From: Liam Howlett <liam.howlett@oracle.com>
To: "maple-tree@lists.infradead.org" <maple-tree@lists.infradead.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Andrew Morton <akpm@linux-foundation.org>
Subject: [PATCH v7 09/70] mm: Start tracking VMAs with maple tree
Date: Mon, 4 Apr 2022 14:35:36 +0000 [thread overview]
Message-ID: <20220404143501.2016403-10-Liam.Howlett@oracle.com> (raw)
In-Reply-To: <20220404143501.2016403-1-Liam.Howlett@oracle.com>
From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
Start tracking the VMAs with the new maple tree structure in parallel
with the rb_tree. Add debug and trace events for maple tree operations
and duplicate the rb_tree that is created on forks into the maple tree.
The maple tree is added to the mm_struct including the mm_init struct,
added support in required mm/mmap functions, added tracking in
kernel/fork for process forking, and used to find the unmapped_area and
checked against what the rbtree finds.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
---
arch/x86/kernel/tboot.c | 1 +
drivers/firmware/efi/efi.c | 1 +
include/linux/mm.h | 2 +
include/linux/mm_types.h | 3 +
include/trace/events/mmap.h | 71 +++++++++++++
kernel/fork.c | 5 +
mm/init-mm.c | 2 +
mm/internal.h | 70 +++++++++++++
mm/mmap.c | 202 +++++++++++++++++++++++++++++++++++-
9 files changed, 355 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index f9af561c3cd4..859e8d2ea070 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -98,6 +98,7 @@ void __init tboot_probe(void)
static pgd_t *tboot_pg_dir;
static struct mm_struct tboot_mm = {
.mm_rb = RB_ROOT,
+ .mm_mt = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, tboot_mm.mmap_lock),
.pgd = swapper_pg_dir,
.mm_users = ATOMIC_INIT(2),
.mm_count = ATOMIC_INIT(1),
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 5502e176d51b..92a765d8d3b6 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -55,6 +55,7 @@ static unsigned long __initdata rt_prop = EFI_INVALID_TABLE_ADDR;
struct mm_struct efi_mm = {
.mm_rb = RB_ROOT,
+ .mm_mt = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, efi_mm.mmap_lock),
.mm_users = ATOMIC_INIT(2),
.mm_count = ATOMIC_INIT(1),
.write_protect_seq = SEQCNT_ZERO(efi_mm.write_protect_seq),
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e34edb775334..d21e4fdbe1a0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2577,6 +2577,8 @@ extern bool arch_has_descending_max_zone_pfns(void);
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
+/* mmap.c */
+void vma_store(struct mm_struct *mm, struct vm_area_struct *vma);
/* interval_tree.c */
void vma_interval_tree_insert(struct vm_area_struct *node,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8834e38c06a4..5efd9a095de4 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -9,6 +9,7 @@
#include <linux/list.h>
#include <linux/spinlock.h>
#include <linux/rbtree.h>
+#include <linux/maple_tree.h>
#include <linux/rwsem.h>
#include <linux/completion.h>
#include <linux/cpumask.h>
@@ -476,6 +477,7 @@ struct kioctx_table;
struct mm_struct {
struct {
struct vm_area_struct *mmap; /* list of VMAs */
+ struct maple_tree mm_mt;
struct rb_root mm_rb;
u64 vmacache_seqnum; /* per-thread vmacache */
#ifdef CONFIG_MMU
@@ -664,6 +666,7 @@ struct mm_struct {
unsigned long cpu_bitmap[];
};
+#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN)
extern struct mm_struct init_mm;
/* Pointer magic because the dynamic array size confuses some compilers. */
diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h
index 4661f7ba07c0..f5c1626f3bbb 100644
--- a/include/trace/events/mmap.h
+++ b/include/trace/events/mmap.h
@@ -42,6 +42,77 @@ TRACE_EVENT(vm_unmapped_area,
__entry->low_limit, __entry->high_limit, __entry->align_mask,
__entry->align_offset)
);
+
+TRACE_EVENT(vma_mt_szero,
+ TP_PROTO(struct mm_struct *mm, unsigned long start,
+ unsigned long end),
+
+ TP_ARGS(mm, start, end),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ __field(unsigned long, start)
+ __field(unsigned long, end)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ __entry->start = start;
+ __entry->end = end - 1;
+ ),
+
+ TP_printk("mt_mod %p, (NULL), SNULL, %lu, %lu,",
+ __entry->mm,
+ (unsigned long) __entry->start,
+ (unsigned long) __entry->end
+ )
+);
+
+TRACE_EVENT(vma_store,
+ TP_PROTO(struct mm_struct *mm, struct vm_area_struct *vma),
+
+ TP_ARGS(mm, vma),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ __field(struct vm_area_struct *, vma)
+ __field(unsigned long, vm_start)
+ __field(unsigned long, vm_end)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ __entry->vma = vma;
+ __entry->vm_start = vma->vm_start;
+ __entry->vm_end = vma->vm_end - 1;
+ ),
+
+ TP_printk("mt_mod %p, (%p), STORE, %lu, %lu,",
+ __entry->mm, __entry->vma,
+ (unsigned long) __entry->vm_start,
+ (unsigned long) __entry->vm_end
+ )
+);
+
+
+TRACE_EVENT(exit_mmap,
+ TP_PROTO(struct mm_struct *mm),
+
+ TP_ARGS(mm),
+
+ TP_STRUCT__entry(
+ __field(struct mm_struct *, mm)
+ ),
+
+ TP_fast_assign(
+ __entry->mm = mm;
+ ),
+
+ TP_printk("mt_mod %p, DESTROY\n",
+ __entry->mm
+ )
+);
+
#endif
/* This part must be outside protection */
diff --git a/kernel/fork.c b/kernel/fork.c
index 9796897560ab..c81993dff42c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -696,6 +696,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
rb_link = &tmp->vm_rb.rb_right;
rb_parent = &tmp->vm_rb;
+ /* Link the vma into the MT */
+ vma_store(mm, tmp);
+
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK))
retval = copy_page_range(tmp, mpnt);
@@ -1107,6 +1110,8 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
{
mm->mmap = NULL;
mm->mm_rb = RB_ROOT;
+ mt_init_flags(&mm->mm_mt, MM_MT_FLAGS);
+ mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock);
mm->vmacache_seqnum = 0;
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
diff --git a/mm/init-mm.c b/mm/init-mm.c
index fbe7844d0912..b912b0f2eced 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/mm_types.h>
#include <linux/rbtree.h>
+#include <linux/maple_tree.h>
#include <linux/rwsem.h>
#include <linux/spinlock.h>
#include <linux/list.h>
@@ -29,6 +30,7 @@
*/
struct mm_struct init_mm = {
.mm_rb = RB_ROOT,
+ .mm_mt = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, init_mm.mmap_lock),
.pgd = swapper_pg_dir,
.mm_users = ATOMIC_INIT(2),
.mm_count = ATOMIC_INIT(1),
diff --git a/mm/internal.h b/mm/internal.h
index cf16280ce132..8221f290d047 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -394,6 +394,76 @@ static inline bool is_data_mapping(vm_flags_t flags)
return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
}
+/* Maple tree operations using VMAs */
+/*
+ * vma_mas_store() - Store a VMA in the maple tree.
+ * @vma: The vm_area_struct
+ * @mas: The maple state
+ *
+ * Efficient way to store a VMA in the maple tree when the @mas has already
+ * walked to the correct location.
+ *
+ * Note: the end address is inclusive in the maple tree.
+ */
+static inline int vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas)
+{
+#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
+ /* Make sure no VMAs are about to be lost. */
+ MA_STATE(test, mas->tree, vma->vm_start, vma->vm_end - 1);
+ struct vm_area_struct *vma_mas;
+ int count = 0;
+
+ mas_for_each(&test, vma_mas, vma->vm_end - 1) {
+ /* Rule out vma_expand */
+ if ((vma->vm_start != vma_mas->vm_start) &&
+ (vma->vm_end != vma_mas->vm_end))
+ count++;
+ }
+
+ /* vma adjust may overwrite a partial entry or remove one */
+ BUG_ON(count > 1);
+
+ BUG_ON(mas->min > vma->vm_start);
+ BUG_ON(mas->index > vma->vm_start);
+#endif
+ mas->index = vma->vm_start;
+ mas->last = vma->vm_end - 1;
+ return mas_store_gfp(mas, vma, GFP_KERNEL);
+}
+
+/*
+ * vma_mas_remove() - Remove a VMA from the maple tree.
+ * @vma: The vm_area_struct
+ * @mas: The maple state
+ *
+ * Efficient way to remove a VMA from the maple tree when the @mas has already
+ * been established and points to the correct location.
+ * Note: the end address is inclusive in the maple tree.
+ */
+static inline int vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas)
+{
+ int ret;
+
+#ifdef CONFIG_DEBUG_VM_MAPLE_TREE
+ /* Make sure no VMAs are about to be lost. */
+ MA_STATE(test, mas->tree, vma->vm_start, vma->vm_end - 1);
+ struct vm_area_struct *vma_mas;
+ int count = 0;
+
+ mas_for_each(&test, vma_mas, vma->vm_end - 1)
+ count++;
+
+ BUG_ON(count != 1);
+
+ BUG_ON(mas->min > vma->vm_start);
+ BUG_ON(mas->min > mas->index);
+#endif
+ mas->index = vma->vm_start;
+ mas->last = vma->vm_end - 1;
+ ret = mas_store_gfp(mas, NULL, GFP_KERNEL);
+ return ret;
+}
+
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev);
diff --git a/mm/mmap.c b/mm/mmap.c
index 3aa839f81e63..ebdee54b92e3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -376,7 +376,70 @@ static int browse_rb(struct mm_struct *mm)
}
return bug ? -1 : i;
}
+#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
+extern void mt_validate(struct maple_tree *mt);
+extern void mt_dump(const struct maple_tree *mt);
+/* Validate the maple tree */
+static void validate_mm_mt(struct mm_struct *mm)
+{
+ struct maple_tree *mt = &mm->mm_mt;
+ struct vm_area_struct *vma_mt, *vma = mm->mmap;
+
+ MA_STATE(mas, mt, 0, 0);
+ mas_for_each(&mas, vma_mt, ULONG_MAX) {
+ if (xa_is_zero(vma_mt))
+ continue;
+
+ if (!vma)
+ break;
+
+ if ((vma != vma_mt) ||
+ (vma->vm_start != vma_mt->vm_start) ||
+ (vma->vm_end != vma_mt->vm_end) ||
+ (vma->vm_start != mas.index) ||
+ (vma->vm_end - 1 != mas.last)) {
+ pr_emerg("issue in %s\n", current->comm);
+ dump_stack();
+#ifdef CONFIG_DEBUG_VM
+ dump_vma(vma_mt);
+ pr_emerg("and next in rb\n");
+ dump_vma(vma->vm_next);
+#endif
+ pr_emerg("mt piv: %px %lu - %lu\n", vma_mt,
+ mas.index, mas.last);
+ pr_emerg("mt vma: %px %lu - %lu\n", vma_mt,
+ vma_mt->vm_start, vma_mt->vm_end);
+ pr_emerg("rb vma: %px %lu - %lu\n", vma,
+ vma->vm_start, vma->vm_end);
+ pr_emerg("rb->next = %px %lu - %lu\n", vma->vm_next,
+ vma->vm_next->vm_start, vma->vm_next->vm_end);
+
+ mt_dump(mas.tree);
+ if (vma_mt->vm_end != mas.last + 1) {
+ pr_err("vma: %px vma_mt %lu-%lu\tmt %lu-%lu\n",
+ mm, vma_mt->vm_start, vma_mt->vm_end,
+ mas.index, mas.last);
+ mt_dump(mas.tree);
+ }
+ VM_BUG_ON_MM(vma_mt->vm_end != mas.last + 1, mm);
+ if (vma_mt->vm_start != mas.index) {
+ pr_err("vma: %px vma_mt %px %lu - %lu doesn't match\n",
+ mm, vma_mt, vma_mt->vm_start, vma_mt->vm_end);
+ mt_dump(mas.tree);
+ }
+ VM_BUG_ON_MM(vma_mt->vm_start != mas.index, mm);
+ }
+ VM_BUG_ON(vma != vma_mt);
+ vma = vma->vm_next;
+
+ }
+ VM_BUG_ON(vma);
+ mt_validate(&mm->mm_mt);
+}
+#else
+#define validate_mm_mt(root) do { } while (0)
+#endif
static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
{
struct rb_node *nd;
@@ -431,6 +494,7 @@ static void validate_mm(struct mm_struct *mm)
}
#else
#define validate_mm_rb(root, ignore) do { } while (0)
+#define validate_mm_mt(root) do { } while (0)
#define validate_mm(mm) do { } while (0)
#endif
@@ -675,11 +739,42 @@ static void __vma_link_file(struct vm_area_struct *vma)
}
}
+/*
+ * vma_mt_szero() - Set a given range to zero. Used when modifying a
+ * vm_area_struct start or end.
+ *
+ * @mm: The struct_mm
+ * @start: The start address to zero
+ * @end: The end address to zero.
+ */
+static inline void vma_mt_szero(struct mm_struct *mm, unsigned long start,
+ unsigned long end)
+{
+ MA_STATE(mas, &mm->mm_mt, start, end - 1);
+
+ trace_vma_mt_szero(mm, start, end);
+ mas_store_gfp(&mas, NULL, GFP_KERNEL);
+}
+
+/*
+ * vma_store() - Store a given vm_area_struct in the maple tree.
+ * @mm: The struct_mm
+ * @vma: The vm_area_struct to store in the maple tree.
+ */
+void vma_store(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
+
+ trace_vma_store(vma->vm_mm, vma);
+ vma_mas_store(vma, &mas);
+}
+
static void
__vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node **rb_link,
struct rb_node *rb_parent)
{
+ vma_store(mm, vma);
__vma_link_list(mm, vma, prev);
__vma_link_rb(mm, vma, rb_link, rb_parent);
}
@@ -752,6 +847,9 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
long adjust_next = 0;
int remove_next = 0;
+ validate_mm(mm);
+ validate_mm_mt(mm);
+
if (next && !insert) {
struct vm_area_struct *exporter = NULL, *importer = NULL;
@@ -877,17 +975,28 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
}
if (start != vma->vm_start) {
+ unsigned long old_start = vma->vm_start;
vma->vm_start = start;
+ if (old_start < start)
+ vma_mt_szero(mm, old_start, start);
start_changed = true;
}
if (end != vma->vm_end) {
+ unsigned long old_end = vma->vm_end;
vma->vm_end = end;
+ if (old_end > end)
+ vma_mt_szero(mm, end, old_end);
end_changed = true;
}
+
+ if (end_changed || start_changed)
+ vma_store(mm, vma);
+
vma->vm_pgoff = pgoff;
if (adjust_next) {
next->vm_start += adjust_next;
next->vm_pgoff += adjust_next >> PAGE_SHIFT;
+ vma_store(mm, next);
}
if (file) {
@@ -901,6 +1010,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
/*
* vma_merge has merged next into vma, and needs
* us to remove next before dropping the locks.
+ * Since we have expanded over this vma, the maple tree will
+ * have overwritten by storing the value
*/
if (remove_next != 3)
__vma_unlink(mm, next, next);
@@ -1020,6 +1131,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
uprobe_mmap(insert);
validate_mm(mm);
+ validate_mm_mt(mm);
return 0;
}
@@ -1173,6 +1285,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
struct vm_area_struct *area, *next;
int err;
+ validate_mm_mt(mm);
/*
* We later require that vma->vm_flags == vm_flags,
* so this tests vma->vm_flags & VM_SPECIAL, too.
@@ -1248,6 +1361,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
khugepaged_enter_vma_merge(area, vm_flags);
return area;
}
+ validate_mm_mt(mm);
return NULL;
}
@@ -1727,6 +1841,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
struct rb_node **rb_link, *rb_parent;
unsigned long charged = 0;
+ validate_mm_mt(mm);
/* Check against address space limit. */
if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) {
unsigned long nr_pages;
@@ -1874,6 +1989,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
vma_set_page_prot(vma);
+ validate_mm_mt(mm);
return addr;
unmap_and_free_vma:
@@ -1890,6 +2006,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
unacct_error:
if (charged)
vm_unacct_memory(charged);
+ validate_mm_mt(mm);
return error;
}
@@ -1906,12 +2023,19 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long length, low_limit, high_limit, gap_start, gap_end;
+ unsigned long gap;
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
/* Adjust search length to account for worst case alignment overhead */
length = info->length + info->align_mask;
if (length < info->length)
return -ENOMEM;
+ mas_empty_area(&mas, info->low_limit, info->high_limit - 1,
+ length);
+ gap = mas.index;
+ gap += (info->align_offset - gap) & info->align_mask;
+
/* Adjust search limits by the desired length */
if (info->high_limit < length)
return -ENOMEM;
@@ -1993,20 +2117,31 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
VM_BUG_ON(gap_start + info->length > info->high_limit);
VM_BUG_ON(gap_start + info->length > gap_end);
+
+ VM_BUG_ON(gap != gap_start);
return gap_start;
}
static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
{
struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
+ struct vm_area_struct *vma = NULL;
unsigned long length, low_limit, high_limit, gap_start, gap_end;
+ unsigned long gap;
+
+ MA_STATE(mas, &mm->mm_mt, 0, 0);
+ validate_mm_mt(mm);
/* Adjust search length to account for worst case alignment overhead */
length = info->length + info->align_mask;
if (length < info->length)
return -ENOMEM;
+ mas_empty_area_rev(&mas, info->low_limit, info->high_limit - 1,
+ length);
+ gap = mas.last + 1 - info->length;
+ gap -= (gap - info->align_offset) & info->align_mask;
+
/*
* Adjust search limits by the desired length.
* See implementation comment at top of unmapped_area().
@@ -2092,6 +2227,32 @@ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
VM_BUG_ON(gap_end < info->low_limit);
VM_BUG_ON(gap_end < gap_start);
+
+ if (gap != gap_end) {
+ pr_err("%s: %px Gap was found: mt %lu gap_end %lu\n", __func__,
+ mm, gap, gap_end);
+ pr_err("window was %lu - %lu size %lu\n", info->high_limit,
+ info->low_limit, length);
+ pr_err("mas.min %lu max %lu mas.last %lu\n", mas.min, mas.max,
+ mas.last);
+ pr_err("mas.index %lu align mask %lu offset %lu\n", mas.index,
+ info->align_mask, info->align_offset);
+ pr_err("rb_find_vma find on %lu => %px (%px)\n", mas.index,
+ find_vma(mm, mas.index), vma);
+#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
+ mt_dump(&mm->mm_mt);
+#endif
+ {
+ struct vm_area_struct *dv = mm->mmap;
+
+ while (dv) {
+ printk("vma %px %lu-%lu\n", dv, dv->vm_start, dv->vm_end);
+ dv = dv->vm_next;
+ }
+ }
+ VM_BUG_ON(gap != gap_end);
+ }
+
return gap_end;
}
@@ -2305,7 +2466,6 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
vmacache_update(addr, vma);
return vma;
}
-
EXPORT_SYMBOL(find_vma);
/*
@@ -2386,6 +2546,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
unsigned long gap_addr;
int error = 0;
+ validate_mm_mt(mm);
if (!(vma->vm_flags & VM_GROWSUP))
return -EFAULT;
@@ -2448,6 +2609,8 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
vm_stat_account(mm, vma->vm_flags, grow);
anon_vma_interval_tree_pre_update_vma(vma);
vma->vm_end = address;
+ /* Overwrite old entry in mtree. */
+ vma_store(mm, vma);
anon_vma_interval_tree_post_update_vma(vma);
if (vma->vm_next)
vma_gap_update(vma->vm_next);
@@ -2462,6 +2625,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
anon_vma_unlock_write(vma->anon_vma);
khugepaged_enter_vma_merge(vma, vma->vm_flags);
validate_mm(mm);
+ validate_mm_mt(mm);
return error;
}
#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */
@@ -2476,6 +2640,7 @@ int expand_downwards(struct vm_area_struct *vma,
struct vm_area_struct *prev;
int error = 0;
+ validate_mm(mm);
address &= PAGE_MASK;
if (address < mmap_min_addr)
return -EPERM;
@@ -2529,6 +2694,8 @@ int expand_downwards(struct vm_area_struct *vma,
anon_vma_interval_tree_pre_update_vma(vma);
vma->vm_start = address;
vma->vm_pgoff -= grow;
+ /* Overwrite old entry in mtree. */
+ vma_store(mm, vma);
anon_vma_interval_tree_post_update_vma(vma);
vma_gap_update(vma);
spin_unlock(&mm->page_table_lock);
@@ -2670,6 +2837,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
insertion_point = (prev ? &prev->vm_next : &mm->mmap);
vma->vm_prev = NULL;
+ vma_mt_szero(mm, vma->vm_start, end);
do {
vma_rb_erase(vma, &mm->mm_rb);
if (vma->vm_flags & VM_LOCKED)
@@ -2710,6 +2878,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
{
struct vm_area_struct *new;
int err;
+ validate_mm_mt(mm);
if (vma->vm_ops && vma->vm_ops->may_split) {
err = vma->vm_ops->may_split(vma, addr);
@@ -2762,6 +2931,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
mpol_put(vma_policy(new));
out_free_vma:
vm_area_free(new);
+ validate_mm_mt(mm);
return err;
}
@@ -3010,6 +3180,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
pgoff_t pgoff = addr >> PAGE_SHIFT;
int error;
unsigned long mapped_addr;
+ validate_mm_mt(mm);
/* Until we need other flags, refuse anything except VM_EXEC. */
if ((flags & (~VM_EXEC)) != 0)
@@ -3067,6 +3238,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
if (flags & VM_LOCKED)
mm->locked_vm += (len >> PAGE_SHIFT);
vma->vm_flags |= VM_SOFTDIRTY;
+ validate_mm_mt(mm);
return 0;
}
@@ -3158,6 +3330,8 @@ void exit_mmap(struct mm_struct *mm)
}
mm->mmap = NULL;
mmap_write_unlock(mm);
+ trace_exit_mmap(mm);
+ __mt_destroy(&mm->mm_mt);
vm_unacct_memory(nr_accounted);
}
@@ -3169,10 +3343,25 @@ int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
{
struct vm_area_struct *prev;
struct rb_node **rb_link, *rb_parent;
+ unsigned long start = vma->vm_start;
+ struct vm_area_struct *overlap = NULL;
if (find_vma_links(mm, vma->vm_start, vma->vm_end,
&prev, &rb_link, &rb_parent))
return -ENOMEM;
+
+ overlap = mt_find(&mm->mm_mt, &start, vma->vm_end - 1);
+ if (overlap) {
+
+ pr_err("Found vma ending at %lu\n", start - 1);
+ pr_err("vma : %lu => %lu-%lu\n", (unsigned long)overlap,
+ overlap->vm_start, overlap->vm_end - 1);
+#if defined(CONFIG_DEBUG_VM_MAPLE_TREE)
+ mt_dump(&mm->mm_mt);
+#endif
+ BUG();
+ }
+
if ((vma->vm_flags & VM_ACCOUNT) &&
security_vm_enough_memory_mm(mm, vma_pages(vma)))
return -ENOMEM;
@@ -3212,7 +3401,9 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
struct vm_area_struct *new_vma, *prev;
struct rb_node **rb_link, *rb_parent;
bool faulted_in_anon_vma = true;
+ unsigned long index = addr;
+ validate_mm_mt(mm);
/*
* If anonymous vma has not yet been faulted, update new pgoff
* to match new location, to increase its chance of merging.
@@ -3224,6 +3415,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent))
return NULL; /* should never get here */
+ if (mt_find(&mm->mm_mt, &index, addr+len - 1))
+ BUG();
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx, anon_vma_name(vma));
@@ -3267,6 +3460,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
vma_link(mm, new_vma, prev, rb_link, rb_parent);
*need_rmap_locks = false;
}
+ validate_mm_mt(mm);
return new_vma;
out_free_mempol:
@@ -3274,6 +3468,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
out_free_vma:
vm_area_free(new_vma);
out:
+ validate_mm_mt(mm);
return NULL;
}
@@ -3410,6 +3605,7 @@ static struct vm_area_struct *__install_special_mapping(
int ret;
struct vm_area_struct *vma;
+ validate_mm_mt(mm);
vma = vm_area_alloc(mm);
if (unlikely(vma == NULL))
return ERR_PTR(-ENOMEM);
@@ -3432,10 +3628,12 @@ static struct vm_area_struct *__install_special_mapping(
perf_event_mmap(vma);
+ validate_mm_mt(mm);
return vma;
out:
vm_area_free(vma);
+ validate_mm_mt(mm);
return ERR_PTR(ret);
}
--
2.34.1
next prev parent reply other threads:[~2022-04-04 14:38 UTC|newest]
Thread overview: 99+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-04 14:35 [PATCH v7 00/70] Introducing the Maple Tree Liam Howlett
2022-04-04 14:35 ` [PATCH v7 01/70] radix tree test suite: Add pr_err define Liam Howlett
2022-04-04 14:35 ` [PATCH v7 02/70] radix tree test suite: Add kmem_cache_set_non_kernel() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 03/70] radix tree test suite: Add allocation counts and size to kmem_cache Liam Howlett
2022-04-04 14:35 ` [PATCH v7 05/70] radix tree test suite: Add lockdep_is_held to header Liam Howlett
2022-04-04 14:35 ` [PATCH v7 04/70] radix tree test suite: Add support for slab bulk APIs Liam Howlett
2022-04-04 14:35 ` [PATCH v7 06/70] mips: Rename mt_init to mips_mt_init Liam Howlett
2022-04-04 14:35 ` [PATCH v7 07/70] Maple Tree: Add new data structure Liam Howlett
2022-04-20 13:47 ` Liam Howlett
2022-04-04 14:35 ` [PATCH v7 08/70] lib/test_maple_tree: Add testing for maple tree Liam Howlett
2022-04-04 14:35 ` [PATCH v7 11/70] arch/arm64: Remove the merge workaround for VMA_ITERATOR Liam Howlett
2022-04-05 9:24 ` Will Deacon
2022-04-05 14:12 ` Liam Howlett
2022-04-04 14:35 ` Liam Howlett [this message]
2022-04-04 14:35 ` [PATCH v7 10/70] mm: Add VMA iterator Liam Howlett
2022-04-04 14:35 ` [PATCH v7 13/70] mm/mmap: Use the maple tree in find_vma() instead of the rbtree Liam Howlett
2022-04-04 14:35 ` [PATCH v7 12/70] mmap: Use the VMA iterator in count_vma_pages_range() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 15/70] mm/mmap: Use maple tree for unmapped_area{_topdown} Liam Howlett
2022-04-04 14:35 ` [PATCH v7 14/70] mm/mmap: Use the maple tree for find_vma_prev() instead of the rbtree Liam Howlett
2022-04-04 14:35 ` [PATCH v7 16/70] kernel/fork: Use maple tree for dup_mmap() during forking Liam Howlett
2022-04-04 14:35 ` [PATCH v7 17/70] damon: Convert __damon_va_three_regions to use the VMA iterator Liam Howlett
2022-04-04 14:35 ` [PATCH v7 18/70] proc: Remove VMA rbtree use from nommu Liam Howlett
2022-04-04 14:35 ` [PATCH v7 19/70] mm: Remove rb tree Liam Howlett
2022-04-04 14:35 ` [PATCH v7 20/70] mmap: Change zeroing of maple tree in __vma_adjust() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 22/70] mm: Optimize find_exact_vma() to use vma_lookup() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 21/70] xen: Use vma_lookup() in privcmd_ioctl_mmap() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 23/70] mm/khugepaged: Optimize collapse_pte_mapped_thp() by using vma_lookup() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 24/70] mm/mmap: Change do_brk_flags() to expand existing VMA and add do_brk_munmap() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 25/70] mm: Use maple tree operations for find_vma_intersection() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 26/70] mm/mmap: Use advanced maple tree API for mmap_region() Liam Howlett
2022-04-14 6:51 ` Andrew Morton
2022-04-19 17:57 ` Liam Howlett
2022-04-04 14:35 ` [PATCH v7 27/70] mm: Remove vmacache Liam Howlett
2022-04-04 14:35 ` [PATCH v7 29/70] mm/mmap: Move mmap_region() below do_munmap() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 28/70] mm: Convert vma_lookup() to use mtree_load() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 30/70] mm/mmap: Reorganize munmap to use maple states Liam Howlett
2022-04-04 14:35 ` [PATCH v7 32/70] arm64: Remove mmap linked list from vdso Liam Howlett
2022-04-04 14:35 ` [PATCH v7 31/70] mm/mmap: Change do_brk_munmap() to use do_mas_align_munmap() Liam Howlett
2022-04-04 14:35 ` [PATCH v7 33/70] parisc: Remove mmap linked list from cache handling Liam Howlett
2022-04-04 14:35 ` [PATCH v7 34/70] powerpc: Remove mmap linked list walks Liam Howlett
2022-04-04 14:35 ` [PATCH v7 36/70] x86: Remove vma " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 37/70] xtensa: " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 35/70] s390: " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 39/70] optee: Remove vma linked list walk Liam Howlett
2022-04-04 14:35 ` [PATCH v7 38/70] cxl: " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 40/70] um: " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 42/70] exec: Use VMA iterator instead of linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 41/70] coredump: Remove vma linked list walk Liam Howlett
2022-04-04 14:35 ` [PATCH v7 43/70] fs/proc/base: Use maple tree iterators in place of linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 45/70] userfaultfd: Use maple tree iterator to iterate VMAs Liam Howlett
2022-04-04 14:35 ` [PATCH v7 44/70] fs/proc/task_mmu: Stop using linked list and highest_vm_end Liam Howlett
2022-04-04 14:35 ` [PATCH v7 46/70] ipc/shm: Use VMA iterator instead of linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 48/70] perf: Use VMA iterator Liam Howlett
2022-04-04 14:35 ` [PATCH v7 47/70] acct: Use VMA iterator instead of linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 51/70] bpf: Remove VMA " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 50/70] fork: Use VMA iterator Liam Howlett
2022-04-04 14:35 ` [PATCH v7 49/70] sched: Use maple tree iterator to walk VMAs Liam Howlett
2022-04-04 14:35 ` [PATCH v7 52/70] mm/gup: Use maple tree navigation instead of linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 53/70] mm/khugepaged: Stop using vma " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 54/70] mm/ksm: Use vma iterators instead of " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 55/70] mm/madvise: Use vma_find() " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 57/70] mm/mempolicy: Use vma iterator & maple state " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 56/70] mm/memcontrol: Stop using mm->highest_vm_end Liam Howlett
2022-04-04 14:35 ` [PATCH v7 59/70] mm/mprotect: Use maple tree navigation instead of vma linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 58/70] mm/mlock: Use vma iterator and " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 61/70] mm/msync: Use vma_find() " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 62/70] mm/oom_kill: Use maple tree iterators " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 60/70] mm/mremap: Use vma_find_intersection() " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 63/70] mm/pagewalk: Use vma_find() " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 65/70] i915: Use the VMA iterator Liam Howlett
2022-04-04 14:35 ` [PATCH v7 64/70] mm/swapfile: Use vma iterator instead of vma linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 66/70] nommu: Remove uses of VMA " Liam Howlett
2022-04-04 14:35 ` [PATCH v7 67/70] riscv: Use vma iterator for vdso Liam Howlett
2022-04-04 14:35 ` [PATCH v7 69/70] mm/mmap: Drop range_has_overlap() function Liam Howlett
2022-04-04 14:35 ` [PATCH v7 68/70] mm: Remove the vma linked list Liam Howlett
2022-04-04 14:35 ` [PATCH v7 70/70] mm/mmap.c: Pass in mapping to __vma_link_file() Liam Howlett
2022-04-14 6:50 ` [PATCH v7 00/70] Introducing the Maple Tree Andrew Morton
2022-04-14 7:39 ` Yu Zhao
2022-04-14 13:55 ` Matthew Wilcox
2022-04-14 13:57 ` Liam Howlett
2022-04-14 16:42 ` Liam Howlett
2022-04-14 16:57 ` Yu Zhao
2022-04-14 17:15 ` Liam Howlett
2022-04-14 19:19 ` Andrew Morton
2022-04-15 7:11 ` Yu Zhao
2022-04-16 1:03 ` Liam Howlett
2022-04-16 4:10 ` Yu Zhao
2022-04-16 15:19 ` Liam Howlett
2022-04-16 19:30 ` Yu Zhao
2022-04-19 15:51 ` Liam Howlett
2022-04-19 21:58 ` Yu Zhao
2022-04-19 23:18 ` Liam Howlett
2022-04-19 23:22 ` Yu Zhao
2022-04-20 13:43 ` Liam Howlett
2022-04-25 18:05 ` Yu Zhao
2022-04-25 19:58 ` Liam Howlett
2022-04-25 20:01 ` Yu Zhao
2022-04-19 19:22 ` Liam Howlett
2022-04-19 17:50 ` Liam Howlett
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220404143501.2016403-10-Liam.Howlett@oracle.com \
--to=liam.howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=maple-tree@lists.infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).