AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-11-24 02:00:54 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'akpm' (patches from Andrew)

Browse Source 
Merge misc updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (159 commits)
  tools/testing/selftests/proc/proc-self-syscall.c: remove duplicate include
  proc: more robust bulk read test
  proc: test /proc/*/maps, smaps, smaps_rollup, statm
  proc: use seq_puts() everywhere
  proc: read kernel cpu stat pointer once
  proc: remove unused argument in proc_pid_lookup()
  fs/proc/thread_self.c: code cleanup for proc_setup_thread_self()
  fs/proc/self.c: code cleanup for proc_setup_self()
  proc: return exit code 4 for skipped tests
  mm,mremap: bail out earlier in mremap_to under map pressure
  mm/sparse: fix a bad comparison
  mm/memory.c: do_fault: avoid usage of stale vm_area_struct
  writeback: fix inode cgroup switching comment
  mm/huge_memory.c: fix "orig_pud" set but not used
  mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC
  mm/memcontrol.c: fix bad line in comment
  mm/cma.c: cma_declare_contiguous: correct err handling
  mm/page_ext.c: fix an imbalance with kmemleak
  mm/compaction: pass pgdat to too_many_isolated() instead of zone
  mm: remove zone_lru_lock() function, access ->lru_lock directly
  ...
This commit is contained in:
Linus Torvalds 2019-03-06 10:31:36 -08:00
commit 8dcd175bc3
213 changed files with 4924 additions and 2321 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
Documentation/admin-guide/cgroup-v2.rst
View File

@ -1189,6 +1189,10 @@ PAGE_SIZE multiple when read back.
Amount of cached filesystem data that was modified and
is currently being written back to disk
anon_thp
Amount of memory used in anonymous mappings backed by
transparent hugepages
inactive_anon, active_anon, inactive_file, active_file, unevictable
Amount of memory, swap-backed and filesystem-backed,
on the internal memory management lists used by the
@ -1248,6 +1252,18 @@ PAGE_SIZE multiple when read back.
Amount of reclaimed lazyfree pages
thp_fault_alloc
Number of transparent hugepages which were allocated to satisfy
a page fault, including COW faults. This counter is not present
when CONFIG_TRANSPARENT_HUGEPAGE is not set.
thp_collapse_alloc
Number of transparent hugepages which were allocated to allow
collapsing an existing range of pages. This counter is not
present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
memory.swap.current
A read-only single value file which exists on non-root
cgroups.

9
Documentation/admin-guide/mm/pagemap.rst
View File

@ -75,9 +75,10 @@ number of times a page is mapped.
20. NOPAGE
21. KSM
22. THP
23. BALLOON
23. OFFLINE
24. ZERO_PAGE
25. IDLE
26. PGTABLE
* ``/proc/kpagecgroup``. This file contains a 64-bit inode number of the
memory cgroup each page is charged to, indexed by PFN. Only available when
@ -118,8 +119,8 @@ Short descriptions to the page flags
identical memory pages dynamically shared between one or more processes
22 - THP
contiguous pages which construct transparent hugepages
23 - BALLOON
balloon compaction page
23 - OFFLINE
page is logically offline
24 - ZERO_PAGE
zero page for pfn_zero or huge_zero page
25 - IDLE
@ -128,6 +129,8 @@ Short descriptions to the page flags
Note that this flag may be stale in case the page was accessed via
a PTE. To make sure the flag is up-to-date one has to read
``/sys/kernel/mm/page_idle/bitmap`` first.
26 - PGTABLE
page is in use as a page table
IO related page flags
---------------------

4
Documentation/cgroup-v1/memcg_test.txt
View File

@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
8. LRU
Each memcg has its own private LRU. Now, its handling is under global
VM's control (means that it's handled under global zone_lru_lock).
VM's control (means that it's handled under global pgdat->lru_lock).
Almost all routines around memcg's LRU is called by global LRU's
list management functions under zone_lru_lock().
list management functions under pgdat->lru_lock.
A special function is mem_cgroup_isolate_pages(). This scans
memcg's private LRU and call __isolate_lru_page() to extract a page

4
Documentation/cgroup-v1/memory.txt
View File

@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered.
Other lock order is following:
PG_locked.
mm->page_table_lock
zone_lru_lock
pgdat->lru_lock
lock_page_cgroup.
In many cases, just lock_page_cgroup() is called.
per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
zone_lru_lock, it has no lock of its own.
pgdat->lru_lock, it has no lock of its own.
2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)

8
MAINTAINERS
View File

@ -9835,6 +9835,14 @@ F: kernel/sched/membarrier.c
F: include/uapi/linux/membarrier.h
F: arch/powerpc/include/asm/membarrier.h
MEMBLOCK
M: Mike Rapoport <rppt@linux.ibm.com>
L: linux-mm@kvack.org
S: Maintained
F: include/linux/memblock.h
F: mm/memblock.c
F: Documentation/core-api/boot-time-mm.rst
MEMORY MANAGEMENT
L: linux-mm@kvack.org
W: http://www.linux-mm.org

3
arch/alpha/include/asm/topology.h
View File

@ -4,6 +4,7 @@
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/numa.h>
#include <asm/machvec.h>
#ifdef CONFIG_NUMA
@ -29,7 +30,7 @@ static const struct cpumask *cpumask_of_node(int node)
{
int cpu;
if (node == -1)
if (node == NUMA_NO_NODE)
return cpu_all_mask;
cpumask_clear(&node_to_cpumask_map[node]);

4
arch/arm64/Kconfig
View File

@ -1467,6 +1467,10 @@ config SYSVIPC_COMPAT
def_bool y
depends on COMPAT && SYSVIPC
config ARCH_ENABLE_HUGEPAGE_MIGRATION
def_bool y
depends on HUGETLB_PAGE && MIGRATION
menu "Power management options"
source "kernel/power/Kconfig"

5
arch/arm64/include/asm/hugetlb.h
View File

@ -20,6 +20,11 @@
#include <asm/page.h>
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
extern bool arch_hugetlb_migration_supported(struct hstate *h);
#endif
#define __HAVE_ARCH_HUGE_PTEP_GET
static inline pte_t huge_ptep_get(pte_t *ptep)
{

4
arch/arm64/include/asm/memory.h
View File

@ -80,11 +80,7 @@
*/
#ifdef CONFIG_KASAN
#define KASAN_SHADOW_SIZE (UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT))
#ifdef CONFIG_KASAN_EXTRA
#define KASAN_THREAD_SHIFT 2
#else
#define KASAN_THREAD_SHIFT 1
#endif /* CONFIG_KASAN_EXTRA */
#else
#define KASAN_SHADOW_SIZE (0)
#define KASAN_THREAD_SHIFT 0

3
arch/arm64/kernel/machine_kexec.c
View File

@ -321,7 +321,7 @@ void crash_post_resume(void)
* but does not hold any data of loaded kernel image.
*
* Note that all the pages in crash dump kernel memory have been initially
* marked as Reserved in kexec_reserve_crashkres_pages().
* marked as Reserved as memory was allocated via memblock_reserve().
*
* In hibernation, the pages which are Reserved and yet "nosave" are excluded
* from the hibernation iamge. crash_is_nosave() does thich check for crash
@ -361,7 +361,6 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
for (addr = begin; addr < end; addr += PAGE_SIZE) {
page = phys_to_page(addr);
ClearPageReserved(page);
free_reserved_page(page);
}
}

20
arch/arm64/mm/hugetlbpage.c
View File

@ -27,6 +27,26 @@
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
bool arch_hugetlb_migration_supported(struct hstate *h)
{
size_t pagesize = huge_page_size(h);
switch (pagesize) {
#ifdef CONFIG_ARM64_4K_PAGES
case PUD_SIZE:
#endif
case PMD_SIZE:
case CONT_PMD_SIZE:
case CONT_PTE_SIZE:
return true;
}
pr_warn("%s: unrecognized huge page size 0x%lx\n",
__func__, pagesize);
return false;
}
#endif
int pmd_huge(pmd_t pmd)
{
return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);

27
arch/arm64/mm/init.c
View File

@ -118,35 +118,10 @@ static void __init reserve_crashkernel(void)
crashk_res.start = crash_base;
crashk_res.end = crash_base + crash_size - 1;
}
static void __init kexec_reserve_crashkres_pages(void)
{
#ifdef CONFIG_HIBERNATION
phys_addr_t addr;
struct page *page;
if (!crashk_res.end)
return;
/*
* To reduce the size of hibernation image, all the pages are
* marked as Reserved initially.
*/
for (addr = crashk_res.start; addr < (crashk_res.end + 1);
addr += PAGE_SIZE) {
page = phys_to_page(addr);
SetPageReserved(page);
}
#endif
}
#else
static void __init reserve_crashkernel(void)
{
}
static void __init kexec_reserve_crashkres_pages(void)
{
}
#endif /* CONFIG_KEXEC_CORE */
#ifdef CONFIG_CRASH_DUMP
@ -586,8 +561,6 @@ void __init mem_init(void)
/* this will put all unused low memory onto the freelists */
memblock_free_all();
kexec_reserve_crashkres_pages();
mem_init_print_info(NULL);
/*

2
arch/arm64/mm/numa.c
View File

@ -120,7 +120,7 @@ static void __init setup_node_to_cpumask_map(void)
}
/* cpumask_of_node() will now work */
pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
}
/*

2
arch/ia64/kernel/numa.c
View File

@ -74,7 +74,7 @@ void __init build_cpu_to_node_map(void)
cpumask_clear(&node_to_cpu_mask[node]);
for_each_possible_early_cpu(cpu) {
node = -1;
node = NUMA_NO_NODE;
for (i = 0; i < NR_CPUS; ++i)
if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) {
node = node_cpuid[i].nid;

59
arch/ia64/kernel/perfmon.c
View File

@ -583,17 +583,6 @@ pfm_put_task(struct task_struct *task)
if (task != current) put_task_struct(task);
}
static inline void
pfm_reserve_page(unsigned long a)
{
SetPageReserved(vmalloc_to_page((void *)a));
}
static inline void
pfm_unreserve_page(unsigned long a)
{
ClearPageReserved(vmalloc_to_page((void*)a));
}
static inline unsigned long
pfm_protect_ctx_ctxsw(pfm_context_t *x)
{
@ -816,44 +805,6 @@ pfm_reset_msgq(pfm_context_t *ctx)
DPRINT(("ctx=%p msgq reset\n", ctx));
}
static void *
pfm_rvmalloc(unsigned long size)
{
void *mem;
unsigned long addr;
size = PAGE_ALIGN(size);
mem = vzalloc(size);
if (mem) {
//printk("perfmon: CPU%d pfm_rvmalloc(%ld)=%p\n", smp_processor_id(), size, mem);
addr = (unsigned long)mem;
while (size > 0) {
pfm_reserve_page(addr);
addr+=PAGE_SIZE;
size-=PAGE_SIZE;
}
}
return mem;
}
static void
pfm_rvfree(void *mem, unsigned long size)
{
unsigned long addr;
if (mem) {
DPRINT(("freeing physical buffer @%p size=%lu\n", mem, size));
addr = (unsigned long) mem;
while ((long) size > 0) {
pfm_unreserve_page(addr);
addr+=PAGE_SIZE;
size-=PAGE_SIZE;
}
vfree(mem);
}
return;
}
static pfm_context_t *
pfm_context_alloc(int ctx_flags)
{
@ -1498,7 +1449,7 @@ pfm_free_smpl_buffer(pfm_context_t *ctx)
/*
* free the buffer
*/
pfm_rvfree(ctx->ctx_smpl_hdr, ctx->ctx_smpl_size);
vfree(ctx->ctx_smpl_hdr);
ctx->ctx_smpl_hdr = NULL;
ctx->ctx_smpl_size = 0UL;
@ -2137,7 +2088,7 @@ pfm_close(struct inode *inode, struct file *filp)
* All memory free operations (especially for vmalloc'ed memory)
* MUST be done with interrupts ENABLED.
*/
if (smpl_buf_addr) pfm_rvfree(smpl_buf_addr, smpl_buf_size);
vfree(smpl_buf_addr);
/*
* return the memory used by the context
@ -2266,10 +2217,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
/*
* We do the easy to undo allocations first.
*
* pfm_rvmalloc(), clears the buffer, so there is no leak
*/
smpl_buf = pfm_rvmalloc(size);
smpl_buf = vzalloc(size);
if (smpl_buf == NULL) {
DPRINT(("Can't allocate sampling buffer\n"));
return -ENOMEM;
@ -2346,7 +2295,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
error:
vm_area_free(vma);
error_kmem:
pfm_rvfree(smpl_buf, size);
vfree(smpl_buf);
return -ENOMEM;
}

6
arch/ia64/mm/discontig.c
View File

@ -227,7 +227,7 @@ void __init setup_per_cpu_areas(void)
* CPUs are put into groups according to node. Walk cpu_map
* and create new groups at node boundaries.
*/
prev_node = -1;
prev_node = NUMA_NO_NODE;
ai->nr_groups = 0;
for (unit = 0; unit < nr_units; unit++) {
cpu = cpu_map[unit];
@ -435,7 +435,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
{
void *ptr = NULL;
u8 best = 0xff;
int bestnode = -1, node, anynode = 0;
int bestnode = NUMA_NO_NODE, node, anynode = 0;
for_each_online_node(node) {
if (node_isset(node, memory_less_mask))
@ -447,7 +447,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
anynode = node;
}
if (bestnode == -1)
if (bestnode == NUMA_NO_NODE)
bestnode = anynode;
ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE,

2
arch/m68k/mm/memory.c
View File

@ -51,7 +51,7 @@ void __init init_pointer_table(unsigned long ptable)
pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
/* unreserve the page so it's possible to free that page */
PD_PAGE(dp)->flags &= ~(1 << PG_reserved);
__ClearPageReserved(PD_PAGE(dp));
init_page_count(PD_PAGE(dp));
return;

12
arch/powerpc/include/asm/book3s/64/hugetlb.h
View File

@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte);
static inline int hstate_get_psize(struct hstate *hstate)
{
unsigned long shift;
@ -42,4 +46,12 @@ static inline bool gigantic_page_supported(void)
/* hugepd entry valid bit */
#define HUGEPD_VAL_BITS (0x8000000000000000UL)
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t new_pte);
#endif

18
arch/powerpc/include/asm/book3s/64/pgtable.h
View File

@ -1306,6 +1306,24 @@ static inline int pud_pfn(pud_t pud)
BUILD_BUG();
return 0;
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
pte_t *, pte_t, pte_t);
/*
* Returns true for a R -> RW upgrade of pte
*/
static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val)
{
if (!(old_val & _PAGE_READ))
return false;
if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE))
return true;
return false;
}
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */

4
arch/powerpc/include/asm/book3s/64/radix.h
View File

@ -127,6 +127,10 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep
pte_t entry, unsigned long address,
int psize);
extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte);
static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
unsigned long set)
{

3
arch/powerpc/include/asm/pci-bridge.h
View File

@ -10,6 +10,7 @@
#include <linux/pci.h>
#include <linux/list.h>
#include <linux/ioport.h>
#include <linux/numa.h>
struct device_node;
@ -265,7 +266,7 @@ extern int pcibios_map_io_space(struct pci_bus *bus);
#ifdef CONFIG_NUMA
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = (NODE))
#else
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = -1)
#define PHB_SET_NODE(PHB, NODE) ((PHB)->node = NUMA_NO_NODE)
#endif
#endif /* CONFIG_PPC64 */

3
arch/powerpc/kernel/paca.c
View File

@ -11,6 +11,7 @@
#include <linux/export.h>
#include <linux/memblock.h>
#include <linux/sched/task.h>
#include <linux/numa.h>
#include <asm/lppaca.h>
#include <asm/paca.h>
@ -36,7 +37,7 @@ static void *__init alloc_paca_data(unsigned long size, unsigned long align,
* which will put its paca in the right place.
*/
if (cpu == boot_cpuid) {
nid = -1;
nid = NUMA_NO_NODE;
memblock_set_bottom_up(true);
} else {
nid = early_cpu_to_node(cpu);

3
arch/powerpc/kernel/pci-common.c
View File

@ -32,6 +32,7 @@
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/vgaarb.h>
#include <linux/numa.h>
#include <asm/processor.h>
#include <asm/io.h>
@ -132,7 +133,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
int nid = of_node_to_nid(dev);
if (nid < 0 || !node_online(nid))
nid = -1;
nid = NUMA_NO_NODE;
PHB_SET_NODE(phb, nid);
}

2
arch/powerpc/kernel/vdso.c
View File

@ -798,7 +798,6 @@ static int __init vdso_init(void)
BUG_ON(vdso32_pagelist == NULL);
for (i = 0; i < vdso32_pages; i++) {
struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
ClearPageReserved(pg);
get_page(pg);
vdso32_pagelist[i] = pg;
}
@ -812,7 +811,6 @@ static int __init vdso_init(void)
BUG_ON(vdso64_pagelist == NULL);
for (i = 0; i < vdso64_pages; i++) {
struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
ClearPageReserved(pg);
get_page(pg);
vdso64_pagelist[i] = pg;
}

25
arch/powerpc/mm/hugetlbpage-hash64.c
View File

@ -121,3 +121,28 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
*ptep = __pte(new_pte & ~H_PAGE_BUSY);
return 0;
}
pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
unsigned long pte_val;
/*
* Clear the _PAGE_PRESENT so that no hardware parallel update is
* possible. Also keep the pte_present true so that we don't take
* wrong fault.
*/
pte_val = pte_update(vma->vm_mm, addr, ptep,
_PAGE_PRESENT, _PAGE_INVALID, 1);
return __pte(pte_val);
}
void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
if (radix_enabled())
return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
old_pte, pte);
set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}

17
arch/powerpc/mm/hugetlbpage-radix.c
View File

@ -90,3 +90,20 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
return vm_unmapped_area(&info);
}
void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
struct mm_struct *mm = vma->vm_mm;
/*
* To avoid NMMU hang while relaxing access we need to flush the tlb before
* we set the new value.
*/
if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
(atomic_read(&mm->context.copros) > 0))
radix__flush_hugetlb_page(vma, addr);
set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}

143
arch/powerpc/mm/mmu_context_iommu.c
View File

@ -21,6 +21,7 @@
#include <linux/sizes.h>
#include <asm/mmu_context.h>
#include <asm/pte-walk.h>
#include <linux/mm_inline.h>
static DEFINE_MUTEX(mem_list_mutex);
@ -34,8 +35,18 @@ struct mm_iommu_table_group_mem_t {
atomic64_t mapped;
unsigned int pageshift;
u64 ua; /* userspace address */
u64 entries; /* number of entries in hpas[] */
u64 *hpas; /* vmalloc'ed */
u64 entries; /* number of entries in hpas/hpages[] */
/*
* in mm_iommu_get we temporarily use this to store
* struct page address.
*
* We need to convert ua to hpa in real mode. Make it
* simpler by storing physical address.
*/
union {
struct page **hpages; /* vmalloc'ed */
phys_addr_t *hpas;
};
#define MM_IOMMU_TABLE_INVALID_HPA ((uint64_t)-1)
u64 dev_hpa; /* Device memory base address */
};
@ -80,64 +91,13 @@ bool mm_iommu_preregistered(struct mm_struct *mm)
}
EXPORT_SYMBOL_GPL(mm_iommu_preregistered);
/*
* Taken from alloc_migrate_target with changes to remove CMA allocations
*/
struct page *new_iommu_non_cma_page(struct page *page, unsigned long private)
{
gfp_t gfp_mask = GFP_USER;
struct page *new_page;
if (PageCompound(page))
return NULL;
if (PageHighMem(page))
gfp_mask |= __GFP_HIGHMEM;
/*
* We don't want the allocation to force an OOM if possibe
*/
new_page = alloc_page(gfp_mask | __GFP_NORETRY | __GFP_NOWARN);
return new_page;
}
static int mm_iommu_move_page_from_cma(struct page *page)
{
int ret = 0;
LIST_HEAD(cma_migrate_pages);
/* Ignore huge pages for now */
if (PageCompound(page))
return -EBUSY;
lru_add_drain();
ret = isolate_lru_page(page);
if (ret)
return ret;
list_add(&page->lru, &cma_migrate_pages);
put_page(page); /* Drop the gup reference */
ret = migrate_pages(&cma_migrate_pages, new_iommu_non_cma_page,
NULL, 0, MIGRATE_SYNC, MR_CONTIG_RANGE);
if (ret) {
if (!list_empty(&cma_migrate_pages))
putback_movable_pages(&cma_migrate_pages);
}
return 0;
}
static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
unsigned long entries, unsigned long dev_hpa,
struct mm_iommu_table_group_mem_t **pmem)
{
struct mm_iommu_table_group_mem_t *mem;
long i, j, ret = 0, locked_entries = 0;
long i, ret, locked_entries = 0;
unsigned int pageshift;
unsigned long flags;
unsigned long cur_ua;
struct page *page = NULL;
mutex_lock(&mem_list_mutex);
@ -187,62 +147,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
goto unlock_exit;
}
down_read(&mm->mmap_sem);
ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
up_read(&mm->mmap_sem);
if (ret != entries) {
/* free the reference taken */
for (i = 0; i < ret; i++)
put_page(mem->hpages[i]);
vfree(mem->hpas);
kfree(mem);
ret = -EFAULT;
goto unlock_exit;
}
pageshift = PAGE_SHIFT;
for (i = 0; i < entries; ++i) {
cur_ua = ua + (i << PAGE_SHIFT);
if (1 != get_user_pages_fast(cur_ua,
1/* pages */, 1/* iswrite */, &page)) {
ret = -EFAULT;
for (j = 0; j < i; ++j)
put_page(pfn_to_page(mem->hpas[j] >>
PAGE_SHIFT));
vfree(mem->hpas);
kfree(mem);
goto unlock_exit;
}
struct page *page = mem->hpages[i];
/*
* If we get a page from the CMA zone, since we are going to
* be pinning these entries, we might as well move them out
* of the CMA zone if possible. NOTE: faulting in + migration
* can be expensive. Batching can be considered later
* Allow to use larger than 64k IOMMU pages. Only do that
* if we are backed by hugetlb.
*/
if (is_migrate_cma_page(page)) {
if (mm_iommu_move_page_from_cma(page))
goto populate;
if (1 != get_user_pages_fast(cur_ua,
1/* pages */, 1/* iswrite */,
&page)) {
ret = -EFAULT;
for (j = 0; j < i; ++j)
put_page(pfn_to_page(mem->hpas[j] >>
PAGE_SHIFT));
vfree(mem->hpas);
kfree(mem);
goto unlock_exit;
}
}
populate:
pageshift = PAGE_SHIFT;
if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
pte_t *pte;
if ((mem->pageshift > PAGE_SHIFT) && PageHuge(page)) {
struct page *head = compound_head(page);
unsigned int compshift = compound_order(head);
unsigned int pteshift;
local_irq_save(flags); /* disables as well */
pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
/* Double check it is still the same pinned page */
if (pte && pte_page(*pte) == head &&
pteshift == compshift + PAGE_SHIFT)
pageshift = max_t(unsigned int, pteshift,
PAGE_SHIFT);
local_irq_restore(flags);
pageshift = compound_order(head) + PAGE_SHIFT;
}
mem->pageshift = min(mem->pageshift, pageshift);
/*
* We don't need struct page reference any more, switch
* to physical address.
*/
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
}
good_exit:
ret = 0;
atomic64_set(&mem->mapped, 1);
mem->used = 1;
mem->ua = ua;

16
arch/powerpc/mm/numa.c
View File

@ -84,7 +84,7 @@ static void __init setup_node_to_cpumask_map(void)
alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
/* cpumask_of_node() will now work */
dbg("Node to cpumask map for %d nodes\n", nr_node_ids);
dbg("Node to cpumask map for %u nodes\n", nr_node_ids);
}
static int __init fake_numa_create_new_node(unsigned long end_pfn,
@ -215,7 +215,7 @@ static void initialize_distance_lookup_table(int nid,
*/
static int associativity_to_nid(const __be32 *associativity)
{
int nid = -1;
int nid = NUMA_NO_NODE;
if (min_common_depth == -1)
goto out;
@ -225,7 +225,7 @@ static int associativity_to_nid(const __be32 *associativity)
/* POWER4 LPAR uses 0xffff as invalid node */
if (nid == 0xffff || nid >= MAX_NUMNODES)
nid = -1;
nid = NUMA_NO_NODE;
if (nid > 0 &&
of_read_number(associativity, 1) >= distance_ref_points_depth) {
@ -244,7 +244,7 @@ static int associativity_to_nid(const __be32 *associativity)
*/
static int of_node_to_nid_single(struct device_node *device)
{
int nid = -1;
int nid = NUMA_NO_NODE;
const __be32 *tmp;
tmp = of_get_associativity(device);
@ -256,7 +256,7 @@ static int of_node_to_nid_single(struct device_node *device)
/* Walk the device tree upwards, looking for an associativity id */
int of_node_to_nid(struct device_node *device)
{
int nid = -1;
int nid = NUMA_NO_NODE;
of_node_get(device);
while (device) {
@ -454,7 +454,7 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
*/
static int numa_setup_cpu(unsigned long lcpu)
{
int nid = -1;
int nid = NUMA_NO_NODE;
struct device_node *cpu;
/*
@ -930,7 +930,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
{
struct drmem_lmb *lmb;
unsigned long lmb_size;
int nid = -1;
int nid = NUMA_NO_NODE;
lmb_size = drmem_lmb_size();
@ -960,7 +960,7 @@ static int hot_add_drconf_scn_to_nid(unsigned long scn_addr)
static int hot_add_node_scn_to_nid(unsigned long scn_addr)
{
struct device_node *memory;
int nid = -1;
int nid = NUMA_NO_NODE;
for_each_node_by_type(memory, "memory") {
unsigned long start, size;

25
arch/powerpc/mm/pgtable-book3s64.c
View File

@ -401,6 +401,31 @@ void arch_report_meminfo(struct seq_file *m)
}
#endif /* CONFIG_PROC_FS */
pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep)
{
unsigned long pte_val;
/*
* Clear the _PAGE_PRESENT so that no hardware parallel update is
* possible. Also keep the pte_present true so that we don't take
* wrong fault.
*/
pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);
return __pte(pte_val);
}
void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
if (radix_enabled())
return radix__ptep_modify_prot_commit(vma, addr,
ptep, old_pte, pte);
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
/*
* For hash translation mode, we use the deposited table to store hash slot
* information and they are stored at PTRS_PER_PMD offset from related pmd

18
arch/powerpc/mm/pgtable-radix.c
View File

@ -1063,3 +1063,21 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
}
/* See ptesync comment in radix__set_pte_at */
}
void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
struct mm_struct *mm = vma->vm_mm;
/*
* To avoid NMMU hang while relaxing access we need to flush the tlb before
* we set the new value. We need to do this only for radix, because hash
* translation does flush when updating the linux pte.
*/
if (is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
(atomic_read(&mm->context.copros) > 0))
radix__flush_tlb_page(vma, addr);
set_pte_at(mm, addr, ptep, pte);
}

5
arch/powerpc/platforms/powernv/memtrace.c
View File

@ -20,6 +20,7 @@
#include <linux/slab.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/numa.h>
#include <asm/machdep.h>
#include <asm/debugfs.h>
@ -223,7 +224,7 @@ static int memtrace_online(void)
ent = &memtrace_array[i];
/* We have onlined this chunk previously */
if (ent->nid == -1)
if (ent->nid == NUMA_NO_NODE)
continue;
/* Remove from io mappings */
@ -257,7 +258,7 @@ static int memtrace_online(void)
*/
debugfs_remove_recursive(ent->dir);
pr_info("Added trace memory back to node %d\n", ent->nid);
ent->size = ent->start = ent->nid = -1;
ent->size = ent->start = ent->nid = NUMA_NO_NODE;
}
if (ret)
return ret;

1
arch/riscv/kernel/vdso.c
View File

@ -54,7 +54,6 @@ static int __init vdso_init(void)
struct page *pg;
pg = virt_to_page(vdso_start + (i << PAGE_SHIFT));
ClearPageReserved(pg);
vdso_pagelist[i] = pg;
}
vdso_pagelist[i] = virt_to_page(vdso_data);

5
arch/s390/include/asm/pgtable.h
View File

@ -1069,8 +1069,9 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
pte_t ptep_modify_prot_start(struct mm_struct *, unsigned long, pte_t *);
void ptep_modify_prot_commit(struct mm_struct *, unsigned long, pte_t *, pte_t);
pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
pte_t *, pte_t, pte_t);
#define __HAVE_ARCH_PTEP_CLEAR_FLUSH
static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,

2
arch/s390/kernel/vdso.c
View File

@ -291,7 +291,6 @@ static int __init vdso_init(void)
BUG_ON(vdso32_pagelist == NULL);
for (i = 0; i < vdso32_pages - 1; i++) {
struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
ClearPageReserved(pg);
get_page(pg);
vdso32_pagelist[i] = pg;
}
@ -309,7 +308,6 @@ static int __init vdso_init(void)
BUG_ON(vdso64_pagelist == NULL);
for (i = 0; i < vdso64_pages - 1; i++) {
struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
ClearPageReserved(pg);
get_page(pg);
vdso64_pagelist[i] = pg;
}

8
arch/s390/mm/pgtable.c
View File

@ -301,12 +301,13 @@ pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
}
EXPORT_SYMBOL(ptep_xchg_lazy);
pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep)
{
pgste_t pgste;
pte_t old;
int nodat;
struct mm_struct *mm = vma->vm_mm;
preempt_disable();
pgste = ptep_xchg_start(mm, addr, ptep);
@ -319,10 +320,11 @@ pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
return old;
}
void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
pgste_t pgste;
struct mm_struct *mm = vma->vm_mm;
if (!MACHINE_HAS_NX)
pte_val(pte) &= ~_PAGE_NOEXEC;

4
arch/sh/kernel/syscalls/syscalltbl.sh
View File

@ -13,10 +13,10 @@ emit() {
t_entry="$3"
while [ $t_nxt -lt $t_nr ]; do
printf "__SYSCALL(%s, sys_ni_syscall, )\n" "${t_nxt}"
printf "__SYSCALL(%s,sys_ni_syscall)\n" "${t_nxt}"
t_nxt=$((t_nxt+1))
done
printf "__SYSCALL(%s, %s, )\n" "${t_nxt}" "${t_entry}"
printf "__SYSCALL(%s,%s)\n" "${t_nxt}" "${t_entry}"
}
grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (

2
arch/sh/kernel/syscalls_32.S
View File

@ -10,7 +10,7 @@
#include <linux/sys.h>
#include <linux/linkage.h>
#define __SYSCALL(nr, entry, nargs) .long entry
#define __SYSCALL(nr, entry) .long entry
.data
ENTRY(sys_call_table)
#include <asm/syscall_table.h>

3
arch/sparc/kernel/pci_fire.c
View File

@ -11,6 +11,7 @@
#include <linux/export.h>
#include <linux/irq.h>
#include <linux/of_device.h>
#include <linux/numa.h>
#include <asm/prom.h>
#include <asm/irq.h>
@ -416,7 +417,7 @@ static int pci_fire_pbm_init(struct pci_pbm_info *pbm,
struct device_node *dp = op->dev.of_node;
int err;
pbm->numa_node = -1;
pbm->numa_node = NUMA_NO_NODE;
pbm->pci_ops = &sun4u_pci_ops;
pbm->config_space_reg_bits = 12;

3
arch/sparc/kernel/pci_schizo.c
View File

@ -12,6 +12,7 @@
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/of_device.h>
#include <linux/numa.h>
#include <asm/iommu.h>
#include <asm/irq.h>
@ -1347,7 +1348,7 @@ static int schizo_pbm_init(struct pci_pbm_info *pbm,
pbm->next = pci_pbm_root;
pci_pbm_root = pbm;
pbm->numa_node = -1;
pbm->numa_node = NUMA_NO_NODE;
pbm->pci_ops = &sun4u_pci_ops;
pbm->config_space_reg_bits = 8;

3
arch/sparc/kernel/psycho_common.c
View File

@ -5,6 +5,7 @@
*/
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/numa.h>
#include <asm/upa.h>
@ -454,7 +455,7 @@ void psycho_pbm_init_common(struct pci_pbm_info *pbm, struct platform_device *op
struct device_node *dp = op->dev.of_node;
pbm->name = dp->full_name;
pbm->numa_node = -1;
pbm->numa_node = NUMA_NO_NODE;
pbm->chip_type = chip_type;
pbm->chip_version = of_getintprop_default(dp, "version#", 0);
pbm->chip_revision = of_getintprop_default(dp, "module-revision#", 0);

3
arch/sparc/kernel/sbus.c
View File

@ -15,6 +15,7 @@
#include <linux/interrupt.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/numa.h>
#include <asm/page.h>
#include <asm/io.h>
@ -561,7 +562,7 @@ static void __init sbus_iommu_init(struct platform_device *op)
op->dev.archdata.iommu = iommu;
op->dev.archdata.stc = strbuf;
op->dev.archdata.numa_node = -1;
op->dev.archdata.numa_node = NUMA_NO_NODE;
reg_base = regs + SYSIO_IOMMUREG_BASE;
iommu->iommu_control = reg_base + IOMMU_CONTROL;

6
arch/sparc/mm/init_64.c
View File

@ -976,13 +976,13 @@ static u64 __init memblock_nid_range_sun4u(u64 start, u64 end, int *nid)
{
int prev_nid, new_nid;
prev_nid = -1;
prev_nid = NUMA_NO_NODE;
for ( ; start < end; start += PAGE_SIZE) {
for (new_nid = 0; new_nid < num_node_masks; new_nid++) {
struct node_mem_mask *p = &node_masks[new_nid];
if ((start & p->mask) == p->match) {
if (prev_nid == -1)
if (prev_nid == NUMA_NO_NODE)
prev_nid = new_nid;
break;
}
@ -1208,7 +1208,7 @@ int of_node_to_nid(struct device_node *dp)
md = mdesc_grab();
count = 0;
nid = -1;
nid = NUMA_NO_NODE;
mdesc_for_each_node_by_name(md, grp, "group") {
if (!scan_arcs_for_cfg_handle(md, grp, cfg_handle)) {
nid = count;

13
arch/x86/include/asm/paravirt.h
View File

@ -422,25 +422,26 @@ static inline pgdval_t pgd_val(pgd_t pgd)
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep)
{
pteval_t ret;
ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep);
ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep);
return (pte_t) { .pte = ret };
}
static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
if (sizeof(pteval_t) > sizeof(long))
/* 5 arg words */
pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte);
pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte);
else
PVOP_VCALL4(mmu.ptep_modify_prot_commit,
mm, addr, ptep, pte.pte);
vma, addr, ptep, pte.pte);
}
static inline void set_pte(pte_t *ptep, pte_t pte)

5
arch/x86/include/asm/paravirt_types.h
View File

@ -55,6 +55,7 @@ struct task_struct;
struct cpumask;
struct flush_tlb_info;
struct mmu_gather;
struct vm_area_struct;
/*
* Wrapper type for pointers to code which uses the non-standard
@ -254,9 +255,9 @@ struct pv_mmu_ops {
pte_t *ptep, pte_t pteval);
void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep);
void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
void (*ptep_modify_prot_commit)(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t pte);
struct paravirt_callee_save pte_val;

3
arch/x86/include/asm/pci.h
View File

@ -7,6 +7,7 @@
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/scatterlist.h>
#include <linux/numa.h>
#include <asm/io.h>
#include <asm/pat.h>
#include <asm/x86_init.h>
@ -141,7 +142,7 @@ cpumask_of_pcibus(const struct pci_bus *bus)
int node;
node = __pcibus_to_node(bus);
return (node == -1) ? cpu_online_mask :
return (node == NUMA_NO_NODE) ? cpu_online_mask :
cpumask_of_node(node);
}
#endif

24
arch/x86/include/asm/uaccess.h
View File

@ -75,7 +75,7 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
#endif
/**
* access_ok: - Checks if a user space pointer is valid
* access_ok - Checks if a user space pointer is valid
* @addr: User space pointer to start of block to check
* @size: Size of block to check
*
@ -84,12 +84,12 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
*
* Checks if a pointer to a block of memory in user space is valid.
*
* Returns true (nonzero) if the memory block may be valid, false (zero)
* if it is definitely invalid.
*
* Note that, depending on architecture, this function probably just
* checks that the pointer is in the user space range - after calling
* this function, memory access functions may still return -EFAULT.
*
* Return: true (nonzero) if the memory block may be valid, false (zero)
* if it is definitely invalid.
*/
#define access_ok(addr, size) \
({ \
@ -134,7 +134,7 @@ extern int __get_user_bad(void);
__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
/**
* get_user: - Get a simple variable from user space.
* get_user - Get a simple variable from user space.
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
@ -148,7 +148,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
* @ptr must have pointer-to-simple-variable type, and the result of
* dereferencing @ptr must be assignable to @x without a cast.
*
* Returns zero on success, or -EFAULT on error.
* Return: zero on success, or -EFAULT on error.
* On error, the variable @x is set to zero.
*/
/*
@ -226,7 +226,7 @@ extern void __put_user_4(void);
extern void __put_user_8(void);
/**
* put_user: - Write a simple value into user space.
* put_user - Write a simple value into user space.
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
@ -240,7 +240,7 @@ extern void __put_user_8(void);
* @ptr must have pointer-to-simple-variable type, and @x must be assignable
* to the result of dereferencing @ptr.
*
* Returns zero on success, or -EFAULT on error.
* Return: zero on success, or -EFAULT on error.
*/
#define put_user(x, ptr) \
({ \
@ -502,7 +502,7 @@ struct __large_struct { unsigned long buf[100]; };
} while (0)
/**
* __get_user: - Get a simple variable from user space, with less checking.
* __get_user - Get a simple variable from user space, with less checking.
* @x: Variable to store result.
* @ptr: Source address, in user space.
*
@ -519,7 +519,7 @@ struct __large_struct { unsigned long buf[100]; };
* Caller must check the pointer with access_ok() before calling this
* function.
*
* Returns zero on success, or -EFAULT on error.
* Return: zero on success, or -EFAULT on error.
* On error, the variable @x is set to zero.
*/
@ -527,7 +527,7 @@ struct __large_struct { unsigned long buf[100]; };
__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
/**
* __put_user: - Write a simple value into user space, with less checking.
* __put_user - Write a simple value into user space, with less checking.
* @x: Value to copy to user space.
* @ptr: Destination address, in user space.
*
@ -544,7 +544,7 @@ struct __large_struct { unsigned long buf[100]; };
* Caller must check the pointer with access_ok() before calling this
* function.
*
* Returns zero on success, or -EFAULT on error.
* Return: zero on success, or -EFAULT on error.
*/
#define __put_user(x, ptr) \

7
arch/x86/kernel/apic/x2apic_uv_x.c
View File

@ -27,6 +27,7 @@
#include <linux/crash_dump.h>
#include <linux/reboot.h>
#include <linux/memory.h>
#include <linux/numa.h>
#include <asm/uv/uv_mmrs.h>
#include <asm/uv/uv_hub.h>
@ -1390,7 +1391,7 @@ static void __init build_socket_tables(void)
}
/* Set socket -> node values: */
lnid = -1;
lnid = NUMA_NO_NODE;
for_each_present_cpu(cpu) {
int nid = cpu_to_node(cpu);
int apicid, sockid;
@ -1521,7 +1522,7 @@ static void __init uv_system_init_hub(void)
new_hub->pnode = 0xffff;
new_hub->numa_blade_id = uv_node_to_blade_id(nodeid);
new_hub->memory_nid = -1;
new_hub->memory_nid = NUMA_NO_NODE;
new_hub->nr_possible_cpus = 0;
new_hub->nr_online_cpus = 0;
}
@ -1538,7 +1539,7 @@ static void __init uv_system_init_hub(void)
uv_cpu_info_per(cpu)->p_uv_hub_info = uv_hub_info_list(nodeid);
uv_cpu_info_per(cpu)->blade_cpu_id = uv_cpu_hub_info(cpu)->nr_possible_cpus++;
if (uv_cpu_hub_info(cpu)->memory_nid == -1)
if (uv_cpu_hub_info(cpu)->memory_nid == NUMA_NO_NODE)
uv_cpu_hub_info(cpu)->memory_nid = cpu_to_node(cpu);
/* Init memoryless node: */

2
arch/x86/kernel/setup_percpu.c
View File

@ -171,7 +171,7 @@ void __init setup_per_cpu_areas(void)
unsigned long delta;
int rc;
pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%d\n",
pr_info("NR_CPUS:%d nr_cpumask_bits:%d nr_cpu_ids:%u nr_node_ids:%u\n",
NR_CPUS, nr_cpumask_bits, nr_cpu_ids, nr_node_ids);
/*

3
arch/x86/kernel/smpboot.c
View File

@ -56,6 +56,7 @@
#include <linux/stackprotector.h>
#include <linux/gfp.h>
#include <linux/cpuidle.h>
#include <linux/numa.h>
#include <asm/acpi.h>
#include <asm/desc.h>
@ -841,7 +842,7 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
/* reduce the number of lines printed when booting a large cpu count system */
static void announce_cpu(int cpu, int apicid)
{
static int current_node = -1;
static int current_node = NUMA_NO_NODE;
int node = early_cpu_to_node(cpu);
static int width, node_width;

8
arch/x86/lib/usercopy_32.c
View File

@ -54,13 +54,13 @@ do { \
} while (0)
/**
* clear_user: - Zero a block of memory in user space.
* clear_user - Zero a block of memory in user space.
* @to: Destination address, in user space.
* @n: Number of bytes to zero.
*
* Zero a block of memory in user space.
*
* Returns number of bytes that could not be cleared.
* Return: number of bytes that could not be cleared.
* On success, this will be zero.
*/
unsigned long
@ -74,14 +74,14 @@ clear_user(void __user *to, unsigned long n)
EXPORT_SYMBOL(clear_user);
/**
* __clear_user: - Zero a block of memory in user space, with less checking.
* __clear_user - Zero a block of memory in user space, with less checking.
* @to: Destination address, in user space.
* @n: Number of bytes to zero.
*
* Zero a block of memory in user space. Caller must check
* the specified block with access_ok() before calling this function.
*
* Returns number of bytes that could not be cleared.
* Return: number of bytes that could not be cleared.
* On success, this will be zero.
*/
unsigned long

4
arch/x86/mm/numa.c
View File

@ -123,7 +123,7 @@ void __init setup_node_to_cpumask_map(void)
alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
/* cpumask_of_node() will now work */
pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
}
static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
@ -866,7 +866,7 @@ const struct cpumask *cpumask_of_node(int node)
{
if (node >= nr_node_ids) {
printk(KERN_WARNING
"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
"cpumask_of_node(%d): node > nr_node_ids(%u)\n",
node, nr_node_ids);
dump_stack();
return cpu_none_mask;

4
arch/x86/xen/mmu.h
View File

@ -17,8 +17,8 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep);
void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t pte);
unsigned long xen_read_cr2_direct(void);

8
arch/x86/xen/mmu_pv.c
View File

@ -306,20 +306,20 @@ static void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
__xen_set_pte(ptep, pteval);
}
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
pte_t xen_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
/* Just return the pte as-is. We preserve the bits on commit */
trace_xen_mmu_ptep_modify_prot_start(mm, addr, ptep, *ptep);
trace_xen_mmu_ptep_modify_prot_start(vma->vm_mm, addr, ptep, *ptep);
return *ptep;
}
void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t pte)
{
struct mmu_update u;
trace_xen_mmu_ptep_modify_prot_commit(mm, addr, ptep, pte);
trace_xen_mmu_ptep_modify_prot_commit(vma->vm_mm, addr, ptep, pte);
xen_mc_batch();
u.ptr = virt_to_machine(ptep).maddr | MMU_PT_UPDATE_PRESERVE_AD;

5
drivers/block/mtip32xx/mtip32xx.c
View File

@ -40,6 +40,7 @@
#include <linux/export.h>
#include <linux/debugfs.h>
#include <linux/prefetch.h>
#include <linux/numa.h>
#include "mtip32xx.h"
#define HW_CMD_SLOT_SZ (MTIP_MAX_COMMAND_SLOTS * 32)
@ -4018,9 +4019,9 @@ static int get_least_used_cpu_on_node(int node)
/* Helper for selecting a node in round robin mode */
static inline int mtip_get_next_rr_node(void)
{
static int next_node = -1;
static int next_node = NUMA_NO_NODE;
if (next_node == -1) {
if (next_node == NUMA_NO_NODE) {
next_node = first_online_node;
return next_node;
}

2
drivers/char/agp/efficeon-agp.c
View File

@ -163,7 +163,6 @@ static int efficeon_free_gatt_table(struct agp_bridge_data *bridge)
unsigned long page = efficeon_private.l1_table[index];
if (page) {
efficeon_private.l1_table[index] = 0;
ClearPageReserved(virt_to_page((char *)page));
free_page(page);
freed++;
}
@ -219,7 +218,6 @@ static int efficeon_create_gatt_table(struct agp_bridge_data *bridge)
efficeon_free_gatt_table(agp_bridge);
return -ENOMEM;
}
SetPageReserved(virt_to_page((char *)page));
for (offset = 0; offset < PAGE_SIZE; offset += clflush_chunk)
clflush((char *)page+offset);

4
drivers/dma/dmaengine.c
View File

@ -63,6 +63,7 @@
#include <linux/acpi_dma.h>
#include <linux/of_dma.h>
#include <linux/mempool.h>
#include <linux/numa.h>
static DEFINE_MUTEX(dma_list_mutex);
static DEFINE_IDA(dma_ida);
@ -386,7 +387,8 @@ EXPORT_SYMBOL(dma_issue_pending_all);
static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
{
int node = dev_to_node(chan->device->dev);
return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node));
return node == NUMA_NO_NODE ||
cpumask_test_cpu(cpu, cpumask_of_node(node));
}
/**

6
drivers/gpu/drm/i915/i915_utils.h
View File

@ -123,12 +123,6 @@ static inline u64 ptr_to_u64(const void *ptr)
#include <linux/list.h>
static inline int list_is_first(const struct list_head *list,
const struct list_head *head)
{
return head->next == list;
}
static inline void __list_del_many(struct list_head *head,
struct list_head *first)
{

21
drivers/hv/hv_balloon.c
View File

@ -681,8 +681,13 @@ static struct notifier_block hv_memory_nb = {
/* Check if the particular page is backed and can be onlined and online it. */
static void hv_page_online_one(struct hv_hotadd_state *has, struct page *pg)
{
if (!has_pfn_is_backed(has, page_to_pfn(pg)))
if (!has_pfn_is_backed(has, page_to_pfn(pg))) {
if (!PageOffline(pg))
__SetPageOffline(pg);
return;
}
if (PageOffline(pg))
__ClearPageOffline(pg);
/* This frame is currently backed; online the page. */
__online_page_set_limits(pg);
@ -771,7 +776,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
}
}
static void hv_online_page(struct page *pg)
static void hv_online_page(struct page *pg, unsigned int order)
{
struct hv_hotadd_state *has;
unsigned long flags;
@ -780,10 +785,11 @@ static void hv_online_page(struct page *pg)
spin_lock_irqsave(&dm_device.ha_lock, flags);
list_for_each_entry(has, &dm_device.ha_region_list, list) {
/* The page belongs to a different HAS. */
if ((pfn < has->start_pfn) || (pfn >= has->end_pfn))
if ((pfn < has->start_pfn) ||
(pfn + (1UL << order) > has->end_pfn))
continue;
hv_page_online_one(has, pg);
hv_bring_pgs_online(has, pfn, 1UL << order);
break;
}
spin_unlock_irqrestore(&dm_device.ha_lock, flags);
@ -1201,6 +1207,7 @@ static void free_balloon_pages(struct hv_dynmem_device *dm,
for (i = 0; i < num_pages; i++) {
pg = pfn_to_page(i + start_frame);
__ClearPageOffline(pg);
__free_page(pg);
dm->num_pages_ballooned--;
}
@ -1213,7 +1220,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
struct dm_balloon_response *bl_resp,
int alloc_unit)
{
unsigned int i = 0;
unsigned int i, j;
struct page *pg;
if (num_pages < alloc_unit)
@ -1245,6 +1252,10 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
if (alloc_unit != 1)
split_page(pg, get_order(alloc_unit << PAGE_SHIFT));
/* mark all pages offline */
for (j = 0; j < (1 << get_order(alloc_unit << PAGE_SHIFT)); j++)
__SetPageOffline(pg + j);
bl_resp->range_count++;
bl_resp->range_array[i].finfo.start_page =
page_to_pfn(pg);

3
drivers/infiniband/hw/hfi1/affinity.c
View File

@ -48,6 +48,7 @@
#include <linux/cpumask.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/numa.h>
#include "hfi.h"
#include "affinity.h"
@ -777,7 +778,7 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd)
_dev_comp_vect_cpu_mask_clean_up(dd, entry);
unlock:
mutex_unlock(&node_affinity.lock);
dd->node = -1;
dd->node = NUMA_NO_NODE;
}
/*

3
drivers/infiniband/hw/hfi1/init.c
View File

@ -54,6 +54,7 @@
#include <linux/printk.h>
#include <linux/hrtimer.h>
#include <linux/bitmap.h>
#include <linux/numa.h>
#include <rdma/rdma_vt.h>
#include "hfi.h"
@ -1303,7 +1304,7 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
dd->unit = ret;
list_add(&dd->list, &hfi1_dev_list);
}
dd->node = -1;
dd->node = NUMA_NO_NODE;
spin_unlock_irqrestore(&hfi1_devs_lock, flags);
idr_preload_end();

5
drivers/iommu/dmar.c
View File

@ -39,6 +39,7 @@
#include <linux/dmi.h>
#include <linux/slab.h>
#include <linux/iommu.h>
#include <linux/numa.h>
#include <asm/irq_remapping.h>
#include <asm/iommu_table.h>
@ -477,7 +478,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
int node = acpi_map_pxm_to_node(rhsa->proximity_domain);
if (!node_online(node))
node = -1;
node = NUMA_NO_NODE;
drhd->iommu->node = node;
return 0;
}
@ -1062,7 +1063,7 @@ static int alloc_iommu(struct dmar_drhd_unit *drhd)
iommu->msagaw = msagaw;
iommu->segment = drhd->segment;
iommu->node = -1;
iommu->node = NUMA_NO_NODE;
ver = readl(iommu->reg + DMAR_VER_REG);
pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",

3
drivers/iommu/intel-iommu.c
View File

@ -47,6 +47,7 @@
#include <linux/dma-contiguous.h>
#include <linux/dma-direct.h>
#include <linux/crash_dump.h>
#include <linux/numa.h>
#include <asm/irq_remapping.h>
#include <asm/cacheflush.h>
#include <asm/iommu.h>
@ -1716,7 +1717,7 @@ static struct dmar_domain *alloc_domain(int flags)
return NULL;
memset(domain, 0, sizeof(*domain));
domain->nid = -1;
domain->nid = NUMA_NO_NODE;
domain->flags = flags;
domain->has_iotlb_device = false;
INIT_LIST_HEAD(&domain->devices);

3
drivers/misc/sgi-xp/xpc_uv.c
View File

@ -22,6 +22,7 @@
#include <linux/module.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/numa.h>
#include <asm/uv/uv_hub.h>
#if defined CONFIG_X86_64
#include <asm/uv/bios.h>
@ -61,7 +62,7 @@ static struct xpc_heartbeat_uv *xpc_heartbeat_uv;
XPC_NOTIFY_MSG_SIZE_UV)
#define XPC_NOTIFY_IRQ_NAME "xpc_notify"
static int xpc_mq_node = -1;
static int xpc_mq_node = NUMA_NO_NODE;
static struct xpc_gru_mq_uv *xpc_activate_mq_uv;
static struct xpc_gru_mq_uv *xpc_notify_mq_uv;

32
drivers/misc/vmw_balloon.c
View File

@ -556,6 +556,36 @@ vmballoon_page_in_frames(enum vmballoon_page_size_type page_size)
return 1 << vmballoon_page_order(page_size);
}
/**
* vmballoon_mark_page_offline() - mark a page as offline
* @page: pointer for the page.
* @page_size: the size of the page.
*/
static void
vmballoon_mark_page_offline(struct page *page,
enum vmballoon_page_size_type page_size)
{
int i;
for (i = 0; i < vmballoon_page_in_frames(page_size); i++)
__SetPageOffline(page + i);
}
/**
* vmballoon_mark_page_online() - mark a page as online
* @page: pointer for the page.
* @page_size: the size of the page.
*/
static void
vmballoon_mark_page_online(struct page *page,
enum vmballoon_page_size_type page_size)
{
int i;
for (i = 0; i < vmballoon_page_in_frames(page_size); i++)
__ClearPageOffline(page + i);
}
/**
* vmballoon_send_get_target() - Retrieve desired balloon size from the host.
*
@ -612,6 +642,7 @@ static int vmballoon_alloc_page_list(struct vmballoon *b,
ctl->page_size);
if (page) {
vmballoon_mark_page_offline(page, ctl->page_size);
/* Success. Add the page to the list and continue. */
list_add(&page->lru, &ctl->pages);
continue;
@ -850,6 +881,7 @@ static void vmballoon_release_page_list(struct list_head *page_list,
list_for_each_entry_safe(page, tmp, page_list, lru) {
list_del(&page->lru);
vmballoon_mark_page_online(page, page_size);
__free_pages(page, vmballoon_page_order(page_size));
}

5
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
View File

@ -27,6 +27,7 @@
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/atomic.h>
#include <linux/numa.h>
#include <scsi/fc/fc_fcoe.h>
#include <net/udp_tunnel.h>
#include <net/pkt_cls.h>
@ -6418,7 +6419,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
{
struct device *dev = tx_ring->dev;
int orig_node = dev_to_node(dev);
int ring_node = -1;
int ring_node = NUMA_NO_NODE;
int size;
size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@ -6512,7 +6513,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
{
struct device *dev = rx_ring->dev;
int orig_node = dev_to_node(dev);
int ring_node = -1;
int ring_node = NUMA_NO_NODE;
int size;
size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;

18
drivers/xen/balloon.c
View File

@ -369,14 +369,20 @@ static enum bp_state reserve_additional_memory(void)
return BP_ECANCELED;
}
static void xen_online_page(struct page *page)
static void xen_online_page(struct page *page, unsigned int order)
{
__online_page_set_limits(page);
unsigned long i, size = (1 << order);
unsigned long start_pfn = page_to_pfn(page);
struct page *p;
pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn);
mutex_lock(&balloon_mutex);
__balloon_append(page);
for (i = 0; i < size; i++) {
p = pfn_to_page(start_pfn + i);
__online_page_set_limits(p);
__SetPageOffline(p);
__balloon_append(p);
}
mutex_unlock(&balloon_mutex);
}
@ -441,6 +447,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
/* Relinquish the page back to the allocator. */
__ClearPageOffline(page);
free_reserved_page(page);
}
@ -467,6 +474,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
state = BP_EAGAIN;
break;
}
__SetPageOffline(page);
adjust_managed_page_count(page, -1);
xenmem_reservation_scrub_page(page);
list_add(&page->lru, &pages);

1
fs/file.c
View File

@ -457,6 +457,7 @@ struct files_struct init_files = {
.full_fds_bits = init_files.full_fds_bits_init,
},
.file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock),
.resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait),
};
static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start)

2
fs/hugetlbfs/inode.c
View File

@ -530,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
inode_lock(inode);
/* protected by i_mutex */
if (info->seals & F_SEAL_WRITE) {
if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
inode_unlock(inode);
return -EPERM;
}

8
fs/inode.c
View File

@ -2093,14 +2093,8 @@ EXPORT_SYMBOL(inode_dio_wait);
void inode_set_flags(struct inode *inode, unsigned int flags,
unsigned int mask)
{
unsigned int old_flags, new_flags;
WARN_ON_ONCE(flags & ~mask);
do {
old_flags = READ_ONCE(inode->i_flags);
new_flags = (old_flags & ~mask) | flags;
} while (unlikely(cmpxchg(&inode->i_flags, old_flags,
new_flags) != old_flags));
set_mask_bits(&inode->i_flags, mask, flags);
}
EXPORT_SYMBOL(inode_set_flags);

31
fs/kernfs/file.c
View File

@ -832,26 +832,35 @@ void kernfs_drain_open_files(struct kernfs_node *kn)
* to see if it supports poll (Neither 'poll' nor 'select' return
* an appropriate error code). When in doubt, set a suitable timeout value.
*/
__poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait)
{
struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry);
struct kernfs_open_node *on = kn->attr.open;
poll_wait(of->file, &on->poll, wait);
if (of->event != atomic_read(&on->event))
return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
return DEFAULT_POLLMASK;
}
static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
{
struct kernfs_open_file *of = kernfs_of(filp);
struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry);
struct kernfs_open_node *on = kn->attr.open;
__poll_t ret;
if (!kernfs_get_active(kn))
goto trigger;
return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
poll_wait(filp, &on->poll, wait);
if (kn->attr.ops->poll)
ret = kn->attr.ops->poll(of, wait);
else
ret = kernfs_generic_poll(of, wait);
kernfs_put_active(kn);
if (of->event != atomic_read(&on->event))
goto trigger;
return DEFAULT_POLLMASK;
trigger:
return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;
return ret;
}
static void kernfs_notify_workfn(struct work_struct *work)

159
fs/ocfs2/alloc.c
View File

@ -7532,10 +7532,11 @@ static int ocfs2_trim_group(struct super_block *sb,
return count;
}
int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
static
int ocfs2_trim_mainbm(struct super_block *sb, struct fstrim_range *range)
{
struct ocfs2_super *osb = OCFS2_SB(sb);
u64 start, len, trimmed, first_group, last_group, group;
u64 start, len, trimmed = 0, first_group, last_group = 0, group = 0;
int ret, cnt;
u32 first_bit, last_bit, minlen;
struct buffer_head *main_bm_bh = NULL;
@ -7543,7 +7544,6 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
struct buffer_head *gd_bh = NULL;
struct ocfs2_dinode *main_bm;
struct ocfs2_group_desc *gd = NULL;
struct ocfs2_trim_fs_info info, *pinfo = NULL;
start = range->start >> osb->s_clustersize_bits;
len = range->len >> osb->s_clustersize_bits;
@ -7552,6 +7552,9 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
if (minlen >= osb->bitmap_cpg || range->len < sb->s_blocksize)
return -EINVAL;
trace_ocfs2_trim_mainbm(start, len, minlen);
next_group:
main_bm_inode = ocfs2_get_system_file_inode(osb,
GLOBAL_BITMAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT);
@ -7570,64 +7573,34 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
}
main_bm = (struct ocfs2_dinode *)main_bm_bh->b_data;
if (start >= le32_to_cpu(main_bm->i_clusters)) {
ret = -EINVAL;
goto out_unlock;
}
len = range->len >> osb->s_clustersize_bits;
if (start + len > le32_to_cpu(main_bm->i_clusters))
len = le32_to_cpu(main_bm->i_clusters) - start;
trace_ocfs2_trim_fs(start, len, minlen);
ocfs2_trim_fs_lock_res_init(osb);
ret = ocfs2_trim_fs_lock(osb, NULL, 1);
if (ret < 0) {
if (ret != -EAGAIN) {
mlog_errno(ret);
ocfs2_trim_fs_lock_res_uninit(osb);
/*
* Do some check before trim the first group.
*/
if (!group) {
if (start >= le32_to_cpu(main_bm->i_clusters)) {
ret = -EINVAL;
goto out_unlock;
}
mlog(ML_NOTICE, "Wait for trim on device (%s) to "
"finish, which is running from another node.\n",
osb->dev_str);
ret = ocfs2_trim_fs_lock(osb, &info, 0);
if (ret < 0) {
mlog_errno(ret);
ocfs2_trim_fs_lock_res_uninit(osb);
goto out_unlock;
}
if (start + len > le32_to_cpu(main_bm->i_clusters))
len = le32_to_cpu(main_bm->i_clusters) - start;
if (info.tf_valid && info.tf_success &&
info.tf_start == start && info.tf_len == len &&
info.tf_minlen == minlen) {
/* Avoid sending duplicated trim to a shared device */
mlog(ML_NOTICE, "The same trim on device (%s) was "
"just done from node (%u), return.\n",
osb->dev_str, info.tf_nodenum);
range->len = info.tf_trimlen;
goto out_trimunlock;
}
/*
* Determine first and last group to examine based on
* start and len
*/
first_group = ocfs2_which_cluster_group(main_bm_inode, start);
if (first_group == osb->first_cluster_group_blkno)
first_bit = start;
else
first_bit = start - ocfs2_blocks_to_clusters(sb,
first_group);
last_group = ocfs2_which_cluster_group(main_bm_inode,
start + len - 1);
group = first_group;
}
info.tf_nodenum = osb->node_num;
info.tf_start = start;
info.tf_len = len;
info.tf_minlen = minlen;
/* Determine first and last group to examine based on start and len */
first_group = ocfs2_which_cluster_group(main_bm_inode, start);
if (first_group == osb->first_cluster_group_blkno)
first_bit = start;
else
first_bit = start - ocfs2_blocks_to_clusters(sb, first_group);
last_group = ocfs2_which_cluster_group(main_bm_inode, start + len - 1);
last_bit = osb->bitmap_cpg;
trimmed = 0;
for (group = first_group; group <= last_group;) {
do {
if (first_bit + len >= osb->bitmap_cpg)
last_bit = osb->bitmap_cpg;
else
@ -7659,21 +7632,81 @@ int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
group = ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
else
group += ocfs2_clusters_to_blocks(sb, osb->bitmap_cpg);
}
range->len = trimmed * sb->s_blocksize;
} while (0);
info.tf_trimlen = range->len;
info.tf_success = (ret ? 0 : 1);
pinfo = &info;
out_trimunlock:
ocfs2_trim_fs_unlock(osb, pinfo);
ocfs2_trim_fs_lock_res_uninit(osb);
out_unlock:
ocfs2_inode_unlock(main_bm_inode, 0);
brelse(main_bm_bh);
main_bm_bh = NULL;
out_mutex:
inode_unlock(main_bm_inode);
iput(main_bm_inode);
/*
* If all the groups trim are not done or failed, but we should release
* main_bm related locks for avoiding the current IO starve, then go to
* trim the next group
*/
if (ret >= 0 && group <= last_group)
goto next_group;
out:
range->len = trimmed * sb->s_blocksize;
return ret;
}
int ocfs2_trim_fs(struct super_block *sb, struct fstrim_range *range)
{
int ret;
struct ocfs2_super *osb = OCFS2_SB(sb);
struct ocfs2_trim_fs_info info, *pinfo = NULL;
ocfs2_trim_fs_lock_res_init(osb);
trace_ocfs2_trim_fs(range->start, range->len, range->minlen);
ret = ocfs2_trim_fs_lock(osb, NULL, 1);
if (ret < 0) {
if (ret != -EAGAIN) {
mlog_errno(ret);
ocfs2_trim_fs_lock_res_uninit(osb);
return ret;
}
mlog(ML_NOTICE, "Wait for trim on device (%s) to "
"finish, which is running from another node.\n",
osb->dev_str);
ret = ocfs2_trim_fs_lock(osb, &info, 0);
if (ret < 0) {
mlog_errno(ret);
ocfs2_trim_fs_lock_res_uninit(osb);
return ret;
}
if (info.tf_valid && info.tf_success &&
info.tf_start == range->start &&
info.tf_len == range->len &&
info.tf_minlen == range->minlen) {
/* Avoid sending duplicated trim to a shared device */
mlog(ML_NOTICE, "The same trim on device (%s) was "
"just done from node (%u), return.\n",
osb->dev_str, info.tf_nodenum);
range->len = info.tf_trimlen;
goto out;
}
}
info.tf_nodenum = osb->node_num;
info.tf_start = range->start;
info.tf_len = range->len;
info.tf_minlen = range->minlen;
ret = ocfs2_trim_mainbm(sb, range);
info.tf_trimlen = range->len;
info.tf_success = (ret < 0 ? 0 : 1);
pinfo = &info;
out:
ocfs2_trim_fs_unlock(osb, pinfo);
ocfs2_trim_fs_lock_res_uninit(osb);
return ret;
}

14
fs/ocfs2/cluster/nodemanager.c
View File

@ -621,13 +621,15 @@ static void o2nm_node_group_drop_item(struct config_group *group,
struct o2nm_node *node = to_o2nm_node(item);
struct o2nm_cluster *cluster = to_o2nm_cluster(group->cg_item.ci_parent);
o2net_disconnect_node(node);
if (cluster->cl_nodes[node->nd_num] == node) {
o2net_disconnect_node(node);
if (cluster->cl_has_local &&
(cluster->cl_local_node == node->nd_num)) {
cluster->cl_has_local = 0;
cluster->cl_local_node = O2NM_INVALID_NODE_NUM;
o2net_stop_listening(node);
if (cluster->cl_has_local &&
(cluster->cl_local_node == node->nd_num)) {
cluster->cl_has_local = 0;
cluster->cl_local_node = O2NM_INVALID_NODE_NUM;
o2net_stop_listening(node);
}
}
/* XXX call into net to stop this node from trading messages */

5
fs/ocfs2/dlmglue.c
View File

@ -686,6 +686,9 @@ void ocfs2_trim_fs_lock_res_init(struct ocfs2_super *osb)
{
struct ocfs2_lock_res *lockres = &osb->osb_trim_fs_lockres;
/* Only one trimfs thread are allowed to work at the same time. */
mutex_lock(&osb->obs_trim_fs_mutex);
ocfs2_lock_res_init_once(lockres);
ocfs2_build_lock_name(OCFS2_LOCK_TYPE_TRIM_FS, 0, 0, lockres->l_name);
ocfs2_lock_res_init_common(osb, lockres, OCFS2_LOCK_TYPE_TRIM_FS,
@ -698,6 +701,8 @@ void ocfs2_trim_fs_lock_res_uninit(struct ocfs2_super *osb)
ocfs2_simple_drop_lockres(osb, lockres);
ocfs2_lock_res_free(lockres);
mutex_unlock(&osb->obs_trim_fs_mutex);
}
static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res,

1
fs/ocfs2/ocfs2.h
View File

@ -407,6 +407,7 @@ struct ocfs2_super
struct ocfs2_lock_res osb_rename_lockres;
struct ocfs2_lock_res osb_nfs_sync_lockres;
struct ocfs2_lock_res osb_trim_fs_lockres;
struct mutex obs_trim_fs_mutex;
struct ocfs2_dlm_debug *osb_dlm_debug;
struct dentry *osb_debug_root;

2
fs/ocfs2/ocfs2_trace.h
View File

@ -712,6 +712,8 @@ TRACE_EVENT(ocfs2_trim_extent,
DEFINE_OCFS2_ULL_UINT_UINT_UINT_EVENT(ocfs2_trim_group);
DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_mainbm);
DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_trim_fs);
/* End of trace events for fs/ocfs2/alloc.c. */

8
fs/ocfs2/slot_map.c
View File

@ -55,7 +55,7 @@ struct ocfs2_slot_info {
unsigned int si_blocks;
struct buffer_head **si_bh;
unsigned int si_num_slots;
struct ocfs2_slot *si_slots;
struct ocfs2_slot si_slots[];
};
@ -420,9 +420,7 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb)
struct inode *inode = NULL;
struct ocfs2_slot_info *si;
si = kzalloc(sizeof(struct ocfs2_slot_info) +
(sizeof(struct ocfs2_slot) * osb->max_slots),
GFP_KERNEL);
si = kzalloc(struct_size(si, si_slots, osb->max_slots), GFP_KERNEL);
if (!si) {
status = -ENOMEM;
mlog_errno(status);
@ -431,8 +429,6 @@ int ocfs2_init_slot_info(struct ocfs2_super *osb)
si->si_extended = ocfs2_uses_extended_slot_map(osb);
si->si_num_slots = osb->max_slots;
si->si_slots = (struct ocfs2_slot *)((char *)si +
sizeof(struct ocfs2_slot_info));
inode = ocfs2_get_system_file_inode(osb, SLOT_MAP_SYSTEM_INODE,
OCFS2_INVALID_SLOT);

2
fs/ocfs2/super.c
View File

@ -1847,6 +1847,8 @@ static int ocfs2_mount_volume(struct super_block *sb)
if (ocfs2_is_hard_readonly(osb))
goto leave;
mutex_init(&osb->obs_trim_fs_mutex);
status = ocfs2_dlm_init(osb);
if (status < 0) {
mlog_errno(status);

3
fs/pipe.c
View File

@ -140,8 +140,7 @@ static int anon_pipe_buf_steal(struct pipe_inode_info *pipe,
struct page *page = buf->page;
if (page_count(page) == 1) {
if (memcg_kmem_enabled())
memcg_kmem_uncharge(page, 0);
memcg_kmem_uncharge(page, 0);
__SetPageLocked(page);
return 0;
}

16
fs/proc/array.c
View File

@ -343,28 +343,28 @@ static inline void task_seccomp(struct seq_file *m, struct task_struct *p)
#ifdef CONFIG_SECCOMP
seq_put_decimal_ull(m, "\nSeccomp:\t", p->seccomp.mode);
#endif
seq_printf(m, "\nSpeculation_Store_Bypass:\t");
seq_puts(m, "\nSpeculation_Store_Bypass:\t");
switch (arch_prctl_spec_ctrl_get(p, PR_SPEC_STORE_BYPASS)) {
case -EINVAL:
seq_printf(m, "unknown");
seq_puts(m, "unknown");
break;
case PR_SPEC_NOT_AFFECTED:
seq_printf(m, "not vulnerable");
seq_puts(m, "not vulnerable");
break;
case PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE:
seq_printf(m, "thread force mitigated");
seq_puts(m, "thread force mitigated");
break;
case PR_SPEC_PRCTL | PR_SPEC_DISABLE:
seq_printf(m, "thread mitigated");
seq_puts(m, "thread mitigated");
break;
case PR_SPEC_PRCTL | PR_SPEC_ENABLE:
seq_printf(m, "thread vulnerable");
seq_puts(m, "thread vulnerable");
break;
case PR_SPEC_DISABLE:
seq_printf(m, "globally mitigated");
seq_puts(m, "globally mitigated");
break;
default:
seq_printf(m, "vulnerable");
seq_puts(m, "vulnerable");
break;
}
seq_putc(m, '\n');

4
fs/proc/base.c
View File

@ -456,7 +456,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
if (unlikely(!sched_info_on()))
seq_printf(m, "0 0 0\n");
seq_puts(m, "0 0 0\n");
else
seq_printf(m, "%llu %llu %lu\n",
(unsigned long long)task->se.sum_exec_runtime,
@ -3161,7 +3161,7 @@ static struct dentry *proc_pid_instantiate(struct dentry * dentry,
return d_splice_alias(inode, dentry);
}
struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
{
struct task_struct *task;
unsigned tgid;

2
fs/proc/internal.h
View File

@ -162,7 +162,7 @@ extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struc
extern void pid_update_inode(struct task_struct *, struct inode *);
extern int pid_delete_dentry(const struct dentry *);
extern int proc_pid_readdir(struct file *, struct dir_context *);
extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
struct dentry *proc_pid_lookup(struct dentry *, unsigned int);
extern loff_t mem_lseek(struct file *, loff_t, int);
/* Lookups */

4
fs/proc/page.c
View File

@ -152,8 +152,8 @@ u64 stable_page_flags(struct page *page)
else if (page_count(page) == 0 && is_free_buddy_page(page))
u |= 1 << KPF_BUDDY;
if (PageBalloon(page))
u |= 1 << KPF_BALLOON;
if (PageOffline(page))
u |= 1 << KPF_OFFLINE;
if (PageTable(page))
u |= 1 << KPF_PGTABLE;

2
fs/proc/root.c
View File

@ -154,7 +154,7 @@ static int proc_root_getattr(const struct path *path, struct kstat *stat,
static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentry, unsigned int flags)
{
if (!proc_pid_lookup(dir, dentry, flags))
if (!proc_pid_lookup(dentry, flags))
return NULL;
return proc_lookup(dir, dentry, flags);

16
fs/proc/self.c
View File

@ -38,6 +38,7 @@ int proc_setup_self(struct super_block *s)
struct inode *root_inode = d_inode(s->s_root);
struct pid_namespace *ns = proc_pid_ns(root_inode);
struct dentry *self;
int ret = -ENOMEM;
inode_lock(root_inode);
self = d_alloc_name(s->s_root, "self");
@ -51,20 +52,19 @@ int proc_setup_self(struct super_block *s)
inode->i_gid = GLOBAL_ROOT_GID;
inode->i_op = &proc_self_inode_operations;
d_add(self, inode);
ret = 0;
} else {
dput(self);
self = ERR_PTR(-ENOMEM);
}
} else {
self = ERR_PTR(-ENOMEM);
}
inode_unlock(root_inode);
if (IS_ERR(self)) {
if (ret)
pr_err("proc_fill_super: can't allocate /proc/self\n");
return PTR_ERR(self);
}
ns->proc_self = self;
return 0;
else
ns->proc_self = self;
return ret;
}
void __init proc_self_init(void)

60
fs/proc/stat.c
View File

@ -23,21 +23,21 @@
#ifdef arch_idle_time
static u64 get_idle_time(int cpu)
static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
{
u64 idle;
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
idle = kcs->cpustat[CPUTIME_IDLE];
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
idle += arch_idle_time(cpu);
return idle;
}
static u64 get_iowait_time(int cpu)
static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
{
u64 iowait;
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
iowait = kcs->cpustat[CPUTIME_IOWAIT];
if (cpu_online(cpu) && nr_iowait_cpu(cpu))
iowait += arch_idle_time(cpu);
return iowait;
@ -45,7 +45,7 @@ static u64 get_iowait_time(int cpu)
#else
static u64 get_idle_time(int cpu)
static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
{
u64 idle, idle_usecs = -1ULL;
@ -54,14 +54,14 @@ static u64 get_idle_time(int cpu)
if (idle_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
idle = kcs->cpustat[CPUTIME_IDLE];
else
idle = idle_usecs * NSEC_PER_USEC;
return idle;
}
static u64 get_iowait_time(int cpu)
static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
{
u64 iowait, iowait_usecs = -1ULL;
@ -70,7 +70,7 @@ static u64 get_iowait_time(int cpu)
if (iowait_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
iowait = kcs->cpustat[CPUTIME_IOWAIT];
else
iowait = iowait_usecs * NSEC_PER_USEC;
@ -120,16 +120,18 @@ static int show_stat(struct seq_file *p, void *v)
getboottime64(&boottime);
for_each_possible_cpu(i) {
user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];
system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
idle += get_idle_time(i);
iowait += get_iowait_time(i);
irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
struct kernel_cpustat *kcs = &kcpustat_cpu(i);
user += kcs->cpustat[CPUTIME_USER];
nice += kcs->cpustat[CPUTIME_NICE];
system += kcs->cpustat[CPUTIME_SYSTEM];
idle += get_idle_time(kcs, i);
iowait += get_iowait_time(kcs, i);
irq += kcs->cpustat[CPUTIME_IRQ];
softirq += kcs->cpustat[CPUTIME_SOFTIRQ];
steal += kcs->cpustat[CPUTIME_STEAL];
guest += kcs->cpustat[CPUTIME_GUEST];
guest_nice += kcs->cpustat[CPUTIME_GUEST_NICE];
sum += kstat_cpu_irqs_sum(i);
sum += arch_irq_stat_cpu(i);
@ -155,17 +157,19 @@ static int show_stat(struct seq_file *p, void *v)
seq_putc(p, '\n');
for_each_online_cpu(i) {
struct kernel_cpustat *kcs = &kcpustat_cpu(i);
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];
system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
idle = get_idle_time(i);
iowait = get_iowait_time(i);
irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
user = kcs->cpustat[CPUTIME_USER];
nice = kcs->cpustat[CPUTIME_NICE];
system = kcs->cpustat[CPUTIME_SYSTEM];
idle = get_idle_time(kcs, i);
iowait = get_iowait_time(kcs, i);
irq = kcs->cpustat[CPUTIME_IRQ];
softirq = kcs->cpustat[CPUTIME_SOFTIRQ];
steal = kcs->cpustat[CPUTIME_STEAL];
guest = kcs->cpustat[CPUTIME_GUEST];
guest_nice = kcs->cpustat[CPUTIME_GUEST_NICE];
seq_printf(p, "cpu%d", i);
seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));

8
fs/proc/task_mmu.c
View File

@ -948,10 +948,12 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
pte_t ptent = *pte;
if (pte_present(ptent)) {
ptent = ptep_modify_prot_start(vma->vm_mm, addr, pte);
ptent = pte_wrprotect(ptent);
pte_t old_pte;
old_pte = ptep_modify_prot_start(vma, addr, pte);
ptent = pte_wrprotect(old_pte);
ptent = pte_clear_soft_dirty(ptent);
ptep_modify_prot_commit(vma->vm_mm, addr, pte, ptent);
ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent);
} else if (is_swap_pte(ptent)) {
ptent = pte_swp_clear_soft_dirty(ptent);
set_pte_at(vma->vm_mm, addr, pte, ptent);

2
fs/proc/task_nommu.c
View File

@ -178,7 +178,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
seq_file_path(m, file, "");
} else if (mm && is_stack(vma)) {
seq_pad(m, ' ');
seq_printf(m, "[stack]");
seq_puts(m, "[stack]");
}
seq_putc(m, '\n');

16
fs/proc/thread_self.c
View File

@ -38,6 +38,7 @@ int proc_setup_thread_self(struct super_block *s)
struct inode *root_inode = d_inode(s->s_root);
struct pid_namespace *ns = proc_pid_ns(root_inode);
struct dentry *thread_self;
int ret = -ENOMEM;
inode_lock(root_inode);
thread_self = d_alloc_name(s->s_root, "thread-self");
@ -51,20 +52,19 @@ int proc_setup_thread_self(struct super_block *s)
inode->i_gid = GLOBAL_ROOT_GID;
inode->i_op = &proc_thread_self_inode_operations;
d_add(thread_self, inode);
ret = 0;
} else {
dput(thread_self);
thread_self = ERR_PTR(-ENOMEM);
}
} else {
thread_self = ERR_PTR(-ENOMEM);
}
inode_unlock(root_inode);
if (IS_ERR(thread_self)) {
if (ret)
pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
return PTR_ERR(thread_self);
}
ns->proc_thread_self = thread_self;
return 0;
else
ns->proc_thread_self = thread_self;
return ret;
}
void __init proc_thread_self_init(void)

18
include/asm-generic/pgtable.h
View File

@ -606,7 +606,7 @@ static inline int pmd_none_or_clear_bad(pmd_t *pmd)
return 0;
}
static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
@ -615,10 +615,10 @@ static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
* non-present, preventing the hardware from asynchronously
* updating it.
*/
return ptep_get_and_clear(mm, addr, ptep);
return ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep, pte_t pte)
{
@ -626,7 +626,7 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
* The pte is non-present, so there's no hardware state to
* preserve.
*/
set_pte_at(mm, addr, ptep, pte);
set_pte_at(vma->vm_mm, addr, ptep, pte);
}
#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
@ -644,22 +644,22 @@ static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
* queue the update to be done at some later time. The update must be
* actually committed before the pte lock is released, however.
*/
static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep)
{
return __ptep_modify_prot_start(mm, addr, ptep);
return __ptep_modify_prot_start(vma, addr, ptep);
}
/*
* Commit an update to a pte, leaving any hardware-controlled bits in
* the PTE unmodified.
*/
static inline void ptep_modify_prot_commit(struct mm_struct *mm,
static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep, pte_t pte)
pte_t *ptep, pte_t old_pte, pte_t pte)
{
__ptep_modify_prot_commit(mm, addr, ptep, pte);
__ptep_modify_prot_commit(vma, addr, ptep, pte);
}
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
#endif /* CONFIG_MMU */

2
include/linux/backing-dev.h
View File

@ -365,7 +365,7 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
rcu_read_lock();
/*
* Paired with store_release in inode_switch_wb_work_fn() and
* Paired with store_release in inode_switch_wbs_work_fn() and
* ensures that we see the new wb if we see cleared I_WB_SWITCH.
*/
cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;

34
include/linux/balloon_compaction.h
View File

@ -4,15 +4,18 @@
*
* Common interface definitions for making balloon pages movable by compaction.
*
* Despite being perfectly possible to perform ballooned pages migration, they
* make a special corner case to compaction scans because balloon pages are not
* enlisted at any LRU list like the other pages we do compact / migrate.
* Balloon page migration makes use of the general non-lru movable page
* feature.
*
* page->private is used to reference the responsible balloon device.
* page->mapping is used in context of non-lru page migration to reference
* the address space operations for page isolation/migration/compaction.
*
* As the page isolation scanning step a compaction thread does is a lockless
* procedure (from a page standpoint), it might bring some racy situations while
* performing balloon page compaction. In order to sort out these racy scenarios
* and safely perform balloon's page compaction and migration we must, always,
* ensure following these three simple rules:
* ensure following these simple rules:
*
* i. when updating a balloon's page ->mapping element, strictly do it under
* the following lock order, independently of the far superior
@ -21,19 +24,8 @@
* +--spin_lock_irq(&b_dev_info->pages_lock);
* ... page->mapping updates here ...
*
* ii. before isolating or dequeueing a balloon page from the balloon device
* pages list, the page reference counter must be raised by one and the
* extra refcount must be dropped when the page is enqueued back into
* the balloon device page list, thus a balloon page keeps its reference
* counter raised only while it is under our special handling;
*
* iii. after the lockless scan step have selected a potential balloon page for
* isolation, re-test the PageBalloon mark and the PagePrivate flag
* under the proper page lock, to ensure isolating a valid balloon page
* (not yet isolated, nor under release procedure)
*
* iv. isolation or dequeueing procedure must clear PagePrivate flag under
* page lock together with removing page from balloon device page list.
* ii. isolation or dequeueing procedure must remove the page from balloon
* device page list under b_dev_info->pages_lock.
*
* The functions provided by this interface are placed to help on coping with
* the aforementioned balloon page corner case, as well as to ensure the simple
@ -103,7 +95,7 @@ extern int balloon_page_migrate(struct address_space *mapping,
static inline void balloon_page_insert(struct balloon_dev_info *balloon,
struct page *page)
{
__SetPageBalloon(page);
__SetPageOffline(page);
__SetPageMovable(page, balloon->inode->i_mapping);
set_page_private(page, (unsigned long)balloon);
list_add(&page->lru, &balloon->pages);
@ -119,7 +111,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
*/
static inline void balloon_page_delete(struct page *page)
{
__ClearPageBalloon(page);
__ClearPageOffline(page);
__ClearPageMovable(page);
set_page_private(page, 0);
/*
@ -149,13 +141,13 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
static inline void balloon_page_insert(struct balloon_dev_info *balloon,
struct page *page)
{
__SetPageBalloon(page);
__SetPageOffline(page);
list_add(&page->lru, &balloon->pages);
}
static inline void balloon_page_delete(struct page *page)
{
__ClearPageBalloon(page);
__ClearPageOffline(page);
list_del(&page->lru);
}

4
include/linux/cgroup-defs.h
View File

@ -32,6 +32,7 @@ struct kernfs_node;
struct kernfs_ops;
struct kernfs_open_file;
struct seq_file;
struct poll_table_struct;
#define MAX_CGROUP_TYPE_NAMELEN 32
#define MAX_CGROUP_ROOT_NAMELEN 64
@ -574,6 +575,9 @@ struct cftype {
ssize_t (*write)(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off);
__poll_t (*poll)(struct kernfs_open_file *of,
struct poll_table_struct *pt);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
struct lock_class_key lockdep_key;
#endif

7
include/linux/compaction.h
View File

@ -88,14 +88,13 @@ extern int sysctl_compact_memory;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos);
extern int sysctl_extfrag_threshold;
extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos);
extern int sysctl_compact_unevictable_allowed;
extern int fragmentation_index(struct zone *zone, unsigned int order);
extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
unsigned int order, unsigned int alloc_flags,
const struct alloc_context *ac, enum compact_priority prio);
const struct alloc_context *ac, enum compact_priority prio,
struct page **page);
extern void reset_isolation_suitable(pg_data_t *pgdat);
extern enum compact_result compaction_suitable(struct zone *zone, int order,
unsigned int alloc_flags, int classzone_idx);
@ -227,8 +226,8 @@ static inline void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_i
#endif /* CONFIG_COMPACTION */
#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
struct node;
#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
extern int compaction_register_node(struct node *node);
extern void compaction_unregister_node(struct node *node);

2
include/linux/device.h
View File

@ -1095,7 +1095,7 @@ static inline void set_dev_node(struct device *dev, int node)
#else
static inline int dev_to_node(struct device *dev)
{
return -1;
return NUMA_NO_NODE;
}
static inline void set_dev_node(struct device *dev, int node)
{

7
include/linux/frontswap.h
View File

@ -7,6 +7,13 @@
#include <linux/bitops.h>
#include <linux/jump_label.h>
/*
* Return code to denote that requested number of
* frontswap pages are unused(moved to page cache).
* Used in in shmem_unuse and try_to_unuse.
*/
#define FRONTSWAP_PAGES_UNUSED 2
struct frontswap_ops {
void (*init)(unsigned); /* this swap type was just swapon'ed */
int (*store)(unsigned, pgoff_t, struct page *); /* store a page */

2
include/linux/fs.h
View File

@ -2091,7 +2091,7 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
* I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to
* synchronize competing switching instances and to tell
* wb stat updates to grab the i_pages lock. See
* inode_switch_wb_work_fn() for details.
* inode_switch_wbs_work_fn() for details.
*
* I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper
* and work dirs among overlayfs mounts.

30
include/linux/gfp.h
View File

@ -24,21 +24,21 @@ struct vm_area_struct;
#define ___GFP_HIGH 0x20u
#define ___GFP_IO 0x40u
#define ___GFP_FS 0x80u
#define ___GFP_WRITE 0x100u
#define ___GFP_NOWARN 0x200u
#define ___GFP_RETRY_MAYFAIL 0x400u
#define ___GFP_NOFAIL 0x800u
#define ___GFP_NORETRY 0x1000u
#define ___GFP_MEMALLOC 0x2000u
#define ___GFP_COMP 0x4000u
#define ___GFP_ZERO 0x8000u
#define ___GFP_NOMEMALLOC 0x10000u
#define ___GFP_HARDWALL 0x20000u
#define ___GFP_THISNODE 0x40000u
#define ___GFP_ATOMIC 0x80000u
#define ___GFP_ACCOUNT 0x100000u
#define ___GFP_DIRECT_RECLAIM 0x200000u
#define ___GFP_KSWAPD_RECLAIM 0x400000u
#define ___GFP_ZERO 0x100u
#define ___GFP_ATOMIC 0x200u
#define ___GFP_DIRECT_RECLAIM 0x400u
#define ___GFP_KSWAPD_RECLAIM 0x800u
#define ___GFP_WRITE 0x1000u
#define ___GFP_NOWARN 0x2000u
#define ___GFP_RETRY_MAYFAIL 0x4000u
#define ___GFP_NOFAIL 0x8000u
#define ___GFP_NORETRY 0x10000u
#define ___GFP_MEMALLOC 0x20000u
#define ___GFP_COMP 0x40000u
#define ___GFP_NOMEMALLOC 0x80000u
#define ___GFP_HARDWALL 0x100000u
#define ___GFP_THISNODE 0x200000u
#define ___GFP_ACCOUNT 0x400000u
#ifdef CONFIG_LOCKDEP
#define ___GFP_NOLOCKDEP 0x800000u
#else

74
include/linux/hugetlb.h
View File

@ -371,6 +371,8 @@ struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask);
struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
unsigned long address);
struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask);
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx);
@ -493,17 +495,54 @@ static inline pgoff_t basepage_index(struct page *page)
extern int dissolve_free_huge_page(struct page *page);
extern int dissolve_free_huge_pages(unsigned long start_pfn,
unsigned long end_pfn);
static inline bool hugepage_migration_supported(struct hstate *h)
{
#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
#ifndef arch_hugetlb_migration_supported
static inline bool arch_hugetlb_migration_supported(struct hstate *h)
{
if ((huge_page_shift(h) == PMD_SHIFT) ||
(huge_page_shift(h) == PGDIR_SHIFT))
(huge_page_shift(h) == PUD_SHIFT) ||
(huge_page_shift(h) == PGDIR_SHIFT))
return true;
else
return false;
#else
return false;
}
#endif
#else
static inline bool arch_hugetlb_migration_supported(struct hstate *h)
{
return false;
}
#endif
static inline bool hugepage_migration_supported(struct hstate *h)
{
return arch_hugetlb_migration_supported(h);
}
/*
* Movability check is different as compared to migration check.
* It determines whether or not a huge page should be placed on
* movable zone or not. Movability of any huge page should be
* required only if huge page size is supported for migration.
* There wont be any reason for the huge page to be movable if
* it is not migratable to start with. Also the size of the huge
* page should be large enough to be placed under a movable zone
* and still feasible enough to be migratable. Just the presence
* in movable zone does not make the migration feasible.
*
* So even though large huge page sizes like the gigantic ones
* are migratable they should not be movable because its not
* feasible to migrate them from movable zone.
*/
static inline bool hugepage_movable_supported(struct hstate *h)
{
if (!hugepage_migration_supported(h))
return false;
if (hstate_is_gigantic(h))
return false;
return true;
}
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
@ -543,6 +582,26 @@ static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr
set_huge_pte_at(mm, addr, ptep, pte);
}
#endif
#ifndef huge_ptep_modify_prot_start
#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
}
#endif
#ifndef huge_ptep_modify_prot_commit
#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}
#endif
#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
#define alloc_huge_page(v, a, r) NULL
@ -602,6 +661,11 @@ static inline bool hugepage_migration_supported(struct hstate *h)
return false;
}
static inline bool hugepage_movable_supported(struct hstate *h)
{
return false;
}
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{

2
include/linux/kasan-checks.h
View File

@ -2,7 +2,7 @@
#ifndef _LINUX_KASAN_CHECKS_H
#define _LINUX_KASAN_CHECKS_H
#ifdef CONFIG_KASAN
#if defined(__SANITIZE_ADDRESS__) || defined(__KASAN_INTERNAL)
void kasan_check_read(const volatile void *p, unsigned int size);
void kasan_check_write(const volatile void *p, unsigned int size);
#else

6
include/linux/kernfs.h
View File

@ -25,6 +25,7 @@ struct seq_file;
struct vm_area_struct;
struct super_block;
struct file_system_type;
struct poll_table_struct;
struct kernfs_open_node;
struct kernfs_iattrs;
@ -261,6 +262,9 @@ struct kernfs_ops {
ssize_t (*write)(struct kernfs_open_file *of, char *buf, size_t bytes,
loff_t off);
__poll_t (*poll)(struct kernfs_open_file *of,
struct poll_table_struct *pt);
int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
@ -350,6 +354,8 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
const char *new_name, const void *new_ns);
int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
__poll_t kernfs_generic_poll(struct kernfs_open_file *of,
struct poll_table_struct *pt);
void kernfs_notify(struct kernfs_node *kn);
const void *kernfs_super_ns(struct super_block *sb);

Some files were not shown because too many files have changed in this diff Show More