Merge tag 'amd-drm-next-5.14-2021-05-19' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-5.14-2021-05-19:

amdgpu:
- Aldebaran updates
- More LTTPR display work
- Vangogh updates
- SDMA 5.x GCR fixes
- RAS fixes
- PCIe ASPM support
- Modifier fixes
- Enable TMZ on Renoir
- Buffer object code cleanup
- Display overlay fixes
- Initial support for multiple eDP panels
- Initial SR-IOV support for Aldebaran
- DP link training refactor
- Misc code cleanups and bug fixes
- SMU regression fixes for variable sized arrays
- MAINTAINERS fixes for amdgpu

amdkfd:
- Initial SR-IOV support for Aldebaran
- Topology fixes
- Initial HMM SVM support
- Misc code cleanups and bug fixes

radeon:
- Misc code cleanups and bug fixes
- SMU regression fixes for variable sized arrays
- Flickering fix for Oland with multiple 4K displays

UAPI:
- amdgpu: Drop AMDGPU_GEM_CREATE_SHADOW flag.
  This was always a kernel internal flag and userspace use of it has always been blocked.
  It's no longer needed so remove it.
- amdkgd: HMM SVM support
  Overview: https://patchwork.freedesktop.org/series/85562/
  Porposed userspace: https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/tree/fxkamd/hmm-wip

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210520031258.231896-1-alexander.deucher@amd.com

2 files changed, 169 insertions, 4 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 728566542f8a..2063a1c10f79 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -116,8 +116,6 @@ extern "C" {
 #define AMDGPU_GEM_CREATE_CPU_GTT_USWC		(1 << 2)
 /* Flag that the memory should be in VRAM and cleared */
 #define AMDGPU_GEM_CREATE_VRAM_CLEARED		(1 << 3)
-/* Flag that create shadow bo(GTT) while allocating vram bo */
-#define AMDGPU_GEM_CREATE_SHADOW		(1 << 4)
 /* Flag that allocating the BO should use linear VRAM */
 #define AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS	(1 << 5)
 /* Flag that BO is always valid in this VM */
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index bf5e7d7846dd..3cb5b5dd9f77 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -30,9 +30,10 @@
  * - 1.1 - initial version
  * - 1.3 - Add SMI events support
  * - 1.4 - Indicate new SRAM EDC bit in device properties
+ * - 1.5 - Add SVM API
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 4
+#define KFD_IOCTL_MINOR_VERSION 5
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -473,6 +474,167 @@ enum kfd_mmio_remap {
 	KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL = 4,
 };
 
+/* Guarantee host access to memory */
+#define KFD_IOCTL_SVM_FLAG_HOST_ACCESS 0x00000001
+/* Fine grained coherency between all devices with access */
+#define KFD_IOCTL_SVM_FLAG_COHERENT    0x00000002
+/* Use any GPU in same hive as preferred device */
+#define KFD_IOCTL_SVM_FLAG_HIVE_LOCAL  0x00000004
+/* GPUs only read, allows replication */
+#define KFD_IOCTL_SVM_FLAG_GPU_RO      0x00000008
+/* Allow execution on GPU */
+#define KFD_IOCTL_SVM_FLAG_GPU_EXEC    0x00000010
+/* GPUs mostly read, may allow similar optimizations as RO, but writes fault */
+#define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY     0x00000020
+
+/**
+ * kfd_ioctl_svm_op - SVM ioctl operations
+ *
+ * @KFD_IOCTL_SVM_OP_SET_ATTR: Modify one or more attributes
+ * @KFD_IOCTL_SVM_OP_GET_ATTR: Query one or more attributes
+ */
+enum kfd_ioctl_svm_op {
+	KFD_IOCTL_SVM_OP_SET_ATTR,
+	KFD_IOCTL_SVM_OP_GET_ATTR
+};
+
+/** kfd_ioctl_svm_location - Enum for preferred and prefetch locations
+ *
+ * GPU IDs are used to specify GPUs as preferred and prefetch locations.
+ * Below definitions are used for system memory or for leaving the preferred
+ * location unspecified.
+ */
+enum kfd_ioctl_svm_location {
+	KFD_IOCTL_SVM_LOCATION_SYSMEM = 0,
+	KFD_IOCTL_SVM_LOCATION_UNDEFINED = 0xffffffff
+};
+
+/**
+ * kfd_ioctl_svm_attr_type - SVM attribute types
+ *
+ * @KFD_IOCTL_SVM_ATTR_PREFERRED_LOC: gpuid of the preferred location, 0 for
+ *                                    system memory
+ * @KFD_IOCTL_SVM_ATTR_PREFETCH_LOC: gpuid of the prefetch location, 0 for
+ *                                   system memory. Setting this triggers an
+ *                                   immediate prefetch (migration).
+ * @KFD_IOCTL_SVM_ATTR_ACCESS:
+ * @KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE:
+ * @KFD_IOCTL_SVM_ATTR_NO_ACCESS: specify memory access for the gpuid given
+ *                                by the attribute value
+ * @KFD_IOCTL_SVM_ATTR_SET_FLAGS: bitmask of flags to set (see
+ *                                KFD_IOCTL_SVM_FLAG_...)
+ * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS: bitmask of flags to clear
+ * @KFD_IOCTL_SVM_ATTR_GRANULARITY: migration granularity
+ *                                  (log2 num pages)
+ */
+enum kfd_ioctl_svm_attr_type {
+	KFD_IOCTL_SVM_ATTR_PREFERRED_LOC,
+	KFD_IOCTL_SVM_ATTR_PREFETCH_LOC,
+	KFD_IOCTL_SVM_ATTR_ACCESS,
+	KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE,
+	KFD_IOCTL_SVM_ATTR_NO_ACCESS,
+	KFD_IOCTL_SVM_ATTR_SET_FLAGS,
+	KFD_IOCTL_SVM_ATTR_CLR_FLAGS,
+	KFD_IOCTL_SVM_ATTR_GRANULARITY
+};
+
+/**
+ * kfd_ioctl_svm_attribute - Attributes as pairs of type and value
+ *
+ * The meaning of the @value depends on the attribute type.
+ *
+ * @type: attribute type (see enum @kfd_ioctl_svm_attr_type)
+ * @value: attribute value
+ */
+struct kfd_ioctl_svm_attribute {
+	__u32 type;
+	__u32 value;
+};
+
+/**
+ * kfd_ioctl_svm_args - Arguments for SVM ioctl
+ *
+ * @op specifies the operation to perform (see enum
+ * @kfd_ioctl_svm_op).  @start_addr and @size are common for all
+ * operations.
+ *
+ * A variable number of attributes can be given in @attrs.
+ * @nattr specifies the number of attributes. New attributes can be
+ * added in the future without breaking the ABI. If unknown attributes
+ * are given, the function returns -EINVAL.
+ *
+ * @KFD_IOCTL_SVM_OP_SET_ATTR sets attributes for a virtual address
+ * range. It may overlap existing virtual address ranges. If it does,
+ * the existing ranges will be split such that the attribute changes
+ * only apply to the specified address range.
+ *
+ * @KFD_IOCTL_SVM_OP_GET_ATTR returns the intersection of attributes
+ * over all memory in the given range and returns the result as the
+ * attribute value. If different pages have different preferred or
+ * prefetch locations, 0xffffffff will be returned for
+ * @KFD_IOCTL_SVM_ATTR_PREFERRED_LOC or
+ * @KFD_IOCTL_SVM_ATTR_PREFETCH_LOC resepctively. For
+ * @KFD_IOCTL_SVM_ATTR_SET_FLAGS, flags of all pages will be
+ * aggregated by bitwise AND. The minimum  migration granularity
+ * throughout the range will be returned for
+ * @KFD_IOCTL_SVM_ATTR_GRANULARITY.
+ *
+ * Querying of accessibility attributes works by initializing the
+ * attribute type to @KFD_IOCTL_SVM_ATTR_ACCESS and the value to the
+ * GPUID being queried. Multiple attributes can be given to allow
+ * querying multiple GPUIDs. The ioctl function overwrites the
+ * attribute type to indicate the access for the specified GPU.
+ *
+ * @KFD_IOCTL_SVM_ATTR_CLR_FLAGS is invalid for
+ * @KFD_IOCTL_SVM_OP_GET_ATTR.
+ */
+struct kfd_ioctl_svm_args {
+	__u64 start_addr;
+	__u64 size;
+	__u32 op;
+	__u32 nattr;
+	/* Variable length array of attributes */
+	struct kfd_ioctl_svm_attribute attrs[0];
+};
+
+/**
+ * kfd_ioctl_set_xnack_mode_args - Arguments for set_xnack_mode
+ *
+ * @xnack_enabled:       [in/out] Whether to enable XNACK mode for this process
+ *
+ * @xnack_enabled indicates whether recoverable page faults should be
+ * enabled for the current process. 0 means disabled, positive means
+ * enabled, negative means leave unchanged. If enabled, virtual address
+ * translations on GFXv9 and later AMD GPUs can return XNACK and retry
+ * the access until a valid PTE is available. This is used to implement
+ * device page faults.
+ *
+ * On output, @xnack_enabled returns the (new) current mode (0 or
+ * positive). Therefore, a negative input value can be used to query
+ * the current mode without changing it.
+ *
+ * The XNACK mode fundamentally changes the way SVM managed memory works
+ * in the driver, with subtle effects on application performance and
+ * functionality.
+ *
+ * Enabling XNACK mode requires shader programs to be compiled
+ * differently. Furthermore, not all GPUs support changing the mode
+ * per-process. Therefore changing the mode is only allowed while no
+ * user mode queues exist in the process. This ensure that no shader
+ * code is running that may be compiled for the wrong mode. And GPUs
+ * that cannot change to the requested mode will prevent the XNACK
+ * mode from occurring. All GPUs used by the process must be in the
+ * same XNACK mode.
+ *
+ * GFXv8 or older GPUs do not support 48 bit virtual addresses or SVM.
+ * Therefore those GPUs are not considered for the XNACK mode switch.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+struct kfd_ioctl_set_xnack_mode_args {
+	__s32 xnack_enabled;
+};
+
 #define AMDKFD_IOCTL_BASE 'K'
 #define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
 #define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
@@ -573,7 +735,12 @@ enum kfd_mmio_remap {
 #define AMDKFD_IOC_SMI_EVENTS			\
 		AMDKFD_IOWR(0x1F, struct kfd_ioctl_smi_events_args)
 
+#define AMDKFD_IOC_SVM	AMDKFD_IOWR(0x20, struct kfd_ioctl_svm_args)
+
+#define AMDKFD_IOC_SET_XNACK_MODE		\
+		AMDKFD_IOWR(0x21, struct kfd_ioctl_set_xnack_mode_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x20
+#define AMDKFD_COMMAND_END		0x22
 
 #endif