mirror of
git://git.yoctoproject.org/linux-yocto.git
synced 2025-10-22 15:03:53 +02:00
b168ed458d
This code is based on the RDMA and misc cgroup initially, but now uses page_counter. It uses the same min/low/max semantics as the memory cgroup as a result. There's a small mismatch as TTM uses u64, and page_counter long pages. In practice it's not a problem. 32-bits systems don't really come with >=4GB cards and as long as we're consistently wrong with units, it's fine. The device page size may not be in the same units as kernel page size, and each region might also have a different page size (VRAM vs GART for example). The interface is simple: - Call dmem_cgroup_register_region() - Use dmem_cgroup_try_charge to check if you can allocate a chunk of memory, use dmem_cgroup__uncharge when freeing it. This may return an error code, or -EAGAIN when the cgroup limit is reached. In that case a reference to the limiting pool is returned. - The limiting cs can be used as compare function for dmem_cgroup_state_evict_valuable. - After having evicted enough, drop reference to limiting cs with dmem_cgroup_pool_state_put. This API allows you to limit device resources with cgroups. You can see the supported cards in /sys/fs/cgroup/dmem.capacity You need to echo +dmem to cgroup.subtree_control, and then you can partition device memory. Co-developed-by: Friedrich Vock <friedrich.vock@gmx.de> Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de> Co-developed-by: Maxime Ripard <mripard@kernel.org> Signed-off-by: Maarten Lankhorst <dev@lankhorst.se> Acked-by: Tejun Heo <tj@kernel.org> Link: https://lore.kernel.org/r/20241204143112.1250983-1-dev@lankhorst.se Signed-off-by: Maxime Ripard <mripard@kernel.org>
110 lines
3.2 KiB
C
110 lines
3.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_PAGE_COUNTER_H
|
|
#define _LINUX_PAGE_COUNTER_H
|
|
|
|
#include <linux/atomic.h>
|
|
#include <linux/cache.h>
|
|
#include <linux/limits.h>
|
|
#include <asm/page.h>
|
|
|
|
struct page_counter {
|
|
/*
|
|
* Make sure 'usage' does not share cacheline with any other field. The
|
|
* memcg->memory.usage is a hot member of struct mem_cgroup.
|
|
*/
|
|
atomic_long_t usage;
|
|
CACHELINE_PADDING(_pad1_);
|
|
|
|
/* effective memory.min and memory.min usage tracking */
|
|
unsigned long emin;
|
|
atomic_long_t min_usage;
|
|
atomic_long_t children_min_usage;
|
|
|
|
/* effective memory.low and memory.low usage tracking */
|
|
unsigned long elow;
|
|
atomic_long_t low_usage;
|
|
atomic_long_t children_low_usage;
|
|
|
|
unsigned long watermark;
|
|
/* Latest cg2 reset watermark */
|
|
unsigned long local_watermark;
|
|
unsigned long failcnt;
|
|
|
|
/* Keep all the read most fields in a separete cacheline. */
|
|
CACHELINE_PADDING(_pad2_);
|
|
|
|
bool protection_support;
|
|
unsigned long min;
|
|
unsigned long low;
|
|
unsigned long high;
|
|
unsigned long max;
|
|
struct page_counter *parent;
|
|
} ____cacheline_internodealigned_in_smp;
|
|
|
|
#if BITS_PER_LONG == 32
|
|
#define PAGE_COUNTER_MAX LONG_MAX
|
|
#else
|
|
#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
|
|
#endif
|
|
|
|
/*
|
|
* Protection is supported only for the first counter (with id 0).
|
|
*/
|
|
static inline void page_counter_init(struct page_counter *counter,
|
|
struct page_counter *parent,
|
|
bool protection_support)
|
|
{
|
|
counter->usage = (atomic_long_t)ATOMIC_LONG_INIT(0);
|
|
counter->max = PAGE_COUNTER_MAX;
|
|
counter->parent = parent;
|
|
counter->protection_support = protection_support;
|
|
}
|
|
|
|
static inline unsigned long page_counter_read(struct page_counter *counter)
|
|
{
|
|
return atomic_long_read(&counter->usage);
|
|
}
|
|
|
|
void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
|
|
void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
|
|
bool page_counter_try_charge(struct page_counter *counter,
|
|
unsigned long nr_pages,
|
|
struct page_counter **fail);
|
|
void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
|
|
void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages);
|
|
void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages);
|
|
|
|
static inline void page_counter_set_high(struct page_counter *counter,
|
|
unsigned long nr_pages)
|
|
{
|
|
WRITE_ONCE(counter->high, nr_pages);
|
|
}
|
|
|
|
int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages);
|
|
int page_counter_memparse(const char *buf, const char *max,
|
|
unsigned long *nr_pages);
|
|
|
|
static inline void page_counter_reset_watermark(struct page_counter *counter)
|
|
{
|
|
unsigned long usage = page_counter_read(counter);
|
|
|
|
/*
|
|
* Update local_watermark first, so it's always <= watermark
|
|
* (modulo CPU/compiler re-ordering)
|
|
*/
|
|
counter->local_watermark = usage;
|
|
counter->watermark = usage;
|
|
}
|
|
|
|
#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM)
|
|
void page_counter_calculate_protection(struct page_counter *root,
|
|
struct page_counter *counter,
|
|
bool recursive_protection);
|
|
#else
|
|
static inline void page_counter_calculate_protection(struct page_counter *root,
|
|
struct page_counter *counter,
|
|
bool recursive_protection) {}
|
|
#endif
|
|
|
|
#endif /* _LINUX_PAGE_COUNTER_H */
|