Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

Documentation/gpu/amdgpu/apu-asic-info-table.csv

@@ -5,6 +5,8 @@ Ryzen 4000 series, RENOIR, DCN 2.1, 9.3, VCN 2.2, 4.1.2, 11.0.3
 Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN2, DCN 1.0, 9.2.2, VCN 1.0.1, 4.1.1, 10.0.1
 SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1, 11.5.0
 Ryzen 5000 series / Ryzen 7x30 series, GREEN SARDINE / Cezanne / Barcelo / Barcelo-R, DCN 2.1, 9.3, VCN 2.2, 4.1.1, 12.0.1
-Ryzen 6000 series / Ryzen 7x35 series, YELLOW CARP / Rembrandt / Rembrandt+, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
+Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series, YELLOW CARP / Rembrandt / Rembrandt-R, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
 Ryzen 7000 series (AM5), Raphael, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
+Ryzen 7x45 series (FL1), / Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
 Ryzen 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8
+Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11

drivers/gpu/drm/Makefile

@@ -140,6 +140,7 @@ obj-$(CONFIG_DRM_TTM)	+= ttm/
 obj-$(CONFIG_DRM_SCHED)	+= scheduler/
 obj-$(CONFIG_DRM_RADEON)+= radeon/
 obj-$(CONFIG_DRM_AMDGPU)+= amd/amdgpu/
+obj-$(CONFIG_DRM_AMDGPU)+= amd/amdxcp/
 obj-$(CONFIG_DRM_I915)	+= i915/
 obj-$(CONFIG_DRM_KMB_DISPLAY)  += kmb/
 obj-$(CONFIG_DRM_MGAG200) += mgag200/

drivers/gpu/drm/amd/amdgpu/Kconfig

@@ -69,6 +69,16 @@ config DRM_AMDGPU_USERPTR
 	  This option selects CONFIG_HMM and CONFIG_HMM_MIRROR if it
 	  isn't already selected to enabled full userptr support.
 
+config DRM_AMDGPU_WERROR
+	bool "Force the compiler to throw an error instead of a warning when compiling"
+	depends on DRM_AMDGPU
+	depends on EXPERT
+	depends on !COMPILE_TEST
+	default n
+	help
+	  Add -Werror to the build flags for amdgpu.ko.
+	  Only enable this if you are warning code for amdgpu.ko.
+
 source "drivers/gpu/drm/amd/acp/Kconfig"
 source "drivers/gpu/drm/amd/display/Kconfig"
 source "drivers/gpu/drm/amd/amdkfd/Kconfig"

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -39,6 +39,15 @@ ccflags-y := -I$(FULL_AMD_PATH)/include/asic_reg \
 	-I$(FULL_AMD_DISPLAY_PATH)/amdgpu_dm \
 	-I$(FULL_AMD_PATH)/amdkfd
 
+subdir-ccflags-y := -Wextra
+subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
+subdir-ccflags-y += -Wno-unused-parameter
+subdir-ccflags-y += -Wno-type-limits
+subdir-ccflags-y += -Wno-sign-compare
+subdir-ccflags-y += -Wno-missing-field-initializers
+subdir-ccflags-y += -Wno-override-init
+subdir-ccflags-$(CONFIG_DRM_AMDGPU_WERROR) += -Werror
+
 amdgpu-y := amdgpu_drv.o
 
 # add KMS driver
@@ -60,7 +69,7 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
 	amdgpu_fw_attestation.o amdgpu_securedisplay.o \
 	amdgpu_eeprom.o amdgpu_mca.o amdgpu_psp_ta.o amdgpu_lsdma.o \
-	amdgpu_ring_mux.o
+	amdgpu_ring_mux.o amdgpu_xcp.o
 
 amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
 
@@ -78,7 +87,7 @@ amdgpu-y += \
 	vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o arct_reg_init.o mxgpu_nv.o \
 	nbio_v7_2.o hdp_v4_0.o hdp_v5_0.o aldebaran_reg_init.o aldebaran.o soc21.o \
 	sienna_cichlid.o smu_v13_0_10.o nbio_v4_3.o hdp_v6_0.o nbio_v7_7.o hdp_v5_2.o lsdma_v6_0.o \
-	nbio_v7_9.o
+	nbio_v7_9.o aqua_vanjaram_reg_init.o
 
 # add DF block
 amdgpu-y += \
@@ -183,12 +192,14 @@ amdgpu-y += \
 	vcn_v2_5.o \
 	vcn_v3_0.o \
 	vcn_v4_0.o \
+	vcn_v4_0_3.o \
 	amdgpu_jpeg.o \
 	jpeg_v1_0.o \
 	jpeg_v2_0.o \
 	jpeg_v2_5.o \
 	jpeg_v3_0.o \
-	jpeg_v4_0.o
+	jpeg_v4_0.o \
+	jpeg_v4_0_3.o
 
 # add ATHUB block
 amdgpu-y += \
@@ -203,6 +214,7 @@ amdgpu-y += \
 	smuio_v11_0.o \
 	smuio_v11_0_6.o \
 	smuio_v13_0.o \
+	smuio_v13_0_3.o \
 	smuio_v13_0_6.o
 
 # add reset block
@@ -228,6 +240,7 @@ amdgpu-y += \
 	amdgpu_amdkfd_gfx_v9.o \
 	amdgpu_amdkfd_arcturus.o \
 	amdgpu_amdkfd_aldebaran.o \
+	amdgpu_amdkfd_gc_9_4_3.o \
 	amdgpu_amdkfd_gfx_v10.o \
 	amdgpu_amdkfd_gfx_v10_3.o \
 	amdgpu_amdkfd_gfx_v11.o

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -107,8 +107,9 @@
 #include "amdgpu_fdinfo.h"
 #include "amdgpu_mca.h"
 #include "amdgpu_ras.h"
+#include "amdgpu_xcp.h"
 
-#define MAX_GPU_INSTANCE		16
+#define MAX_GPU_INSTANCE		64
 
 struct amdgpu_gpu_instance
 {
@@ -212,6 +213,8 @@ extern int amdgpu_noretry;
 extern int amdgpu_force_asic_type;
 extern int amdgpu_smartshift_bias;
 extern int amdgpu_use_xgmi_p2p;
+extern int amdgpu_mtype_local;
+extern bool enforce_isolation;
 #ifdef CONFIG_HSA_AMD
 extern int sched_policy;
 extern bool debug_evictions;
@@ -242,9 +245,10 @@ extern int amdgpu_num_kcq;
 extern int amdgpu_vcnfw_log;
 extern int amdgpu_sg_display;
 
+extern int amdgpu_user_partt_mode;
+
 #define AMDGPU_VM_MAX_NUM_CTX			4096
 #define AMDGPU_SG_THRESHOLD			(256*1024*1024)
-#define AMDGPU_DEFAULT_GTT_SIZE_MB		3072ULL /* 3GB by default */
 #define AMDGPU_WAIT_IDLE_TIMEOUT_IN_MS	        3000
 #define AMDGPU_MAX_USEC_TIMEOUT			100000	/* 100 ms */
 #define AMDGPU_FENCE_JIFFIES_TIMEOUT		(HZ / 2)
@@ -282,6 +286,7 @@ extern int amdgpu_sg_display;
 #define AMDGPU_SMARTSHIFT_MAX_BIAS (100)
 #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100)
 
+struct amdgpu_xcp_mgr;
 struct amdgpu_device;
 struct amdgpu_irq_src;
 struct amdgpu_fpriv;
@@ -463,6 +468,8 @@ struct amdgpu_fpriv {
 	struct mutex		bo_list_lock;
 	struct idr		bo_list_handles;
 	struct amdgpu_ctx_mgr	ctx_mgr;
+	/** GPU partition selection */
+	uint32_t		xcp_id;
 };
 
 int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv);
@@ -573,6 +580,8 @@ struct amdgpu_asic_funcs {
 	/* query video codecs */
 	int (*query_video_codecs)(struct amdgpu_device *adev, bool encode,
 				  const struct amdgpu_video_codecs **codecs);
+	/* encode "> 32bits" smn addressing */
+	u64 (*encode_ext_smn_addressing)(int ext_id);
 };
 
 /*
@@ -607,6 +616,9 @@ void amdgpu_cgs_destroy_device(struct cgs_device *cgs_device);
 typedef uint32_t (*amdgpu_rreg_t)(struct amdgpu_device*, uint32_t);
 typedef void (*amdgpu_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 
+typedef uint32_t (*amdgpu_rreg_ext_t)(struct amdgpu_device*, uint64_t);
+typedef void (*amdgpu_wreg_ext_t)(struct amdgpu_device*, uint64_t, uint32_t);
+
 typedef uint64_t (*amdgpu_rreg64_t)(struct amdgpu_device*, uint32_t);
 typedef void (*amdgpu_wreg64_t)(struct amdgpu_device*, uint32_t, uint64_t);
 
@@ -657,14 +669,25 @@ enum amd_hw_ip_block_type {
 	MAX_HWIP
 };
 
-#define HWIP_MAX_INSTANCE	28
+#define HWIP_MAX_INSTANCE	44
 
 #define HW_ID_MAX		300
 #define IP_VERSION(mj, mn, rv) (((mj) << 16) | ((mn) << 8) | (rv))
 #define IP_VERSION_MAJ(ver) ((ver) >> 16)
 #define IP_VERSION_MIN(ver) (((ver) >> 8) & 0xFF)
 #define IP_VERSION_REV(ver) ((ver) & 0xFF)
 
+struct amdgpu_ip_map_info {
+	/* Map of logical to actual dev instances/mask */
+	uint32_t 		dev_inst[MAX_HWIP][HWIP_MAX_INSTANCE];
+	int8_t (*logical_to_dev_inst)(struct amdgpu_device *adev,
+				      enum amd_hw_ip_block_type block,
+				      int8_t inst);
+	uint32_t (*logical_to_dev_mask)(struct amdgpu_device *adev,
+					enum amd_hw_ip_block_type block,
+					uint32_t mask);
+};
+
 struct amd_powerplay {
 	void *pp_handle;
 	const struct amd_pm_funcs *pp_funcs;
@@ -750,6 +773,7 @@ struct amdgpu_device {
 	struct amdgpu_acp		acp;
 #endif
 	struct amdgpu_hive_info *hive;
+	struct amdgpu_xcp_mgr *xcp_mgr;
 	/* ASIC */
 	enum amd_asic_type		asic_type;
 	uint32_t			family;
@@ -797,6 +821,8 @@ struct amdgpu_device {
 	amdgpu_wreg_t			pcie_wreg;
 	amdgpu_rreg_t			pciep_rreg;
 	amdgpu_wreg_t			pciep_wreg;
+	amdgpu_rreg_ext_t		pcie_rreg_ext;
+	amdgpu_wreg_ext_t		pcie_wreg_ext;
 	amdgpu_rreg64_t			pcie_rreg64;
 	amdgpu_wreg64_t			pcie_wreg64;
 	/* protects concurrent UVD register access */
@@ -830,7 +856,7 @@ struct amdgpu_device {
 	dma_addr_t			dummy_page_addr;
 	struct amdgpu_vm_manager	vm_manager;
 	struct amdgpu_vmhub             vmhub[AMDGPU_MAX_VMHUBS];
-	unsigned			num_vmhubs;
+	DECLARE_BITMAP(vmhubs_mask, AMDGPU_MAX_VMHUBS);
 
 	/* memory management */
 	struct amdgpu_mman		mman;
@@ -962,6 +988,7 @@ struct amdgpu_device {
 
 	/* soc15 register offset based on ip, instance and  segment */
 	uint32_t		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
+	struct amdgpu_ip_map_info	ip_map;
 
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     delayed_init_work;
@@ -1020,6 +1047,9 @@ struct amdgpu_device {
 	struct pci_saved_state          *pci_state;
 	pci_channel_state_t		pci_channel_state;
 
+	/* Track auto wait count on s_barrier settings */
+	bool				barrier_has_auto_waitcnt;
+
 	struct amdgpu_reset_control     *reset_cntl;
 	uint32_t                        ip_versions[MAX_HWIP][HWIP_MAX_INSTANCE];
 
@@ -1050,6 +1080,8 @@ struct amdgpu_device {
 
 	bool                            job_hang;
 	bool                            dc_enabled;
+	/* Mask of active clusters */
+	uint32_t			aid_mask;
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
@@ -1081,11 +1113,18 @@ size_t amdgpu_device_aper_access(struct amdgpu_device *adev, loff_t pos,
 
 void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
 			       void *buf, size_t size, bool write);
+uint32_t amdgpu_device_wait_on_rreg(struct amdgpu_device *adev,
+			    uint32_t inst, uint32_t reg_addr, char reg_name[],
+			    uint32_t expected_value, uint32_t mask);
 uint32_t amdgpu_device_rreg(struct amdgpu_device *adev,
 			    uint32_t reg, uint32_t acc_flags);
+u32 amdgpu_device_indirect_rreg_ext(struct amdgpu_device *adev,
+				    u64 reg_addr);
 void amdgpu_device_wreg(struct amdgpu_device *adev,
 			uint32_t reg, uint32_t v,
 			uint32_t acc_flags);
+void amdgpu_device_indirect_wreg_ext(struct amdgpu_device *adev,
+				     u64 reg_addr, u32 reg_data);
 void amdgpu_mm_wreg_mmio_rlc(struct amdgpu_device *adev,
 			     uint32_t reg, uint32_t v);
 void amdgpu_mm_wreg8(struct amdgpu_device *adev, uint32_t offset, uint8_t value);
@@ -1137,6 +1176,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 #define WREG32_PCIE(reg, v) adev->pcie_wreg(adev, (reg), (v))
 #define RREG32_PCIE_PORT(reg) adev->pciep_rreg(adev, (reg))
 #define WREG32_PCIE_PORT(reg, v) adev->pciep_wreg(adev, (reg), (v))
+#define RREG32_PCIE_EXT(reg) adev->pcie_rreg_ext(adev, (reg))
+#define WREG32_PCIE_EXT(reg, v) adev->pcie_wreg_ext(adev, (reg), (v))
 #define RREG64_PCIE(reg) adev->pcie_rreg64(adev, (reg))
 #define WREG64_PCIE(reg, v) adev->pcie_wreg64(adev, (reg), (v))
 #define RREG32_SMC(reg) adev->smc_rreg(adev, (reg))
@@ -1204,7 +1245,8 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 /*
  * ASICs macro.
  */
-#define amdgpu_asic_set_vga_state(adev, state) (adev)->asic_funcs->set_vga_state((adev), (state))
+#define amdgpu_asic_set_vga_state(adev, state) \
+    ((adev)->asic_funcs->set_vga_state ? (adev)->asic_funcs->set_vga_state((adev), (state)) : 0)
 #define amdgpu_asic_reset(adev) (adev)->asic_funcs->reset((adev))
 #define amdgpu_asic_reset_method(adev) (adev)->asic_funcs->reset_method((adev))
 #define amdgpu_asic_get_xclk(adev) (adev)->asic_funcs->get_xclk((adev))
@@ -1235,6 +1277,10 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
+#define for_each_inst(i, inst_mask)                                            \
+	for (i = ffs(inst_mask) - 1; inst_mask;                                \
+	     inst_mask &= ~(1U << i), i = ffs(inst_mask) - 1)
+
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
 
 /* Common functions */
@@ -1348,6 +1394,12 @@ struct amdgpu_afmt_acr amdgpu_afmt_acr(uint32_t clock);
 
 /* amdgpu_acpi.c */
 
+struct amdgpu_numa_info {
+	uint64_t size;
+	int pxm;
+	int nid;
+};
+
 /* ATCS Device/Driver State */
 #define AMDGPU_ATCS_PSC_DEV_STATE_D0		0
 #define AMDGPU_ATCS_PSC_DEV_STATE_D3_HOT	3
@@ -1365,15 +1417,32 @@ int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,
 				    u8 dev_state, bool drv_state);
 int amdgpu_acpi_smart_shift_update(struct drm_device *dev, enum amdgpu_ss ss_state);
 int amdgpu_acpi_pcie_notify_device_ready(struct amdgpu_device *adev);
+int amdgpu_acpi_get_tmr_info(struct amdgpu_device *adev, u64 *tmr_offset,
+			     u64 *tmr_size);
+int amdgpu_acpi_get_mem_info(struct amdgpu_device *adev, int xcc_id,
+			     struct amdgpu_numa_info *numa_info);
 
 void amdgpu_acpi_get_backlight_caps(struct amdgpu_dm_backlight_caps *caps);
 bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev);
 void amdgpu_acpi_detect(void);
+void amdgpu_acpi_release(void);
 #else
 static inline int amdgpu_acpi_init(struct amdgpu_device *adev) { return 0; }
+static inline int amdgpu_acpi_get_tmr_info(struct amdgpu_device *adev,
+					   u64 *tmr_offset, u64 *tmr_size)
+{
+	return -EINVAL;
+}
+static inline int amdgpu_acpi_get_mem_info(struct amdgpu_device *adev,
+					   int xcc_id,
+					   struct amdgpu_numa_info *numa_info)
+{
+	return -EINVAL;
+}
 static inline void amdgpu_acpi_fini(struct amdgpu_device *adev) { }
 static inline bool amdgpu_acpi_should_gpu_reset(struct amdgpu_device *adev) { return false; }
 static inline void amdgpu_acpi_detect(void) { }
+static inline void amdgpu_acpi_release(void) { }
 static inline bool amdgpu_acpi_is_power_shift_control_supported(void) { return false; }
 static inline int amdgpu_acpi_power_shift_control(struct amdgpu_device *adev,
 						  u8 dev_state, bool drv_state) { return 0; }