| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <bpfe3i2ffk3jcezkhdsbf2jlencdeevkqbtzi36wxgsg5jhiky@czttx7r2i7wh>
Date: Mon, 11 Aug 2025 13:21:20 +0100
From: Adrián Larumbe <adrian.larumbe@...labora.com>
To: Lukas Zapolskas <lukas.zapolskas@....com>
Cc: dri-devel@...ts.freedesktop.org, nd@....com,
Boris Brezillon <boris.brezillon@...labora.com>, Steven Price <steven.price@....com>,
Liviu Dudau <liviu.dudau@....com>, Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
Maxime Ripard <mripard@...nel.org>, Thomas Zimmermann <tzimmermann@...e.de>,
David Airlie <airlied@...il.com>, Simona Vetter <simona@...ll.ch>, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v5 2/7] drm/panthor: Add DEV_QUERY.PERF_INFO handling for
Gx10
Hi Lukas,
On 25.07.2025 15:57, Lukas Zapolskas wrote:
> This change adds the IOCTL to query data about the performance counter
> setup. Some of this data was available via previous DEV_QUERY calls,
> for instance for GPU info, but exposing it via PERF_INFO
> minimizes the overhead of creating a single session to just the one
> aggregate IOCTL.
>
> Signed-off-by: Lukas Zapolskas <lukas.zapolskas@....com>
> Reviewed-by: Adrián Larumbe <adrian.larumbe@...labora.com>
> ---
> drivers/gpu/drm/panthor/Makefile | 1 +
> drivers/gpu/drm/panthor/panthor_device.c | 7 +++
> drivers/gpu/drm/panthor/panthor_device.h | 3 +
> drivers/gpu/drm/panthor/panthor_drv.c | 10 ++-
> drivers/gpu/drm/panthor/panthor_fw.h | 3 +
> drivers/gpu/drm/panthor/panthor_perf.c | 77 ++++++++++++++++++++++++
> drivers/gpu/drm/panthor/panthor_perf.h | 15 +++++
> drivers/gpu/drm/panthor/panthor_regs.h | 1 +
> 8 files changed, 116 insertions(+), 1 deletion(-)
> create mode 100644 drivers/gpu/drm/panthor/panthor_perf.c
> create mode 100644 drivers/gpu/drm/panthor/panthor_perf.h
>
> diff --git a/drivers/gpu/drm/panthor/Makefile b/drivers/gpu/drm/panthor/Makefile
> index 15294719b09c..0df9947f3575 100644
> --- a/drivers/gpu/drm/panthor/Makefile
> +++ b/drivers/gpu/drm/panthor/Makefile
> @@ -9,6 +9,7 @@ panthor-y := \
> panthor_gpu.o \
> panthor_heap.o \
> panthor_mmu.o \
> + panthor_perf.o \
> panthor_sched.o
>
> obj-$(CONFIG_DRM_PANTHOR) += panthor.o
> diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
> index f0b2da5b2b96..15ab329722cc 100644
> --- a/drivers/gpu/drm/panthor/panthor_device.c
> +++ b/drivers/gpu/drm/panthor/panthor_device.c
> @@ -19,6 +19,7 @@
> #include "panthor_fw.h"
> #include "panthor_gpu.h"
> #include "panthor_mmu.h"
> +#include "panthor_perf.h"
> #include "panthor_regs.h"
> #include "panthor_sched.h"
>
> @@ -264,6 +265,10 @@ int panthor_device_init(struct panthor_device *ptdev)
> if (ret)
> goto err_unplug_fw;
>
> + ret = panthor_perf_init(ptdev);
> + if (ret)
> + goto err_unplug_sched;
> +
> /* ~3 frames */
> pm_runtime_set_autosuspend_delay(ptdev->base.dev, 50);
> pm_runtime_use_autosuspend(ptdev->base.dev);
> @@ -277,6 +282,8 @@ int panthor_device_init(struct panthor_device *ptdev)
>
> err_disable_autosuspend:
> pm_runtime_dont_use_autosuspend(ptdev->base.dev);
> +
> +err_unplug_sched:
> panthor_sched_unplug(ptdev);
>
> err_unplug_fw:
> diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
> index 4fc7cf2aeed5..720d39b9e783 100644
> --- a/drivers/gpu/drm/panthor/panthor_device.h
> +++ b/drivers/gpu/drm/panthor/panthor_device.h
> @@ -120,6 +120,9 @@ struct panthor_device {
> /** @csif_info: Command stream interface information. */
> struct drm_panthor_csif_info csif_info;
>
> + /** @perf_info: Performance counter interface information. */
> + struct drm_panthor_perf_info perf_info;
> +
> /** @gpu: GPU management data. */
> struct panthor_gpu *gpu;
>
> diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
> index 9256806eb662..8b1e3e38b12e 100644
> --- a/drivers/gpu/drm/panthor/panthor_drv.c
> +++ b/drivers/gpu/drm/panthor/panthor_drv.c
> @@ -175,7 +175,8 @@ panthor_get_uobj_array(const struct drm_panthor_obj_array *in, u32 min_stride,
> PANTHOR_UOBJ_DECL(struct drm_panthor_sync_op, timeline_value), \
> PANTHOR_UOBJ_DECL(struct drm_panthor_queue_submit, syncs), \
> PANTHOR_UOBJ_DECL(struct drm_panthor_queue_create, ringbuf_size), \
> - PANTHOR_UOBJ_DECL(struct drm_panthor_vm_bind_op, syncs))
> + PANTHOR_UOBJ_DECL(struct drm_panthor_vm_bind_op, syncs), \
> + PANTHOR_UOBJ_DECL(struct drm_panthor_perf_info, shader_blocks))
>
> /**
> * PANTHOR_UOBJ_SET() - Copy a kernel object to a user object.
> @@ -835,6 +836,10 @@ static int panthor_ioctl_dev_query(struct drm_device *ddev, void *data, struct d
> args->size = sizeof(priorities_info);
> return 0;
>
> + case DRM_PANTHOR_DEV_QUERY_PERF_INFO:
> + args->size = sizeof(ptdev->perf_info);
> + return 0;
> +
> default:
> return -EINVAL;
> }
> @@ -859,6 +864,9 @@ static int panthor_ioctl_dev_query(struct drm_device *ddev, void *data, struct d
> panthor_query_group_priorities_info(file, &priorities_info);
> return PANTHOR_UOBJ_SET(args->pointer, args->size, priorities_info);
>
> + case DRM_PANTHOR_DEV_QUERY_PERF_INFO:
> + return PANTHOR_UOBJ_SET(args->pointer, args->size, ptdev->perf_info);
> +
> default:
> return -EINVAL;
> }
> diff --git a/drivers/gpu/drm/panthor/panthor_fw.h b/drivers/gpu/drm/panthor/panthor_fw.h
> index 6598d96c6d2a..8bcb933fa790 100644
> --- a/drivers/gpu/drm/panthor/panthor_fw.h
> +++ b/drivers/gpu/drm/panthor/panthor_fw.h
> @@ -197,8 +197,11 @@ struct panthor_fw_global_control_iface {
> u32 output_va;
> u32 group_num;
> u32 group_stride;
> +#define GLB_PERFCNT_FW_SIZE(x) ((((x) >> 16) << 8))
> u32 perfcnt_size;
> u32 instr_features;
> +#define PERFCNT_FEATURES_MD_SIZE(x) (((x) & GENMASK(3, 0)) << 8)
> + u32 perfcnt_features;
> };
>
> struct panthor_fw_global_input_iface {
> diff --git a/drivers/gpu/drm/panthor/panthor_perf.c b/drivers/gpu/drm/panthor/panthor_perf.c
> new file mode 100644
> index 000000000000..e58a62ad7988
> --- /dev/null
> +++ b/drivers/gpu/drm/panthor/panthor_perf.c
> @@ -0,0 +1,77 @@
> +// SPDX-License-Identifier: GPL-2.0 or MIT
> +/* Copyright 2023 Collabora Ltd */
> +/* Copyright 2025 Arm ltd. */
> +
> +#include <linux/bitops.h>
> +#include <drm/panthor_drm.h>
> +
> +#include "panthor_device.h"
> +#include "panthor_fw.h"
> +#include "panthor_perf.h"
> +#include "panthor_regs.h"
> +
> +struct panthor_perf_counter_block {
> + struct drm_panthor_perf_block_header header;
> + u64 counters[];
> +};
> +
> +static size_t get_annotated_block_size(size_t counters_per_block)
> +{
> + return struct_size_t(struct panthor_perf_counter_block, counters, counters_per_block);
> +}
> +
> +static size_t session_get_user_sample_size(const struct drm_panthor_perf_info *const info)
> +{
> + const size_t block_size = get_annotated_block_size(info->counters_per_block);
> + const size_t block_nr = info->cshw_blocks + info->fw_blocks +
> + info->tiler_blocks + info->memsys_blocks + info->shader_blocks;
> +
> + return info->sample_header_size + (block_size * block_nr);
> +}
> +
> +/**
> + * PANTHOR_PERF_COUNTERS_PER_BLOCK - On CSF architectures pre-11.x, the number of counters
> + * per block was hardcoded to be 64. Arch 11.0 onwards supports the PRFCNT_FEATURES GPU register,
> + * which indicates the same information.
> + */
> +#define PANTHOR_PERF_COUNTERS_PER_BLOCK (64)
> +
> +static void panthor_perf_info_init(struct panthor_device *const ptdev)
> +{
> + struct panthor_fw_global_iface *glb_iface = panthor_fw_get_glb_iface(ptdev);
> + struct drm_panthor_perf_info *const perf_info = &ptdev->perf_info;
> +
> + if (PERFCNT_FEATURES_MD_SIZE(glb_iface->control->perfcnt_features))
> + perf_info->flags |= DRM_PANTHOR_PERF_BLOCK_STATES_SUPPORT;
> +
> + perf_info->counters_per_block = PANTHOR_PERF_COUNTERS_PER_BLOCK;
I might've mentioned this in a previous review, but maybe we could add PRFCNT_FEATURES register
access in this commit, and both ways of retrieving the number of counters per block depending
in the CSF firmware version?
Other than that:
Reviewed-by: Adrián Larumbe <adrian.larumbe@...labora.com>
> +
> + perf_info->sample_header_size = sizeof(struct drm_panthor_perf_sample_header);
> + perf_info->block_header_size = sizeof(struct drm_panthor_perf_block_header);
> +
> + if (GLB_PERFCNT_FW_SIZE(glb_iface->control->perfcnt_size))
> + perf_info->fw_blocks = 1;
> +
> + perf_info->cshw_blocks = 1;
> + perf_info->tiler_blocks = 1;
> + perf_info->memsys_blocks = GPU_MEM_FEATURES_L2_SLICES(ptdev->gpu_info.mem_features);
> + perf_info->shader_blocks = hweight64(ptdev->gpu_info.shader_present);
> +
> + perf_info->sample_size = session_get_user_sample_size(perf_info);
> +}
> +
> +/**
> + * panthor_perf_init - Initialize the performance counter subsystem.
> + * @ptdev: Panthor device
> + *
> + * Return: 0 on success, negative error code on failure.
> + */
> +int panthor_perf_init(struct panthor_device *ptdev)
> +{
> + if (!ptdev)
> + return -EINVAL;
> +
> + panthor_perf_info_init(ptdev);
> +
> + return 0;
> +}
> diff --git a/drivers/gpu/drm/panthor/panthor_perf.h b/drivers/gpu/drm/panthor/panthor_perf.h
> new file mode 100644
> index 000000000000..3c32c24c164c
> --- /dev/null
> +++ b/drivers/gpu/drm/panthor/panthor_perf.h
> @@ -0,0 +1,15 @@
> +/* SPDX-License-Identifier: GPL-2.0 or MIT */
> +/* Copyright 2025 Collabora Ltd */
> +/* Copyright 2025 Arm ltd. */
> +
> +#ifndef __PANTHOR_PERF_H__
> +#define __PANTHOR_PERF_H__
> +
> +#include <linux/types.h>
> +
> +struct panthor_device;
> +
> +int panthor_perf_init(struct panthor_device *ptdev);
> +
> +#endif /* __PANTHOR_PERF_H__ */
> +
> diff --git a/drivers/gpu/drm/panthor/panthor_regs.h b/drivers/gpu/drm/panthor/panthor_regs.h
> index 48bbfd40138c..d613ce723981 100644
> --- a/drivers/gpu/drm/panthor/panthor_regs.h
> +++ b/drivers/gpu/drm/panthor/panthor_regs.h
> @@ -27,6 +27,7 @@
> #define GPU_TILER_FEATURES 0xC
> #define GPU_MEM_FEATURES 0x10
> #define GROUPS_L2_COHERENT BIT(0)
> +#define GPU_MEM_FEATURES_L2_SLICES(x) ((((x) & GENMASK(11, 8)) >> 8) + 1)
>
> #define GPU_MMU_FEATURES 0x14
> #define GPU_MMU_FEATURES_VA_BITS(x) ((x) & GENMASK(7, 0))
> --
> 2.33.0.dirty
Powered by blists - more mailing lists