aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig22
-rw-r--r--mm/cma.c12
-rw-r--r--mm/huge_memory.c11
-rw-r--r--mm/hugetlb.c4
-rw-r--r--mm/kasan/kasan.c14
-rw-r--r--mm/memcontrol.c20
-rw-r--r--mm/memory.c7
-rw-r--r--mm/mlock.c4
-rw-r--r--mm/nommu.c5
-rw-r--r--mm/page_alloc.c12
-rw-r--r--mm/shmem.c7
-rw-r--r--mm/vmalloc.c1
12 files changed, 77 insertions, 42 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index de5239c152f9..a03131b6ba8e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -129,28 +129,28 @@ config SPARSEMEM_VMEMMAP
efficient option when sufficient kernel resources are available.
config HAVE_MEMBLOCK
- boolean
+ bool
config HAVE_MEMBLOCK_NODE_MAP
- boolean
+ bool
config HAVE_MEMBLOCK_PHYS_MAP
- boolean
+ bool
config HAVE_GENERIC_RCU_GUP
- boolean
+ bool
config ARCH_DISCARD_MEMBLOCK
- boolean
+ bool
config NO_BOOTMEM
- boolean
+ bool
config MEMORY_ISOLATION
- boolean
+ bool
config MOVABLE_NODE
- boolean "Enable to assign a node which has only movable memory"
+ bool "Enable to assign a node which has only movable memory"
depends on HAVE_MEMBLOCK
depends on NO_BOOTMEM
depends on X86_64
@@ -228,12 +228,12 @@ config SPLIT_PTLOCK_CPUS
default "4"
config ARCH_ENABLE_SPLIT_PMD_PTLOCK
- boolean
+ bool
#
# support for memory balloon
config MEMORY_BALLOON
- boolean
+ bool
#
# support for memory balloon compaction
@@ -276,7 +276,7 @@ config MIGRATION
allocation instead of reclaiming.
config ARCH_ENABLE_HUGEPAGE_MIGRATION
- boolean
+ bool
config PHYS_ADDR_T_64BIT
def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
diff --git a/mm/cma.c b/mm/cma.c
index 75016fd1de90..68ecb7a42983 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -64,15 +64,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
return (1UL << (align_order - cma->order_per_bit)) - 1;
}
+/*
+ * Find a PFN aligned to the specified order and return an offset represented in
+ * order_per_bits.
+ */
static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order)
{
- unsigned int alignment;
-
if (align_order <= cma->order_per_bit)
return 0;
- alignment = 1UL << (align_order - cma->order_per_bit);
- return ALIGN(cma->base_pfn, alignment) -
- (cma->base_pfn >> cma->order_per_bit);
+
+ return (ALIGN(cma->base_pfn, (1UL << align_order))
+ - cma->base_pfn) >> cma->order_per_bit;
}
static unsigned long cma_bitmap_maxno(struct cma *cma)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index fc00c8cb5a82..626e93db28ba 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1295,8 +1295,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
* Avoid grouping on DSO/COW pages in specific and RO pages
* in general, RO pages shouldn't hurt as much anyway since
* they can be in shared cache state.
+ *
+ * FIXME! This checks "pmd_dirty()" as an approximation of
+ * "is this a read-only page", since checking "pmd_write()"
+ * is even more broken. We haven't actually turned this into
+ * a writable page, so pmd_write() will always be false.
*/
- if (!pmd_write(pmd))
+ if (!pmd_dirty(pmd))
flags |= TNF_NO_GROUP;
/*
@@ -1482,6 +1487,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
pmd_t entry;
+ ret = 1;
/*
* Avoid trapping faults against the zero page. The read-only
@@ -1490,11 +1496,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
*/
if (prot_numa && is_huge_zero_pmd(*pmd)) {
spin_unlock(ptl);
- return 0;
+ return ret;
}
if (!prot_numa || !pmd_protnone(*pmd)) {
- ret = 1;
entry = pmdp_get_and_clear_notify(mm, addr, pmd);
entry = pmd_modify(entry, newprot);
ret = HPAGE_PMD_NR;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0a9ac6c26832..c41b2a0ee273 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -917,7 +917,6 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
__SetPageHead(page);
__ClearPageReserved(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
- __SetPageTail(p);
/*
* For gigantic hugepages allocated through bootmem at
* boot, it's safer to be consistent with the not-gigantic
@@ -933,6 +932,9 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
__ClearPageReserved(p);
set_page_count(p, 0);
p->first_page = page;
+ /* Make sure p->first_page is always valid for PageTail() */
+ smp_wmb();
+ __SetPageTail(p);
}
}
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 78fee632a7ee..936d81661c47 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -29,6 +29,7 @@
#include <linux/stacktrace.h>
#include <linux/string.h>
#include <linux/types.h>
+#include <linux/vmalloc.h>
#include <linux/kasan.h>
#include "kasan.h"
@@ -414,12 +415,19 @@ int kasan_module_alloc(void *addr, size_t size)
GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE,
__builtin_return_address(0));
- return ret ? 0 : -ENOMEM;
+
+ if (ret) {
+ find_vm_area(addr)->flags |= VM_KASAN;
+ return 0;
+ }
+
+ return -ENOMEM;
}
-void kasan_module_free(void *addr)
+void kasan_free_shadow(const struct vm_struct *vm)
{
- vfree(kasan_mem_to_shadow(addr));
+ if (vm->flags & VM_KASAN)
+ vfree(kasan_mem_to_shadow(vm->addr));
}
static void register_global(struct kasan_global *global)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d18d3a6e7337..b34ef4a32a3b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5232,7 +5232,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
* on for the root memcg is enough.
*/
if (cgroup_on_dfl(root_css->cgroup))
- mem_cgroup_from_css(root_css)->use_hierarchy = true;
+ root_mem_cgroup->use_hierarchy = true;
+ else
+ root_mem_cgroup->use_hierarchy = false;
}
static u64 memory_current_read(struct cgroup_subsys_state *css,
@@ -5247,7 +5249,7 @@ static int memory_low_show(struct seq_file *m, void *v)
unsigned long low = ACCESS_ONCE(memcg->low);
if (low == PAGE_COUNTER_MAX)
- seq_puts(m, "infinity\n");
+ seq_puts(m, "max\n");
else
seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE);
@@ -5262,7 +5264,7 @@ static ssize_t memory_low_write(struct kernfs_open_file *of,
int err;
buf = strstrip(buf);
- err = page_counter_memparse(buf, "infinity", &low);
+ err = page_counter_memparse(buf, "max", &low);
if (err)
return err;
@@ -5277,7 +5279,7 @@ static int memory_high_show(struct seq_file *m, void *v)
unsigned long high = ACCESS_ONCE(memcg->high);
if (high == PAGE_COUNTER_MAX)
- seq_puts(m, "infinity\n");
+ seq_puts(m, "max\n");
else
seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE);
@@ -5292,7 +5294,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
int err;
buf = strstrip(buf);
- err = page_counter_memparse(buf, "infinity", &high);
+ err = page_counter_memparse(buf, "max", &high);
if (err)
return err;
@@ -5307,7 +5309,7 @@ static int memory_max_show(struct seq_file *m, void *v)
unsigned long max = ACCESS_ONCE(memcg->memory.limit);
if (max == PAGE_COUNTER_MAX)
- seq_puts(m, "infinity\n");
+ seq_puts(m, "max\n");
else
seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
@@ -5322,7 +5324,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
int err;
buf = strstrip(buf);
- err = page_counter_memparse(buf, "infinity", &max);
+ err = page_counter_memparse(buf, "max", &max);
if (err)
return err;
@@ -5426,7 +5428,7 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
if (memcg == root_mem_cgroup)
return false;
- if (page_counter_read(&memcg->memory) > memcg->low)
+ if (page_counter_read(&memcg->memory) >= memcg->low)
return false;
while (memcg != root) {
@@ -5435,7 +5437,7 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
if (memcg == root_mem_cgroup)
break;
- if (page_counter_read(&memcg->memory) > memcg->low)
+ if (page_counter_read(&memcg->memory) >= memcg->low)
return false;
}
return true;
diff --git a/mm/memory.c b/mm/memory.c
index 8068893697bb..411144f977b1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3072,8 +3072,13 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
* Avoid grouping on DSO/COW pages in specific and RO pages
* in general, RO pages shouldn't hurt as much anyway since
* they can be in shared cache state.
+ *
+ * FIXME! This checks "pmd_dirty()" as an approximation of
+ * "is this a read-only page", since checking "pmd_write()"
+ * is even more broken. We haven't actually turned this into
+ * a writable page, so pmd_write() will always be false.
*/
- if (!pte_write(pte))
+ if (!pte_dirty(pte))
flags |= TNF_NO_GROUP;
/*
diff --git a/mm/mlock.c b/mm/mlock.c
index 73cf0987088c..8a54cd214925 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -26,10 +26,10 @@
int can_do_mlock(void)
{
- if (capable(CAP_IPC_LOCK))
- return 1;
if (rlimit(RLIMIT_MEMLOCK) != 0)
return 1;
+ if (capable(CAP_IPC_LOCK))
+ return 1;
return 0;
}
EXPORT_SYMBOL(can_do_mlock);
diff --git a/mm/nommu.c b/mm/nommu.c
index 7296360fc057..3fba2dc97c44 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -62,6 +62,7 @@ void *high_memory;
EXPORT_SYMBOL(high_memory);
struct page *mem_map;
unsigned long max_mapnr;
+EXPORT_SYMBOL(max_mapnr);
unsigned long highest_memmap_pfn;
struct percpu_counter vm_committed_as;
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
@@ -1213,11 +1214,9 @@ static int do_mmap_private(struct vm_area_struct *vma,
if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) {
total = point;
kdebug("try to alloc exact %lu pages", total);
- base = alloc_pages_exact(len, GFP_KERNEL);
- } else {
- base = (void *)__get_free_pages(GFP_KERNEL, order);
}
+ base = alloc_pages_exact(total << PAGE_SHIFT, GFP_KERNEL);
if (!base)
goto enomem;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a47f0b229a1a..40e29429e7b0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2353,8 +2353,15 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
if (ac->high_zoneidx < ZONE_NORMAL)
goto out;
/* The OOM killer does not compensate for light reclaim */
- if (!(gfp_mask & __GFP_FS))
+ if (!(gfp_mask & __GFP_FS)) {
+ /*
+ * XXX: Page reclaim didn't yield anything,
+ * and the OOM killer can't be invoked, but
+ * keep looping as per should_alloc_retry().
+ */
+ *did_some_progress = 1;
goto out;
+ }
/*
* GFP_THISNODE contains __GFP_NORETRY and we never hit this.
* Sanity check for bare calls of __GFP_THISNODE, not real OOM.
@@ -2366,7 +2373,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
goto out;
}
/* Exhausted what can be done so it's blamo time */
- if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false))
+ if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)
+ || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
*did_some_progress = 1;
out:
oom_zonelist_unlock(ac->zonelist, gfp_mask);
diff --git a/mm/shmem.c b/mm/shmem.c
index a63031fa3e0c..cf2d0ca010bc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1455,6 +1455,9 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
bool shmem_mapping(struct address_space *mapping)
{
+ if (!mapping->host)
+ return false;
+
return mapping->host->i_sb->s_op == &shmem_ops;
}
@@ -2319,8 +2322,8 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry)
{
- bool old_is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
- bool new_is_dir = S_ISDIR(new_dentry->d_inode->i_mode);
+ bool old_is_dir = d_is_dir(old_dentry);
+ bool new_is_dir = d_is_dir(new_dentry);
if (old_dir != new_dir && old_is_dir != new_is_dir) {
if (old_is_dir) {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 35b25e1340ca..49abccf29a29 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1418,6 +1418,7 @@ struct vm_struct *remove_vm_area(const void *addr)
spin_unlock(&vmap_area_lock);
vmap_debug_free_range(va->va_start, va->va_end);
+ kasan_free_shadow(vm);
free_unmap_vmap_area(va);
vm->size -= PAGE_SIZE;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.