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>
323 lines
9.3 KiB
C
323 lines
9.3 KiB
C
/*
|
|
* Copyright(c) 2011-2016 Intel Corporation. All rights reserved.
|
|
*
|
|
* 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, sublicense,
|
|
* 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 NONINFRINGEMENT. IN NO EVENT SHALL
|
|
* THE AUTHORS OR COPYRIGHT HOLDERS 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 "i915_drv.h"
|
|
#include "i915_vgpu.h"
|
|
#include "intel_gvt.h"
|
|
#include "gem/i915_gem_dmabuf.h"
|
|
#include "gt/intel_context.h"
|
|
#include "gt/intel_ring.h"
|
|
#include "gt/shmem_utils.h"
|
|
#include <linux/vmalloc.h>
|
|
|
|
/**
|
|
* DOC: Intel GVT-g host support
|
|
*
|
|
* Intel GVT-g is a graphics virtualization technology which shares the
|
|
* GPU among multiple virtual machines on a time-sharing basis. Each
|
|
* virtual machine is presented a virtual GPU (vGPU), which has equivalent
|
|
* features as the underlying physical GPU (pGPU), so i915 driver can run
|
|
* seamlessly in a virtual machine.
|
|
*
|
|
* To virtualize GPU resources GVT-g driver depends on hypervisor technology
|
|
* e.g KVM/VFIO/mdev, Xen, etc. to provide resource access trapping capability
|
|
* and be virtualized within GVT-g device module. More architectural design
|
|
* doc is available on https://github.com/intel/gvt-linux/wiki.
|
|
*/
|
|
|
|
static LIST_HEAD(intel_gvt_devices);
|
|
static const struct intel_vgpu_ops *intel_gvt_ops;
|
|
static DEFINE_MUTEX(intel_gvt_mutex);
|
|
|
|
static bool is_supported_device(struct drm_i915_private *dev_priv)
|
|
{
|
|
if (IS_BROADWELL(dev_priv))
|
|
return true;
|
|
if (IS_SKYLAKE(dev_priv))
|
|
return true;
|
|
if (IS_KABYLAKE(dev_priv))
|
|
return true;
|
|
if (IS_BROXTON(dev_priv))
|
|
return true;
|
|
if (IS_COFFEELAKE(dev_priv))
|
|
return true;
|
|
if (IS_COMETLAKE(dev_priv))
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
static void free_initial_hw_state(struct drm_i915_private *dev_priv)
|
|
{
|
|
struct i915_virtual_gpu *vgpu = &dev_priv->vgpu;
|
|
|
|
vfree(vgpu->initial_mmio);
|
|
vgpu->initial_mmio = NULL;
|
|
|
|
kfree(vgpu->initial_cfg_space);
|
|
vgpu->initial_cfg_space = NULL;
|
|
}
|
|
|
|
static void save_mmio(struct intel_gvt_mmio_table_iter *iter, u32 offset,
|
|
u32 size)
|
|
{
|
|
struct drm_i915_private *dev_priv = iter->i915;
|
|
u32 *mmio, i;
|
|
|
|
for (i = offset; i < offset + size; i += 4) {
|
|
mmio = iter->data + i;
|
|
*mmio = intel_uncore_read_notrace(to_gt(dev_priv)->uncore,
|
|
_MMIO(i));
|
|
}
|
|
}
|
|
|
|
static int handle_mmio(struct intel_gvt_mmio_table_iter *iter,
|
|
u32 offset, u32 size)
|
|
{
|
|
if (WARN_ON(!IS_ALIGNED(offset, 4)))
|
|
return -EINVAL;
|
|
|
|
save_mmio(iter, offset, size);
|
|
return 0;
|
|
}
|
|
|
|
static int save_initial_hw_state(struct drm_i915_private *dev_priv)
|
|
{
|
|
struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev);
|
|
struct i915_virtual_gpu *vgpu = &dev_priv->vgpu;
|
|
struct intel_gvt_mmio_table_iter iter;
|
|
void *mem;
|
|
int i, ret;
|
|
|
|
mem = kzalloc(PCI_CFG_SPACE_EXP_SIZE, GFP_KERNEL);
|
|
if (!mem)
|
|
return -ENOMEM;
|
|
|
|
vgpu->initial_cfg_space = mem;
|
|
|
|
for (i = 0; i < PCI_CFG_SPACE_EXP_SIZE; i += 4)
|
|
pci_read_config_dword(pdev, i, mem + i);
|
|
|
|
mem = vzalloc(2 * SZ_1M);
|
|
if (!mem) {
|
|
ret = -ENOMEM;
|
|
goto err_mmio;
|
|
}
|
|
|
|
vgpu->initial_mmio = mem;
|
|
|
|
iter.i915 = dev_priv;
|
|
iter.data = vgpu->initial_mmio;
|
|
iter.handle_mmio_cb = handle_mmio;
|
|
|
|
ret = intel_gvt_iterate_mmio_table(&iter);
|
|
if (ret)
|
|
goto err_iterate;
|
|
|
|
return 0;
|
|
|
|
err_iterate:
|
|
vfree(vgpu->initial_mmio);
|
|
vgpu->initial_mmio = NULL;
|
|
err_mmio:
|
|
kfree(vgpu->initial_cfg_space);
|
|
vgpu->initial_cfg_space = NULL;
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void intel_gvt_init_device(struct drm_i915_private *dev_priv)
|
|
{
|
|
if (!dev_priv->params.enable_gvt) {
|
|
drm_dbg(&dev_priv->drm,
|
|
"GVT-g is disabled by kernel params\n");
|
|
return;
|
|
}
|
|
|
|
if (intel_vgpu_active(dev_priv)) {
|
|
drm_info(&dev_priv->drm, "GVT-g is disabled for guest\n");
|
|
return;
|
|
}
|
|
|
|
if (!is_supported_device(dev_priv)) {
|
|
drm_info(&dev_priv->drm,
|
|
"Unsupported device. GVT-g is disabled\n");
|
|
return;
|
|
}
|
|
|
|
if (intel_uc_wants_guc_submission(&to_gt(dev_priv)->uc)) {
|
|
drm_err(&dev_priv->drm,
|
|
"Graphics virtualization is not yet supported with GuC submission\n");
|
|
return;
|
|
}
|
|
|
|
if (save_initial_hw_state(dev_priv)) {
|
|
drm_dbg(&dev_priv->drm, "Failed to save initial HW state\n");
|
|
return;
|
|
}
|
|
|
|
if (intel_gvt_ops->init_device(dev_priv))
|
|
drm_dbg(&dev_priv->drm, "Fail to init GVT device\n");
|
|
}
|
|
|
|
static void intel_gvt_clean_device(struct drm_i915_private *dev_priv)
|
|
{
|
|
if (dev_priv->gvt)
|
|
intel_gvt_ops->clean_device(dev_priv);
|
|
free_initial_hw_state(dev_priv);
|
|
}
|
|
|
|
int intel_gvt_set_ops(const struct intel_vgpu_ops *ops)
|
|
{
|
|
struct drm_i915_private *dev_priv;
|
|
|
|
mutex_lock(&intel_gvt_mutex);
|
|
if (intel_gvt_ops) {
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
return -EINVAL;
|
|
}
|
|
intel_gvt_ops = ops;
|
|
|
|
list_for_each_entry(dev_priv, &intel_gvt_devices, vgpu.entry)
|
|
intel_gvt_init_device(dev_priv);
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_NS_GPL(intel_gvt_set_ops, I915_GVT);
|
|
|
|
void intel_gvt_clear_ops(const struct intel_vgpu_ops *ops)
|
|
{
|
|
struct drm_i915_private *dev_priv;
|
|
|
|
mutex_lock(&intel_gvt_mutex);
|
|
if (intel_gvt_ops != ops) {
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
return;
|
|
}
|
|
|
|
list_for_each_entry(dev_priv, &intel_gvt_devices, vgpu.entry)
|
|
intel_gvt_clean_device(dev_priv);
|
|
|
|
intel_gvt_ops = NULL;
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
}
|
|
EXPORT_SYMBOL_NS_GPL(intel_gvt_clear_ops, I915_GVT);
|
|
|
|
/**
|
|
* intel_gvt_init - initialize GVT components
|
|
* @dev_priv: drm i915 private data
|
|
*
|
|
* This function is called at the initialization stage to create a GVT device.
|
|
*
|
|
* Returns:
|
|
* Zero on success, negative error code if failed.
|
|
*
|
|
*/
|
|
int intel_gvt_init(struct drm_i915_private *dev_priv)
|
|
{
|
|
if (i915_inject_probe_failure(dev_priv))
|
|
return -ENODEV;
|
|
|
|
mutex_lock(&intel_gvt_mutex);
|
|
list_add_tail(&dev_priv->vgpu.entry, &intel_gvt_devices);
|
|
if (intel_gvt_ops)
|
|
intel_gvt_init_device(dev_priv);
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* intel_gvt_driver_remove - cleanup GVT components when i915 driver is
|
|
* unbinding
|
|
* @dev_priv: drm i915 private *
|
|
*
|
|
* This function is called at the i915 driver unloading stage, to shutdown
|
|
* GVT components and release the related resources.
|
|
*/
|
|
void intel_gvt_driver_remove(struct drm_i915_private *dev_priv)
|
|
{
|
|
mutex_lock(&intel_gvt_mutex);
|
|
intel_gvt_clean_device(dev_priv);
|
|
list_del(&dev_priv->vgpu.entry);
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
}
|
|
|
|
/**
|
|
* intel_gvt_resume - GVT resume routine wapper
|
|
*
|
|
* @dev_priv: drm i915 private *
|
|
*
|
|
* This function is called at the i915 driver resume stage to restore required
|
|
* HW status for GVT so that vGPU can continue running after resumed.
|
|
*/
|
|
void intel_gvt_resume(struct drm_i915_private *dev_priv)
|
|
{
|
|
mutex_lock(&intel_gvt_mutex);
|
|
if (dev_priv->gvt)
|
|
intel_gvt_ops->pm_resume(dev_priv);
|
|
mutex_unlock(&intel_gvt_mutex);
|
|
}
|
|
|
|
/*
|
|
* Exported here so that the exports only get created when GVT support is
|
|
* actually enabled.
|
|
*/
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_object_alloc, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_object_create_shmem, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_object_init, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_object_ggtt_pin_ww, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_object_pin_map, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_object_set_to_cpu_domain, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(__i915_gem_object_flush_map, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(__i915_gem_object_set_pages, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_gtt_insert, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_prime_export, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_ww_ctx_init, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_ww_ctx_backoff, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_gem_ww_ctx_fini, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_ppgtt_create, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_request_add, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_request_create, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_request_wait, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_reserve_fence, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_unreserve_fence, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_vm_release, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(_i915_vma_move_to_active, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(intel_context_create, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(__intel_context_do_pin, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(__intel_context_do_unpin, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(intel_ring_begin, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(intel_runtime_pm_get, I915_GVT);
|
|
#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
|
|
EXPORT_SYMBOL_NS_GPL(intel_runtime_pm_put, I915_GVT);
|
|
#endif
|
|
EXPORT_SYMBOL_NS_GPL(intel_runtime_pm_put_unchecked, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(intel_uncore_forcewake_for_reg, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(intel_uncore_forcewake_get, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(intel_uncore_forcewake_put, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(shmem_pin_map, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(shmem_unpin_map, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(__px_dma, I915_GVT);
|
|
EXPORT_SYMBOL_NS_GPL(i915_fence_ops, I915_GVT);
|