From: Felix Kuehling <felix.kuehling@amd.com>
To: Jonathan Kim <jonathan.kim@amd.com>,
amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Subject: Re: [PATCH 27/32] drm/amdkfd: add debug set flags operation
Date: Wed, 22 Mar 2023 17:47:36 -0400 [thread overview]
Message-ID: <9d75cfa7-47a7-320d-a209-2eac1d0b99c4@amd.com> (raw)
In-Reply-To: <20230125195401.4183544-28-jonathan.kim@amd.com>
Am 2023-01-25 um 14:53 schrieb Jonathan Kim:
> Allow the debugger to set single memory and single ALU operations.
>
> Some exceptions are imprecise (memory violations, address watch) in the
> sense that a trap occurs only when the exception interrupt occurs and
> not at the non-halting faulty instruction. Trap temporaries 0 & 1 save
> the program counter address, which means that these values will not point
> to the faulty instruction address but to whenever the interrupt was
> raised.
>
> Setting the Single Memory Operations flag will inject an automatic wait
> on every memory operation instruction forcing imprecise memory exceptions
> to become precise at the cost of performance. This setting is not
> permitted on debug devices that support only a global setting of this
> option.
>
> Return the previous set flags to the debugger as well.
>
> v3: make precise mem op the only available flag for now.
>
> v2: add gfx11 support.
>
> Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 ++
> drivers/gpu/drm/amd/amdkfd/kfd_debug.c | 38 ++++++++++++++++++++++++
> drivers/gpu/drm/amd/amdkfd/kfd_debug.h | 1 +
> 3 files changed, 41 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> index 8f2ede781863..c34caa14b84e 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> @@ -2947,6 +2947,8 @@ static int kfd_ioctl_set_debug_trap(struct file *filep, struct kfd_process *p, v
> args->clear_node_address_watch.id);
> break;
> case KFD_IOC_DBG_TRAP_SET_FLAGS:
> + r = kfd_dbg_trap_set_flags(target, &args->set_flags.flags);
> + break;
> case KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT:
> case KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO:
> case KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT:
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> index 8d2e1adb442d..77ba7da2bb9d 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
> @@ -23,6 +23,7 @@
> #include "kfd_debug.h"
> #include "kfd_device_queue_manager.h"
> #include <linux/file.h>
> +#include <uapi/linux/kfd_ioctl.h>
>
> #define MAX_WATCH_ADDRESSES 4
>
> @@ -425,6 +426,40 @@ static void kfd_dbg_clear_process_address_watch(struct kfd_process *target)
> kfd_dbg_trap_clear_dev_address_watch(target->pdds[i], j);
> }
>
> +int kfd_dbg_trap_set_flags(struct kfd_process *target, uint32_t *flags)
> +{
> + uint32_t prev_flags = target->dbg_flags;
> + int i, r = 0;
> +
> + for (i = 0; i < target->n_pdds; i++) {
> + if (!kfd_dbg_is_per_vmid_supported(target->pdds[i]->dev) &&
> + (*flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP)) {
> + *flags = prev_flags;
> + return -EACCES;
> + }
> + }
> +
> + target->dbg_flags = *flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP;
> + *flags = prev_flags;
> + for (i = 0; i < target->n_pdds; i++) {
> + struct kfd_process_device *pdd = target->pdds[i];
> +
> + if (!kfd_dbg_is_per_vmid_supported(pdd->dev))
> + continue;
> +
> + if (!pdd->dev->shared_resources.enable_mes)
> + r = debug_refresh_runlist(pdd->dev->dqm);
> + else
> + r = kfd_dbg_set_mes_debug_mode(pdd);
> +
> + if (r) {
> + target->dbg_flags = prev_flags;
> + break;
Do we need to roll back changes on the other GPUs when this happens?
> + }
> + }
> +
> + return r;
> +}
>
> /* kfd_dbg_trap_deactivate:
> * target: target process
> @@ -439,9 +474,12 @@ void kfd_dbg_trap_deactivate(struct kfd_process *target, bool unwind, int unwind
> int i, count = 0;
>
> if (!unwind) {
> + uint32_t flags = 0;
checkpatch.pl will complain without an empty line after the variable
declaration.
Regards,
Felix
> cancel_work_sync(&target->debug_event_workarea);
> kfd_dbg_clear_process_address_watch(target);
> kfd_dbg_trap_set_wave_launch_mode(target, 0);
> +
> + kfd_dbg_trap_set_flags(target, &flags);
> }
>
> for (i = 0; i < target->n_pdds; i++) {
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
> index 63c716ce5ab9..782362d82890 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
> @@ -57,6 +57,7 @@ int kfd_dbg_trap_set_dev_address_watch(struct kfd_process_device *pdd,
> uint32_t watch_address_mask,
> uint32_t *watch_id,
> uint32_t watch_mode);
> +int kfd_dbg_trap_set_flags(struct kfd_process *target, uint32_t *flags);
> int kfd_dbg_send_exception_to_runtime(struct kfd_process *p,
> unsigned int dev_id,
> unsigned int queue_id,
next prev parent reply other threads:[~2023-03-22 21:47 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-25 19:53 [PATCH 00/32] Upstream of kernel support for AMDGPU ISA debugging Jonathan Kim
2023-01-25 19:53 ` [PATCH 01/32] drm/amdkfd: add debug and runtime enable interface Jonathan Kim
2023-02-16 22:16 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 02/32] drm/amdkfd: display debug capabilities Jonathan Kim
2023-02-16 22:24 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 03/32] drm/amdkfd: prepare per-process debug enable and disable Jonathan Kim
2023-02-16 23:44 ` Felix Kuehling
2023-03-23 19:12 ` Kim, Jonathan
2023-03-23 20:08 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 04/32] drm/amdgpu: add kgd hw debug mode setting interface Jonathan Kim
2023-01-25 19:53 ` [PATCH 05/32] drm/amdgpu: setup hw debug registers on driver initialization Jonathan Kim
2023-02-16 22:39 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 06/32] drm/amdgpu: add gfx9 hw debug mode enable and disable calls Jonathan Kim
2023-01-29 5:12 ` kernel test robot
2023-02-16 22:54 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 07/32] drm/amdgpu: add gfx9.4.1 " Jonathan Kim
2023-01-29 6:34 ` kernel test robot
2023-02-16 23:01 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 08/32] drm/amdgpu: add gfx10 " Jonathan Kim
2023-01-29 7:55 ` kernel test robot
2023-02-16 23:11 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 09/32] drm/amdgpu: add gfx9.4.2 " Jonathan Kim
2023-02-16 23:14 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 10/32] drm/amdgpu: add gfx11 " Jonathan Kim
2023-02-16 23:19 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 11/32] drm/amdgpu: add configurable grace period for unmap queues Jonathan Kim
2023-03-20 19:19 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 12/32] drm/amdkfd: prepare map process for single process debug devices Jonathan Kim
2023-03-20 20:06 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 13/32] drm/amdgpu: prepare map process for multi-process " Jonathan Kim
2023-03-20 20:16 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 14/32] drm/amdgpu: expose debug api for mes Jonathan Kim
2023-03-20 20:47 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 15/32] drm/amdkfd: prepare trap workaround for gfx11 Jonathan Kim
2023-03-20 21:49 ` Felix Kuehling
2023-03-23 13:50 ` Kim, Jonathan
2023-03-23 14:00 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 16/32] drm/amdkfd: add per process hw trap enable and disable functions Jonathan Kim
2023-03-20 23:06 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 17/32] drm/amdkfd: add raise exception event function Jonathan Kim
2023-03-20 23:18 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 18/32] drm/amdkfd: add send exception operation Jonathan Kim
2023-03-20 23:26 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 19/32] drm/amdkfd: add runtime enable operation Jonathan Kim
2023-03-21 0:31 ` Felix Kuehling
2023-03-23 19:45 ` Kim, Jonathan
2023-01-25 19:53 ` [PATCH 20/32] drm/amdkfd: add debug trap enabled flag to tma Jonathan Kim
2023-01-25 19:53 ` [PATCH 21/32] drm/amdkfd: update process interrupt handling for debug events Jonathan Kim
2023-03-21 21:07 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 22/32] drm/amdkfd: add debug set exceptions enabled operation Jonathan Kim
2023-01-25 19:53 ` [PATCH 23/32] drm/amdkfd: add debug wave launch override operation Jonathan Kim
2023-03-21 21:37 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 24/32] drm/amdkfd: add debug wave launch mode operation Jonathan Kim
2023-03-21 21:42 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 25/32] drm/amdkfd: add debug suspend and resume process queues operation Jonathan Kim
2023-03-21 22:16 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 26/32] drm/amdkfd: add debug set and clear address watch points operation Jonathan Kim
2023-03-22 21:38 ` Felix Kuehling
2023-01-25 19:53 ` [PATCH 27/32] drm/amdkfd: add debug set flags operation Jonathan Kim
2023-03-22 21:47 ` Felix Kuehling [this message]
2023-01-25 19:53 ` [PATCH 28/32] drm/amdkfd: add debug query event operation Jonathan Kim
2023-01-25 19:53 ` [PATCH 29/32] drm/amdkfd: add debug query exception info operation Jonathan Kim
2023-01-25 19:53 ` [PATCH 30/32] drm/amdkfd: add debug queue snapshot operation Jonathan Kim
2023-03-22 21:52 ` Felix Kuehling
2023-01-25 19:54 ` [PATCH 31/32] drm/amdkfd: add debug device " Jonathan Kim
2023-03-22 21:54 ` Felix Kuehling
2023-01-25 19:54 ` [PATCH 32/32] drm/amdkfd: bump kfd ioctl minor version for debug api availability Jonathan Kim
2023-03-22 21:56 ` Felix Kuehling
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=9d75cfa7-47a7-320d-a209-2eac1d0b99c4@amd.com \
--to=felix.kuehling@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=jonathan.kim@amd.com \
/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