From 24cf226a2ee4b67db43e339fbe8b62e0d0a0adf9 Mon Sep 17 00:00:00 2001
From: Chengming Gui <Jack.Gui@amd.com>
Date: Thu, 28 Jul 2022 09:15:43 +0800
Subject: drm/amd/amdgpu: add memory training support for PSP_V13
Git-commit: 6fdd2077ec03f4b34d127a1713ca19248539d6e0
Patch-mainline: v6.0-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225 jsc#PED-2849
Add PSP_V13 memory training support funcs.
v2: replace DRM_{DEBUG/ERROR} with dev_{dbg/err}. (Hawking)
v3: fix checkpatch error (Alex)
Signed-off-by: Chengming Gui <Jack.Gui@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
drivers/gpu/drm/amd/amdgpu/psp_v13_0.c | 159 +++++++++++++++++++++++++
1 file changed, 159 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index 30386d34d0d6..63b2d32545cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -20,6 +20,8 @@
* OTHER DEALINGS IN THE SOFTWARE.
*
*/
+#include <linux/dev_printk.h>
+#include <drm/drm_drv.h>
#include "amdgpu.h"
#include "amdgpu_psp.h"
#include "amdgpu_ucode.h"
@@ -58,6 +60,9 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_7_ta.bin");
#define C2PMSG_CMD_SPI_UPDATE_ROM_IMAGE_ADDR_HI 0x3
#define C2PMSG_CMD_SPI_UPDATE_FLASH_IMAGE 0x4
+/* memory training timeout define */
+#define MEM_TRAIN_SEND_MSG_TIMEOUT_US 3000000
+
static int psp_v13_0_init_microcode(struct psp_context *psp)
{
struct amdgpu_device *adev = psp->adev;
@@ -419,6 +424,159 @@ static void psp_v13_0_ring_set_wptr(struct psp_context *psp, uint32_t value)
WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_67, value);
}
+static int psp_v13_0_memory_training_send_msg(struct psp_context *psp, int msg)
+{
+ int ret;
+ int i;
+ uint32_t data_32;
+ int max_wait;
+ struct amdgpu_device *adev = psp->adev;
+
+ data_32 = (psp->mem_train_ctx.c2p_train_data_offset >> 20);
+ WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_36, data_32);
+ WREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_35, msg);
+
+ max_wait = MEM_TRAIN_SEND_MSG_TIMEOUT_US / adev->usec_timeout;
+ for (i = 0; i < max_wait; i++) {
+ ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35),
+ 0x80000000, 0x80000000, false);
+ if (ret == 0)
+ break;
+ }
+ if (i < max_wait)
+ ret = 0;
+ else
+ ret = -ETIME;
+
+ dev_dbg(adev->dev, "training %s %s, cost %d @ %d ms\n",
+ (msg == PSP_BL__DRAM_SHORT_TRAIN) ? "short" : "long",
+ (ret == 0) ? "succeed" : "failed",
+ i, adev->usec_timeout/1000);
+ return ret;
+}
+
+
+static int psp_v13_0_memory_training(struct psp_context *psp, uint32_t ops)
+{
+ struct psp_memory_training_context *ctx = &psp->mem_train_ctx;
+ uint32_t *pcache = (uint32_t *)ctx->sys_cache;
+ struct amdgpu_device *adev = psp->adev;
+ uint32_t p2c_header[4];
+ uint32_t sz;
+ void *buf;
+ int ret, idx;
+
+ if (ctx->init == PSP_MEM_TRAIN_NOT_SUPPORT) {
+ dev_dbg(adev->dev, "Memory training is not supported.\n");
+ return 0;
+ } else if (ctx->init != PSP_MEM_TRAIN_INIT_SUCCESS) {
+ dev_err(adev->dev, "Memory training initialization failure.\n");
+ return -EINVAL;
+ }
+
+ if (psp_v13_0_is_sos_alive(psp)) {
+ dev_dbg(adev->dev, "SOS is alive, skip memory training.\n");
+ return 0;
+ }
+
+ amdgpu_device_vram_access(adev, ctx->p2c_train_data_offset, p2c_header, sizeof(p2c_header), false);
+ dev_dbg(adev->dev, "sys_cache[%08x,%08x,%08x,%08x] p2c_header[%08x,%08x,%08x,%08x]\n",
+ pcache[0], pcache[1], pcache[2], pcache[3],
+ p2c_header[0], p2c_header[1], p2c_header[2], p2c_header[3]);
+
+ if (ops & PSP_MEM_TRAIN_SEND_SHORT_MSG) {
+ dev_dbg(adev->dev, "Short training depends on restore.\n");
+ ops |= PSP_MEM_TRAIN_RESTORE;
+ }
+
+ if ((ops & PSP_MEM_TRAIN_RESTORE) &&
+ pcache[0] != MEM_TRAIN_SYSTEM_SIGNATURE) {
+ dev_dbg(adev->dev, "sys_cache[0] is invalid, restore depends on save.\n");
+ ops |= PSP_MEM_TRAIN_SAVE;
+ }
+
+ if (p2c_header[0] == MEM_TRAIN_SYSTEM_SIGNATURE &&
+ !(pcache[0] == MEM_TRAIN_SYSTEM_SIGNATURE &&
+ pcache[3] == p2c_header[3])) {
+ dev_dbg(adev->dev, "sys_cache is invalid or out-of-date, need save training data to sys_cache.\n");
+ ops |= PSP_MEM_TRAIN_SAVE;
+ }
+
+ if ((ops & PSP_MEM_TRAIN_SAVE) &&
+ p2c_header[0] != MEM_TRAIN_SYSTEM_SIGNATURE) {
+ dev_dbg(adev->dev, "p2c_header[0] is invalid, save depends on long training.\n");
+ ops |= PSP_MEM_TRAIN_SEND_LONG_MSG;
+ }
+
+ if (ops & PSP_MEM_TRAIN_SEND_LONG_MSG) {
+ ops &= ~PSP_MEM_TRAIN_SEND_SHORT_MSG;
+ ops |= PSP_MEM_TRAIN_SAVE;
+ }
+
+ dev_dbg(adev->dev, "Memory training ops:%x.\n", ops);
+
+ if (ops & PSP_MEM_TRAIN_SEND_LONG_MSG) {
+ /*
+ * Long training will encroach a certain amount on the bottom of VRAM;
+ * save the content from the bottom of VRAM to system memory
+ * before training, and restore it after training to avoid
+ * VRAM corruption.
+ */
+ sz = GDDR6_MEM_TRAINING_ENCROACHED_SIZE;
+
+ if (adev->gmc.visible_vram_size < sz || !adev->mman.aper_base_kaddr) {
+ dev_err(adev->dev, "visible_vram_size %llx or aper_base_kaddr %p is not initialized.\n",
+ adev->gmc.visible_vram_size,
+ adev->mman.aper_base_kaddr);
+ return -EINVAL;
+ }
+
+ buf = vmalloc(sz);
+ if (!buf) {
+ dev_err(adev->dev, "failed to allocate system memory.\n");
+ return -ENOMEM;
+ }
+
+ if (drm_dev_enter(adev_to_drm(adev), &idx)) {
+ memcpy_fromio(buf, adev->mman.aper_base_kaddr, sz);
+ ret = psp_v13_0_memory_training_send_msg(psp, PSP_BL__DRAM_LONG_TRAIN);
+ if (ret) {
+ DRM_ERROR("Send long training msg failed.\n");
+ vfree(buf);
+ drm_dev_exit(idx);
+ return ret;
+ }
+
+ memcpy_toio(adev->mman.aper_base_kaddr, buf, sz);
+ adev->hdp.funcs->flush_hdp(adev, NULL);
+ vfree(buf);
+ drm_dev_exit(idx);
+ } else {
+ vfree(buf);
+ return -ENODEV;
+ }
+ }
+
+ if (ops & PSP_MEM_TRAIN_SAVE) {
+ amdgpu_device_vram_access(psp->adev, ctx->p2c_train_data_offset, ctx->sys_cache, ctx->train_data_size, false);
+ }
+
+ if (ops & PSP_MEM_TRAIN_RESTORE) {
+ amdgpu_device_vram_access(psp->adev, ctx->c2p_train_data_offset, ctx->sys_cache, ctx->train_data_size, true);
+ }
+
+ if (ops & PSP_MEM_TRAIN_SEND_SHORT_MSG) {
+ ret = psp_v13_0_memory_training_send_msg(psp, (amdgpu_force_long_training > 0) ?
+ PSP_BL__DRAM_LONG_TRAIN : PSP_BL__DRAM_SHORT_TRAIN);
+ if (ret) {
+ dev_err(adev->dev, "send training msg failed.\n");
+ return ret;
+ }
+ }
+ ctx->training_cnt++;
+ return 0;
+}
+
static int psp_v13_0_load_usbc_pd_fw(struct psp_context *psp, uint64_t fw_pri_mc_addr)
{
struct amdgpu_device *adev = psp->adev;
@@ -567,6 +725,7 @@ static const struct psp_funcs psp_v13_0_funcs = {
.ring_destroy = psp_v13_0_ring_destroy,
.ring_get_wptr = psp_v13_0_ring_get_wptr,
.ring_set_wptr = psp_v13_0_ring_set_wptr,
+ .mem_training = psp_v13_0_memory_training,
.load_usbc_pd_fw = psp_v13_0_load_usbc_pd_fw,
.read_usbc_pd_fw = psp_v13_0_read_usbc_pd_fw,
.update_spirom = psp_v13_0_update_spirom,
--
2.38.1