a/xf86drm.c
>> +++ b/xf86drm.c
>> @@ -4277,3 +4277,47 @@ drm_public int drmSyncobjSignal(int fd, const 
>> uint32_t *handles,
>>       ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_SIGNAL, &args);
>>       return ret;
>>   }
>> +
>> +drm_public int drmSyncobjTimelineWait(int fd, uint32_t *handles, 
>> uint64_t *points,
>> +                      unsigned num_handles,
>> +                      int64_t timeout_nsec, unsigned flags,
>> +                      uint32_t *first_signaled)
>> +{
>> +    struct drm_syncobj_timeline_wait args;
>> +    int ret;
>> +
>> +    memclear(args);
>> +    args.handles = (uintptr_t)handles;
>> +    args.points = (uint64_t)(uintptr_t)points;
>> +    args.timeout_nsec = timeout_nsec;
>> +    args.count_handles = num_handles;
>> +    args.flags = flags;
>> +
>> +    ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT, &args);
>> +    if (ret < 0)
>> +        return -errno;
>> +
>> +    if (first_signaled)
>> +        *first_signaled = args.first_signaled;
>> +    return ret;
>> +}
>> +
>> +
>> +drm_public int drmSyncobjQuery(int fd, uint32_t *handles, uint64_t 
>> *points,
> We should change 'uint64_t *point' to 'uint64_t **points', otherwise, 
> userspace always needs a copy to their own variable.

No, that was something I intentionally changed. It's irrelevant if 
userspace or kernel copies the variable and it is better suited in 
userspace to do this.

Christian.

>
> -David
>> +                   uint32_t handle_count)
>> +{
>> +    struct drm_syncobj_timeline_query args;
>> +    int ret;
>> +
>> +    memclear(args);
>> +    args.handles = (uintptr_t)handles;
>> +    args.points = (uint64_t)(uintptr_t)points;
>> +    args.count_handles = handle_count;
>> +
>> +    ret = drmIoctl(fd, DRM_IOCTL_SYNCOBJ_QUERY, &args);
>> +    if (ret)
>> +        return ret;
>> +    return 0;
>> +}
>> +
>> +
>> diff --git a/xf86drm.h b/xf86drm.h
>> index 7773d71a..2dae1694 100644
>> --- a/xf86drm.h
>> +++ b/xf86drm.h
>> @@ -870,11 +870,19 @@ extern int drmSyncobjFDToHandle(int fd, int 
>> obj_fd, uint32_t *handle);
>>     extern int drmSyncobjImportSyncFile(int fd, uint32_t handle, int 
>> sync_file_fd);
>>   extern int drmSyncobjExportSyncFile(int fd, uint32_t handle, int 
>> *sync_file_fd);
>> +extern int drmSyncobjImportSyncFile2(int fd, uint32_t handle, 
>> uint64_t point, int sync_file_fd);
>> +extern int drmSyncobjExportSyncFile2(int fd, uint32_t handle, 
>> uint64_t point, int *sync_file_fd);
>>   extern int drmSyncobjWait(int fd, uint32_t *handles, unsigned 
>> num_handles,
>>                 int64_t timeout_nsec, unsigned flags,
>>                 uint32_t *first_signaled);
>>   extern int drmSyncobjReset(int fd, const uint32_t *handles, 
>> uint32_t handle_count);
>>   extern int drmSyncobjSignal(int fd, const uint32_t *handles, 
>> uint32_t handle_count);
>> +extern int drmSyncobjTimelineWait(int fd, uint32_t *handles, 
>> uint64_t *points,
>> +                  unsigned num_handles,
>> +                  int64_t timeout_nsec, unsigned flags,
>> +                  uint32_t *first_signaled);
>> +extern int drmSyncobjQuery(int fd, uint32_t *handles, uint64_t *points,
>> +               uint32_t handle_count);
>>     #if defined(__cplusplus)
>>   }
>

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

Re: [PATCH libdrm 4/5] wrap syncobj timeline query/wait APIs for amdgpu v3

[zhoucm1]

On 2018年11月28日 22:50, Christian König wrote:
> From: Chunming Zhou <david1.zhou@amd.com>
>
> v2: symbos are stored in lexical order.
> v3: drop export/import and extra query indirection
>
> Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
> Signed-off-by: Christian König <christian.koenig@amd.com>
> ---
>   amdgpu/amdgpu-symbol-check |  2 ++
>   amdgpu/amdgpu.h            | 39 +++++++++++++++++++++++++++++++++++++++
>   amdgpu/amdgpu_cs.c         | 23 +++++++++++++++++++++++
>   3 files changed, 64 insertions(+)
>
> diff --git a/amdgpu/amdgpu-symbol-check b/amdgpu/amdgpu-symbol-check
> index 6f5e0f95..4553736f 100755
> --- a/amdgpu/amdgpu-symbol-check
> +++ b/amdgpu/amdgpu-symbol-check
> @@ -49,8 +49,10 @@ amdgpu_cs_submit
>   amdgpu_cs_submit_raw
>   amdgpu_cs_syncobj_export_sync_file
>   amdgpu_cs_syncobj_import_sync_file
> +amdgpu_cs_syncobj_query
>   amdgpu_cs_syncobj_reset
>   amdgpu_cs_syncobj_signal
> +amdgpu_cs_syncobj_timeline_wait
>   amdgpu_cs_syncobj_wait
>   amdgpu_cs_wait_fences
>   amdgpu_cs_wait_semaphore
> diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
> index dc51659a..330658a0 100644
> --- a/amdgpu/amdgpu.h
> +++ b/amdgpu/amdgpu.h
> @@ -1489,6 +1489,45 @@ int amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
>   			   int64_t timeout_nsec, unsigned flags,
>   			   uint32_t *first_signaled);
>   
> +/**
> + *  Wait for one or all sync objects on their points to signal.
> + *
> + * \param   dev	    - \c [in] self-explanatory
> + * \param   handles - \c [in] array of sync object handles
> + * \param   points - \c [in] array of sync points to wait
> + * \param   num_handles - \c [in] self-explanatory
> + * \param   timeout_nsec - \c [in] self-explanatory
> + * \param   flags   - \c [in] a bitmask of DRM_SYNCOBJ_WAIT_FLAGS_*
> + * \param   first_signaled - \c [in] self-explanatory
> + *
> + * \return   0 on success\n
> + *          -ETIME - Timeout
> + *          <0 - Negative POSIX Error code
> + *
> + */
> +int amdgpu_cs_syncobj_timeline_wait(amdgpu_device_handle dev,
> +				    uint32_t *handles, uint64_t *points,
> +				    unsigned num_handles,
> +				    int64_t timeout_nsec, unsigned flags,
> +				    uint32_t *first_signaled);
> +/**
> + *  Query sync objects payloads.
> + *
> + * \param   dev	    - \c [in] self-explanatory
> + * \param   handles - \c [in] array of sync object handles
> + * \param   points - \c [out] array of sync points returned, which presents
> + * syncobj payload.
> + * \param   num_handles - \c [in] self-explanatory
> + *
> + * \return   0 on success\n
> + *          -ETIME - Timeout
> + *          <0 - Negative POSIX Error code
> + *
> + */
> +int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
> +			    uint32_t *handles, uint64_t *points,
> +			    unsigned num_handles);
> +
>   /**
>    *  Export kernel sync object to shareable fd.
>    *
> diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
> index 3b8231aa..e4a547c6 100644
> --- a/amdgpu/amdgpu_cs.c
> +++ b/amdgpu/amdgpu_cs.c
> @@ -661,6 +661,29 @@ drm_public int amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
>   			      flags, first_signaled);
>   }
>   
> +drm_public int amdgpu_cs_syncobj_timeline_wait(amdgpu_device_handle dev,
> +					       uint32_t *handles, uint64_t *points,
> +					       unsigned num_handles,
> +					       int64_t timeout_nsec, unsigned flags,
> +					       uint32_t *first_signaled)
> +{
> +	if (NULL == dev)
> +		return -EINVAL;
> +
> +	return drmSyncobjTimelineWait(dev->fd, handles, points, num_handles,
> +				      timeout_nsec, flags, first_signaled);
> +}
> +
> +drm_public int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
> +				       uint32_t *handles, uint64_t *points,
This interfaces is public to umd, I think they like "uint64_t **points" 
for batch query, I've verified before, it works well and more convenience.
If removing num_handles, that means only one syncobj to query, I agree 
with "uint64_t *point".

-David
> +				       unsigned num_handles)
> +{
> +	if (NULL == dev)
> +		return -EINVAL;
> +
> +	return drmSyncobjQuery(dev->fd, handles, points, num_handles);
> +}
> +
>   drm_public int amdgpu_cs_export_syncobj(amdgpu_device_handle dev,
>   					uint32_t handle,
>   					int *shared_fd)

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH libdrm 4/5] wrap syncobj timeline query/wait APIs for amdgpu v3

[Christian König]

Am 30.11.18 um 08:35 schrieb zhoucm1:
>
>
> On 2018年11月28日 22:50, Christian König wrote:
>> From: Chunming Zhou <david1.zhou@amd.com>
>>
>> v2: symbos are stored in lexical order.
>> v3: drop export/import and extra query indirection
>>
>> Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
>> Signed-off-by: Christian König <christian.koenig@amd.com>
>> ---
>>   amdgpu/amdgpu-symbol-check |  2 ++
>>   amdgpu/amdgpu.h            | 39 
>> +++++++++++++++++++++++++++++++++++++++
>>   amdgpu/amdgpu_cs.c         | 23 +++++++++++++++++++++++
>>   3 files changed, 64 insertions(+)
>>
>> diff --git a/amdgpu/amdgpu-symbol-check b/amdgpu/amdgpu-symbol-check
>> index 6f5e0f95..4553736f 100755
>> --- a/amdgpu/amdgpu-symbol-check
>> +++ b/amdgpu/amdgpu-symbol-check
>> @@ -49,8 +49,10 @@ amdgpu_cs_submit
>>   amdgpu_cs_submit_raw
>>   amdgpu_cs_syncobj_export_sync_file
>>   amdgpu_cs_syncobj_import_sync_file
>> +amdgpu_cs_syncobj_query
>>   amdgpu_cs_syncobj_reset
>>   amdgpu_cs_syncobj_signal
>> +amdgpu_cs_syncobj_timeline_wait
>>   amdgpu_cs_syncobj_wait
>>   amdgpu_cs_wait_fences
>>   amdgpu_cs_wait_semaphore
>> diff --git a/amdgpu/amdgpu.h b/amdgpu/amdgpu.h
>> index dc51659a..330658a0 100644
>> --- a/amdgpu/amdgpu.h
>> +++ b/amdgpu/amdgpu.h
>> @@ -1489,6 +1489,45 @@ int 
>> amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
>>                  int64_t timeout_nsec, unsigned flags,
>>                  uint32_t *first_signaled);
>>   +/**
>> + *  Wait for one or all sync objects on their points to signal.
>> + *
>> + * \param   dev        - \c [in] self-explanatory
>> + * \param   handles - \c [in] array of sync object handles
>> + * \param   points - \c [in] array of sync points to wait
>> + * \param   num_handles - \c [in] self-explanatory
>> + * \param   timeout_nsec - \c [in] self-explanatory
>> + * \param   flags   - \c [in] a bitmask of DRM_SYNCOBJ_WAIT_FLAGS_*
>> + * \param   first_signaled - \c [in] self-explanatory
>> + *
>> + * \return   0 on success\n
>> + *          -ETIME - Timeout
>> + *          <0 - Negative POSIX Error code
>> + *
>> + */
>> +int amdgpu_cs_syncobj_timeline_wait(amdgpu_device_handle dev,
>> +                    uint32_t *handles, uint64_t *points,
>> +                    unsigned num_handles,
>> +                    int64_t timeout_nsec, unsigned flags,
>> +                    uint32_t *first_signaled);
>> +/**
>> + *  Query sync objects payloads.
>> + *
>> + * \param   dev        - \c [in] self-explanatory
>> + * \param   handles - \c [in] array of sync object handles
>> + * \param   points - \c [out] array of sync points returned, which 
>> presents
>> + * syncobj payload.
>> + * \param   num_handles - \c [in] self-explanatory
>> + *
>> + * \return   0 on success\n
>> + *          -ETIME - Timeout
>> + *          <0 - Negative POSIX Error code
>> + *
>> + */
>> +int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
>> +                uint32_t *handles, uint64_t *points,
>> +                unsigned num_handles);
>> +
>>   /**
>>    *  Export kernel sync object to shareable fd.
>>    *
>> diff --git a/amdgpu/amdgpu_cs.c b/amdgpu/amdgpu_cs.c
>> index 3b8231aa..e4a547c6 100644
>> --- a/amdgpu/amdgpu_cs.c
>> +++ b/amdgpu/amdgpu_cs.c
>> @@ -661,6 +661,29 @@ drm_public int 
>> amdgpu_cs_syncobj_wait(amdgpu_device_handle dev,
>>                     flags, first_signaled);
>>   }
>>   +drm_public int 
>> amdgpu_cs_syncobj_timeline_wait(amdgpu_device_handle dev,
>> +                           uint32_t *handles, uint64_t *points,
>> +                           unsigned num_handles,
>> +                           int64_t timeout_nsec, unsigned flags,
>> +                           uint32_t *first_signaled)
>> +{
>> +    if (NULL == dev)
>> +        return -EINVAL;
>> +
>> +    return drmSyncobjTimelineWait(dev->fd, handles, points, 
>> num_handles,
>> +                      timeout_nsec, flags, first_signaled);
>> +}
>> +
>> +drm_public int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
>> +                       uint32_t *handles, uint64_t *points,
> This interfaces is public to umd, I think they like "uint64_t 
> **points" for batch query, I've verified before, it works well and 
> more convenience.
> If removing num_handles, that means only one syncobj to query, I agree 
> with "uint64_t *point".

"handles" as well as "points" are an array of objects. If the UMD wants 
to write the points to separate locations it can do so manually after 
calling the function.

It doesn't make any sense that libdrm or the kernel does the extra 
indirection, the transferred pointers are 64bit as well (even on a 32bit 
system) so the overhead is identical.

Adding another indirection just makes the implementation unnecessary 
complex.

Christian.

>
> -David
>> +                       unsigned num_handles)
>> +{
>> +    if (NULL == dev)
>> +        return -EINVAL;
>> +
>> +    return drmSyncobjQuery(dev->fd, handles, points, num_handles);
>> +}
>> +
>>   drm_public int amdgpu_cs_export_syncobj(amdgpu_device_handle dev,
>>                       uint32_t handle,
>>                       int *shared_fd)
>

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

RE: [PATCH libdrm 4/5] wrap syncobj timeline query/wait APIs for amdgpu v3

[Zhou, David(ChunMing)]

> -----Original Message-----
> From: Christian König <ckoenig.leichtzumerken@gmail.com>
> Sent: Friday, November 30, 2018 5:15 PM
> To: Zhou, David(ChunMing) <David1.Zhou@amd.com>; dri-
> devel@lists.freedesktop.org; amd-gfx@lists.freedesktop.org
> Subject: Re: [PATCH libdrm 4/5] wrap syncobj timeline query/wait APIs for
> amdgpu v3
> 
[snip]
> >> +drm_public int amdgpu_cs_syncobj_query(amdgpu_device_handle dev,
> >> +                       uint32_t *handles, uint64_t *points,
> > This interfaces is public to umd, I think they like "uint64_t
> > **points" for batch query, I've verified before, it works well and
> > more convenience.
> > If removing num_handles, that means only one syncobj to query, I agree
> > with "uint64_t *point".
> 
> "handles" as well as "points" are an array of objects. If the UMD wants to
> write the points to separate locations it can do so manually after calling the
> function.

Ok, it doesn't matter.

-David
> 
> It doesn't make any sense that libdrm or the kernel does the extra
> indirection, the transferred pointers are 64bit as well (even on a 32bit
> system) so the overhead is identical.
> 
> Adding another indirection just makes the implementation unnecessary
> complex.


> 
> Christian.
> 
> >
> > -David
> >> +                       unsigned num_handles) {
> >> +    if (NULL == dev)
> >> +        return -EINVAL;
> >> +
> >> +    return drmSyncobjQuery(dev->fd, handles, points, num_handles); }
> >> +
> >>   drm_public int amdgpu_cs_export_syncobj(amdgpu_device_handle dev,
> >>                       uint32_t handle,
> >>                       int *shared_fd)
> >

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx