android_kernel_xiaomi_sm8350/mm/cma.c
Mike Kravetz 302b9e1899 cma: don't quit at first error when activating reserved areas
[ Upstream commit 3a5139f1c5bb76d69756fb8f13fffa173e261153 ]

The routine cma_init_reserved_areas is designed to activate all
reserved cma areas.  It quits when it first encounters an error.
This can leave some areas in a state where they are reserved but
not activated.  There is no feedback to code which performed the
reservation.  Attempting to allocate memory from areas in such a
state will result in a BUG.

Modify cma_init_reserved_areas to always attempt to activate all
areas.  The called routine, cma_activate_area is responsible for
leaving the area in a valid state.  No one is making active use
of returned error codes, so change the routine to void.

How to reproduce:  This example uses kernelcore, hugetlb and cma
as an easy way to reproduce.  However, this is a more general cma
issue.

Two node x86 VM 16GB total, 8GB per node
Kernel command line parameters, kernelcore=4G hugetlb_cma=8G
Related boot time messages,
  hugetlb_cma: reserve 8192 MiB, up to 4096 MiB per node
  cma: Reserved 4096 MiB at 0x0000000100000000
  hugetlb_cma: reserved 4096 MiB on node 0
  cma: Reserved 4096 MiB at 0x0000000300000000
  hugetlb_cma: reserved 4096 MiB on node 1
  cma: CMA area hugetlb could not be activated

 # echo 8 > /sys/kernel/mm/hugepages/hugepages-1048576kB/nr_hugepages

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  PGD 0 P4D 0
  Oops: 0000 [#1] SMP PTI
  ...
  Call Trace:
    bitmap_find_next_zero_area_off+0x51/0x90
    cma_alloc+0x1a5/0x310
    alloc_fresh_huge_page+0x78/0x1a0
    alloc_pool_huge_page+0x6f/0xf0
    set_max_huge_pages+0x10c/0x250
    nr_hugepages_store_common+0x92/0x120
    ? __kmalloc+0x171/0x270
    kernfs_fop_write+0xc1/0x1a0
    vfs_write+0xc7/0x1f0
    ksys_write+0x5f/0xe0
    do_syscall_64+0x4d/0x90
    entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fixes: c64be2bb1c ("drivers: add Contiguous Memory Allocator")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Roman Gushchin <guro@fb.com>
Acked-by: Barry Song <song.bao.hua@hisilicon.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: <stable@vger.kernel.org>
Link: http://lkml.kernel.org/r/20200730163123.6451-1-mike.kravetz@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2020-09-03 11:26:51 +02:00

543 lines
14 KiB
C

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Contiguous Memory Allocator
*
* Copyright (c) 2010-2011 by Samsung Electronics.
* Copyright IBM Corporation, 2013
* Copyright LG Electronics Inc., 2014
* Written by:
* Marek Szyprowski <m.szyprowski@samsung.com>
* Michal Nazarewicz <mina86@mina86.com>
* Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
* Joonsoo Kim <iamjoonsoo.kim@lge.com>
*/
#define pr_fmt(fmt) "cma: " fmt
#ifdef CONFIG_CMA_DEBUG
#ifndef DEBUG
# define DEBUG
#endif
#endif
#define CREATE_TRACE_POINTS
#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/log2.h>
#include <linux/cma.h>
#include <linux/highmem.h>
#include <linux/io.h>
#include <linux/kmemleak.h>
#include <trace/events/cma.h>
#include "cma.h"
struct cma cma_areas[MAX_CMA_AREAS];
unsigned cma_area_count;
static DEFINE_MUTEX(cma_mutex);
phys_addr_t cma_get_base(const struct cma *cma)
{
return PFN_PHYS(cma->base_pfn);
}
unsigned long cma_get_size(const struct cma *cma)
{
return cma->count << PAGE_SHIFT;
}
const char *cma_get_name(const struct cma *cma)
{
return cma->name ? cma->name : "(undefined)";
}
static unsigned long cma_bitmap_aligned_mask(const struct cma *cma,
unsigned int align_order)
{
if (align_order <= cma->order_per_bit)
return 0;
return (1UL << (align_order - cma->order_per_bit)) - 1;
}
/*
* Find the offset of the base PFN from the specified align_order.
* The value returned is represented in order_per_bits.
*/
static unsigned long cma_bitmap_aligned_offset(const struct cma *cma,
unsigned int align_order)
{
return (cma->base_pfn & ((1UL << align_order) - 1))
>> cma->order_per_bit;
}
static unsigned long cma_bitmap_pages_to_bits(const struct cma *cma,
unsigned long pages)
{
return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit;
}
static void cma_clear_bitmap(struct cma *cma, unsigned long pfn,
unsigned int count)
{
unsigned long bitmap_no, bitmap_count;
bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit;
bitmap_count = cma_bitmap_pages_to_bits(cma, count);
mutex_lock(&cma->lock);
bitmap_clear(cma->bitmap, bitmap_no, bitmap_count);
mutex_unlock(&cma->lock);
}
static void __init cma_activate_area(struct cma *cma)
{
unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
unsigned i = cma->count >> pageblock_order;
struct zone *zone;
cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL);
if (!cma->bitmap)
goto out_error;
WARN_ON_ONCE(!pfn_valid(pfn));
zone = page_zone(pfn_to_page(pfn));
do {
unsigned j;
base_pfn = pfn;
for (j = pageblock_nr_pages; j; --j, pfn++) {
WARN_ON_ONCE(!pfn_valid(pfn));
/*
* alloc_contig_range requires the pfn range
* specified to be in the same zone. Make this
* simple by forcing the entire CMA resv range
* to be in the same zone.
*/
if (page_zone(pfn_to_page(pfn)) != zone)
goto not_in_zone;
}
init_cma_reserved_pageblock(pfn_to_page(base_pfn));
} while (--i);
mutex_init(&cma->lock);
#ifdef CONFIG_CMA_DEBUGFS
INIT_HLIST_HEAD(&cma->mem_head);
spin_lock_init(&cma->mem_head_lock);
#endif
return;
not_in_zone:
bitmap_free(cma->bitmap);
out_error:
cma->count = 0;
pr_err("CMA area %s could not be activated\n", cma->name);
return;
}
static int __init cma_init_reserved_areas(void)
{
int i;
for (i = 0; i < cma_area_count; i++)
cma_activate_area(&cma_areas[i]);
return 0;
}
core_initcall(cma_init_reserved_areas);
/**
* cma_init_reserved_mem() - create custom contiguous area from reserved memory
* @base: Base address of the reserved area
* @size: Size of the reserved area (in bytes),
* @order_per_bit: Order of pages represented by one bit on bitmap.
* @name: The name of the area. If this parameter is NULL, the name of
* the area will be set to "cmaN", where N is a running counter of
* used areas.
* @res_cma: Pointer to store the created cma region.
*
* This function creates custom contiguous area from already reserved memory.
*/
int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
unsigned int order_per_bit,
const char *name,
struct cma **res_cma)
{
struct cma *cma;
phys_addr_t alignment;
/* Sanity checks */
if (cma_area_count == ARRAY_SIZE(cma_areas)) {
pr_err("Not enough slots for CMA reserved regions!\n");
return -ENOSPC;
}
if (!size || !memblock_is_region_reserved(base, size))
return -EINVAL;
/* ensure minimal alignment required by mm core */
alignment = PAGE_SIZE <<
max_t(unsigned long, MAX_ORDER - 1, pageblock_order);
/* alignment should be aligned with order_per_bit */
if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit))
return -EINVAL;
if (ALIGN(base, alignment) != base || ALIGN(size, alignment) != size)
return -EINVAL;
/*
* Each reserved area must be initialised later, when more kernel
* subsystems (like slab allocator) are available.
*/
cma = &cma_areas[cma_area_count];
if (name) {
cma->name = name;
} else {
cma->name = kasprintf(GFP_KERNEL, "cma%d\n", cma_area_count);
if (!cma->name)
return -ENOMEM;
}
cma->base_pfn = PFN_DOWN(base);
cma->count = size >> PAGE_SHIFT;
cma->order_per_bit = order_per_bit;
*res_cma = cma;
cma_area_count++;
totalcma_pages += (size / PAGE_SIZE);
return 0;
}
/**
* cma_declare_contiguous() - reserve custom contiguous area
* @base: Base address of the reserved area optional, use 0 for any
* @size: Size of the reserved area (in bytes),
* @limit: End address of the reserved memory (optional, 0 for any).
* @alignment: Alignment for the CMA area, should be power of 2 or zero
* @order_per_bit: Order of pages represented by one bit on bitmap.
* @fixed: hint about where to place the reserved area
* @name: The name of the area. See function cma_init_reserved_mem()
* @res_cma: Pointer to store the created cma region.
*
* 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.
*
* If @fixed is true, reserve contiguous area at exactly @base. If false,
* reserve in range from @base to @limit.
*/
int __init cma_declare_contiguous(phys_addr_t base,
phys_addr_t size, phys_addr_t limit,
phys_addr_t alignment, unsigned int order_per_bit,
bool fixed, const char *name, struct cma **res_cma)
{
phys_addr_t memblock_end = memblock_end_of_DRAM();
phys_addr_t highmem_start;
int ret = 0;
/*
* We can't use __pa(high_memory) directly, since high_memory
* isn't a valid direct map VA, and DEBUG_VIRTUAL will (validly)
* complain. Find the boundary by adding one to the last valid
* address.
*/
highmem_start = __pa(high_memory - 1) + 1;
pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n",
__func__, &size, &base, &limit, &alignment);
if (cma_area_count == ARRAY_SIZE(cma_areas)) {
pr_err("Not enough slots for CMA reserved regions!\n");
return -ENOSPC;
}
if (!size)
return -EINVAL;
if (alignment && !is_power_of_2(alignment))
return -EINVAL;
/*
* Sanitise input arguments.
* Pages both ends in CMA area could be merged into adjacent unmovable
* migratetype page by page allocator's buddy algorithm. In the case,
* you couldn't get a contiguous memory, which is not what we want.
*/
alignment = max(alignment, (phys_addr_t)PAGE_SIZE <<
max_t(unsigned long, MAX_ORDER - 1, pageblock_order));
if (fixed && base & (alignment - 1)) {
ret = -EINVAL;
pr_err("Region at %pa must be aligned to %pa bytes\n",
&base, &alignment);
goto err;
}
base = ALIGN(base, alignment);
size = ALIGN(size, alignment);
limit &= ~(alignment - 1);
if (!base)
fixed = false;
/* size should be aligned with order_per_bit */
if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
return -EINVAL;
/*
* If allocating at a fixed base the request region must not cross the
* low/high memory boundary.
*/
if (fixed && base < highmem_start && base + size > highmem_start) {
ret = -EINVAL;
pr_err("Region at %pa defined on low/high memory boundary (%pa)\n",
&base, &highmem_start);
goto err;
}
/*
* If the limit is unspecified or above the memblock end, its effective
* value will be the memblock end. Set it explicitly to simplify further
* checks.
*/
if (limit == 0 || limit > memblock_end)
limit = memblock_end;
if (base + size > limit) {
ret = -EINVAL;
pr_err("Size (%pa) of region at %pa exceeds limit (%pa)\n",
&size, &base, &limit);
goto err;
}
/* Reserve memory */
if (fixed) {
if (memblock_is_region_reserved(base, size) ||
memblock_reserve(base, size) < 0) {
ret = -EBUSY;
goto err;
}
} else {
phys_addr_t addr = 0;
/*
* All pages in the reserved area must come from the same zone.
* If the requested region crosses the low/high memory boundary,
* try allocating from high memory first and fall back to low
* memory in case of failure.
*/
if (base < highmem_start && limit > highmem_start) {
addr = memblock_phys_alloc_range(size, alignment,
highmem_start, limit);
limit = highmem_start;
}
if (!addr) {
addr = memblock_phys_alloc_range(size, alignment, base,
limit);
if (!addr) {
ret = -ENOMEM;
goto err;
}
}
/*
* kmemleak scans/reads tracked objects for pointers to other
* objects but this address isn't mapped and accessible
*/
kmemleak_ignore_phys(addr);
base = addr;
}
ret = cma_init_reserved_mem(base, size, order_per_bit, name, res_cma);
if (ret)
goto free_mem;
pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M,
&base);
return 0;
free_mem:
memblock_free(base, size);
err:
pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
return ret;
}
#ifdef CONFIG_CMA_DEBUG
static void cma_debug_show_areas(struct cma *cma)
{
unsigned long next_zero_bit, next_set_bit, nr_zero;
unsigned long start = 0;
unsigned long nr_part, nr_total = 0;
unsigned long nbits = cma_bitmap_maxno(cma);
mutex_lock(&cma->lock);
pr_info("number of available pages: ");
for (;;) {
next_zero_bit = find_next_zero_bit(cma->bitmap, nbits, start);
if (next_zero_bit >= nbits)
break;
next_set_bit = find_next_bit(cma->bitmap, nbits, next_zero_bit);
nr_zero = next_set_bit - next_zero_bit;
nr_part = nr_zero << cma->order_per_bit;
pr_cont("%s%lu@%lu", nr_total ? "+" : "", nr_part,
next_zero_bit);
nr_total += nr_part;
start = next_zero_bit + nr_zero;
}
pr_cont("=> %lu free of %lu total pages\n", nr_total, cma->count);
mutex_unlock(&cma->lock);
}
#else
static inline void cma_debug_show_areas(struct cma *cma) { }
#endif
/**
* cma_alloc() - allocate pages from contiguous area
* @cma: Contiguous memory region 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 part of contiguous memory on specific
* contiguous memory area.
*/
struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align,
bool no_warn)
{
unsigned long mask, offset;
unsigned long pfn = -1;
unsigned long start = 0;
unsigned long bitmap_maxno, bitmap_no, bitmap_count;
size_t i;
struct page *page = NULL;
int ret = -ENOMEM;
if (!cma || !cma->count)
return NULL;
pr_debug("%s(cma %p, count %zu, align %d)\n", __func__, (void *)cma,
count, align);
if (!count)
return NULL;
mask = cma_bitmap_aligned_mask(cma, align);
offset = cma_bitmap_aligned_offset(cma, align);
bitmap_maxno = cma_bitmap_maxno(cma);
bitmap_count = cma_bitmap_pages_to_bits(cma, count);
if (bitmap_count > bitmap_maxno)
return NULL;
for (;;) {
mutex_lock(&cma->lock);
bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
bitmap_maxno, start, bitmap_count, mask,
offset);
if (bitmap_no >= bitmap_maxno) {
mutex_unlock(&cma->lock);
break;
}
bitmap_set(cma->bitmap, bitmap_no, bitmap_count);
/*
* It's safe to drop the lock here. We've marked this region for
* our exclusive use. If the migration fails we will take the
* lock again and unmark it.
*/
mutex_unlock(&cma->lock);
pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
mutex_lock(&cma_mutex);
ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA,
GFP_KERNEL | (no_warn ? __GFP_NOWARN : 0));
mutex_unlock(&cma_mutex);
if (ret == 0) {
page = pfn_to_page(pfn);
break;
}
cma_clear_bitmap(cma, pfn, count);
if (ret != -EBUSY)
break;
pr_debug("%s(): memory range at %p is busy, retrying\n",
__func__, pfn_to_page(pfn));
/* try again with a bit different memory target */
start = bitmap_no + mask + 1;
}
trace_cma_alloc(pfn, page, count, align);
/*
* CMA can allocate multiple page blocks, which results in different
* blocks being marked with different tags. Reset the tags to ignore
* those page blocks.
*/
if (page) {
for (i = 0; i < count; i++)
page_kasan_tag_reset(page + i);
}
if (ret && !no_warn) {
pr_err("%s: alloc failed, req-size: %zu pages, ret: %d\n",
__func__, count, ret);
cma_debug_show_areas(cma);
}
pr_debug("%s(): returned %p\n", __func__, page);
return page;
}
/**
* cma_release() - release allocated pages
* @cma: Contiguous memory region for which the allocation is performed.
* @pages: Allocated pages.
* @count: Number of allocated pages.
*
* This function releases memory allocated by cma_alloc().
* It returns false when provided pages do not belong to contiguous area and
* true otherwise.
*/
bool cma_release(struct cma *cma, const struct page *pages, unsigned int count)
{
unsigned long pfn;
if (!cma || !pages)
return false;
pr_debug("%s(page %p)\n", __func__, (void *)pages);
pfn = page_to_pfn(pages);
if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
return false;
VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
free_contig_range(pfn, count);
cma_clear_bitmap(cma, pfn, count);
trace_cma_release(pfn, pages, count);
return true;
}
int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data)
{
int i;
for (i = 0; i < cma_area_count; i++) {
int ret = it(&cma_areas[i], data);
if (ret)
return ret;
}
return 0;
}