AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Alex Deucher <alexdeucher-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org
Cc: Tao Zhou <tao.zhou1-5C7GfCeVMHo@public.gmane.org>,
	Dennis Li <dennis.li-5C7GfCeVMHo@public.gmane.org>,
	Hawking Zhang <Hawking.Zhang-5C7GfCeVMHo@public.gmane.org>
Subject: [PATCH 17/26] drm/amdgpu: allow ras interrupt callback to return error data
Date: Wed, 31 Jul 2019 12:58:09 -0500	[thread overview]
Message-ID: <20190731175818.20159-18-alexander.deucher@amd.com> (raw)
In-Reply-To: <20190731175818.20159-1-alexander.deucher-5C7GfCeVMHo@public.gmane.org>

From: Tao Zhou <tao.zhou1@amd.com>

add error data as parameter for ras interrupt cb and process it

Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Dennis Li <dennis.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c |  6 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h | 37 +++++++++++++------------
 2 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 1914f37bee59..0eeb85d8399d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1003,7 +1003,7 @@ static void amdgpu_ras_interrupt_handler(struct ras_manager *obj)
 	struct ras_ih_data *data = &obj->ih_data;
 	struct amdgpu_iv_entry entry;
 	int ret;
-	struct ras_err_data err_data = {0, 0};
+	struct ras_err_data err_data = {0, 0, 0, NULL};
 
 	while (data->rptr != data->wptr) {
 		rmb();
@@ -1018,14 +1018,14 @@ static void amdgpu_ras_interrupt_handler(struct ras_manager *obj)
 		 * from the callback to udpate the error type/count, etc
 		 */
 		if (data->cb) {
-			ret = data->cb(obj->adev, &entry);
+			ret = data->cb(obj->adev, &err_data, &entry);
 			/* ue will trigger an interrupt, and in that case
 			 * we need do a reset to recovery the whole system.
 			 * But leave IP do that recovery, here we just dispatch
 			 * the error.
 			 */
 			if (ret == AMDGPU_RAS_UE) {
-				obj->err_data.ue_count++;
+				obj->err_data.ue_count += err_data.ue_count;
 			}
 			/* Might need get ce count by register, but not all IP
 			 * saves ce count, some IP just use one bit or two bits
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 0920db7aff34..2c86a5135ec9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -76,9 +76,6 @@ struct ras_common_if {
 	char name[32];
 };
 
-typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
-		struct amdgpu_iv_entry *entry);
-
 struct amdgpu_ras {
 	/* ras infrastructure */
 	/* for ras itself. */
@@ -108,21 +105,6 @@ struct amdgpu_ras {
 	uint32_t flags;
 };
 
-struct ras_ih_data {
-	/* interrupt bottom half */
-	struct work_struct ih_work;
-	int inuse;
-	/* IP callback */
-	ras_ih_cb cb;
-	/* full of entries */
-	unsigned char *ring;
-	unsigned int ring_size;
-	unsigned int element_size;
-	unsigned int aligned_element_size;
-	unsigned int rptr;
-	unsigned int wptr;
-};
-
 struct ras_fs_data {
 	char sysfs_name[32];
 	char debugfs_name[32];
@@ -149,6 +131,25 @@ struct ras_err_handler_data {
 	int last_reserved;
 };
 
+typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
+		struct ras_err_data *err_data,
+		struct amdgpu_iv_entry *entry);
+
+struct ras_ih_data {
+	/* interrupt bottom half */
+	struct work_struct ih_work;
+	int inuse;
+	/* IP callback */
+	ras_ih_cb cb;
+	/* full of entries */
+	unsigned char *ring;
+	unsigned int ring_size;
+	unsigned int element_size;
+	unsigned int aligned_element_size;
+	unsigned int rptr;
+	unsigned int wptr;
+};
+
 struct ras_manager {
 	struct ras_common_if head;
 	/* reference count */
-- 
2.20.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

  parent reply	other threads:[~2019-07-31 17:58 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-31 17:57 [PATCH 00/26] Further RAS enablement for vega20 Alex Deucher
     [not found] ` <20190731175818.20159-1-alexander.deucher-5C7GfCeVMHo@public.gmane.org>
2019-07-31 17:57   ` [PATCH 01/26] drm/amdgpu: move some ras data structure to amdgpu_ras.h Alex Deucher
2019-07-31 17:57   ` [PATCH 02/26] drm/amdgpu: init RSMU and UMC ip base address for vega20 Alex Deucher
2019-07-31 17:57   ` [PATCH 03/26] drm/amdgpu: add amdgpu_umc_functions structure Alex Deucher
2019-07-31 17:57   ` [PATCH 04/26] drm/amdgpu: add rsmu v_0_0_2 ip headers Alex Deucher
2019-07-31 17:57   ` [PATCH 05/26] drm/amdgpu: add umc v6_1_1 IP headers Alex Deucher
2019-07-31 17:57   ` [PATCH 06/26] drm/amdgpu: add umc v6_1 query error count support Alex Deucher
2019-07-31 17:57   ` [PATCH 07/26] drm/amdgpu: init umc v6_1 functions for vega20 Alex Deucher
2019-07-31 17:58   ` [PATCH 08/26] drm/amdgpu: querry umc error count Alex Deucher
2019-07-31 17:58   ` [PATCH 09/26] drm/amdgpu: add ras error count after each query (v2) Alex Deucher
2019-07-31 17:58   ` [PATCH 10/26] drm/amdgpu: add RREG64/WREG64(_PCIE) operations Alex Deucher
2019-07-31 17:58   ` [PATCH 11/26] drm/amdgpu: use 64bit operation macros for umc Alex Deucher
2019-07-31 17:58   ` [PATCH 12/26] drm/amdgpu: switch to amdgpu_umc structure Alex Deucher
2019-07-31 17:58   ` [PATCH 13/26] drm/amdgpu: update algorithm of umc uncorrectable error counting Alex Deucher
2019-07-31 17:58   ` [PATCH 14/26] drm/amdgpu: add support for recording ras error address Alex Deucher
2019-07-31 17:58   ` [PATCH 15/26] drm/amdgpu: add structures for umc error address translation Alex Deucher
2019-07-31 17:58   ` [PATCH 16/26] drm/amdgpu: query umc ras error address Alex Deucher
2019-07-31 17:58   ` Alex Deucher [this message]
2019-07-31 17:58   ` [PATCH 18/26] drm/amdgpu: update interrupt callback for all ras clients Alex Deucher
2019-07-31 17:58   ` [PATCH 19/26] drm/amdgpu: add check for ras error type Alex Deucher
2019-07-31 17:58   ` [PATCH 20/26] drm/amdgpu: remove ras_reserve_vram in ras injection Alex Deucher
2019-07-31 17:58   ` [PATCH 21/26] drm/amd/include: add bitfield define for EDC registers Alex Deucher
2019-07-31 17:58   ` [PATCH 22/26] drm/amd/include: add define of TCP_EDC_CNT_NEW Alex Deucher
2019-07-31 17:58   ` [PATCH 23/26] drm/amdgpu: add define for gfx ras subblock Alex Deucher
2019-07-31 17:58   ` [PATCH 24/26] drm/amdgpu: add RAS callback for gfx Alex Deucher
     [not found]     ` <20190731175818.20159-25-alexander.deucher-5C7GfCeVMHo@public.gmane.org>
2019-08-01  5:40       ` Kevin Wang
2019-07-31 17:58   ` [PATCH 25/26] drm/amdgpu: support gfx ras error injection and err_cnt query Alex Deucher
2019-07-31 17:58   ` [PATCH 26/26] drm/amdgpu: disable inject for failed subblocks of gfx Alex Deucher

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190731175818.20159-18-alexander.deucher@amd.com \
    --to=alexdeucher-re5jqeeqqe8avxtiumwx3w@public.gmane.org \
    --cc=Hawking.Zhang-5C7GfCeVMHo@public.gmane.org \
    --cc=amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW@public.gmane.org \
    --cc=dennis.li-5C7GfCeVMHo@public.gmane.org \
    --cc=tao.zhou1-5C7GfCeVMHo@public.gmane.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox