[PATCH V2 3/4] drm/amdgpu: refine poison consumption interrupt handler

[Zhang, Hawking]

[AMD Official Use Only - AMD Internal Distribution Only]

Reviewed-by: Hawking Zhang <Hawking.Zhang at amd.com>

Regards,
Hawking
-----Original Message-----
From: Chai, Thomas <YiPeng.Chai at amd.com>
Sent: Thursday, June 20, 2024 13:40
To: amd-gfx at lists.freedesktop.org
Cc: Zhang, Hawking <Hawking.Zhang at amd.com>; Zhou1, Tao <Tao.Zhou1 at amd.com>; Li, Candice <Candice.Li at amd.com>; Wang, Yang(Kevin) <KevinYang.Wang at amd.com>; Yang, Stanley <Stanley.Yang at amd.com>; Chai, Thomas <YiPeng.Chai at amd.com>
Subject: [PATCH V2 3/4] drm/amdgpu: refine poison consumption interrupt handler

1. The poison fifo is only used for poison consumption
   requests.
2. Merge reset requests when poison fifo caches multiple
   poison consumption messages

Signed-off-by: YiPeng Chai <YiPeng.Chai at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 56 ++++++++++++++++---------  drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 12 +++---
 2 files changed, 44 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 308348b4644f..a4030dc12a1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -2917,23 +2917,41 @@ static int amdgpu_ras_poison_creation_handler(struct amdgpu_device *adev,  }

 static int amdgpu_ras_poison_consumption_handler(struct amdgpu_device *adev,
-                       struct ras_poison_msg *poison_msg)
+                       uint32_t msg_count, uint32_t *gpu_reset)
 {
        struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-       uint32_t reset = poison_msg->reset;
-       uint16_t pasid = poison_msg->pasid;
+       uint32_t reset_flags = 0, reset = 0;
+       struct ras_poison_msg msg;
+       int ret, i;

        kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);

-       if (poison_msg->pasid_fn)
-               poison_msg->pasid_fn(adev, pasid, poison_msg->data);
+       for (i = 0; i < msg_count; i++) {
+               ret = amdgpu_ras_get_poison_req(adev, &msg);
+               if (!ret)
+                       continue;
+
+               if (msg.pasid_fn)
+                       msg.pasid_fn(adev, msg.pasid, msg.data);
+
+               reset_flags |= msg.reset;
+       }

        /* for RMA, amdgpu_ras_poison_creation_handler will trigger gpu reset */
-       if (reset && !con->is_rma) {
+       if (reset_flags && !con->is_rma) {
+               if (reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET)
+                       reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET;
+               else if (reset_flags & AMDGPU_RAS_GPU_RESET_MODE2_RESET)
+                       reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET;
+               else
+                       reset = reset_flags;
+
                flush_delayed_work(&con->page_retirement_dwork);

                con->gpu_reset_flags |= reset;
                amdgpu_ras_reset_gpu(adev);
+
+               *gpu_reset = reset;
        }

        return 0;
@@ -2943,11 +2961,9 @@ static int amdgpu_ras_page_retirement_thread(void *param)  {
        struct amdgpu_device *adev = (struct amdgpu_device *)param;
        struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-       uint32_t poison_creation_count;
+       uint32_t poison_creation_count, msg_count;
+       uint32_t gpu_reset;
        int ret;
-       struct ras_poison_msg poison_msg;
-       enum amdgpu_ras_block ras_block;
-       bool poison_creation_is_handled = false;

        while (!kthread_should_stop()) {

@@ -2958,6 +2974,7 @@ static int amdgpu_ras_page_retirement_thread(void *param)
                if (kthread_should_stop())
                        break;

+               gpu_reset = 0;

                do {
                        poison_creation_count = atomic_read(&con->poison_creation_count);
@@ -2972,16 +2989,17 @@ static int amdgpu_ras_page_retirement_thread(void *param)
                } while (atomic_read(&con->poison_creation_count));

 #ifdef HAVE_KFIFO_PUT_NON_POINTER
-               if (!amdgpu_ras_get_poison_req(adev, &poison_msg))
-                       continue;
-
-               ras_block = poison_msg.block;
-
-               dev_dbg(adev->dev, "Start processing ras block %s(%d)\n",
-                               ras_block_str(ras_block), ras_block);
-
+               if (ret != -EIO) {
+                       msg_count = kfifo_len(&con->poison_fifo);
+                       if (msg_count) {
+                               ret = amdgpu_ras_poison_consumption_handler(adev,
+                                               msg_count, &gpu_reset);
+                               if ((ret != -EIO) &&
+                                   (gpu_reset != AMDGPU_RAS_GPU_RESET_MODE1_RESET))
+                                       atomic_sub(msg_count, &con->page_retirement_req_cnt);
+                       }
+               }

-                       amdgpu_ras_poison_consumption_handler(adev, &poison_msg);
 #else
         dev_info(adev->dev, "Start processing page retirement. request:%d\n",
                     atomic_read(&con->page_retirement_req_cnt));
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index 4a72ff8d8d80..38e7793137ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -296,13 +296,15 @@ int amdgpu_umc_pasid_poison_handler(struct amdgpu_device *adev,
                                struct amdgpu_ras *con = amdgpu_ras_get_context(adev);

 #ifdef HAVE_KFIFO_PUT_NON_POINTER
-                               amdgpu_ras_put_poison_req(adev,
+                               int ret;
+
+                               ret = amdgpu_ras_put_poison_req(adev,
                                        block, pasid, pasid_fn, data, reset);
+                               if (!ret) {
+                                       atomic_inc(&con->page_retirement_req_cnt);
+                                       wake_up(&con->page_retirement_wq);
+                               }
 #endif
-
-                               atomic_inc(&con->page_retirement_req_cnt);
-
-                               wake_up(&con->page_retirement_wq);
                }
        } else {
                if (adev->virt.ops && adev->virt.ops->ras_poison_handler)
--
2.34.1