From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/internal.h | 193 ++++++++++++++++++++++++++++++++++++-----------
1 files changed, 147 insertions(+), 46 deletions(-)
diff --git a/kernel/mm/internal.h b/kernel/mm/internal.h
index 3a2e973..5a3f372 100644
--- a/kernel/mm/internal.h
+++ b/kernel/mm/internal.h
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
/* internal.h: mm/ internal definitions
*
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
*/
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H
@@ -40,10 +36,30 @@
vm_fault_t do_swap_page(struct vm_fault *vmf);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+extern struct vm_area_struct *get_vma(struct mm_struct *mm,
+ unsigned long addr);
+extern void put_vma(struct vm_area_struct *vma);
+
+static inline bool vma_has_changed(struct vm_fault *vmf)
+{
+ int ret = RB_EMPTY_NODE(&vmf->vma->vm_rb);
+ unsigned int seq = READ_ONCE(vmf->vma->vm_sequence.sequence);
+
+ /*
+ * Matches both the wmb in write_seqlock_{begin,end}() and
+ * the wmb in vma_rb_erase().
+ */
+ smp_rmb();
+
+ return ret || seq != vmf->sequence;
+}
+#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */
+
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
-static inline bool can_madv_dontneed_vma(struct vm_area_struct *vma)
+static inline bool can_madv_lru_vma(struct vm_area_struct *vma)
{
return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP));
}
@@ -53,18 +69,41 @@
unsigned long addr, unsigned long end,
struct zap_details *details);
-extern unsigned int __do_page_cache_readahead(struct address_space *mapping,
- struct file *filp, pgoff_t offset, unsigned long nr_to_read,
+void do_page_cache_ra(struct readahead_control *, unsigned long nr_to_read,
unsigned long lookahead_size);
-
-/*
- * Submit IO for the read-ahead request in file_ra_state.
- */
-static inline unsigned long ra_submit(struct file_ra_state *ra,
- struct address_space *mapping, struct file *filp)
+void force_page_cache_ra(struct readahead_control *, struct file_ra_state *,
+ unsigned long nr);
+static inline void force_page_cache_readahead(struct address_space *mapping,
+ struct file *file, pgoff_t index, unsigned long nr_to_read)
{
- return __do_page_cache_readahead(mapping, filp,
- ra->start, ra->size, ra->async_size);
+ DEFINE_READAHEAD(ractl, file, mapping, index);
+ force_page_cache_ra(&ractl, &file->f_ra, nr_to_read);
+}
+
+struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
+struct page *find_lock_entry(struct address_space *mapping, pgoff_t index);
+
+/**
+ * page_evictable - test whether a page is evictable
+ * @page: the page to test
+ *
+ * Test whether page is evictable--i.e., should be placed on active/inactive
+ * lists vs unevictable list.
+ *
+ * Reasons page might not be evictable:
+ * (1) page's mapping marked unevictable
+ * (2) page is part of an mlocked VMA
+ *
+ */
+static inline bool page_evictable(struct page *page)
+{
+ bool ret;
+
+ /* Prevent address_space of inode and swap cache from being freed */
+ rcu_read_lock();
+ ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+ rcu_read_unlock();
+ return ret;
}
/*
@@ -106,12 +145,12 @@
* between functions involved in allocations, including the alloc_pages*
* family of functions.
*
- * nodemask, migratetype and high_zoneidx are initialized only once in
+ * nodemask, migratetype and highest_zoneidx are initialized only once in
* __alloc_pages_nodemask() and then never change.
*
- * zonelist, preferred_zone and classzone_idx are set first in
+ * zonelist, preferred_zone and highest_zoneidx are set first in
* __alloc_pages_nodemask() for the fast path, and might be later changed
- * in __alloc_pages_slowpath(). All other functions pass the whole strucure
+ * in __alloc_pages_slowpath(). All other functions pass the whole structure
* by a const pointer.
*/
struct alloc_context {
@@ -119,11 +158,20 @@
nodemask_t *nodemask;
struct zoneref *preferred_zoneref;
int migratetype;
- enum zone_type high_zoneidx;
+
+ /*
+ * highest_zoneidx represents highest usable zone index of
+ * the allocation request. Due to the nature of the zone,
+ * memory on lower zone than the highest_zoneidx will be
+ * protected by lowmem_reserve[highest_zoneidx].
+ *
+ * highest_zoneidx is also used by reclaim/compaction to limit
+ * the target zone since higher zone than this index cannot be
+ * usable for this allocation request.
+ */
+ enum zone_type highest_zoneidx;
bool spread_dirty_pages;
};
-
-#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref)
/*
* Locate the struct page for both the matching buddy in our
@@ -161,12 +209,18 @@
}
extern int __isolate_free_page(struct page *page, unsigned int order);
-extern void __free_pages_bootmem(struct page *page, unsigned long pfn,
+extern void __putback_isolated_page(struct page *page, unsigned int order,
+ int mt);
+extern void memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order);
+extern void __free_pages_core(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned int order);
extern void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags);
extern int user_min_free_kbytes;
+
+extern void zone_pcp_update(struct zone *zone);
+extern void zone_pcp_reset(struct zone *zone);
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
@@ -183,27 +237,40 @@
struct compact_control {
struct list_head freepages; /* List of free pages to migrate to */
struct list_head migratepages; /* List of pages being migrated */
- struct zone *zone;
- unsigned long nr_freepages; /* Number of isolated free pages */
- unsigned long nr_migratepages; /* Number of pages to migrate */
- unsigned long total_migrate_scanned;
- unsigned long total_free_scanned;
+ unsigned int nr_freepages; /* Number of isolated free pages */
+ unsigned int nr_migratepages; /* Number of pages to migrate */
unsigned long free_pfn; /* isolate_freepages search base */
unsigned long migrate_pfn; /* isolate_migratepages search base */
- unsigned long last_migrated_pfn;/* Not yet flushed page being freed */
+ unsigned long fast_start_pfn; /* a pfn to start linear scan from */
+ struct zone *zone;
+ unsigned long total_migrate_scanned;
+ unsigned long total_free_scanned;
+ unsigned short fast_search_fail;/* failures to use free list searches */
+ short search_order; /* order to start a fast search at */
const gfp_t gfp_mask; /* gfp mask of a direct compactor */
int order; /* order a direct compactor needs */
int migratetype; /* migratetype of direct compactor */
const unsigned int alloc_flags; /* alloc flags of a direct compactor */
- const int classzone_idx; /* zone index of a direct compactor */
+ const int highest_zoneidx; /* zone index of a direct compactor */
enum migrate_mode mode; /* Async or sync migration mode */
bool ignore_skip_hint; /* Scan blocks even if marked skip */
bool no_set_skip_hint; /* Don't mark blocks for skipping */
bool ignore_block_suitable; /* Scan blocks considered unsuitable */
bool direct_compaction; /* False from kcompactd or /proc/... */
+ bool proactive_compaction; /* kcompactd proactive compaction */
bool whole_zone; /* Whole zone should/has been scanned */
bool contended; /* Signal lock or sched contention */
- bool finishing_block; /* Finishing current pageblock */
+ bool rescan; /* Rescanning the same pageblock */
+ bool alloc_contig; /* alloc_contig_range allocation */
+};
+
+/*
+ * Used in direct compaction when a page should be taken from the freelists
+ * immediately when one is created during the free path.
+ */
+struct capture_control {
+ struct compact_control *cc;
+ struct page *page;
};
unsigned long
@@ -223,16 +290,16 @@
* page from being allocated in parallel and returning garbage as the order.
* If a caller does not hold page_zone(page)->lock, it must guarantee that the
* page cannot be allocated or merged in parallel. Alternatively, it must
- * handle invalid values gracefully, and use page_order_unsafe() below.
+ * handle invalid values gracefully, and use buddy_order_unsafe() below.
*/
-static inline unsigned int page_order(struct page *page)
+static inline unsigned int buddy_order(struct page *page)
{
/* PageBuddy() must be checked by the caller */
return page_private(page);
}
/*
- * Like page_order(), but for callers who cannot afford to hold the zone lock.
+ * Like buddy_order(), but for callers who cannot afford to hold the zone lock.
* PageBuddy() should be checked first by the caller to minimize race window,
* and invalid values must be handled gracefully.
*
@@ -242,7 +309,7 @@
* times, potentially observing different values in the tests and the actual
* use of the result.
*/
-#define page_order_unsafe(page) READ_ONCE(page_private(page))
+#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
static inline bool is_cow_mapping(vm_flags_t flags)
{
@@ -282,7 +349,8 @@
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev, struct rb_node *rb_parent);
+ struct vm_area_struct *prev);
+void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma);
#ifdef CONFIG_MMU
extern long populate_vma_page_range(struct vm_area_struct *vma,
@@ -295,7 +363,7 @@
}
/*
- * must be called with vma's mmap_sem held for read or write, and page locked.
+ * must be called with vma's mmap_lock held for read or write, and page locked.
*/
extern void mlock_vma_page(struct page *page);
extern unsigned int munlock_vma_page(struct page *page);
@@ -319,7 +387,7 @@
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
{
if (TestClearPageMlocked(page)) {
- int nr_pages = hpage_nr_pages(page);
+ int nr_pages = thp_nr_pages(page);
/* Holding pmd lock, no change in irq context: __mod is safe */
__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
@@ -350,7 +418,7 @@
if (address < vma->vm_start || address >= vma->vm_end)
address = -EFAULT;
} else if (PageHead(page) &&
- pgoff + (1UL << compound_order(page)) - 1 >= vma->vm_pgoff) {
+ pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
/* Test above avoids possibility of wrap to 0 on 32-bit */
address = vma->vm_start;
} else {
@@ -371,12 +439,33 @@
unsigned long address;
VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */
- pgoff = page_to_pgoff(page) + (1UL << compound_order(page));
+ pgoff = page_to_pgoff(page) + compound_nr(page);
address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
/* Check for address beyond vma (or wrapped through 0?) */
if (address < vma->vm_start || address > vma->vm_end)
address = vma->vm_end;
return address;
+}
+
+static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
+ struct file *fpin)
+{
+ int flags = vmf->flags;
+
+ if (fpin)
+ return fpin;
+
+ /*
+ * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
+ * anything, so we only pin the file and drop the mmap_lock if only
+ * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt.
+ */
+ if (fault_flag_allow_retry_first(flags) &&
+ !(flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ fpin = get_file(vmf->vma->vm_file);
+ mmap_read_unlock(vmf->vma->vm_mm);
+ }
+ return fpin;
}
#else /* !CONFIG_MMU */
@@ -493,7 +582,7 @@
unsigned long, unsigned long);
extern void set_pageblock_order(void);
-unsigned long reclaim_clean_pages_from_list(struct zone *zone,
+unsigned int reclaim_clean_pages_from_list(struct zone *zone,
struct list_head *page_list);
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN WMARK_MIN
@@ -515,10 +604,16 @@
#define ALLOC_OOM ALLOC_NO_WATERMARKS
#endif
-#define ALLOC_HARDER 0x10 /* try to alloc harder */
-#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
-#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
-#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
+#define ALLOC_HARDER 0x10 /* try to alloc harder */
+#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
+#ifdef CONFIG_ZONE_DMA32
+#define ALLOC_NOFRAGMENT 0x100 /* avoid mixing pageblock types */
+#else
+#define ALLOC_NOFRAGMENT 0x0
+#endif
+#define ALLOC_KSWAPD 0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */
enum ttu_flags;
struct tlbflush_unmap_batch;
@@ -561,5 +656,11 @@
}
void setup_zone_pageset(struct zone *zone);
-extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
+
+struct migration_target_control {
+ int nid; /* preferred node id */
+ nodemask_t *nmask;
+ gfp_t gfp_mask;
+};
+
#endif /* __MM_INTERNAL_H */
--
Gitblit v1.6.2