From: "Liam R. Howlett" <Liam.Howlett@Oracle.com>
To: maple-tree@lists.infradead.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Cc: Andrew Morton <akpm@google.com>, Song Liu <songliubraving@fb.com>,
Davidlohr Bueso <dave@stgolabs.net>,
"Paul E . McKenney" <paulmck@kernel.org>,
Matthew Wilcox <willy@infradead.org>,
Jerome Glisse <jglisse@redhat.com>,
David Rientjes <rientjes@google.com>,
Axel Rasmussen <axelrasmussen@google.com>,
Suren Baghdasaryan <surenb@google.com>,
Vlastimil Babka <vbabka@suse.cz>, Rik van Riel <riel@surriel.com>,
Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH v2 06/70] mm: Start tracking VMAs with maple tree
Date: Tue, 12 Jan 2021 11:11:36 -0500 [thread overview]
Message-ID: <20210112161240.2024684-7-Liam.Howlett@Oracle.com> (raw)
In-Reply-To: <20210112161240.2024684-1-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.
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 | 2 +
include/trace/events/mmap.h | 71 ++++++++++++
init/main.c | 2 +
kernel/fork.c | 4 +
mm/init-mm.c | 2 +
mm/mmap.c | 218 +++++++++++++++++++++++++++++++++++-
9 files changed, 301 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index ae64f98ec2ab6..d9b1cc30976c4 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -90,6 +90,7 @@ 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(mm_mt, MAPLE_ALLOC_RANGE),
.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 6c6eec044a978..e40effbf028a6 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(mm_mt, MAPLE_ALLOC_RANGE),
.mm_users = ATOMIC_INIT(2),
.mm_count = ATOMIC_INIT(1),
MMAP_LOCK_INITIALIZER(efi_mm)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index db6ae4d3fb4ed..9cbbbbc3043a9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2467,6 +2467,8 @@ 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);
+/* maple_tree */
+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 5a9238f6caad9..f2c725e1052f8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -8,6 +8,7 @@
#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>
@@ -388,6 +389,7 @@ 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
diff --git a/include/trace/events/mmap.h b/include/trace/events/mmap.h
index 4661f7ba07c05..4ffe3d348966f 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 %px, (NULL), SNULL, %lu, %lu,",
+ __entry->mm,
+ (unsigned long) __entry->start,
+ (unsigned long) __entry->end
+ )
+);
+
+TRACE_EVENT(vma_mt_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 %px, (%px), 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 %px, DESTROY\n",
+ __entry->mm
+ )
+);
+
#endif
/* This part must be outside protection */
diff --git a/init/main.c b/init/main.c
index 32b2a8affafd1..506bcdbeb02d8 100644
--- a/init/main.c
+++ b/init/main.c
@@ -114,6 +114,7 @@ static int kernel_init(void *);
extern void init_IRQ(void);
extern void radix_tree_init(void);
+extern void maple_tree_init(void);
/*
* Debug helper: via this flag we know that we are in 'early bootup code'
@@ -923,6 +924,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
"Interrupts were enabled *very* early, fixing it\n"))
local_irq_disable();
radix_tree_init();
+ maple_tree_init();
/*
* Set up housekeeping before setting up workqueues to allow the unbound
diff --git a/kernel/fork.c b/kernel/fork.c
index 6d266388d3804..8c7273b0d4b77 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -588,6 +588,9 @@ 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);
@@ -1004,6 +1007,7 @@ 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, MAPLE_ALLOC_RANGE);
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 3a613c85f9ede..27229044a0702 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>
@@ -28,6 +29,7 @@
*/
struct mm_struct init_mm = {
.mm_rb = RB_ROOT,
+ .mm_mt = MTREE_INIT(mm_mt, MAPLE_ALLOC_RANGE),
.pgd = swapper_pg_dir,
.mm_users = ATOMIC_INIT(2),
.mm_count = ATOMIC_INIT(1),
diff --git a/mm/mmap.c b/mm/mmap.c
index 5c8b4485860de..bf0de273161e1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -373,7 +373,71 @@ static int browse_rb(struct mm_struct *mm)
}
return bug ? -1 : i;
}
+#if defined(CONFIG_DEBUG_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);
+ rcu_read_lock();
+ 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);
+
+ rcu_read_unlock();
+ mt_validate(&mm->mm_mt);
+}
+#endif
static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
{
struct rb_node *nd;
@@ -428,6 +492,7 @@ 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
@@ -606,6 +671,7 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm,
unsigned long addr, unsigned long end)
{
unsigned long nr_pages = 0;
+ unsigned long nr_mt_pages = 0;
struct vm_area_struct *vma;
/* Find first overlaping mapping */
@@ -627,6 +693,13 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm,
nr_pages += overlap_len >> PAGE_SHIFT;
}
+ mt_for_each(&mm->mm_mt, vma, addr, end) {
+ nr_mt_pages +=
+ (min(end, vma->vm_end) - vma->vm_start) >> PAGE_SHIFT;
+ }
+
+ VM_BUG_ON_MM(nr_pages != nr_mt_pages, mm);
+
return nr_pages;
}
@@ -673,11 +746,40 @@ 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)
+{
+ trace_vma_mt_szero(mm, start, end);
+ mtree_store_range(&mm->mm_mt, start, end - 1, NULL, GFP_KERNEL);
+}
+
+/*
+ * vma_mt_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.
+ */
+static inline void vma_mt_store(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ trace_vma_mt_store(mm, vma);
+ mtree_store_range(&mm->mm_mt, vma->vm_start, vma->vm_end - 1, vma,
+ GFP_KERNEL);
+}
+
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_mt_store(mm, vma);
__vma_link_list(mm, vma, prev);
__vma_link_rb(mm, vma, rb_link, rb_parent);
}
@@ -750,6 +852,9 @@ 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;
@@ -875,17 +980,28 @@ 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_mt_store(mm, vma);
+
vma->vm_pgoff = pgoff;
if (adjust_next) {
next->vm_start += adjust_next;
next->vm_pgoff += adjust_next >> PAGE_SHIFT;
+ vma_mt_store(mm, next);
}
if (file) {
@@ -899,6 +1015,8 @@ 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);
@@ -1018,6 +1136,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
uprobe_mmap(insert);
validate_mm(mm);
+ validate_mm_mt(mm);
return 0;
}
@@ -1165,6 +1284,7 @@ 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.
@@ -1240,6 +1360,7 @@ 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;
}
@@ -1733,6 +1854,7 @@ 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;
@@ -1894,6 +2016,7 @@ 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:
@@ -1913,6 +2036,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
unacct_error:
if (charged)
vm_unacct_memory(charged);
+ validate_mm_mt(mm);
return error;
}
@@ -1929,12 +2053,26 @@ 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;
+
+ /* Maple tree is self contained. */
+ rcu_read_lock();
+ if (mas_get_empty_area(&mas, info->low_limit, info->high_limit - 1,
+ length)) {
+ rcu_read_unlock();
+ return -ENOMEM;
+ }
+ rcu_read_unlock();
+ 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;
@@ -2016,20 +2154,34 @@ 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;
+ rcu_read_lock();
+ if (mas_get_empty_area_rev(&mas, info->low_limit, info->high_limit,
+ length)) {
+ rcu_read_unlock();
+ return -ENOMEM;
+ }
+ rcu_read_unlock();
+ gap = (mas.index + info->align_mask) & ~info->align_mask;
+ gap -= info->align_offset & info->align_mask;
/*
* Adjust search limits by the desired length.
* See implementation comment at top of unmapped_area().
@@ -2115,6 +2267,32 @@ 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_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;
}
@@ -2327,7 +2505,6 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
vmacache_update(addr, vma);
return vma;
}
-
EXPORT_SYMBOL(find_vma);
/*
@@ -2408,6 +2585,7 @@ 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;
@@ -2484,6 +2662,7 @@ 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 */
@@ -2498,6 +2677,7 @@ 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;
@@ -2551,6 +2731,8 @@ 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_mt_store(mm, vma);
anon_vma_interval_tree_post_update_vma(vma);
vma_gap_update(vma);
spin_unlock(&mm->page_table_lock);
@@ -2692,6 +2874,7 @@ 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);
mm->map_count--;
@@ -2730,6 +2913,7 @@ 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->split) {
err = vma->vm_ops->split(vma, addr);
@@ -2782,6 +2966,7 @@ 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;
}
@@ -3070,6 +3255,7 @@ 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)
@@ -3127,6 +3313,7 @@ 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;
}
@@ -3231,6 +3418,9 @@ void exit_mmap(struct mm_struct *mm)
vma = remove_vma(vma);
cond_resched();
}
+
+ trace_exit_mmap(mm);
+ mtree_destroy(&mm->mm_mt);
vm_unacct_memory(nr_accounted);
}
@@ -3242,10 +3432,25 @@ 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_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;
@@ -3285,7 +3490,9 @@ 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.
@@ -3297,6 +3504,8 @@ 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);
@@ -3340,6 +3549,7 @@ 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:
@@ -3347,6 +3557,7 @@ 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;
}
@@ -3471,6 +3682,7 @@ 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);
@@ -3492,10 +3704,12 @@ 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);
}
--
2.28.0
next prev parent reply other threads:[~2021-01-12 16:13 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-12 16:11 [PATCH v2 00/70] RFC mm: Introducing the Maple Tree Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 01/70] radix tree test suite: Enhancements for " Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 02/70] radix tree test suite: Add support for fallthrough attribute Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 03/70] radix tree test suite: Add support for kmem_cache_free_bulk Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 04/70] radix tree test suite: Add keme_cache_alloc_bulk() support Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 05/70] Maple Tree: Add new data structure Liam R. Howlett
2021-01-12 16:11 ` Liam R. Howlett [this message]
2021-01-12 16:11 ` [PATCH v2 07/70] mm/mmap: Introduce unlock_range() for code cleanup Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 08/70] mm/mmap: Change find_vma() to use the maple tree Liam R. Howlett
2021-01-12 21:01 ` Randy Dunlap
2021-01-12 16:11 ` [PATCH v2 09/70] mm/mmap: Change find_vma_prev() to use " Liam R. Howlett
2021-01-12 21:03 ` Randy Dunlap
2021-01-12 16:11 ` [PATCH v2 10/70] mm/mmap: Change unmapped_area and unmapped_area_topdown " Liam R. Howlett
2021-01-12 21:05 ` Randy Dunlap
2021-01-12 16:11 ` [PATCH v2 11/70] kernel/fork: Convert dup_mmap " Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 12/70] mm: Remove rb tree Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 13/70] mm/gup: Add mm_populate_vma() for use when the vma is known Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 14/70] mm/mmap: Change do_brk_flags() to expand existing VMA and add do_brk_munmap() Liam R. Howlett
2021-01-12 21:15 ` Randy Dunlap
2021-01-13 14:20 ` Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 15/70] mm/mmap: Change vm_brk_flags() to use mm_populate_vma() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 16/70] mm: Move find_vma_intersection to mmap.c and change implementation to maple tree Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 17/70] mm/mmap: Change mmap_region to use maple tree state Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 18/70] mm/mmap: Drop munmap_vma_range() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 19/70] mm: Remove vmacache Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 20/70] mm/mmap: Change __do_munmap() to avoid unnecessary lookups Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 21/70] mm/mmap: Move mmap_region() below do_munmap() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 22/70] mm/mmap: Add do_mas_munmap() and wraper for __do_munmap() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 23/70] mmap: Use find_vma_intersection in do_mmap() for overlap Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 24/70] mmap: Remove __do_munmap() in favour of do_mas_munmap() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 25/70] mm/mmap: Change do_brk_munmap() to use do_mas_align_munmap() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 26/70] mmap: make remove_vma_list() inline Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 27/70] mm: Introduce vma_next() and vma_prev() Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 28/70] arch/arm64: Remove mmap linked list from vdso Liam R. Howlett
2021-01-12 16:11 ` [PATCH v2 29/70] arch/parsic: Remove mmap linked list from kernel/cache Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 30/70] arch/powerpc: Remove mmap linked list from mm/book2s32/tlb Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 31/70] arch/powerpc: Remove mmap linked list from mm/book2s32/subpage_prot Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 32/70] arch/powerpc: Optimize cell spu task sync Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 33/70] arch/s390: Use maple tree iterators instead of linked list Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 34/70] arch/um: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 35/70] arch/x86: Use maple tree iterators for vdso/vma Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 36/70] arch/xtensa: Use maple tree iterators for unmapped area Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 37/70] drivers/misc/cxl: Use maple tree iterators for cxl_prefault_vma() Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 38/70] drivers/oprofile: Lookup address in tree instead of linked list Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 39/70] drivers/tee/optee: Use maple tree iterators for __check_mem_type() Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 40/70] fs/binfmt_elf: Use maple tree iterators for fill_files_note() Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 41/70] fs/coredump: Use maple tree iterators in place of linked list Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 42/70] fs/exec: Use vma_next() instead " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 43/70] fs/proc/base: Use maple tree iterators in place " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 44/70] fs/proc/task_mmu: Stop using linked list and highest_vm_end Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 45/70] fs/userfaultfd: Stop using vma linked list Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 46/70] ipc/shm: Stop using the " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 47/70] kernel/acct: Use maple tree iterators instead of " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 48/70] kernel/events/core: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 49/70] kernel/events/uprobes: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 50/70] kernel/sched/fair: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 51/70] kernel/sys: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 52/70] mm/gup: Use maple tree navigation " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 53/70] mm/huge_memory: Use vma_next() instead of vma " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 54/70] mm/khugepaged: Use maple tree iterators " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 55/70] mm/ksm: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 56/70] mm/madvise: Use vma_next " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 57/70] mm/memcontrol: Stop using mm->highest_vm_end Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 58/70] mm/mempolicy: Use maple tree iterators instead of vma linked list Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 59/70] mm/mlock: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 60/70] mm/mprotect: Use maple tree navigation " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 61/70] mm/mremap: Use vma_next() " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 62/70] mm/msync: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 63/70] mm/nommu: Use maple tree iterators " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 64/70] mm/oom_kill: " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 65/70] mm/pagewalk: Use vma_next() " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 66/70] mm/swapfile: Use maple tree iterator " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 67/70] mm/nommu: Stop inserting into the " Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 68/70] mm/util: Remove __vma_link_list() and __vma_unlink_list() Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 69/70] mm: Remove vma linked list Liam R. Howlett
2021-01-12 16:12 ` [PATCH v2 70/70] mm/mmap: Convert __insert_vm_struct to use mas, convert vma_link to use vma_mas_link() Liam R. 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=20210112161240.2024684-7-Liam.Howlett@Oracle.com \
--to=liam.howlett@oracle.com \
--cc=akpm@google.com \
--cc=axelrasmussen@google.com \
--cc=dave@stgolabs.net \
--cc=jglisse@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=maple-tree@lists.infradead.org \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--cc=rientjes@google.com \
--cc=songliubraving@fb.com \
--cc=surenb@google.com \
--cc=vbabka@suse.cz \
--cc=willy@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).