Hi, On 11/03/2024 10:06, Maíra Canal wrote:
Create a separate "tmpfs" kernel mount for V3D. This will allow us to move away from the shmemfs `shm_mnt` and gives the flexibility to do things like set our own mount options. Here, the interest is to use "huge=", which should allow us to enable the use of THP for our shmem-backed objects. Signed-off-by: Maíra Canal <mcanal@xxxxxxxxxx> --- drivers/gpu/drm/v3d/Makefile | 3 ++- drivers/gpu/drm/v3d/v3d_drv.h | 9 +++++++ drivers/gpu/drm/v3d/v3d_gem.c | 3 +++ drivers/gpu/drm/v3d/v3d_gemfs.c | 46 +++++++++++++++++++++++++++++++++ 4 files changed, 60 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/v3d/v3d_gemfs.c diff --git a/drivers/gpu/drm/v3d/Makefile b/drivers/gpu/drm/v3d/Makefile index b7d673f1153b..fcf710926057 100644 --- a/drivers/gpu/drm/v3d/Makefile +++ b/drivers/gpu/drm/v3d/Makefile @@ -13,7 +13,8 @@ v3d-y := \ v3d_trace_points.o \ v3d_sched.o \ v3d_sysfs.o \ - v3d_submit.o + v3d_submit.o \ + v3d_gemfs.o v3d-$(CONFIG_DEBUG_FS) += v3d_debugfs.o diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 1950c723dde1..d2ce8222771a 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -119,6 +119,11 @@ struct v3d_dev { struct drm_mm mm; spinlock_t mm_lock; + /* + * tmpfs instance used for shmem backed objects + */ + struct vfsmount *gemfs; + struct work_struct overflow_mem_work; struct v3d_bin_job *bin_job; @@ -519,6 +524,10 @@ void v3d_reset(struct v3d_dev *v3d); void v3d_invalidate_caches(struct v3d_dev *v3d); void v3d_clean_caches(struct v3d_dev *v3d); +/* v3d_gemfs.c */ +void v3d_gemfs_init(struct v3d_dev *v3d); +void v3d_gemfs_fini(struct v3d_dev *v3d); + /* v3d_submit.c */ void v3d_job_cleanup(struct v3d_job *job); void v3d_job_put(struct v3d_job *job); diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 66f4b78a6b2e..faefbe497e8d 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -287,6 +287,8 @@ v3d_gem_init(struct drm_device *dev) v3d_init_hw_state(v3d); v3d_mmu_set_page_table(v3d); + v3d_gemfs_init(v3d); + ret = v3d_sched_init(v3d); if (ret) { drm_mm_takedown(&v3d->mm); @@ -304,6 +306,7 @@ v3d_gem_destroy(struct drm_device *dev) struct v3d_dev *v3d = to_v3d_dev(dev); v3d_sched_fini(v3d); + v3d_gemfs_fini(v3d); /* Waiting for jobs to finish would need to be done before * unregistering V3D. diff --git a/drivers/gpu/drm/v3d/v3d_gemfs.c b/drivers/gpu/drm/v3d/v3d_gemfs.c new file mode 100644 index 000000000000..8518b7da6f73 --- /dev/null +++ b/drivers/gpu/drm/v3d/v3d_gemfs.c @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (C) 2024 Raspberry Pi */ + +#include <linux/fs.h> +#include <linux/mount.h> + +#include "v3d_drv.h" + +void v3d_gemfs_init(struct v3d_dev *v3d) +{ + char huge_opt[] = "huge=always";
Using 'always' and not 'within_size' is deliberate? It can waste memory but indeed could be best for performance. I am just asking and perhaps I missed some prior discussion on this.
Regards, Tvrtko
+ struct file_system_type *type; + struct vfsmount *gemfs; + + /* + * By creating our own shmemfs mountpoint, we can pass in + * mount flags that better match our usecase. However, we + * only do so on platforms which benefit from it. + */ + if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) + goto err; + + type = get_fs_type("tmpfs"); + if (!type) + goto err; + + gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, huge_opt); + if (IS_ERR(gemfs)) + goto err; + + v3d->gemfs = gemfs; + drm_info(&v3d->drm, "Using Transparent Hugepages\n"); + + return; + +err: + v3d->gemfs = NULL; + drm_notice(&v3d->drm, + "Transparent Hugepage support is recommended for optimal performance on this platform!\n"); +} + +void v3d_gemfs_fini(struct v3d_dev *v3d) +{ + if (v3d->gemfs) + kern_unmount(v3d->gemfs); +} -- 2.43.0