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>
144 lines
4.2 KiB
C
144 lines
4.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 OR MIT */
|
|
/**************************************************************************
|
|
*
|
|
* Copyright 2021 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 <linux/vmalloc.h>
|
|
#include "vmwgfx_devcaps.h"
|
|
|
|
#include "vmwgfx_drv.h"
|
|
|
|
|
|
struct svga_3d_compat_cap {
|
|
SVGA3dFifoCapsRecordHeader header;
|
|
SVGA3dFifoCapPair pairs[SVGA3D_DEVCAP_MAX];
|
|
};
|
|
|
|
|
|
static u32 vmw_mask_legacy_multisample(unsigned int cap, u32 fmt_value)
|
|
{
|
|
/*
|
|
* A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES
|
|
* to check the sample count supported by virtual device. Since there
|
|
* never was support for multisample count for backing MOB return 0.
|
|
*
|
|
* MULTISAMPLE_MASKABLESAMPLES devcap is marked as deprecated by virtual
|
|
* device.
|
|
*/
|
|
if (cap == SVGA3D_DEVCAP_DEAD5)
|
|
return 0;
|
|
|
|
return fmt_value;
|
|
}
|
|
|
|
static int vmw_fill_compat_cap(struct vmw_private *dev_priv, void *bounce,
|
|
size_t size)
|
|
{
|
|
struct svga_3d_compat_cap *compat_cap =
|
|
(struct svga_3d_compat_cap *) bounce;
|
|
unsigned int i;
|
|
size_t pair_offset = offsetof(struct svga_3d_compat_cap, pairs);
|
|
unsigned int max_size;
|
|
|
|
if (size < pair_offset)
|
|
return -EINVAL;
|
|
|
|
max_size = (size - pair_offset) / sizeof(SVGA3dFifoCapPair);
|
|
|
|
if (max_size > SVGA3D_DEVCAP_MAX)
|
|
max_size = SVGA3D_DEVCAP_MAX;
|
|
|
|
compat_cap->header.length =
|
|
(pair_offset + max_size * sizeof(SVGA3dFifoCapPair)) / sizeof(u32);
|
|
compat_cap->header.type = SVGA3D_FIFO_CAPS_RECORD_DEVCAPS;
|
|
|
|
for (i = 0; i < max_size; ++i) {
|
|
compat_cap->pairs[i][0] = i;
|
|
compat_cap->pairs[i][1] = vmw_mask_legacy_multisample
|
|
(i, dev_priv->devcaps[i]);
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
int vmw_devcaps_create(struct vmw_private *vmw)
|
|
{
|
|
bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
|
|
uint32_t i;
|
|
|
|
if (gb_objects) {
|
|
vmw->devcaps = vzalloc(sizeof(uint32_t) * SVGA3D_DEVCAP_MAX);
|
|
if (!vmw->devcaps)
|
|
return -ENOMEM;
|
|
for (i = 0; i < SVGA3D_DEVCAP_MAX; ++i) {
|
|
vmw_write(vmw, SVGA_REG_DEV_CAP, i);
|
|
vmw->devcaps[i] = vmw_read(vmw, SVGA_REG_DEV_CAP);
|
|
}
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void vmw_devcaps_destroy(struct vmw_private *vmw)
|
|
{
|
|
vfree(vmw->devcaps);
|
|
vmw->devcaps = NULL;
|
|
}
|
|
|
|
|
|
uint32 vmw_devcaps_size(const struct vmw_private *vmw,
|
|
bool gb_aware)
|
|
{
|
|
bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
|
|
if (gb_objects && gb_aware)
|
|
return SVGA3D_DEVCAP_MAX * sizeof(uint32_t);
|
|
else if (gb_objects)
|
|
return sizeof(struct svga_3d_compat_cap) +
|
|
sizeof(uint32_t);
|
|
else if (vmw->fifo_mem != NULL)
|
|
return (SVGA_FIFO_3D_CAPS_LAST - SVGA_FIFO_3D_CAPS + 1) *
|
|
sizeof(uint32_t);
|
|
else
|
|
return 0;
|
|
}
|
|
|
|
int vmw_devcaps_copy(struct vmw_private *vmw, bool gb_aware,
|
|
void *dst, uint32_t dst_size)
|
|
{
|
|
int ret;
|
|
bool gb_objects = !!(vmw->capabilities & SVGA_CAP_GBOBJECTS);
|
|
if (gb_objects && gb_aware) {
|
|
memcpy(dst, vmw->devcaps, dst_size);
|
|
} else if (gb_objects) {
|
|
ret = vmw_fill_compat_cap(vmw, dst, dst_size);
|
|
if (unlikely(ret != 0))
|
|
return ret;
|
|
} else if (vmw->fifo_mem) {
|
|
u32 *fifo_mem = vmw->fifo_mem;
|
|
memcpy(dst, &fifo_mem[SVGA_FIFO_3D_CAPS], dst_size);
|
|
} else
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|