mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 07:50:53 +07:00
bd2e75633c
The addresses within a single page are always contiguous, so it's not so necessary to always allocate one single page from CMA area. Since the CMA area has a limited predefined size of space, it may run out of space in heavy use cases, where there might be quite a lot CMA pages being allocated for single pages. However, there is also a concern that a device might care where a page comes from -- it might expect the page from CMA area and act differently if the page doesn't. This patch tries to use the fallback alloc_pages path, instead of one-page size allocations from the global CMA area in case that a device does not have its own CMA area. This'd save resources from the CMA global area for more CMA allocations, and also reduce CMA fragmentations resulted from trivial allocations. Signed-off-by: Nicolin Chen <nicoleotsuka@gmail.com> Tested-by: dann frazier <dann.frazier@canonical.com> Signed-off-by: Christoph Hellwig <hch@lst.de>
339 lines
9.9 KiB
C
339 lines
9.9 KiB
C
// SPDX-License-Identifier: GPL-2.0+
|
|
/*
|
|
* Contiguous Memory Allocator for DMA mapping framework
|
|
* Copyright (c) 2010-2011 by Samsung Electronics.
|
|
* Written by:
|
|
* Marek Szyprowski <m.szyprowski@samsung.com>
|
|
* Michal Nazarewicz <mina86@mina86.com>
|
|
*/
|
|
|
|
#define pr_fmt(fmt) "cma: " fmt
|
|
|
|
#ifdef CONFIG_CMA_DEBUG
|
|
#ifndef DEBUG
|
|
# define DEBUG
|
|
#endif
|
|
#endif
|
|
|
|
#include <asm/page.h>
|
|
#include <asm/dma-contiguous.h>
|
|
|
|
#include <linux/memblock.h>
|
|
#include <linux/err.h>
|
|
#include <linux/sizes.h>
|
|
#include <linux/dma-contiguous.h>
|
|
#include <linux/cma.h>
|
|
|
|
#ifdef CONFIG_CMA_SIZE_MBYTES
|
|
#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
|
|
#else
|
|
#define CMA_SIZE_MBYTES 0
|
|
#endif
|
|
|
|
struct cma *dma_contiguous_default_area;
|
|
|
|
/*
|
|
* Default global CMA area size can be defined in kernel's .config.
|
|
* This is useful mainly for distro maintainers to create a kernel
|
|
* that works correctly for most supported systems.
|
|
* The size can be set in bytes or as a percentage of the total memory
|
|
* in the system.
|
|
*
|
|
* Users, who want to set the size of global CMA area for their system
|
|
* should use cma= kernel parameter.
|
|
*/
|
|
static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
|
|
static phys_addr_t size_cmdline = -1;
|
|
static phys_addr_t base_cmdline;
|
|
static phys_addr_t limit_cmdline;
|
|
|
|
static int __init early_cma(char *p)
|
|
{
|
|
if (!p) {
|
|
pr_err("Config string not provided\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
size_cmdline = memparse(p, &p);
|
|
if (*p != '@')
|
|
return 0;
|
|
base_cmdline = memparse(p + 1, &p);
|
|
if (*p != '-') {
|
|
limit_cmdline = base_cmdline + size_cmdline;
|
|
return 0;
|
|
}
|
|
limit_cmdline = memparse(p + 1, &p);
|
|
|
|
return 0;
|
|
}
|
|
early_param("cma", early_cma);
|
|
|
|
#ifdef CONFIG_CMA_SIZE_PERCENTAGE
|
|
|
|
static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
|
|
{
|
|
struct memblock_region *reg;
|
|
unsigned long total_pages = 0;
|
|
|
|
/*
|
|
* We cannot use memblock_phys_mem_size() here, because
|
|
* memblock_analyze() has not been called yet.
|
|
*/
|
|
for_each_memblock(memory, reg)
|
|
total_pages += memblock_region_memory_end_pfn(reg) -
|
|
memblock_region_memory_base_pfn(reg);
|
|
|
|
return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
|
|
}
|
|
|
|
#else
|
|
|
|
static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif
|
|
|
|
/**
|
|
* dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
|
|
* @limit: End address of the reserved memory (optional, 0 for any).
|
|
*
|
|
* This function reserves memory from early allocator. It should be
|
|
* called by arch specific code once the early allocator (memblock or bootmem)
|
|
* has been activated and all other subsystems have already allocated/reserved
|
|
* memory.
|
|
*/
|
|
void __init dma_contiguous_reserve(phys_addr_t limit)
|
|
{
|
|
phys_addr_t selected_size = 0;
|
|
phys_addr_t selected_base = 0;
|
|
phys_addr_t selected_limit = limit;
|
|
bool fixed = false;
|
|
|
|
pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
|
|
|
|
if (size_cmdline != -1) {
|
|
selected_size = size_cmdline;
|
|
selected_base = base_cmdline;
|
|
selected_limit = min_not_zero(limit_cmdline, limit);
|
|
if (base_cmdline + size_cmdline == limit_cmdline)
|
|
fixed = true;
|
|
} else {
|
|
#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
|
|
selected_size = size_bytes;
|
|
#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
|
|
selected_size = cma_early_percent_memory();
|
|
#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
|
|
selected_size = min(size_bytes, cma_early_percent_memory());
|
|
#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
|
|
selected_size = max(size_bytes, cma_early_percent_memory());
|
|
#endif
|
|
}
|
|
|
|
if (selected_size && !dma_contiguous_default_area) {
|
|
pr_debug("%s: reserving %ld MiB for global area\n", __func__,
|
|
(unsigned long)selected_size / SZ_1M);
|
|
|
|
dma_contiguous_reserve_area(selected_size, selected_base,
|
|
selected_limit,
|
|
&dma_contiguous_default_area,
|
|
fixed);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* dma_contiguous_reserve_area() - reserve custom contiguous area
|
|
* @size: Size of the reserved area (in bytes),
|
|
* @base: Base address of the reserved area optional, use 0 for any
|
|
* @limit: End address of the reserved memory (optional, 0 for any).
|
|
* @res_cma: Pointer to store the created cma region.
|
|
* @fixed: hint about where to place the reserved area
|
|
*
|
|
* This function reserves memory from early allocator. It should be
|
|
* called by arch specific code once the early allocator (memblock or bootmem)
|
|
* has been activated and all other subsystems have already allocated/reserved
|
|
* memory. This function allows to create custom reserved areas for specific
|
|
* devices.
|
|
*
|
|
* If @fixed is true, reserve contiguous area at exactly @base. If false,
|
|
* reserve in range from @base to @limit.
|
|
*/
|
|
int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
|
|
phys_addr_t limit, struct cma **res_cma,
|
|
bool fixed)
|
|
{
|
|
int ret;
|
|
|
|
ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed,
|
|
"reserved", res_cma);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/* Architecture specific contiguous memory fixup. */
|
|
dma_contiguous_early_fixup(cma_get_base(*res_cma),
|
|
cma_get_size(*res_cma));
|
|
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* dma_alloc_from_contiguous() - allocate pages from contiguous area
|
|
* @dev: Pointer to device for which the allocation is performed.
|
|
* @count: Requested number of pages.
|
|
* @align: Requested alignment of pages (in PAGE_SIZE order).
|
|
* @no_warn: Avoid printing message about failed allocation.
|
|
*
|
|
* This function allocates memory buffer for specified device. It uses
|
|
* device specific contiguous memory area if available or the default
|
|
* global one. Requires architecture specific dev_get_cma_area() helper
|
|
* function.
|
|
*/
|
|
struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
|
|
unsigned int align, bool no_warn)
|
|
{
|
|
if (align > CONFIG_CMA_ALIGNMENT)
|
|
align = CONFIG_CMA_ALIGNMENT;
|
|
|
|
return cma_alloc(dev_get_cma_area(dev), count, align, no_warn);
|
|
}
|
|
|
|
/**
|
|
* dma_release_from_contiguous() - release allocated pages
|
|
* @dev: Pointer to device for which the pages were allocated.
|
|
* @pages: Allocated pages.
|
|
* @count: Number of allocated pages.
|
|
*
|
|
* This function releases memory allocated by dma_alloc_from_contiguous().
|
|
* It returns false when provided pages do not belong to contiguous area and
|
|
* true otherwise.
|
|
*/
|
|
bool dma_release_from_contiguous(struct device *dev, struct page *pages,
|
|
int count)
|
|
{
|
|
return cma_release(dev_get_cma_area(dev), pages, count);
|
|
}
|
|
|
|
/**
|
|
* dma_alloc_contiguous() - allocate contiguous pages
|
|
* @dev: Pointer to device for which the allocation is performed.
|
|
* @size: Requested allocation size.
|
|
* @gfp: Allocation flags.
|
|
*
|
|
* This function allocates contiguous memory buffer for specified device. It
|
|
* first tries to use device specific contiguous memory area if available or
|
|
* the default global one, then tries a fallback allocation of normal pages.
|
|
*
|
|
* Note that it byapss one-page size of allocations from the global area as
|
|
* the addresses within one page are always contiguous, so there is no need
|
|
* to waste CMA pages for that kind; it also helps reduce fragmentations.
|
|
*/
|
|
struct page *dma_alloc_contiguous(struct device *dev, size_t size, gfp_t gfp)
|
|
{
|
|
int node = dev ? dev_to_node(dev) : NUMA_NO_NODE;
|
|
size_t count = PAGE_ALIGN(size) >> PAGE_SHIFT;
|
|
size_t align = get_order(PAGE_ALIGN(size));
|
|
struct page *page = NULL;
|
|
struct cma *cma = NULL;
|
|
|
|
if (dev && dev->cma_area)
|
|
cma = dev->cma_area;
|
|
else if (count > 1)
|
|
cma = dma_contiguous_default_area;
|
|
|
|
/* CMA can be used only in the context which permits sleeping */
|
|
if (cma && gfpflags_allow_blocking(gfp)) {
|
|
align = min_t(size_t, align, CONFIG_CMA_ALIGNMENT);
|
|
page = cma_alloc(cma, count, align, gfp & __GFP_NOWARN);
|
|
}
|
|
|
|
/* Fallback allocation of normal pages */
|
|
if (!page)
|
|
page = alloc_pages_node(node, gfp, align);
|
|
return page;
|
|
}
|
|
|
|
/**
|
|
* dma_free_contiguous() - release allocated pages
|
|
* @dev: Pointer to device for which the pages were allocated.
|
|
* @page: Pointer to the allocated pages.
|
|
* @size: Size of allocated pages.
|
|
*
|
|
* This function releases memory allocated by dma_alloc_contiguous(). As the
|
|
* cma_release returns false when provided pages do not belong to contiguous
|
|
* area and true otherwise, this function then does a fallback __free_pages()
|
|
* upon a false-return.
|
|
*/
|
|
void dma_free_contiguous(struct device *dev, struct page *page, size_t size)
|
|
{
|
|
if (!cma_release(dev_get_cma_area(dev), page, size >> PAGE_SHIFT))
|
|
__free_pages(page, get_order(size));
|
|
}
|
|
|
|
/*
|
|
* Support for reserved memory regions defined in device tree
|
|
*/
|
|
#ifdef CONFIG_OF_RESERVED_MEM
|
|
#include <linux/of.h>
|
|
#include <linux/of_fdt.h>
|
|
#include <linux/of_reserved_mem.h>
|
|
|
|
#undef pr_fmt
|
|
#define pr_fmt(fmt) fmt
|
|
|
|
static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
|
|
{
|
|
dev_set_cma_area(dev, rmem->priv);
|
|
return 0;
|
|
}
|
|
|
|
static void rmem_cma_device_release(struct reserved_mem *rmem,
|
|
struct device *dev)
|
|
{
|
|
dev_set_cma_area(dev, NULL);
|
|
}
|
|
|
|
static const struct reserved_mem_ops rmem_cma_ops = {
|
|
.device_init = rmem_cma_device_init,
|
|
.device_release = rmem_cma_device_release,
|
|
};
|
|
|
|
static int __init rmem_cma_setup(struct reserved_mem *rmem)
|
|
{
|
|
phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
|
|
phys_addr_t mask = align - 1;
|
|
unsigned long node = rmem->fdt_node;
|
|
struct cma *cma;
|
|
int err;
|
|
|
|
if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
|
|
of_get_flat_dt_prop(node, "no-map", NULL))
|
|
return -EINVAL;
|
|
|
|
if ((rmem->base & mask) || (rmem->size & mask)) {
|
|
pr_err("Reserved memory: incorrect alignment of CMA region\n");
|
|
return -EINVAL;
|
|
}
|
|
|
|
err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma);
|
|
if (err) {
|
|
pr_err("Reserved memory: unable to setup CMA region\n");
|
|
return err;
|
|
}
|
|
/* Architecture specific contiguous memory fixup. */
|
|
dma_contiguous_early_fixup(rmem->base, rmem->size);
|
|
|
|
if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
|
|
dma_contiguous_set_default(cma);
|
|
|
|
rmem->ops = &rmem_cma_ops;
|
|
rmem->priv = cma;
|
|
|
|
pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
|
|
&rmem->base, (unsigned long)rmem->size / SZ_1M);
|
|
|
|
return 0;
|
|
}
|
|
RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
|
|
#endif
|