From 9f0fc191371843c4fc000a226b0a26b6c059aacd Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 18 May 2024 19:40:19 +0200 Subject: Merging upstream version 6.7.7. Signed-off-by: Daniel Baumann --- drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c | 92 +++++++++++++++++++++++++++---- 1 file changed, 82 insertions(+), 10 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c index 5fed06ffcc..4baa300121 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c @@ -21,24 +21,19 @@ * */ +#include +#include + #include "amdgpu_reset.h" #include "aldebaran.h" #include "sienna_cichlid.h" #include "smu_v13_0_10.h" -int amdgpu_reset_add_handler(struct amdgpu_reset_control *reset_ctl, - struct amdgpu_reset_handler *handler) -{ - /* TODO: Check if handler exists? */ - list_add_tail(&handler->handler_list, &reset_ctl->reset_handlers); - return 0; -} - int amdgpu_reset_init(struct amdgpu_device *adev) { int ret = 0; - switch (adev->ip_versions[MP1_HWIP][0]) { + switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) { case IP_VERSION(13, 0, 2): case IP_VERSION(13, 0, 6): ret = aldebaran_reset_init(adev); @@ -60,7 +55,7 @@ int amdgpu_reset_fini(struct amdgpu_device *adev) { int ret = 0; - switch (adev->ip_versions[MP1_HWIP][0]) { + switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) { case IP_VERSION(13, 0, 2): case IP_VERSION(13, 0, 6): ret = aldebaran_reset_fini(adev); @@ -167,5 +162,82 @@ void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain) up_write(&reset_domain->sem); } +#ifndef CONFIG_DEV_COREDUMP +void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost, + struct amdgpu_reset_context *reset_context) +{ +} +#else +static ssize_t +amdgpu_devcoredump_read(char *buffer, loff_t offset, size_t count, + void *data, size_t datalen) +{ + struct drm_printer p; + struct amdgpu_coredump_info *coredump = data; + struct drm_print_iterator iter; + int i; + + iter.data = buffer; + iter.offset = 0; + iter.start = offset; + iter.remain = count; + + p = drm_coredump_printer(&iter); + + drm_printf(&p, "**** AMDGPU Device Coredump ****\n"); + drm_printf(&p, "version: " AMDGPU_COREDUMP_VERSION "\n"); + drm_printf(&p, "kernel: " UTS_RELEASE "\n"); + drm_printf(&p, "module: " KBUILD_MODNAME "\n"); + drm_printf(&p, "time: %lld.%09ld\n", coredump->reset_time.tv_sec, + coredump->reset_time.tv_nsec); + + if (coredump->reset_task_info.pid) + drm_printf(&p, "process_name: %s PID: %d\n", + coredump->reset_task_info.process_name, + coredump->reset_task_info.pid); + + if (coredump->reset_vram_lost) + drm_printf(&p, "VRAM is lost due to GPU reset!\n"); + if (coredump->adev->reset_info.num_regs) { + drm_printf(&p, "AMDGPU register dumps:\nOffset: Value:\n"); + + for (i = 0; i < coredump->adev->reset_info.num_regs; i++) + drm_printf(&p, "0x%08x: 0x%08x\n", + coredump->adev->reset_info.reset_dump_reg_list[i], + coredump->adev->reset_info.reset_dump_reg_value[i]); + } + + return count - iter.remain; +} + +static void amdgpu_devcoredump_free(void *data) +{ + kfree(data); +} + +void amdgpu_coredump(struct amdgpu_device *adev, bool vram_lost, + struct amdgpu_reset_context *reset_context) +{ + struct amdgpu_coredump_info *coredump; + struct drm_device *dev = adev_to_drm(adev); + + coredump = kzalloc(sizeof(*coredump), GFP_NOWAIT); + if (!coredump) { + DRM_ERROR("%s: failed to allocate memory for coredump\n", __func__); + return; + } + coredump->reset_vram_lost = vram_lost; + + if (reset_context->job && reset_context->job->vm) + coredump->reset_task_info = reset_context->job->vm->task_info; + + coredump->adev = adev; + + ktime_get_ts64(&coredump->reset_time); + + dev_coredumpm(dev->dev, THIS_MODULE, coredump, 0, GFP_NOWAIT, + amdgpu_devcoredump_read, amdgpu_devcoredump_free); +} +#endif -- cgit v1.2.3