From 2c2b0d880f1b4c01f30e14242977b82fa527342d Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Thu, 23 Jul 2020 23:09:57 -0400
Subject: drm/amdkfd: Add thermal throttling SMI event

Add support for reporting thermal throttling events through SMI.
Also, add a counter to count the number of throttling interrupts
observed and report the count in the SMI event message.

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>
---
 include/uapi/linux/kfd_ioctl.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index f738c3b53f4e..df6c7a43aadc 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -450,7 +450,8 @@ struct kfd_ioctl_import_dmabuf_args {
  * KFD SMI(System Management Interface) events
  */
 /* Event type (defined by bitmask) */
-#define KFD_SMI_EVENT_VMFAULT     0x0000000000000001
+#define KFD_SMI_EVENT_VMFAULT			0x0000000000000001
+#define KFD_SMI_EVENT_THERMAL_THROTTLE		0x0000000000000002
 
 struct kfd_ioctl_smi_events_args {
 	__u32 gpuid;	/* to KFD */
-- 
cgit v1.2.3


From 522ec6e0eed0ab0678e7d5b5bf00487dfe83f7ce Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Thu, 30 Jul 2020 18:04:33 -0400
Subject: drm/amdkfd: Replace bitmask with event idx in SMI event msg

Event bitmask is a 64-bit mask with only 1 bit set. Sending this
event bitmask in KFD SMI event message is both wasteful of memory
and potentially limiting to only 64 events. Instead send event
index in SMI event message.
Please note this change does not break the ABI for the two event
types defined so far. The new index is identical to the mask used
before.

Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 24 +++++++++++++-----------
 include/uapi/linux/kfd_ioctl.h              | 10 +++++++---
 2 files changed, 20 insertions(+), 14 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 86c2c3e97944..4d4b6e3ab697 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -149,7 +149,7 @@ static int kfd_smi_ev_release(struct inode *inode, struct file *filep)
 	return 0;
 }
 
-static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event,
+static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event,
 			      char *event_msg, int len)
 {
 	struct kfd_smi_client *client;
@@ -157,14 +157,15 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned long long smi_event
 	rcu_read_lock();
 
 	list_for_each_entry_rcu(client, &dev->smi_clients, list) {
-		if (!(READ_ONCE(client->events) & smi_event))
+		if (!(READ_ONCE(client->events) &
+				KFD_SMI_EVENT_MASK_FROM_INDEX(smi_event)))
 			continue;
 		spin_lock(&client->lock);
 		if (kfifo_avail(&client->fifo) >= len) {
 			kfifo_in(&client->fifo, event_msg, len);
 			wake_up_all(&client->wait_queue);
 		} else {
-			pr_debug("smi_event(EventID: %llu): no space left\n",
+			pr_debug("smi_event(EventID: %u): no space left\n",
 					smi_event);
 		}
 		spin_unlock(&client->lock);
@@ -180,21 +181,21 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 	/*
 	 * ThermalThrottle msg = throttle_bitmask(8):
 	 * 			 thermal_interrupt_count(16):
-	 * 16 bytes event + 1 byte space + 8 byte throttle_bitmask +
+	 * 1 byte event + 1 byte space + 8 byte throttle_bitmask +
 	 * 1 byte : + 16 byte thermal_interupt_counter + 1 byte \n +
-	 * 1 byte \0 = 44
+	 * 1 byte \0 = 29
 	 */
-	char fifo_in[44];
+	char fifo_in[29];
 	int len;
 
 	if (list_empty(&dev->smi_clients))
 		return;
 
-	len = snprintf(fifo_in, 44, "%x %x:%llx\n",
+	len = snprintf(fifo_in, 29, "%x %x:%llx\n",
 		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
 		       atomic64_read(&adev->smu.throttle_int_counter));
 
-	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE, fifo_in, len);
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_THERMAL_THROTTLE,	fifo_in, len);
 }
 
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
@@ -202,9 +203,10 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd;
 	struct amdgpu_task_info task_info;
 	/* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */
-	/* 16 bytes event + 1 byte space + 25 bytes msg + 1 byte \n = 43
+	/* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n +
+	 * 1 byte \0 = 29
 	 */
-	char fifo_in[43];
+	char fifo_in[29];
 	int len;
 
 	if (list_empty(&dev->smi_clients))
@@ -216,7 +218,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	if (!task_info.pid)
 		return;
 
-	len = snprintf(fifo_in, 43, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
+	len = snprintf(fifo_in, 29, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
 		task_info.pid, task_info.task_name);
 
 	add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len);
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index df6c7a43aadc..cb1f963a84e0 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -449,9 +449,13 @@ struct kfd_ioctl_import_dmabuf_args {
 /*
  * KFD SMI(System Management Interface) events
  */
-/* Event type (defined by bitmask) */
-#define KFD_SMI_EVENT_VMFAULT			0x0000000000000001
-#define KFD_SMI_EVENT_THERMAL_THROTTLE		0x0000000000000002
+enum kfd_smi_event {
+        KFD_SMI_EVENT_NONE = 0, /* not used */
+        KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
+        KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+};
+
+#define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
 
 struct kfd_ioctl_smi_events_args {
 	__u32 gpuid;	/* to KFD */
-- 
cgit v1.2.3


From 16c642ec3fe9a144fbe1e97dc56f13a6308f1381 Mon Sep 17 00:00:00 2001
From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Date: Thu, 30 Jul 2020 15:54:59 +0200
Subject: drm/amdgpu: new ids flag for tmz (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allows UMD to know if TMZ is supported and enabled.

This commit also bumps KMS_DRIVER_MINOR because if we don't
UMD can't tell if "ids_flags & AMDGPU_IDS_FLAGS_TMZ == 0" means
"tmz is not enabled" or "tmz may be enabled but the kernel doesn't
report it".

v2: use amdgpu_is_tmz() and reworded commit message.

Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 2 ++
 include/uapi/drm/amdgpu_drm.h           | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 5156c67ec67b..92d0368217a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -88,9 +88,10 @@
  * - 3.37.0 - L2 is invalidated before SDMA IBs, needed for correctness
  * - 3.38.0 - Add AMDGPU_IB_FLAG_EMIT_MEM_SYNC
  * - 3.39.0 - DMABUF implicit sync does a full pipeline sync
+ * - 3.40.0 - Add AMDGPU_IDS_FLAGS_TMZ
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	39
+#define KMS_DRIVER_MINOR	40
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index e99ad031efd4..58580a48b648 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -737,6 +737,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
 		if (amdgpu_mcbp || amdgpu_sriov_vf(adev))
 			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
+		if (amdgpu_is_tmz(adev))
+			dev_info.ids_flags |= AMDGPU_IDS_FLAGS_TMZ;
 
 		vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
 		vm_size -= AMDGPU_VA_RESERVED_SIZE;
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 3218576e109d..c5ff2b275fcd 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -673,6 +673,7 @@ struct drm_amdgpu_cs_chunk_data {
  */
 #define AMDGPU_IDS_FLAGS_FUSION         0x1
 #define AMDGPU_IDS_FLAGS_PREEMPTION     0x2
+#define AMDGPU_IDS_FLAGS_TMZ            0x4
 
 /* indicate if acceleration can be working */
 #define AMDGPU_INFO_ACCEL_WORKING		0x00
-- 
cgit v1.2.3


From cda9edd02425d7902714c60a6f6e31881d2f2741 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Tue, 4 Aug 2020 11:59:53 +0300
Subject: drm/i915: introduce a mechanism to extend execbuf2

We're planning to use this for a couple of new feature where we need
to provide additional parameters to execbuf.

v2: Check for invalid flags in execbuffer2 (Lionel)

v3: Rename I915_EXEC_EXT -> I915_EXEC_USE_EXTENSIONS (Chris)

v4: Rebase
    Move array fence parsing in i915_gem_do_execbuffer()

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-2-lionel.g.landwerlin@intel.com
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 131 +++++++++++++++----------
 include/uapi/drm/i915_drm.h                    |  25 ++++-
 2 files changed, 102 insertions(+), 54 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 6b4ec66cb558..09d2f955b11e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -26,6 +26,7 @@
 #include "i915_gem_ioctls.h"
 #include "i915_sw_fence_work.h"
 #include "i915_trace.h"
+#include "i915_user_extensions.h"
 
 struct eb_vma {
 	struct i915_vma *vma;
@@ -281,6 +282,13 @@ struct i915_execbuffer {
 	int lut_size;
 	struct hlist_head *buckets; /** ht for relocation handles */
 	struct eb_vma_array *array;
+
+	struct i915_eb_fence {
+		struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	} *fences;
+	u32 n_fences;
+
+	u64 extension_flags; /** Available extensions parameters */
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -1622,7 +1630,8 @@ static int i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 		return -EINVAL;
 
 	/* Kernel clipping was a DRI1 misfeature */
-	if (!(exec->flags & I915_EXEC_FENCE_ARRAY)) {
+	if (!(exec->flags & (I915_EXEC_FENCE_ARRAY |
+			     I915_EXEC_USE_EXTENSIONS))) {
 		if (exec->num_cliprects || exec->cliprects_ptr)
 			return -EINVAL;
 	}
@@ -2201,41 +2210,41 @@ eb_pin_engine(struct i915_execbuffer *eb,
 }
 
 static void
-__free_fence_array(struct drm_syncobj **fences, unsigned int n)
+__free_fence_array(struct i915_eb_fence *fences, unsigned int n)
 {
 	while (n--)
-		drm_syncobj_put(ptr_mask_bits(fences[n], 2));
+		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
 	kvfree(fences);
 }
 
-static struct drm_syncobj **
+static int
 get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_file *file)
+		struct i915_execbuffer *eb)
 {
 	const unsigned long nfences = args->num_cliprects;
 	struct drm_i915_gem_exec_fence __user *user;
-	struct drm_syncobj **fences;
+	struct i915_eb_fence *fences;
 	unsigned long n;
 	int err;
 
 	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
-		return NULL;
+		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
 			    ULONG_MAX / sizeof(*user),
 			    SIZE_MAX / sizeof(*fences)))
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	user = u64_to_user_ptr(args->cliprects_ptr);
 	if (!access_ok(user, nfences * sizeof(*user)))
-		return ERR_PTR(-EFAULT);
+		return -EFAULT;
 
 	fences = kvmalloc_array(nfences, sizeof(*fences),
 				__GFP_NOWARN | GFP_KERNEL);
 	if (!fences)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	for (n = 0; n < nfences; n++) {
 		struct drm_i915_gem_exec_fence fence;
@@ -2251,7 +2260,7 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 			goto err;
 		}
 
-		syncobj = drm_syncobj_find(file, fence.handle);
+		syncobj = drm_syncobj_find(eb->file, fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
 			err = -ENOENT;
@@ -2261,38 +2270,31 @@ get_fence_array(struct drm_i915_gem_execbuffer2 *args,
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n] = ptr_pack_bits(syncobj, fence.flags, 2);
+		fences[n].syncobj = ptr_pack_bits(syncobj, fence.flags, 2);
 	}
 
-	return fences;
+	eb->fences = fences;
+	eb->n_fences = nfences;
+
+	return 0;
 
 err:
 	__free_fence_array(fences, n);
-	return ERR_PTR(err);
-}
-
-static void
-put_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct drm_syncobj **fences)
-{
-	if (fences)
-		__free_fence_array(fences, args->num_cliprects);
+	return err;
 }
 
 static int
-await_fence_array(struct i915_execbuffer *eb,
-		  struct drm_syncobj **fences)
+await_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->n_fences; n++) {
 		struct drm_syncobj *syncobj;
 		struct dma_fence *fence;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_WAIT))
 			continue;
 
@@ -2310,18 +2312,16 @@ await_fence_array(struct i915_execbuffer *eb,
 }
 
 static void
-signal_fence_array(struct i915_execbuffer *eb,
-		   struct drm_syncobj **fences)
+signal_fence_array(struct i915_execbuffer *eb)
 {
-	const unsigned int nfences = eb->args->num_cliprects;
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < nfences; n++) {
+	for (n = 0; n < eb->n_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
-		syncobj = ptr_unpack_bits(fences[n], &flags, 2);
+		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
@@ -2370,12 +2370,38 @@ static void eb_request_add(struct i915_execbuffer *eb)
 	mutex_unlock(&tl->mutex);
 }
 
+static const i915_user_extension_fn execbuf_extensions[] = {
+};
+
+static int
+parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
+			  struct i915_execbuffer *eb)
+{
+	eb->extension_flags = 0;
+
+	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
+		return 0;
+
+	/* The execbuf2 extension mechanism reuses cliprects_ptr. So we cannot
+	 * have another flag also using it at the same time.
+	 */
+	if (eb->args->flags & I915_EXEC_FENCE_ARRAY)
+		return -EINVAL;
+
+	if (args->num_cliprects != 0)
+		return -EINVAL;
+
+	return i915_user_extensions(u64_to_user_ptr(args->cliprects_ptr),
+				    execbuf_extensions,
+				    ARRAY_SIZE(execbuf_extensions),
+				    eb);
+}
+
 static int
 i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_file *file,
 		       struct drm_i915_gem_execbuffer2 *args,
-		       struct drm_i915_gem_exec_object2 *exec,
-		       struct drm_syncobj **fences)
+		       struct drm_i915_gem_exec_object2 *exec)
 {
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
@@ -2405,6 +2431,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.batch_len = args->batch_len;
 	eb.trampoline = NULL;
 
+	eb.fences = NULL;
+	eb.n_fences = 0;
+
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
 		if (INTEL_GEN(i915) >= 11)
@@ -2441,10 +2470,18 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		}
 	}
 
-	err = eb_create(&eb);
+	err = parse_execbuf2_extensions(args, &eb);
 	if (err)
 		goto err_out_fence;
 
+	err = get_fence_array(args, &eb);
+	if (err)
+		goto err_arr_fence;
+
+	err = eb_create(&eb);
+	if (err)
+		goto err_arr_fence;
+
 	GEM_BUG_ON(!eb.lut_size);
 
 	err = eb_select_context(&eb);
@@ -2539,8 +2576,8 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (fences) {
-		err = await_fence_array(&eb, fences);
+	if (eb.n_fences) {
+		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
 	}
@@ -2571,8 +2608,8 @@ err_request:
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (fences)
-		signal_fence_array(&eb, fences);
+	if (eb.n_fences)
+		signal_fence_array(&eb);
 
 	if (out_fence) {
 		if (err == 0) {
@@ -2600,6 +2637,8 @@ err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
 	eb_destroy(&eb);
+err_arr_fence:
+	__free_fence_array(eb.fences, eb.n_fences);
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
@@ -2699,7 +2738,7 @@ i915_gem_execbuffer_ioctl(struct drm_device *dev, void *data,
 			exec2_list[i].flags = 0;
 	}
 
-	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list, NULL);
+	err = i915_gem_do_execbuffer(dev, file, &exec2, exec2_list);
 	if (exec2.flags & __EXEC_HAS_RELOC) {
 		struct drm_i915_gem_exec_object __user *user_exec_list =
 			u64_to_user_ptr(args->buffers_ptr);
@@ -2731,7 +2770,6 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_gem_execbuffer2 *args = data;
 	struct drm_i915_gem_exec_object2 *exec2_list;
-	struct drm_syncobj **fences = NULL;
 	const size_t count = args->buffer_count;
 	int err;
 
@@ -2759,15 +2797,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		return -EFAULT;
 	}
 
-	if (args->flags & I915_EXEC_FENCE_ARRAY) {
-		fences = get_fence_array(args, file);
-		if (IS_ERR(fences)) {
-			kvfree(exec2_list);
-			return PTR_ERR(fences);
-		}
-	}
-
-	err = i915_gem_do_execbuffer(dev, file, args, exec2_list, fences);
+	err = i915_gem_do_execbuffer(dev, file, args, exec2_list);
 
 	/*
 	 * Now that we have begun execution of the batchbuffer, we ignore
@@ -2808,7 +2838,6 @@ end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
-	put_fence_array(args, fences);
 	kvfree(exec2_list);
 	return err;
 }
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 00546062e023..dcada8c3a693 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1046,6 +1046,10 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
+enum drm_i915_gem_execbuffer_ext {
+	DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */
+};
+
 struct drm_i915_gem_execbuffer2 {
 	/**
 	 * List of gem_exec_object2 structs
@@ -1062,8 +1066,14 @@ struct drm_i915_gem_execbuffer2 {
 	__u32 num_cliprects;
 	/**
 	 * This is a struct drm_clip_rect *cliprects if I915_EXEC_FENCE_ARRAY
-	 * is not set.  If I915_EXEC_FENCE_ARRAY is set, then this is a
-	 * struct drm_i915_gem_exec_fence *fences.
+	 * & I915_EXEC_USE_EXTENSIONS are not set.
+	 *
+	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+	 * of struct drm_i915_gem_exec_fence and num_cliprects is the length
+	 * of the array.
+	 *
+	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+	 * single struct i915_user_extension and num_cliprects is 0.
 	 */
 	__u64 cliprects_ptr;
 #define I915_EXEC_RING_MASK              (0x3f)
@@ -1181,7 +1191,16 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_FENCE_SUBMIT		(1 << 20)
 
-#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SUBMIT << 1))
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
+
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
 
 #define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \
-- 
cgit v1.2.3


From 13149e8bafc4657254831ba6c16ed8780aa64a06 Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Tue, 4 Aug 2020 11:59:54 +0300
Subject: drm/i915: add syncobj timeline support

Introduces a new parameters to execbuf so that we can specify syncobj
handles as well as timeline points.

v2: Reuse i915_user_extension_fn

v3: Check that the chained extension is only present once (Chris)

v4: Check that dma_fence_chain_find_seqno returns a non NULL fence (Lionel)

v5: Use BIT_ULL (Chris)

v6: Fix issue with already signaled timeline points,
    dma_fence_chain_find_seqno() setting fence to NULL (Chris)

v7: Report ENOENT with invalid syncobj handle (Lionel)

v8: Check for out of order timeline point insertion (Chris)

v9: After explanations on
    https://lists.freedesktop.org/archives/dri-devel/2019-August/229287.html
    drop the ordering check from v8 (Lionel)

v10: Set first extension enum item to 1 (Jason)

v11: Rebase

v12: Allow multiple extension nodes of timeline syncobj (Chris)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Co-authored-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> (v11)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20200804085954.350343-3-lionel.g.landwerlin@intel.com
Link: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2901
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 312 +++++++++++++++++++------
 drivers/gpu/drm/i915/i915_drv.c                |   3 +-
 drivers/gpu/drm/i915/i915_getparam.c           |   1 +
 include/uapi/drm/i915_drm.h                    |  38 ++-
 4 files changed, 279 insertions(+), 75 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 09d2f955b11e..02b1630f513e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -223,6 +223,13 @@ struct eb_vma_array {
  * the batchbuffer in trusted mode, otherwise the ioctl is rejected.
  */
 
+struct eb_fence {
+	struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
+	struct dma_fence *dma_fence;
+	u64 value;
+	struct dma_fence_chain *chain_fence;
+};
+
 struct i915_execbuffer {
 	struct drm_i915_private *i915; /** i915 backpointer */
 	struct drm_file *file; /** per-file lookup tables and limits */
@@ -283,12 +290,8 @@ struct i915_execbuffer {
 	struct hlist_head *buckets; /** ht for relocation handles */
 	struct eb_vma_array *array;
 
-	struct i915_eb_fence {
-		struct drm_syncobj *syncobj; /* Use with ptr_mask_bits() */
-	} *fences;
-	u32 n_fences;
-
-	u64 extension_flags; /** Available extensions parameters */
+	struct eb_fence *fences;
+	unsigned long num_fences;
 };
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
@@ -2210,77 +2213,222 @@ eb_pin_engine(struct i915_execbuffer *eb,
 }
 
 static void
-__free_fence_array(struct i915_eb_fence *fences, unsigned int n)
+__free_fence_array(struct eb_fence *fences, unsigned int n)
 {
-	while (n--)
+	while (n--) {
 		drm_syncobj_put(ptr_mask_bits(fences[n].syncobj, 2));
+		dma_fence_put(fences[n].dma_fence);
+		kfree(fences[n].chain_fence);
+	}
 	kvfree(fences);
 }
 
 static int
-get_fence_array(struct drm_i915_gem_execbuffer2 *args,
-		struct i915_execbuffer *eb)
+add_timeline_fence_array(struct i915_execbuffer *eb,
+			 const struct drm_i915_gem_execbuffer_ext_timeline_fences *timeline_fences)
 {
-	const unsigned long nfences = args->num_cliprects;
-	struct drm_i915_gem_exec_fence __user *user;
-	struct i915_eb_fence *fences;
-	unsigned long n;
-	int err;
+	struct drm_i915_gem_exec_fence __user *user_fences;
+	u64 __user *user_values;
+	struct eb_fence *f;
+	u64 nfences;
+	int err = 0;
 
-	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+	nfences = timeline_fences->fence_count;
+	if (!nfences)
 		return 0;
 
 	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
 	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
 	if (nfences > min_t(unsigned long,
-			    ULONG_MAX / sizeof(*user),
-			    SIZE_MAX / sizeof(*fences)))
+			    ULONG_MAX / sizeof(*user_fences),
+			    SIZE_MAX / sizeof(*f)) - eb->num_fences)
 		return -EINVAL;
 
-	user = u64_to_user_ptr(args->cliprects_ptr);
-	if (!access_ok(user, nfences * sizeof(*user)))
+	user_fences = u64_to_user_ptr(timeline_fences->handles_ptr);
+	if (!access_ok(user_fences, nfences * sizeof(*user_fences)))
+		return -EFAULT;
+
+	user_values = u64_to_user_ptr(timeline_fences->values_ptr);
+	if (!access_ok(user_values, nfences * sizeof(*user_values)))
 		return -EFAULT;
 
-	fences = kvmalloc_array(nfences, sizeof(*fences),
-				__GFP_NOWARN | GFP_KERNEL);
-	if (!fences)
+	f = krealloc(eb->fences,
+		     (eb->num_fences + nfences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
 		return -ENOMEM;
 
-	for (n = 0; n < nfences; n++) {
-		struct drm_i915_gem_exec_fence fence;
+	eb->fences = f;
+	f += eb->num_fences;
+
+	BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
+		     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
+
+	while (nfences--) {
+		struct drm_i915_gem_exec_fence user_fence;
 		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+		u64 point;
+
+		if (__copy_from_user(&user_fence,
+				     user_fences++,
+				     sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		if (__get_user(point, user_values++))
+			return -EFAULT;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
+		if (!syncobj) {
+			DRM_DEBUG("Invalid syncobj handle provided\n");
+			return -ENOENT;
+		}
+
+		fence = drm_syncobj_fence_get(syncobj);
 
-		if (__copy_from_user(&fence, user++, sizeof(fence))) {
-			err = -EFAULT;
-			goto err;
+		if (!fence && user_fence.flags &&
+		    !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle has no fence\n");
+			drm_syncobj_put(syncobj);
+			return -EINVAL;
 		}
 
-		if (fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS) {
-			err = -EINVAL;
-			goto err;
+		if (fence)
+			err = dma_fence_chain_find_seqno(&fence, point);
+
+		if (err && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			DRM_DEBUG("Syncobj handle missing requested point %llu\n", point);
+			drm_syncobj_put(syncobj);
+			return err;
+		}
+
+		/*
+		 * A point might have been signaled already and
+		 * garbage collected from the timeline. In this case
+		 * just ignore the point and carry on.
+		 */
+		if (!fence && !(user_fence.flags & I915_EXEC_FENCE_SIGNAL)) {
+			drm_syncobj_put(syncobj);
+			continue;
+		}
+
+		/*
+		 * For timeline syncobjs we need to preallocate chains for
+		 * later signaling.
+		 */
+		if (point != 0 && user_fence.flags & I915_EXEC_FENCE_SIGNAL) {
+			/*
+			 * Waiting and signaling the same point (when point !=
+			 * 0) would break the timeline.
+			 */
+			if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+				DRM_DEBUG("Trying to wait & signal the same timeline point.\n");
+				dma_fence_put(fence);
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
+
+			f->chain_fence =
+				kmalloc(sizeof(*f->chain_fence),
+					GFP_KERNEL);
+			if (!f->chain_fence) {
+				drm_syncobj_put(syncobj);
+				dma_fence_put(fence);
+				return -ENOMEM;
+			}
+		} else {
+			f->chain_fence = NULL;
 		}
 
-		syncobj = drm_syncobj_find(eb->file, fence.handle);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = point;
+		f++;
+		eb->num_fences++;
+	}
+
+	return 0;
+}
+
+static int add_fence_array(struct i915_execbuffer *eb)
+{
+	struct drm_i915_gem_execbuffer2 *args = eb->args;
+	struct drm_i915_gem_exec_fence __user *user;
+	unsigned long num_fences = args->num_cliprects;
+	struct eb_fence *f;
+
+	if (!(args->flags & I915_EXEC_FENCE_ARRAY))
+		return 0;
+
+	if (!num_fences)
+		return 0;
+
+	/* Check multiplication overflow for access_ok() and kvmalloc_array() */
+	BUILD_BUG_ON(sizeof(size_t) > sizeof(unsigned long));
+	if (num_fences > min_t(unsigned long,
+			       ULONG_MAX / sizeof(*user),
+			       SIZE_MAX / sizeof(*f) - eb->num_fences))
+		return -EINVAL;
+
+	user = u64_to_user_ptr(args->cliprects_ptr);
+	if (!access_ok(user, num_fences * sizeof(*user)))
+		return -EFAULT;
+
+	f = krealloc(eb->fences,
+		     (eb->num_fences + num_fences) * sizeof(*f),
+		     __GFP_NOWARN | GFP_KERNEL);
+	if (!f)
+		return -ENOMEM;
+
+	eb->fences = f;
+	f += eb->num_fences;
+	while (num_fences--) {
+		struct drm_i915_gem_exec_fence user_fence;
+		struct drm_syncobj *syncobj;
+		struct dma_fence *fence = NULL;
+
+		if (__copy_from_user(&user_fence, user++, sizeof(user_fence)))
+			return -EFAULT;
+
+		if (user_fence.flags & __I915_EXEC_FENCE_UNKNOWN_FLAGS)
+			return -EINVAL;
+
+		syncobj = drm_syncobj_find(eb->file, user_fence.handle);
 		if (!syncobj) {
 			DRM_DEBUG("Invalid syncobj handle provided\n");
-			err = -ENOENT;
-			goto err;
+			return -ENOENT;
+		}
+
+		if (user_fence.flags & I915_EXEC_FENCE_WAIT) {
+			fence = drm_syncobj_fence_get(syncobj);
+			if (!fence) {
+				DRM_DEBUG("Syncobj handle has no fence\n");
+				drm_syncobj_put(syncobj);
+				return -EINVAL;
+			}
 		}
 
 		BUILD_BUG_ON(~(ARCH_KMALLOC_MINALIGN - 1) &
 			     ~__I915_EXEC_FENCE_UNKNOWN_FLAGS);
 
-		fences[n].syncobj = ptr_pack_bits(syncobj, fence.flags, 2);
+		f->syncobj = ptr_pack_bits(syncobj, user_fence.flags, 2);
+		f->dma_fence = fence;
+		f->value = 0;
+		f->chain_fence = NULL;
+		f++;
+		eb->num_fences++;
 	}
 
-	eb->fences = fences;
-	eb->n_fences = nfences;
-
 	return 0;
+}
 
-err:
-	__free_fence_array(fences, n);
-	return err;
+static void put_fence_array(struct eb_fence *fences, int num_fences)
+{
+	if (fences)
+		__free_fence_array(fences, num_fences);
 }
 
 static int
@@ -2289,21 +2437,17 @@ await_fence_array(struct i915_execbuffer *eb)
 	unsigned int n;
 	int err;
 
-	for (n = 0; n < eb->n_fences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
-		struct dma_fence *fence;
 		unsigned int flags;
 
 		syncobj = ptr_unpack_bits(eb->fences[n].syncobj, &flags, 2);
-		if (!(flags & I915_EXEC_FENCE_WAIT))
-			continue;
 
-		fence = drm_syncobj_fence_get(syncobj);
-		if (!fence)
-			return -EINVAL;
+		if (!eb->fences[n].dma_fence)
+			continue;
 
-		err = i915_request_await_dma_fence(eb->request, fence);
-		dma_fence_put(fence);
+		err = i915_request_await_dma_fence(eb->request,
+						   eb->fences[n].dma_fence);
 		if (err < 0)
 			return err;
 	}
@@ -2311,13 +2455,12 @@ await_fence_array(struct i915_execbuffer *eb)
 	return 0;
 }
 
-static void
-signal_fence_array(struct i915_execbuffer *eb)
+static void signal_fence_array(const struct i915_execbuffer *eb)
 {
 	struct dma_fence * const fence = &eb->request->fence;
 	unsigned int n;
 
-	for (n = 0; n < eb->n_fences; n++) {
+	for (n = 0; n < eb->num_fences; n++) {
 		struct drm_syncobj *syncobj;
 		unsigned int flags;
 
@@ -2325,10 +2468,34 @@ signal_fence_array(struct i915_execbuffer *eb)
 		if (!(flags & I915_EXEC_FENCE_SIGNAL))
 			continue;
 
-		drm_syncobj_replace_fence(syncobj, fence);
+		if (eb->fences[n].chain_fence) {
+			drm_syncobj_add_point(syncobj,
+					      eb->fences[n].chain_fence,
+					      fence,
+					      eb->fences[n].value);
+			/*
+			 * The chain's ownership is transferred to the
+			 * timeline.
+			 */
+			eb->fences[n].chain_fence = NULL;
+		} else {
+			drm_syncobj_replace_fence(syncobj, fence);
+		}
 	}
 }
 
+static int
+parse_timeline_fences(struct i915_user_extension __user *ext, void *data)
+{
+	struct i915_execbuffer *eb = data;
+	struct drm_i915_gem_execbuffer_ext_timeline_fences timeline_fences;
+
+	if (copy_from_user(&timeline_fences, ext, sizeof(timeline_fences)))
+		return -EFAULT;
+
+	return add_timeline_fence_array(eb, &timeline_fences);
+}
+
 static void retire_requests(struct intel_timeline *tl, struct i915_request *end)
 {
 	struct i915_request *rq, *rn;
@@ -2371,14 +2538,13 @@ static void eb_request_add(struct i915_execbuffer *eb)
 }
 
 static const i915_user_extension_fn execbuf_extensions[] = {
+	[DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES] = parse_timeline_fences,
 };
 
 static int
 parse_execbuf2_extensions(struct drm_i915_gem_execbuffer2 *args,
 			  struct i915_execbuffer *eb)
 {
-	eb->extension_flags = 0;
-
 	if (!(args->flags & I915_EXEC_USE_EXTENSIONS))
 		return 0;
 
@@ -2432,7 +2598,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	eb.trampoline = NULL;
 
 	eb.fences = NULL;
-	eb.n_fences = 0;
+	eb.num_fences = 0;
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
@@ -2451,14 +2617,24 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	if (args->flags & I915_EXEC_IS_PINNED)
 		eb.batch_flags |= I915_DISPATCH_PINNED;
 
+	err = parse_execbuf2_extensions(args, &eb);
+	if (err)
+		goto err_ext;
+
+	err = add_fence_array(&eb);
+	if (err)
+		goto err_ext;
+
 #define IN_FENCES (I915_EXEC_FENCE_IN | I915_EXEC_FENCE_SUBMIT)
 	if (args->flags & IN_FENCES) {
 		if ((args->flags & IN_FENCES) == IN_FENCES)
 			return -EINVAL;
 
 		in_fence = sync_file_get_fence(lower_32_bits(args->rsvd2));
-		if (!in_fence)
-			return -EINVAL;
+		if (!in_fence) {
+			err = -EINVAL;
+			goto err_ext;
+		}
 	}
 #undef IN_FENCES
 
@@ -2470,17 +2646,9 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		}
 	}
 
-	err = parse_execbuf2_extensions(args, &eb);
-	if (err)
-		goto err_out_fence;
-
-	err = get_fence_array(args, &eb);
-	if (err)
-		goto err_arr_fence;
-
 	err = eb_create(&eb);
 	if (err)
-		goto err_arr_fence;
+		goto err_out_fence;
 
 	GEM_BUG_ON(!eb.lut_size);
 
@@ -2576,7 +2744,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 			goto err_request;
 	}
 
-	if (eb.n_fences) {
+	if (eb.fences) {
 		err = await_fence_array(&eb);
 		if (err)
 			goto err_request;
@@ -2608,7 +2776,7 @@ err_request:
 	i915_request_get(eb.request);
 	eb_request_add(&eb);
 
-	if (eb.n_fences)
+	if (eb.fences)
 		signal_fence_array(&eb);
 
 	if (out_fence) {
@@ -2637,13 +2805,13 @@ err_context:
 	i915_gem_context_put(eb.gem_context);
 err_destroy:
 	eb_destroy(&eb);
-err_arr_fence:
-	__free_fence_array(eb.fences, eb.n_fences);
 err_out_fence:
 	if (out_fence_fd != -1)
 		put_unused_fd(out_fence_fd);
 err_in_fence:
 	dma_fence_put(in_fence);
+err_ext:
+	put_fence_array(eb.fences, eb.num_fences);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 5fd5af4bc855..2d10f6a2c042 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1846,7 +1846,8 @@ static struct drm_driver driver = {
 	 */
 	.driver_features =
 	    DRIVER_GEM |
-	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ,
+	    DRIVER_RENDER | DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_SYNCOBJ |
+	    DRIVER_SYNCOBJ_TIMELINE,
 	.release = i915_driver_release,
 	.open = i915_driver_open,
 	.lastclose = i915_driver_lastclose,
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index 421613219ae9..f96032c60a12 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -132,6 +132,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 	case I915_PARAM_HAS_EXEC_BATCH_FIRST:
 	case I915_PARAM_HAS_EXEC_FENCE_ARRAY:
 	case I915_PARAM_HAS_EXEC_SUBMIT_FENCE:
+	case I915_PARAM_HAS_EXEC_TIMELINE_FENCES:
 		/* For the time being all of these are always true;
 		 * if some supported hardware does not have one of these
 		 * features this value needs to be provided from
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index dcada8c3a693..fa1f3d62f9a6 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -619,6 +619,12 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_PERF_REVISION	54
 
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
 /* Must be kept compact -- no holes and well documented */
 
 typedef struct drm_i915_getparam {
@@ -1046,8 +1052,36 @@ struct drm_i915_gem_exec_fence {
 	__u32 flags;
 };
 
-enum drm_i915_gem_execbuffer_ext {
-	DRM_I915_GEM_EXECBUFFER_EXT_MAX /* non-ABI */
+/**
+ * See drm_i915_gem_execbuffer_ext_timeline_fences.
+ */
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+
+/**
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+	struct i915_user_extension base;
+
+	/**
+	 * Number of element in the handles_ptr & value_ptr arrays.
+	 */
+	__u64 fence_count;
+
+	/**
+	 * Pointer to an array of struct drm_i915_gem_exec_fence of length
+	 * fence_count.
+	 */
+	__u64 handles_ptr;
+
+	/**
+	 * Pointer to an array of u64 values of length fence_count. Values
+	 * must be 0 for a binary drm_syncobj. A Value of 0 for a timeline
+	 * drm_syncobj is invalid as it turns a drm_syncobj into a binary one.
+	 */
+	__u64 values_ptr;
 };
 
 struct drm_i915_gem_execbuffer2 {
-- 
cgit v1.2.3


From 004a01241c5a0d375266ebf1c72f208de99294e9 Mon Sep 17 00:00:00 2001
From: Andrew Jones <drjones@redhat.com>
Date: Tue, 4 Aug 2020 19:06:04 +0200
Subject: arm64/x86: KVM: Introduce steal-time cap

arm64 requires a vcpu fd (KVM_HAS_DEVICE_ATTR vcpu ioctl) to probe
support for steal-time. However this is unnecessary, as only a KVM
fd is required, and it complicates userspace (userspace may prefer
delaying vcpu creation until after feature probing). Introduce a cap
that can be checked instead. While x86 can already probe steal-time
support with a kvm fd (KVM_GET_SUPPORTED_CPUID), we add the cap there
too for consistency.

Signed-off-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Steven Price <steven.price@arm.com>
Link: https://lore.kernel.org/r/20200804170604.42662-7-drjones@redhat.com
---
 Documentation/virt/kvm/api.rst    | 13 +++++++++++++
 arch/arm64/include/asm/kvm_host.h |  1 +
 arch/arm64/kvm/arm.c              |  3 +++
 arch/arm64/kvm/pvtime.c           |  2 +-
 arch/x86/kvm/x86.c                |  3 +++
 include/uapi/linux/kvm.h          |  1 +
 6 files changed, 22 insertions(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 49af23d2b462..d2b733dc7892 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6160,3 +6160,16 @@ KVM can therefore start protected VMs.
 This capability governs the KVM_S390_PV_COMMAND ioctl and the
 KVM_MP_STATE_LOAD MP_STATE. KVM_SET_MP_STATE can fail for protected
 guests when the state change is invalid.
+
+8.24 KVM_CAP_STEAL_TIME
+-----------------------
+
+:Architectures: arm64, x86
+
+This capability indicates that KVM supports steal time accounting.
+When steal time accounting is supported it may be enabled with
+architecture-specific interfaces.  This capability and the architecture-
+specific interfaces must be consistent, i.e. if one says the feature
+is supported, than the other should as well and vice versa.  For arm64
+see Documentation/virt/kvm/devices/vcpu.rst "KVM_ARM_VCPU_PVTIME_CTRL".
+For x86 see Documentation/virt/kvm/msr.rst "MSR_KVM_STEAL_TIME".
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index dd9c3b25aa1e..af4989a25bb7 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -543,6 +543,7 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
 gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
 void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
 
+bool kvm_arm_pvtime_supported(void);
 int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu,
 			    struct kvm_device_attr *attr);
 int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 691d21e4c717..57876b0b870b 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -206,6 +206,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		 */
 		r = 1;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = kvm_arm_pvtime_supported();
+		break;
 	default:
 		r = kvm_arch_vm_ioctl_check_extension(kvm, ext);
 		break;
diff --git a/arch/arm64/kvm/pvtime.c b/arch/arm64/kvm/pvtime.c
index 75234321d896..920ac43077ad 100644
--- a/arch/arm64/kvm/pvtime.c
+++ b/arch/arm64/kvm/pvtime.c
@@ -71,7 +71,7 @@ gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
 	return base;
 }
 
-static bool kvm_arm_pvtime_supported(void)
+bool kvm_arm_pvtime_supported(void)
 {
 	return !!sched_info_on();
 }
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 599d73206299..c44d3a73b8eb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3581,6 +3581,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_SMALLER_MAXPHYADDR:
 		r = (int) allow_smaller_maxphyaddr;
 		break;
+	case KVM_CAP_STEAL_TIME:
+		r = sched_info_on();
+		break;
 	default:
 		break;
 	}
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f6d86033c4fa..3d8023474f2a 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1035,6 +1035,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_LAST_CPU 184
 #define KVM_CAP_SMALLER_MAXPHYADDR 185
 #define KVM_CAP_S390_DIAG318 186
+#define KVM_CAP_STEAL_TIME 187
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From da9125df854ea48a6240c66e8a67be06e2c12c03 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 20 Aug 2020 14:12:55 +0200
Subject: netfilter: nf_tables: incorrect enum nft_list_attributes definition

This should be NFTA_LIST_UNSPEC instead of NFTA_LIST_UNPEC, all other
similar attribute definitions are postfixed with _UNSPEC.

Fixes: 96518518cc41 ("netfilter: add nftables")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 42f351c1f5c5..2b8e12f7a4a6 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -133,7 +133,7 @@ enum nf_tables_msg_types {
  * @NFTA_LIST_ELEM: list element (NLA_NESTED)
  */
 enum nft_list_attributes {
-	NFTA_LIST_UNPEC,
+	NFTA_LIST_UNSPEC,
 	NFTA_LIST_ELEM,
 	__NFTA_LIST_MAX
 };
-- 
cgit v1.2.3


From b16fc097bc283184cde40e5b30d15705e1590410 Mon Sep 17 00:00:00 2001
From: Tobias Klauser <tklauser@distanz.ch>
Date: Fri, 21 Aug 2020 15:36:42 +0200
Subject: bpf: Fix two typos in uapi/linux/bpf.h

Also remove trailing whitespaces in bpf_skb_get_tunnel_key example code.

Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200821133642.18870-1-tklauser@distanz.ch
---
 include/uapi/linux/bpf.h       | 10 +++++-----
 tools/include/uapi/linux/bpf.h | 10 +++++-----
 2 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0480f893facd..b6238b2209b7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -767,7 +767,7 @@ union bpf_attr {
  *
  * 		Also, note that **bpf_trace_printk**\ () is slow, and should
  * 		only be used for debugging purposes. For this reason, a notice
- * 		bloc (spanning several lines) is printed to kernel logs and
+ * 		block (spanning several lines) is printed to kernel logs and
  * 		states that the helper should not be used "for production use"
  * 		the first time this helper is used (or more precisely, when
  * 		**trace_printk**\ () buffers are allocated). For passing values
@@ -1033,14 +1033,14 @@ union bpf_attr {
  *
  * 			int ret;
  * 			struct bpf_tunnel_key key = {};
- * 			
+ *
  * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
  * 			if (ret < 0)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			if (key.remote_ipv4 != 0x0a000001)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			return TC_ACT_OK;		// accept packet
  *
  * 		This interface can also be used with all encapsulation devices
@@ -1147,7 +1147,7 @@ union bpf_attr {
  * 	Description
  * 		Retrieve the realm or the route, that is to say the
  * 		**tclassid** field of the destination for the *skb*. The
- * 		indentifier retrieved is a user-provided tag, similar to the
+ * 		identifier retrieved is a user-provided tag, similar to the
  * 		one used with the net_cls cgroup (see description for
  * 		**bpf_get_cgroup_classid**\ () helper), but here this tag is
  * 		held by a route (a destination entry), not by a task.
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0480f893facd..b6238b2209b7 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -767,7 +767,7 @@ union bpf_attr {
  *
  * 		Also, note that **bpf_trace_printk**\ () is slow, and should
  * 		only be used for debugging purposes. For this reason, a notice
- * 		bloc (spanning several lines) is printed to kernel logs and
+ * 		block (spanning several lines) is printed to kernel logs and
  * 		states that the helper should not be used "for production use"
  * 		the first time this helper is used (or more precisely, when
  * 		**trace_printk**\ () buffers are allocated). For passing values
@@ -1033,14 +1033,14 @@ union bpf_attr {
  *
  * 			int ret;
  * 			struct bpf_tunnel_key key = {};
- * 			
+ *
  * 			ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
  * 			if (ret < 0)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			if (key.remote_ipv4 != 0x0a000001)
  * 				return TC_ACT_SHOT;	// drop packet
- * 			
+ *
  * 			return TC_ACT_OK;		// accept packet
  *
  * 		This interface can also be used with all encapsulation devices
@@ -1147,7 +1147,7 @@ union bpf_attr {
  * 	Description
  * 		Retrieve the realm or the route, that is to say the
  * 		**tclassid** field of the destination for the *skb*. The
- * 		indentifier retrieved is a user-provided tag, similar to the
+ * 		identifier retrieved is a user-provided tag, similar to the
  * 		one used with the net_cls cgroup (see description for
  * 		**bpf_get_cgroup_classid**\ () helper), but here this tag is
  * 		held by a route (a destination entry), not by a task.
-- 
cgit v1.2.3


From 645f08975f49441b3e753d8dc5b740cbcb226594 Mon Sep 17 00:00:00 2001
From: Miaohe Lin <linmiaohe@huawei.com>
Date: Thu, 27 Aug 2020 07:27:49 -0400
Subject: net: Fix some comments

Fix some comments, including wrong function name, duplicated word and so
on.

Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h  | 4 ++--
 include/uapi/linux/in.h | 2 +-
 net/core/sock.c         | 2 +-
 net/ipv4/raw.c          | 2 +-
 net/l3mdev/l3mdev.c     | 2 +-
 net/socket.c            | 4 ++--
 6 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/uapi')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index e8bca74857a3..8d9ab50b08c9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -71,7 +71,7 @@
  *	NETIF_F_IPV6_CSUM - Driver (device) is only able to checksum plain
  *			  TCP or UDP packets over IPv6. These are specifically
  *			  unencapsulated packets of the form IPv6|TCP or
- *			  IPv4|UDP where the Next Header field in the IPv6
+ *			  IPv6|UDP where the Next Header field in the IPv6
  *			  header is either TCP or UDP. IPv6 extension headers
  *			  are not supported with this feature. This feature
  *			  cannot be set in features for a device with
@@ -2667,7 +2667,7 @@ static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
  *
  * Using max(32, L1_CACHE_BYTES) makes sense (especially with RPS)
  * to reduce average number of cache lines per packet.
- * get_rps_cpus() for example only access one 64 bytes aligned block :
+ * get_rps_cpu() for example only access one 64 bytes aligned block :
  * NET_IP_ALIGN(2) + ethernet_header(14) + IP_header(20/40) + ports(8)
  */
 #ifndef NET_SKB_PAD
diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h
index 3d0d8231dc19..7d6687618d80 100644
--- a/include/uapi/linux/in.h
+++ b/include/uapi/linux/in.h
@@ -135,7 +135,7 @@ struct in_addr {
  * this socket to prevent accepting spoofed ones.
  */
 #define IP_PMTUDISC_INTERFACE		4
-/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+/* weaker version of IP_PMTUDISC_INTERFACE, which allows packets to get
  * fragmented if they exeed the interface mtu
  */
 #define IP_PMTUDISC_OMIT		5
diff --git a/net/core/sock.c b/net/core/sock.c
index e4f40b175acb..8eb2c924805a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3254,7 +3254,7 @@ void sk_common_release(struct sock *sk)
 		sk->sk_prot->destroy(sk);
 
 	/*
-	 * Observation: when sock_common_release is called, processes have
+	 * Observation: when sk_common_release is called, processes have
 	 * no access to socket. But net still has.
 	 * Step one, detach it from networking:
 	 *
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6fd4330287c2..407956be7deb 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -610,7 +610,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	} else if (!ipc.oif) {
 		ipc.oif = inet->uc_index;
 	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
-		/* oif is set, packet is to local broadcast and
+		/* oif is set, packet is to local broadcast
 		 * and uc_index is set. oif is most likely set
 		 * by sk_bound_dev_if. If uc_index != oif check if the
 		 * oif is an L3 master and uc_index is an L3 slave.
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index e71ca5aec684..864326f150e2 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -154,7 +154,7 @@ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
 EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu);
 
 /**
- *	l3mdev_fib_table - get FIB table id associated with an L3
+ *	l3mdev_fib_table_rcu - get FIB table id associated with an L3
  *                             master interface
  *	@dev: targeted interface
  */
diff --git a/net/socket.c b/net/socket.c
index dbbe8ea7d395..0c0144604f81 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -3610,7 +3610,7 @@ int kernel_getsockname(struct socket *sock, struct sockaddr *addr)
 EXPORT_SYMBOL(kernel_getsockname);
 
 /**
- *	kernel_peername - get the address which the socket is connected (kernel space)
+ *	kernel_getpeername - get the address which the socket is connected (kernel space)
  *	@sock: socket
  *	@addr: address holder
  *
@@ -3671,7 +3671,7 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset,
 EXPORT_SYMBOL(kernel_sendpage_locked);
 
 /**
- *	kernel_shutdown - shut down part of a full-duplex connection (kernel space)
+ *	kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space)
  *	@sock: socket
  *	@how: connection part
  *
-- 
cgit v1.2.3


From 55977744f9d862512a524fea93fc5226b09e76a9 Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Fri, 28 Aug 2020 18:50:42 -0400
Subject: drm/amdkfd: Add GPU reset SMI event

Add support for reporting GPU reset events through SMI. KFD
would report both pre and post GPU reset events.

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/amdkfd/kfd_device.c     |  4 ++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h       |  2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 34 +++++++++++++++++++++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  1 +
 include/uapi/linux/kfd_ioctl.h              |  2 ++
 5 files changed, 41 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index e1cd6599529f..0e71a0543f98 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -812,6 +812,8 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 	if (!kfd->init_complete)
 		return 0;
 
+	kfd_smi_event_update_gpu_reset(kfd, false);
+
 	kfd->dqm->ops.pre_reset(kfd->dqm);
 
 	kgd2kfd_suspend(kfd, false);
@@ -840,6 +842,8 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 
 	atomic_set(&kfd->sram_ecc_flag, 0);
 
+	kfd_smi_event_update_gpu_reset(kfd, true);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index f14beb93acb4..023629f28495 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -312,6 +312,8 @@ struct kfd_dev {
 	/* Clients watching SMI events */
 	struct list_head smi_clients;
 	spinlock_t smi_lock;
+
+	uint32_t reset_seq_num;
 };
 
 enum kfd_mempool {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 4d4b6e3ab697..17d1736367ea 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -174,6 +174,36 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event,
 	rcu_read_unlock();
 }
 
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset)
+{
+	/*
+	 * GpuReset msg = Reset seq number (incremented for
+	 * every reset message sent before GPU reset).
+	 * 1 byte event + 1 byte space + 8 bytes seq num +
+	 * 1 byte \n + 1 byte \0 = 12
+	 */
+	char fifo_in[12];
+	int len;
+	unsigned int event;
+
+	if (list_empty(&dev->smi_clients))
+		return;
+
+	memset(fifo_in, 0x0, sizeof(fifo_in));
+
+	if (post_reset) {
+		event = KFD_SMI_EVENT_GPU_POST_RESET;
+	} else {
+		event = KFD_SMI_EVENT_GPU_PRE_RESET;
+		++(dev->reset_seq_num);
+	}
+
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x\n", event,
+						dev->reset_seq_num);
+
+	add_event_to_kfifo(dev, event, fifo_in, len);
+}
+
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 					     uint32_t throttle_bitmask)
 {
@@ -191,7 +221,7 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 	if (list_empty(&dev->smi_clients))
 		return;
 
-	len = snprintf(fifo_in, 29, "%x %x:%llx\n",
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%llx\n",
 		       KFD_SMI_EVENT_THERMAL_THROTTLE, throttle_bitmask,
 		       atomic64_read(&adev->smu.throttle_int_counter));
 
@@ -218,7 +248,7 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid)
 	if (!task_info.pid)
 		return;
 
-	len = snprintf(fifo_in, 29, "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
+	len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT,
 		task_info.pid, task_info.task_name);
 
 	add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index 15537b2cccb5..b9b0438202e2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -27,5 +27,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid);
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 					     uint32_t throttle_bitmask);
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev, bool post_reset);
 
 #endif
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index cb1f963a84e0..8b7368bfbd84 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -453,6 +453,8 @@ enum kfd_smi_event {
         KFD_SMI_EVENT_NONE = 0, /* not used */
         KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
         KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+	KFD_SMI_EVENT_GPU_PRE_RESET = 3,
+	KFD_SMI_EVENT_GPU_POST_RESET = 4,
 };
 
 #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
-- 
cgit v1.2.3


From 5dc1a0bcb758c343b873e8330ee986417f5a1727 Mon Sep 17 00:00:00 2001
From: Mukul Joshi <mukul.joshi@amd.com>
Date: Fri, 28 Aug 2020 19:53:08 -0400
Subject: include/uapi/linux: Fix indentation in kfd_smi_event enum

Replace spaces with Tabs to fix indentation in kfd_smi_event
enum.

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>
---
 include/uapi/linux/kfd_ioctl.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/uapi')

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 8b7368bfbd84..695b606da4b1 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -450,9 +450,9 @@ struct kfd_ioctl_import_dmabuf_args {
  * KFD SMI(System Management Interface) events
  */
 enum kfd_smi_event {
-        KFD_SMI_EVENT_NONE = 0, /* not used */
-        KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
-        KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+	KFD_SMI_EVENT_NONE = 0, /* not used */
+	KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
+	KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
 	KFD_SMI_EVENT_GPU_PRE_RESET = 3,
 	KFD_SMI_EVENT_GPU_POST_RESET = 4,
 };
-- 
cgit v1.2.3


From 15e9e35cd1dec2bc138464de6bf8ef828df19235 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Thu, 10 Sep 2020 18:33:51 +0800
Subject: KVM: MIPS: Change the definition of kvm type

MIPS defines two kvm types:

 #define KVM_VM_MIPS_TE          0
 #define KVM_VM_MIPS_VZ          1

In Documentation/virt/kvm/api.rst it is said that "You probably want to
use 0 as machine type", which implies that type 0 be the "automatic" or
"default" type. And, in user-space libvirt use the null-machine (with
type 0) to detect the kvm capability, which returns "KVM not supported"
on a VZ platform.

I try to fix it in QEMU but it is ugly:
https://lists.nongnu.org/archive/html/qemu-devel/2020-08/msg05629.html

And Thomas Huth suggests me to change the definition of kvm type:
https://lists.nongnu.org/archive/html/qemu-devel/2020-09/msg03281.html

So I define like this:

 #define KVM_VM_MIPS_AUTO        0
 #define KVM_VM_MIPS_VZ          1
 #define KVM_VM_MIPS_TE          2

Since VZ and TE cannot co-exists, using type 0 on a TE platform will
still return success (so old user-space tools have no problems on new
kernels); the advantage is that using type 0 on a VZ platform will not
return failure. So, the only problem is "new user-space tools use type
2 on old kernels", but if we treat this as a kernel bug, we can backport
this patch to old stable kernels.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Message-Id: <1599734031-28746-1-git-send-email-chenhc@lemote.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/mips/kvm/mips.c     | 2 ++
 include/uapi/linux/kvm.h | 5 +++--
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/uapi')

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7de85d2253ff..0c50ac444222 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -137,6 +137,8 @@ extern void kvm_init_loongson_ipi(struct kvm *kvm);
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 {
 	switch (type) {
+	case KVM_VM_MIPS_AUTO:
+		break;
 #ifdef CONFIG_KVM_MIPS_VZ
 	case KVM_VM_MIPS_VZ:
 #else
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 3d8023474f2a..7d8eced6f459 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -790,9 +790,10 @@ struct kvm_ppc_resize_hpt {
 #define KVM_VM_PPC_HV 1
 #define KVM_VM_PPC_PR 2
 
-/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */
-#define KVM_VM_MIPS_TE		0
+/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */
+#define KVM_VM_MIPS_AUTO	0
 #define KVM_VM_MIPS_VZ		1
+#define KVM_VM_MIPS_TE		2
 
 #define KVM_S390_SIE_PAGE_OFFSET 1
 
-- 
cgit v1.2.3