Merge tag 'amd-drm-next-5.16-2021-10-08' of https://gitlab.freedeskto…

…p.org/agd5f/linux into drm-next

amd-drm-next-5.16-2021-10-08:

amdgpu:
- gart BO pin count fix
- RAS fixes
- Misc display fixes
- Misc code cleanups
- Validate IP discovery table
- IOMMU handling fixes for hotplug
- Cyan Skillfish display support
- DP 2.0 fixes
- Covert vega and navi to IP discovery based asic enumeration
- JPEG fixes
- More FP cleanup for display
- DCC fixes for DCN3.x
- Initial USB4 DP tunnelling support
- Aldebaran MCE support

amdkfd:
- Misc bug fixes
- Misc code cleanups
- RAS fixes

x86/MCE:
- Export symbol for use by GPU driver

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211008200345.4689-1-alexander.deucher@amd.com

Documentation/gpu/amdgpu.rst

@@ -300,8 +300,8 @@ pcie_replay_count
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
    :doc: pcie_replay_count
 
-+GPU SmartShift Information
-============================
+GPU SmartShift Information
+==========================
 
 GPU SmartShift information via sysfs
 

arch/x86/include/asm/mce.h

@@ -358,7 +358,7 @@ extern int mce_threshold_remove_device(unsigned int cpu);
 
 void mce_amd_feature_init(struct cpuinfo_x86 *c);
 int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
-
+enum smca_bank_types smca_get_bank_type(unsigned int bank);
 #else
 
 static inline int mce_threshold_create_device(unsigned int cpu)		{ return 0; };

arch/x86/kernel/cpu/mce/amd.c

@@ -119,7 +119,7 @@ const char *smca_get_long_name(enum smca_bank_types t)
 }
 EXPORT_SYMBOL_GPL(smca_get_long_name);
 
-static enum smca_bank_types smca_get_bank_type(unsigned int bank)
+enum smca_bank_types smca_get_bank_type(unsigned int bank)
 {
 	struct smca_bank *b;
 
@@ -132,6 +132,7 @@ static enum smca_bank_types smca_get_bank_type(unsigned int bank)
 
 	return b->hwid->bank_type;
 }
+EXPORT_SYMBOL_GPL(smca_get_bank_type);
 
 static struct smca_hwid smca_hwid_mcatypes[] = {
 	/* { bank_type, hwid_mcatype } */

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

@@ -744,6 +744,7 @@ enum amd_hw_ip_block_type {
 	UVD_HWIP,
 	VCN_HWIP = UVD_HWIP,
 	JPEG_HWIP = VCN_HWIP,
+	VCN1_HWIP,
 	VCE_HWIP,
 	DF_HWIP,
 	DCE_HWIP,
@@ -755,11 +756,16 @@ enum amd_hw_ip_block_type {
 	CLK_HWIP,
 	UMC_HWIP,
 	RSMU_HWIP,
+	XGMI_HWIP,
+	DCI_HWIP,
 	MAX_HWIP
 };
 
 #define HWIP_MAX_INSTANCE	10
 
+#define HW_ID_MAX		300
+#define IP_VERSION(mj, mn, rv) (((mj) << 16) | ((mn) << 8) | (rv))
+
 struct amd_powerplay {
 	void *pp_handle;
 	const struct amd_pm_funcs *pp_funcs;
@@ -830,6 +836,7 @@ struct amdgpu_device {
 	struct notifier_block		acpi_nb;
 	struct amdgpu_i2c_chan		*i2c_bus[AMDGPU_MAX_I2C_BUS];
 	struct debugfs_blob_wrapper     debugfs_vbios_blob;
+	struct debugfs_blob_wrapper     debugfs_discovery_blob;
 	struct mutex			srbm_mutex;
 	/* GRBM index mutex. Protects concurrent access to GRBM index */
 	struct mutex                    grbm_idx_mutex;
@@ -1078,17 +1085,17 @@ struct amdgpu_device {
 	char				product_name[32];
 	char				serial[20];
 
-	struct amdgpu_autodump		autodump;
-
 	atomic_t			throttling_logging_enabled;
 	struct ratelimit_state		throttling_logging_rs;
 	uint32_t                        ras_hw_enabled;
 	uint32_t                        ras_enabled;
 
 	bool                            no_hw_access;
 	struct pci_saved_state          *pci_state;
+	pci_channel_state_t		pci_channel_state;
 
 	struct amdgpu_reset_control     *reset_cntl;
+	uint32_t                        ip_versions[HW_ID_MAX][HWIP_MAX_INSTANCE];
 };
 
 static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -31,6 +31,8 @@
 #include <linux/dma-buf.h>
 #include "amdgpu_xgmi.h"
 #include <uapi/linux/kfd_ioctl.h>
+#include "amdgpu_ras.h"
+#include "amdgpu_umc.h"
 
 /* Total memory size in system memory and all GPU VRAM. Used to
  * estimate worst case amount of memory to reserve for page tables
@@ -70,8 +72,7 @@ void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 	if (!kfd_initialized)
 		return;
 
-	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev,
-				      adev->pdev, adev->asic_type, vf);
+	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev, vf);
 
 	if (adev->kfd.dev)
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
@@ -780,3 +781,15 @@ bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd)
 
 	return adev->have_atomics_support;
 }
+
+void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+	struct ras_err_data err_data = {0, 0, 0, NULL};
+
+	/* CPU MCA will handle page retirement if connected_to_cpu is 1 */
+	if (!adev->gmc.xgmi.connected_to_cpu)
+		amdgpu_umc_process_ras_data_cb(adev, &err_data, NULL);
+	else
+		amdgpu_amdkfd_gpu_reset(kgd);
+}

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

@@ -290,6 +290,7 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 				      uint64_t *mmap_offset);
 int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
 				struct tile_config *config);
+void amdgpu_amdkfd_ras_poison_consumption_handler(struct kgd_dev *kgd);
 #if IS_ENABLED(CONFIG_HSA_AMD)
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
@@ -321,8 +322,7 @@ int kgd2kfd_schedule_evict_and_restore_process(struct mm_struct *mm,
 #if IS_ENABLED(CONFIG_HSA_AMD)
 int kgd2kfd_init(void);
 void kgd2kfd_exit(void);
-struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
-			      unsigned int asic_type, bool vf);
+struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, bool vf);
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
 			 struct drm_device *ddev,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
@@ -346,8 +346,7 @@ static inline void kgd2kfd_exit(void)
 }
 
 static inline
-struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
-					unsigned int asic_type, bool vf)
+struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, bool vf)
 {
 	return NULL;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -563,6 +563,7 @@ kfd_mem_dmaunmap_userptr(struct kgd_mem *mem,
 
 	dma_unmap_sgtable(adev->dev, ttm->sg, direction, 0);
 	sg_free_table(ttm->sg);
+	kfree(ttm->sg);
 	ttm->sg = NULL;
 }
 

drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c

@@ -61,7 +61,7 @@ static void amdgpu_bo_list_free(struct kref *ref)
 
 int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 			  struct drm_amdgpu_bo_list_entry *info,
-			  unsigned num_entries, struct amdgpu_bo_list **result)
+			  size_t num_entries, struct amdgpu_bo_list **result)
 {
 	unsigned last_entry = 0, first_userptr = num_entries;
 	struct amdgpu_bo_list_entry *array;

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

@@ -61,7 +61,7 @@ int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
 int amdgpu_bo_list_create(struct amdgpu_device *adev,
 				 struct drm_file *filp,
 				 struct drm_amdgpu_bo_list_entry *info,
-				 unsigned num_entries,
+				 size_t num_entries,
 				 struct amdgpu_bo_list **list);
 
 static inline struct amdgpu_bo_list_entry *

drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c

@@ -27,7 +27,6 @@
 #include <linux/pci.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
-#include <linux/poll.h>
 
 #include "amdgpu.h"
 #include "amdgpu_pm.h"
@@ -38,86 +37,8 @@
 #include "amdgpu_fw_attestation.h"
 #include "amdgpu_umr.h"
 
-int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev)
-{
-#if defined(CONFIG_DEBUG_FS)
-	unsigned long timeout = 600 * HZ;
-	int ret;
-
-	wake_up_interruptible(&adev->autodump.gpu_hang);
-
-	ret = wait_for_completion_interruptible_timeout(&adev->autodump.dumping, timeout);
-	if (ret == 0) {
-		pr_err("autodump: timeout, move on to gpu recovery\n");
-		return -ETIMEDOUT;
-	}
-#endif
-	return 0;
-}
-
 #if defined(CONFIG_DEBUG_FS)
 
-static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)
-{
-	struct amdgpu_device *adev = inode->i_private;
-	int ret;
-
-	file->private_data = adev;
-
-	ret = down_read_killable(&adev->reset_sem);
-	if (ret)
-		return ret;
-
-	if (adev->autodump.dumping.done) {
-		reinit_completion(&adev->autodump.dumping);
-		ret = 0;
-	} else {
-		ret = -EBUSY;
-	}
-
-	up_read(&adev->reset_sem);
-
-	return ret;
-}
-
-static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file)
-{
-	struct amdgpu_device *adev = file->private_data;
-
-	complete_all(&adev->autodump.dumping);
-	return 0;
-}
-
-static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_table_struct *poll_table)
-{
-	struct amdgpu_device *adev = file->private_data;
-
-	poll_wait(file, &adev->autodump.gpu_hang, poll_table);
-
-	if (amdgpu_in_reset(adev))
-		return POLLIN | POLLRDNORM | POLLWRNORM;
-
-	return 0;
-}
-
-static const struct file_operations autodump_debug_fops = {
-	.owner = THIS_MODULE,
-	.open = amdgpu_debugfs_autodump_open,
-	.poll = amdgpu_debugfs_autodump_poll,
-	.release = amdgpu_debugfs_autodump_release,
-};
-
-static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)
-{
-	init_completion(&adev->autodump.dumping);
-	complete_all(&adev->autodump.dumping);
-	init_waitqueue_head(&adev->autodump.gpu_hang);
-
-	debugfs_create_file("amdgpu_autodump", 0600,
-		adev_to_drm(adev)->primary->debugfs_root,
-		adev, &autodump_debug_fops);
-}
-
 /**
  * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes
  *
@@ -1407,7 +1328,7 @@ static int amdgpu_debugfs_evict_vram(void *data, u64 *val)
 		return r;
 	}
 
-	*val = amdgpu_bo_evict_vram(adev);
+	*val = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -1420,17 +1341,15 @@ static int amdgpu_debugfs_evict_gtt(void *data, u64 *val)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)data;
 	struct drm_device *dev = adev_to_drm(adev);
-	struct ttm_resource_manager *man;
 	int r;
 
 	r = pm_runtime_get_sync(dev->dev);
 	if (r < 0) {
-		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
+		pm_runtime_put_autosuspend(dev->dev);
 		return r;
 	}
 
-	man = ttm_manager_type(&adev->mman.bdev, TTM_PL_TT);
-	*val = ttm_resource_manager_evict_all(&adev->mman.bdev, man);
+	*val = amdgpu_ttm_evict_resources(adev, TTM_PL_TT);
 
 	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
@@ -1696,6 +1615,9 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	struct dentry *ent;
 	int r, i;
 
+	if (!debugfs_initialized())
+		return 0;
+
 	ent = debugfs_create_file("amdgpu_preempt_ib", 0600, root, adev,
 				  &fops_ib_preempt);
 	if (IS_ERR(ent)) {
@@ -1738,7 +1660,6 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	}
 
 	amdgpu_ras_debugfs_create_all(adev);
-	amdgpu_debugfs_autodump_init(adev);
 	amdgpu_rap_debugfs_init(adev);
 	amdgpu_securedisplay_debugfs_init(adev);
 	amdgpu_fw_attestation_debugfs_init(adev);
@@ -1757,6 +1678,11 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 	debugfs_create_blob("amdgpu_vbios", 0444, root,
 			    &adev->debugfs_vbios_blob);
 
+	adev->debugfs_discovery_blob.data = adev->mman.discovery_bin;
+	adev->debugfs_discovery_blob.size = adev->mman.discovery_tmr_size;
+	debugfs_create_blob("amdgpu_discovery", 0444, root,
+			    &adev->debugfs_discovery_blob);
+
 	return 0;
 }
 

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

@@ -25,15 +25,10 @@
 /*
  * Debugfs
  */
-struct amdgpu_autodump {
-	struct completion		dumping;
-	struct wait_queue_head		gpu_hang;
-};
 
 int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);
 int amdgpu_debugfs_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_fini(struct amdgpu_device *adev);
 void amdgpu_debugfs_fence_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);
 void amdgpu_debugfs_gem_init(struct amdgpu_device *adev);
-int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev);