1
0
Fork 0
mirror of synced 2025-03-06 20:59:54 +01:00
linux/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
Kent Overstreet 0069455bcb fix missing vmalloc.h includes
Patch series "Memory allocation profiling", v6.

Overview:
Low overhead [1] per-callsite memory allocation profiling. Not just for
debug kernels, overhead low enough to be deployed in production.

Example output:
  root@moria-kvm:~# sort -rn /proc/allocinfo
   127664128    31168 mm/page_ext.c:270 func:alloc_page_ext
    56373248     4737 mm/slub.c:2259 func:alloc_slab_page
    14880768     3633 mm/readahead.c:247 func:page_cache_ra_unbounded
    14417920     3520 mm/mm_init.c:2530 func:alloc_large_system_hash
    13377536      234 block/blk-mq.c:3421 func:blk_mq_alloc_rqs
    11718656     2861 mm/filemap.c:1919 func:__filemap_get_folio
     9192960     2800 kernel/fork.c:307 func:alloc_thread_stack_node
     4206592        4 net/netfilter/nf_conntrack_core.c:2567 func:nf_ct_alloc_hashtable
     4136960     1010 drivers/staging/ctagmod/ctagmod.c:20 [ctagmod] func:ctagmod_start
     3940352      962 mm/memory.c:4214 func:alloc_anon_folio
     2894464    22613 fs/kernfs/dir.c:615 func:__kernfs_new_node
     ...

Usage:
kconfig options:
 - CONFIG_MEM_ALLOC_PROFILING
 - CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT
 - CONFIG_MEM_ALLOC_PROFILING_DEBUG
   adds warnings for allocations that weren't accounted because of a
   missing annotation

sysctl:
  /proc/sys/vm/mem_profiling

Runtime info:
  /proc/allocinfo

Notes:

[1]: Overhead
To measure the overhead we are comparing the following configurations:
(1) Baseline with CONFIG_MEMCG_KMEM=n
(2) Disabled by default (CONFIG_MEM_ALLOC_PROFILING=y &&
    CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=n)
(3) Enabled by default (CONFIG_MEM_ALLOC_PROFILING=y &&
    CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=y)
(4) Enabled at runtime (CONFIG_MEM_ALLOC_PROFILING=y &&
    CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=n && /proc/sys/vm/mem_profiling=1)
(5) Baseline with CONFIG_MEMCG_KMEM=y && allocating with __GFP_ACCOUNT
(6) Disabled by default (CONFIG_MEM_ALLOC_PROFILING=y &&
    CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=n)  && CONFIG_MEMCG_KMEM=y
(7) Enabled by default (CONFIG_MEM_ALLOC_PROFILING=y &&
    CONFIG_MEM_ALLOC_PROFILING_BY_DEFAULT=y) && CONFIG_MEMCG_KMEM=y

Performance overhead:
To evaluate performance we implemented an in-kernel test executing
multiple get_free_page/free_page and kmalloc/kfree calls with allocation
sizes growing from 8 to 240 bytes with CPU frequency set to max and CPU
affinity set to a specific CPU to minimize the noise. Below are results
from running the test on Ubuntu 22.04.2 LTS with 6.8.0-rc1 kernel on
56 core Intel Xeon:

                        kmalloc                 pgalloc
(1 baseline)            6.764s                  16.902s
(2 default disabled)    6.793s  (+0.43%)        17.007s (+0.62%)
(3 default enabled)     7.197s  (+6.40%)        23.666s (+40.02%)
(4 runtime enabled)     7.405s  (+9.48%)        23.901s (+41.41%)
(5 memcg)               13.388s (+97.94%)       48.460s (+186.71%)
(6 def disabled+memcg)  13.332s (+97.10%)       48.105s (+184.61%)
(7 def enabled+memcg)   13.446s (+98.78%)       54.963s (+225.18%)

Memory overhead:
Kernel size:

   text           data        bss         dec         diff
(1) 26515311	      18890222    17018880    62424413
(2) 26524728	      19423818    16740352    62688898    264485
(3) 26524724	      19423818    16740352    62688894    264481
(4) 26524728	      19423818    16740352    62688898    264485
(5) 26541782	      18964374    16957440    62463596    39183

Memory consumption on a 56 core Intel CPU with 125GB of memory:
Code tags:           192 kB
PageExts:         262144 kB (256MB)
SlabExts:           9876 kB (9.6MB)
PcpuExts:            512 kB (0.5MB)

Total overhead is 0.2% of total memory.

Benchmarks:

Hackbench tests run 100 times:
hackbench -s 512 -l 200 -g 15 -f 25 -P
      baseline       disabled profiling           enabled profiling
avg   0.3543         0.3559 (+0.0016)             0.3566 (+0.0023)
stdev 0.0137         0.0188                       0.0077


hackbench -l 10000
      baseline       disabled profiling           enabled profiling
avg   6.4218         6.4306 (+0.0088)             6.5077 (+0.0859)
stdev 0.0933         0.0286                       0.0489

stress-ng tests:
stress-ng --class memory --seq 4 -t 60
stress-ng --class cpu --seq 4 -t 60
Results posted at: https://evilpiepirate.org/~kent/memalloc_prof_v4_stress-ng/

[2] https://lore.kernel.org/all/20240306182440.2003814-1-surenb@google.com/


This patch (of 37):

The next patch drops vmalloc.h from a system header in order to fix a
circular dependency; this adds it to all the files that were pulling it in
implicitly.

[kent.overstreet@linux.dev: fix arch/alpha/lib/memcpy.c]
  Link: https://lkml.kernel.org/r/20240327002152.3339937-1-kent.overstreet@linux.dev
[surenb@google.com: fix arch/x86/mm/numa_32.c]
  Link: https://lkml.kernel.org/r/20240402180933.1663992-1-surenb@google.com
[kent.overstreet@linux.dev: a few places were depending on sizes.h]
  Link: https://lkml.kernel.org/r/20240404034744.1664840-1-kent.overstreet@linux.dev
[arnd@arndb.de: fix mm/kasan/hw_tags.c]
  Link: https://lkml.kernel.org/r/20240404124435.3121534-1-arnd@kernel.org
[surenb@google.com: fix arc build]
  Link: https://lkml.kernel.org/r/20240405225115.431056-1-surenb@google.com
Link: https://lkml.kernel.org/r/20240321163705.3067592-1-surenb@google.com
Link: https://lkml.kernel.org/r/20240321163705.3067592-2-surenb@google.com
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alex Gaynor <alex.gaynor@gmail.com>
Cc: Alice Ryhl <aliceryhl@google.com>
Cc: Andreas Hindborg <a.hindborg@samsung.com>
Cc: Benno Lossin <benno.lossin@proton.me>
Cc: "Björn Roy Baron" <bjorn3_gh@protonmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Gary Guo <gary@garyguo.net>
Cc: Miguel Ojeda <ojeda@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wedson Almeida Filho <wedsonaf@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-04-25 20:55:49 -07:00

318 lines
8.6 KiB
C

// SPDX-License-Identifier: GPL-2.0 OR MIT
/**************************************************************************
*
* Copyright 2009-2022 VMware, Inc., Palo Alto, CA., USA
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the
* "Software"), to deal in the Software without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sub license, and/or sell copies of the Software, and to
* permit persons to whom the Software is furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice (including the
* next paragraph) shall be included in all copies or substantial portions
* of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
* THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
* DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
* OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
* USE OR OTHER DEALINGS IN THE SOFTWARE.
*
**************************************************************************/
#include "vmwgfx_drv.h"
#include "vmwgfx_devcaps.h"
#include "vmwgfx_kms.h"
#include <drm/vmwgfx_drm.h>
#include <linux/pci.h>
#include <linux/vmalloc.h>
int vmw_getparam_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct vmw_private *dev_priv = vmw_priv(dev);
struct drm_vmw_getparam_arg *param =
(struct drm_vmw_getparam_arg *)data;
struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
switch (param->param) {
case DRM_VMW_PARAM_NUM_STREAMS:
param->value = vmw_overlay_num_overlays(dev_priv);
break;
case DRM_VMW_PARAM_NUM_FREE_STREAMS:
param->value = vmw_overlay_num_free_overlays(dev_priv);
break;
case DRM_VMW_PARAM_3D:
param->value = vmw_supports_3d(dev_priv) ? 1 : 0;
break;
case DRM_VMW_PARAM_HW_CAPS:
param->value = dev_priv->capabilities;
break;
case DRM_VMW_PARAM_HW_CAPS2:
param->value = dev_priv->capabilities2;
break;
case DRM_VMW_PARAM_FIFO_CAPS:
param->value = vmw_fifo_caps(dev_priv);
break;
case DRM_VMW_PARAM_MAX_FB_SIZE:
param->value = dev_priv->max_primary_mem;
break;
case DRM_VMW_PARAM_FIFO_HW_VERSION:
{
if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS))
param->value = SVGA3D_HWVERSION_WS8_B1;
else
param->value = vmw_fifo_mem_read(
dev_priv,
((vmw_fifo_caps(dev_priv) &
SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ?
SVGA_FIFO_3D_HWVERSION_REVISED :
SVGA_FIFO_3D_HWVERSION));
break;
}
case DRM_VMW_PARAM_MAX_SURF_MEMORY:
if ((dev_priv->capabilities & SVGA_CAP_GBOBJECTS) &&
!vmw_fp->gb_aware)
param->value = dev_priv->max_mob_pages * PAGE_SIZE / 2;
else
param->value = dev_priv->memory_size;
break;
case DRM_VMW_PARAM_3D_CAPS_SIZE:
param->value = vmw_devcaps_size(dev_priv, vmw_fp->gb_aware);
break;
case DRM_VMW_PARAM_MAX_MOB_MEMORY:
vmw_fp->gb_aware = true;
param->value = dev_priv->max_mob_pages * PAGE_SIZE;
break;
case DRM_VMW_PARAM_MAX_MOB_SIZE:
param->value = dev_priv->max_mob_size;
break;
case DRM_VMW_PARAM_SCREEN_TARGET:
param->value =
(dev_priv->active_display_unit == vmw_du_screen_target);
break;
case DRM_VMW_PARAM_DX:
param->value = has_sm4_context(dev_priv);
break;
case DRM_VMW_PARAM_SM4_1:
param->value = has_sm4_1_context(dev_priv);
break;
case DRM_VMW_PARAM_SM5:
param->value = has_sm5_context(dev_priv);
break;
case DRM_VMW_PARAM_GL43:
param->value = has_gl43_context(dev_priv);
break;
case DRM_VMW_PARAM_DEVICE_ID:
param->value = to_pci_dev(dev_priv->drm.dev)->device;
break;
default:
return -EINVAL;
}
return 0;
}
int vmw_get_cap_3d_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct drm_vmw_get_3d_cap_arg *arg =
(struct drm_vmw_get_3d_cap_arg *) data;
struct vmw_private *dev_priv = vmw_priv(dev);
uint32_t size;
void __user *buffer = (void __user *)((unsigned long)(arg->buffer));
void *bounce = NULL;
int ret;
struct vmw_fpriv *vmw_fp = vmw_fpriv(file_priv);
if (unlikely(arg->pad64 != 0 || arg->max_size == 0)) {
VMW_DEBUG_USER("Illegal GET_3D_CAP argument.\n");
return -EINVAL;
}
size = vmw_devcaps_size(dev_priv, vmw_fp->gb_aware);
if (unlikely(size == 0)) {
DRM_ERROR("Failed to figure out the devcaps size (no 3D).\n");
return -ENOMEM;
}
if (arg->max_size < size)
size = arg->max_size;
bounce = vzalloc(size);
if (unlikely(bounce == NULL)) {
DRM_ERROR("Failed to allocate bounce buffer for 3D caps.\n");
return -ENOMEM;
}
ret = vmw_devcaps_copy(dev_priv, vmw_fp->gb_aware, bounce, size);
if (unlikely (ret != 0))
goto out_err;
ret = copy_to_user(buffer, bounce, size);
if (ret)
ret = -EFAULT;
out_err:
vfree(bounce);
if (unlikely(ret != 0))
DRM_ERROR("Failed to report 3D caps info.\n");
return ret;
}
int vmw_present_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
struct vmw_private *dev_priv = vmw_priv(dev);
struct drm_vmw_present_arg *arg =
(struct drm_vmw_present_arg *)data;
struct vmw_surface *surface;
struct drm_vmw_rect __user *clips_ptr;
struct drm_vmw_rect *clips = NULL;
struct drm_framebuffer *fb;
struct vmw_framebuffer *vfb;
struct vmw_resource *res;
uint32_t num_clips;
int ret;
num_clips = arg->num_clips;
clips_ptr = (struct drm_vmw_rect __user *)(unsigned long)arg->clips_ptr;
if (unlikely(num_clips == 0))
return 0;
if (clips_ptr == NULL) {
VMW_DEBUG_USER("Variable clips_ptr must be specified.\n");
ret = -EINVAL;
goto out_clips;
}
clips = kcalloc(num_clips, sizeof(*clips), GFP_KERNEL);
if (clips == NULL) {
DRM_ERROR("Failed to allocate clip rect list.\n");
ret = -ENOMEM;
goto out_clips;
}
ret = copy_from_user(clips, clips_ptr, num_clips * sizeof(*clips));
if (ret) {
DRM_ERROR("Failed to copy clip rects from userspace.\n");
ret = -EFAULT;
goto out_no_copy;
}
drm_modeset_lock_all(dev);
fb = drm_framebuffer_lookup(dev, file_priv, arg->fb_id);
if (!fb) {
VMW_DEBUG_USER("Invalid framebuffer id.\n");
ret = -ENOENT;
goto out_no_fb;
}
vfb = vmw_framebuffer_to_vfb(fb);
ret = vmw_user_resource_lookup_handle(dev_priv, tfile, arg->sid,
user_surface_converter,
&res);
if (ret)
goto out_no_surface;
surface = vmw_res_to_srf(res);
ret = vmw_kms_present(dev_priv, file_priv,
vfb, surface, arg->sid,
arg->dest_x, arg->dest_y,
clips, num_clips);
/* vmw_user_surface_lookup takes one ref so does new_fb */
vmw_surface_unreference(&surface);
out_no_surface:
drm_framebuffer_put(fb);
out_no_fb:
drm_modeset_unlock_all(dev);
out_no_copy:
kfree(clips);
out_clips:
return ret;
}
int vmw_present_readback_ioctl(struct drm_device *dev, void *data,
struct drm_file *file_priv)
{
struct vmw_private *dev_priv = vmw_priv(dev);
struct drm_vmw_present_readback_arg *arg =
(struct drm_vmw_present_readback_arg *)data;
struct drm_vmw_fence_rep __user *user_fence_rep =
(struct drm_vmw_fence_rep __user *)
(unsigned long)arg->fence_rep;
struct drm_vmw_rect __user *clips_ptr;
struct drm_vmw_rect *clips = NULL;
struct drm_framebuffer *fb;
struct vmw_framebuffer *vfb;
uint32_t num_clips;
int ret;
num_clips = arg->num_clips;
clips_ptr = (struct drm_vmw_rect __user *)(unsigned long)arg->clips_ptr;
if (unlikely(num_clips == 0))
return 0;
if (clips_ptr == NULL) {
VMW_DEBUG_USER("Argument clips_ptr must be specified.\n");
ret = -EINVAL;
goto out_clips;
}
clips = kcalloc(num_clips, sizeof(*clips), GFP_KERNEL);
if (clips == NULL) {
DRM_ERROR("Failed to allocate clip rect list.\n");
ret = -ENOMEM;
goto out_clips;
}
ret = copy_from_user(clips, clips_ptr, num_clips * sizeof(*clips));
if (ret) {
DRM_ERROR("Failed to copy clip rects from userspace.\n");
ret = -EFAULT;
goto out_no_copy;
}
drm_modeset_lock_all(dev);
fb = drm_framebuffer_lookup(dev, file_priv, arg->fb_id);
if (!fb) {
VMW_DEBUG_USER("Invalid framebuffer id.\n");
ret = -ENOENT;
goto out_no_fb;
}
vfb = vmw_framebuffer_to_vfb(fb);
if (!vfb->bo) {
VMW_DEBUG_USER("Framebuffer not buffer backed.\n");
ret = -EINVAL;
goto out_no_ttm_lock;
}
ret = vmw_kms_readback(dev_priv, file_priv,
vfb, user_fence_rep,
clips, num_clips);
out_no_ttm_lock:
drm_framebuffer_put(fb);
out_no_fb:
drm_modeset_unlock_all(dev);
out_no_copy:
kfree(clips);
out_clips:
return ret;
}