mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-10-31 16:38:12 +00:00
b3d40a2b6d
Some places in the kernel don't really expect pageblock_order >= MAX_ORDER, and it looks like this is only possible in corner cases: 1) CONFIG_DEFERRED_STRUCT_PAGE_INIT we'll end up freeing pageblock_order pages via __free_pages_core(), which cannot possibly work. 2) find_zone_movable_pfns_for_nodes() will roundup the ZONE_MOVABLE start PFN to MAX_ORDER_NR_PAGES. Consequently with a bigger pageblock_order, we could have a single pageblock partially managed by two zones. 3) compaction code runs into __fragmentation_index() with order >= MAX_ORDER, when checking WARN_ON_ONCE(order >= MAX_ORDER). [1] 4) mm/page_reporting.c won't be reporting any pages with default page_reporting_order == pageblock_order, as we'll be skipping the reporting loop inside page_reporting_process_zone(). 5) __rmqueue_fallback() will never be able to steal with ALLOC_NOFRAGMENT. pageblock_order >= MAX_ORDER is weird either way: it's a pure optimization for making alloc_contig_range(), as used for allcoation of gigantic pages, a little more reliable to succeed. However, if there is demand for somewhat reliable allocation of gigantic pages, affected setups should be using CMA or boottime allocations instead. So let's make sure that pageblock_order < MAX_ORDER and simplify. [1] https://lkml.kernel.org/r/87r189a2ks.fsf@linux.ibm.com Link: https://lkml.kernel.org/r/20220214174132.219303-3-david@redhat.com Signed-off-by: David Hildenbrand <david@redhat.com> Reviewed-by: Zi Yan <ziy@nvidia.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Frank Rowand <frowand.list@gmail.com> Cc: John Garry via iommu <iommu@lists.linux-foundation.org> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
94 lines
2.4 KiB
C
94 lines
2.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0-only */
|
|
/*
|
|
* Macros for manipulating and testing flags related to a
|
|
* pageblock_nr_pages number of pages.
|
|
*
|
|
* Copyright (C) IBM Corporation, 2006
|
|
*
|
|
* Original author, Mel Gorman
|
|
* Major cleanups and reduction of bit operations, Andy Whitcroft
|
|
*/
|
|
#ifndef PAGEBLOCK_FLAGS_H
|
|
#define PAGEBLOCK_FLAGS_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
#define PB_migratetype_bits 3
|
|
/* Bit indices that affect a whole block of pages */
|
|
enum pageblock_bits {
|
|
PB_migrate,
|
|
PB_migrate_end = PB_migrate + PB_migratetype_bits - 1,
|
|
/* 3 bits required for migrate types */
|
|
PB_migrate_skip,/* If set the block is skipped by compaction */
|
|
|
|
/*
|
|
* Assume the bits will always align on a word. If this assumption
|
|
* changes then get/set pageblock needs updating.
|
|
*/
|
|
NR_PAGEBLOCK_BITS
|
|
};
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
|
|
|
|
/* Huge page sizes are variable */
|
|
extern unsigned int pageblock_order;
|
|
|
|
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
|
|
|
|
/*
|
|
* Huge pages are a constant size, but don't exceed the maximum allocation
|
|
* granularity.
|
|
*/
|
|
#define pageblock_order min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER - 1)
|
|
|
|
#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
|
|
|
|
#else /* CONFIG_HUGETLB_PAGE */
|
|
|
|
/* If huge pages are not used, group by MAX_ORDER_NR_PAGES */
|
|
#define pageblock_order (MAX_ORDER-1)
|
|
|
|
#endif /* CONFIG_HUGETLB_PAGE */
|
|
|
|
#define pageblock_nr_pages (1UL << pageblock_order)
|
|
|
|
/* Forward declaration */
|
|
struct page;
|
|
|
|
unsigned long get_pfnblock_flags_mask(const struct page *page,
|
|
unsigned long pfn,
|
|
unsigned long mask);
|
|
|
|
void set_pfnblock_flags_mask(struct page *page,
|
|
unsigned long flags,
|
|
unsigned long pfn,
|
|
unsigned long mask);
|
|
|
|
/* Declarations for getting and setting flags. See mm/page_alloc.c */
|
|
#ifdef CONFIG_COMPACTION
|
|
#define get_pageblock_skip(page) \
|
|
get_pfnblock_flags_mask(page, page_to_pfn(page), \
|
|
(1 << (PB_migrate_skip)))
|
|
#define clear_pageblock_skip(page) \
|
|
set_pfnblock_flags_mask(page, 0, page_to_pfn(page), \
|
|
(1 << PB_migrate_skip))
|
|
#define set_pageblock_skip(page) \
|
|
set_pfnblock_flags_mask(page, (1 << PB_migrate_skip), \
|
|
page_to_pfn(page), \
|
|
(1 << PB_migrate_skip))
|
|
#else
|
|
static inline bool get_pageblock_skip(struct page *page)
|
|
{
|
|
return false;
|
|
}
|
|
static inline void clear_pageblock_skip(struct page *page)
|
|
{
|
|
}
|
|
static inline void set_pageblock_skip(struct page *page)
|
|
{
|
|
}
|
|
#endif /* CONFIG_COMPACTION */
|
|
|
|
#endif /* PAGEBLOCK_FLAGS_H */
|