Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "26 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (26 commits)
  userfaultfd: remove wrong comment from userfaultfd_ctx_get()
  fat: fix using uninitialized fields of fat_inode/fsinfo_inode
  sh: cayman: IDE support fix
  kasan: fix races in quarantine_remove_cache()
  kasan: resched in quarantine_remove_cache()
  mm: do not call mem_cgroup_free() from within mem_cgroup_alloc()
  thp: fix another corner case of munlock() vs. THPs
  rmap: fix NULL-pointer dereference on THP munlocking
  mm/memblock.c: fix memblock_next_valid_pfn()
  userfaultfd: selftest: vm: allow to build in vm/ directory
  userfaultfd: non-cooperative: userfaultfd_remove revalidate vma in MADV_DONTNEED
  userfaultfd: non-cooperative: fix fork fctx->new memleak
  mm/cgroup: avoid panic when init with low memory
  drivers/md/bcache/util.h: remove duplicate inclusion of blkdev.h
  mm/vmstats: add thp_split_pud event for clarity
  include/linux/fs.h: fix unsigned enum warning with gcc-4.2
  userfaultfd: non-cooperative: release all ctx in dup_userfaultfd_complete
  userfaultfd: non-cooperative: robustness check
  userfaultfd: non-cooperative: rollback userfaultfd_exit
  x86, mm: unify exit paths in gup_pte_range()
  ...
This commit is contained in:
Linus Torvalds 2017-03-10 08:34:42 -08:00
commit 8fe3ccaed0
54 changed files with 277 additions and 185 deletions

View File

@ -10,7 +10,7 @@ Note that kcov does not aim to collect as much coverage as possible. It aims
to collect more or less stable coverage that is function of syscall inputs.
To achieve this goal it does not collect coverage in soft/hard interrupts
and instrumentation of some inherently non-deterministic parts of kernel is
disbled (e.g. scheduler, locking).
disabled (e.g. scheduler, locking).
Usage
-----

View File

@ -45,7 +45,7 @@ Required Properties:
Optional Properties:
- reg-names: In addition to the required properties, the following are optional
- "efuse-address" - Contains efuse base address used to pick up ABB info.
- "ldo-address" - Contains address of ABB LDO overide register address.
- "ldo-address" - Contains address of ABB LDO override register.
"efuse-address" is required for this.
- ti,ldovbb-vset-mask - Required if ldo-address is set, mask for LDO override
register to provide override vset value.

View File

@ -172,10 +172,6 @@ the same read(2) protocol as for the page fault notifications. The
manager has to explicitly enable these events by setting appropriate
bits in uffdio_api.features passed to UFFDIO_API ioctl:
UFFD_FEATURE_EVENT_EXIT - enable notification about exit() of the
non-cooperative process. When the monitored process exits, the uffd
manager will get UFFD_EVENT_EXIT.
UFFD_FEATURE_EVENT_FORK - enable userfaultfd hooks for fork(). When
this feature is enabled, the userfaultfd context of the parent process
is duplicated into the newly created process. The manager receives

View File

@ -2086,7 +2086,7 @@ static void cryptocop_job_queue_close(void)
dma_in_cfg.en = regk_dma_no;
REG_WR(dma, IN_DMA_INST, rw_cfg, dma_in_cfg);
/* Disble the cryptocop. */
/* Disable the cryptocop. */
rw_cfg = REG_RD(strcop, regi_strcop, rw_cfg);
rw_cfg.en = 0;
REG_WR(strcop, regi_strcop, rw_cfg, rw_cfg);

View File

@ -347,23 +347,58 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
__r; \
})
static inline int __pte_write(pte_t pte)
{
return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
}
#ifdef CONFIG_NUMA_BALANCING
#define pte_savedwrite pte_savedwrite
static inline bool pte_savedwrite(pte_t pte)
{
/*
* Saved write ptes are prot none ptes that doesn't have
* privileged bit sit. We mark prot none as one which has
* present and pviliged bit set and RWX cleared. To mark
* protnone which used to have _PAGE_WRITE set we clear
* the privileged bit.
*/
return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
}
#else
#define pte_savedwrite pte_savedwrite
static inline bool pte_savedwrite(pte_t pte)
{
return false;
}
#endif
static inline int pte_write(pte_t pte)
{
return __pte_write(pte) || pte_savedwrite(pte);
}
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
return;
pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
if (__pte_write(*ptep))
pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
else if (unlikely(pte_savedwrite(*ptep)))
pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
}
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
return;
pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
/*
* We should not find protnone for hugetlb, but this complete the
* interface.
*/
if (__pte_write(*ptep))
pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
else if (unlikely(pte_savedwrite(*ptep)))
pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
}
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@ -397,11 +432,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_update(mm, addr, ptep, ~0UL, 0, 0);
}
static inline int pte_write(pte_t pte)
{
return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
}
static inline int pte_dirty(pte_t pte)
{
return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@ -465,19 +495,12 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
VM_BUG_ON(!pte_protnone(pte));
return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
}
#define pte_savedwrite pte_savedwrite
static inline bool pte_savedwrite(pte_t pte)
#else
#define pte_clear_savedwrite pte_clear_savedwrite
static inline pte_t pte_clear_savedwrite(pte_t pte)
{
/*
* Saved write ptes are prot none ptes that doesn't have
* privileged bit sit. We mark prot none as one which has
* present and pviliged bit set and RWX cleared. To mark
* protnone which used to have _PAGE_WRITE set we clear
* the privileged bit.
*/
VM_BUG_ON(!pte_protnone(pte));
return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
VM_WARN_ON(1);
return __pte(pte_val(pte) & ~_PAGE_WRITE);
}
#endif /* CONFIG_NUMA_BALANCING */
@ -506,6 +529,8 @@ static inline unsigned long pte_pfn(pte_t pte)
/* Generic modifiers for PTE bits */
static inline pte_t pte_wrprotect(pte_t pte)
{
if (unlikely(pte_savedwrite(pte)))
return pte_clear_savedwrite(pte);
return __pte(pte_val(pte) & ~_PAGE_WRITE);
}
@ -926,6 +951,7 @@ static inline int pmd_protnone(pmd_t pmd)
#define __HAVE_ARCH_PMD_WRITE
#define pmd_write(pmd) pte_write(pmd_pte(pmd))
#define __pmd_write(pmd) __pte_write(pmd_pte(pmd))
#define pmd_savedwrite(pmd) pte_savedwrite(pmd_pte(pmd))
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@ -982,11 +1008,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp)
{
if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
return;
pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
if (__pmd_write((*pmdp)))
pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
else if (unlikely(pmd_savedwrite(*pmdp)))
pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
}
static inline int pmd_trans_huge(pmd_t pmd)

View File

@ -601,7 +601,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
hva, NULL, NULL);
if (ptep) {
pte = kvmppc_read_update_linux_pte(ptep, 1);
if (pte_write(pte))
if (__pte_write(pte))
write_ok = 1;
}
local_irq_restore(flags);

View File

@ -256,7 +256,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
}
pte = kvmppc_read_update_linux_pte(ptep, writing);
if (pte_present(pte) && !pte_protnone(pte)) {
if (writing && !pte_write(pte))
if (writing && !__pte_write(pte))
/* make the actual HPTE be read-only */
ptel = hpte_make_readonly(ptel);
is_ci = pte_ci(pte);

View File

@ -128,7 +128,6 @@ static int __init smsc_superio_setup(void)
SMSC_SUPERIO_WRITE_INDEXED(1, SMSC_PRIMARY_INT_INDEX);
SMSC_SUPERIO_WRITE_INDEXED(12, SMSC_SECONDARY_INT_INDEX);
#ifdef CONFIG_IDE
/*
* Only IDE1 exists on the Cayman
*/
@ -158,7 +157,6 @@ static int __init smsc_superio_setup(void)
SMSC_SUPERIO_WRITE_INDEXED(0x01, 0xc5); /* GP45 = IDE1_IRQ */
SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc6); /* GP46 = nIOROP */
SMSC_SUPERIO_WRITE_INDEXED(0x00, 0xc7); /* GP47 = nIOWOP */
#endif
/* Exit the configuration state */
outb(SMSC_EXIT_CONFIG_KEY, SMSC_CONFIG_PORT_ADDR);

View File

@ -535,7 +535,7 @@ static void run_sync(void)
{
int enable_irqs = irqs_disabled();
/* We may be called with interrupts disbled (on bootup). */
/* We may be called with interrupts disabled (on bootup). */
if (enable_irqs)
local_irq_enable();
on_each_cpu(do_sync_core, NULL, 1);

View File

@ -106,32 +106,35 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
unsigned long end, int write, struct page **pages, int *nr)
{
struct dev_pagemap *pgmap = NULL;
int nr_start = *nr;
pte_t *ptep;
int nr_start = *nr, ret = 0;
pte_t *ptep, *ptem;
ptep = pte_offset_map(&pmd, addr);
/*
* Keep the original mapped PTE value (ptem) around since we
* might increment ptep off the end of the page when finishing
* our loop iteration.
*/
ptem = ptep = pte_offset_map(&pmd, addr);
do {
pte_t pte = gup_get_pte(ptep);
struct page *page;
/* Similar to the PMD case, NUMA hinting must take slow path */
if (pte_protnone(pte)) {
pte_unmap(ptep);
return 0;
}
if (pte_protnone(pte))
break;
if (!pte_allows_gup(pte_val(pte), write))
break;
if (pte_devmap(pte)) {
pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
if (unlikely(!pgmap)) {
undo_dev_pagemap(nr, nr_start, pages);
pte_unmap(ptep);
return 0;
break;
}
} else if (!pte_allows_gup(pte_val(pte), write) ||
pte_special(pte)) {
pte_unmap(ptep);
return 0;
}
} else if (pte_special(pte))
break;
VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
page = pte_page(pte);
get_page(page);
@ -141,9 +144,11 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
(*nr)++;
} while (ptep++, addr += PAGE_SIZE, addr != end);
pte_unmap(ptep - 1);
if (addr == end)
ret = 1;
pte_unmap(ptem);
return 1;
return ret;
}
static inline void get_head_page_multiple(struct page *page, int nr)

View File

@ -50,7 +50,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
major You may use this parameter to overide the
major You may use this parameter to override the
default major number (46) that this driver
will use. Be sure to change the device
name as well.

View File

@ -61,7 +61,7 @@
first drive found.
major You may use this parameter to overide the
major You may use this parameter to override the
default major number (45) that this driver
will use. Be sure to change the device
name as well.

View File

@ -59,7 +59,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
major You may use this parameter to overide the
major You may use this parameter to override the
default major number (47) that this driver
will use. Be sure to change the device
name as well.

View File

@ -84,7 +84,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
major You may use this parameter to overide the
major You may use this parameter to override the
default major number (97) that this driver
will use. Be sure to change the device
name as well.

View File

@ -61,7 +61,7 @@
the slower the port i/o. In some cases, setting
this to zero will speed up the device. (default -1)
major You may use this parameter to overide the
major You may use this parameter to override the
default major number (96) that this driver
will use. Be sure to change the device
name as well.

View File

@ -82,7 +82,7 @@ void cryp_activity(struct cryp_device_data *device_data,
void cryp_flush_inoutfifo(struct cryp_device_data *device_data)
{
/*
* We always need to disble the hardware before trying to flush the
* We always need to disable the hardware before trying to flush the
* FIFO. This is something that isn't written in the design
* specification, but we have been informed by the hardware designers
* that this must be done.

View File

@ -788,7 +788,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev)
}
}
/* disble sdma engine before programing it */
/* disable sdma engine before programing it */
sdma_v3_0_ctx_switch_enable(adev, false);
sdma_v3_0_enable(adev, false);

View File

@ -543,7 +543,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
/*
* In case a device driver's probe() fails (e.g.,
* util_probe() -> vmbus_open() returns -ENOMEM) and the device is
* rescinded later (e.g., we dynamically disble an Integrated Service
* rescinded later (e.g., we dynamically disable an Integrated Service
* in Hyper-V Manager), the driver's remove() invokes vmbus_close():
* here we should skip most of the below cleanup work.
*/

View File

@ -239,7 +239,7 @@ static void st5481B_mode(struct st5481_bcs *bcs, int mode)
}
}
} else {
// Disble B channel interrupts
// Disable B channel interrupts
st5481_usb_device_ctrl_msg(adapter, FFMSK_B1+(bcs->channel * 2), 0, NULL, NULL);
// Disable B channel FIFOs

View File

@ -4,7 +4,6 @@
#include <linux/blkdev.h>
#include <linux/errno.h>
#include <linux/blkdev.h>
#include <linux/kernel.h>
#include <linux/sched/clock.h>
#include <linux/llist.h>

View File

@ -256,8 +256,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
*
* The actual DAP implementation may be restricted to only one of the modes.
* A compiler warning or error will be generated if the DAP implementation
* overides or cannot handle the mode defined below.
*
* overrides or cannot handle the mode defined below.
*/
#ifndef DRXDAP_SINGLE_MASTER
#define DRXDAP_SINGLE_MASTER 1
@ -272,7 +271,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
*
* This maximum size may be restricted by the actual DAP implementation.
* A compiler warning or error will be generated if the DAP implementation
* overides or cannot handle the chunksize defined below.
* overrides or cannot handle the chunksize defined below.
*
* Beware that the DAP uses DRXDAP_MAX_WCHUNKSIZE to create a temporary data
* buffer. Do not undefine or choose too large, unless your system is able to
@ -292,8 +291,7 @@ int drxbsp_tuner_default_i2c_write_read(struct tuner_instance *tuner,
*
* This maximum size may be restricted by the actual DAP implementation.
* A compiler warning or error will be generated if the DAP implementation
* overides or cannot handle the chunksize defined below.
*
* overrides or cannot handle the chunksize defined below.
*/
#ifndef DRXDAP_MAX_RCHUNKSIZE
#define DRXDAP_MAX_RCHUNKSIZE 60

View File

@ -186,7 +186,7 @@ static inline int write_enable(struct spi_nor *nor)
}
/*
* Send write disble instruction to the chip.
* Send write disable instruction to the chip.
*/
static inline int write_disable(struct spi_nor *nor)
{

View File

@ -1162,8 +1162,8 @@ struct ob_mac_tso_iocb_rsp {
struct ib_mac_iocb_rsp {
u8 opcode; /* 0x20 */
u8 flags1;
#define IB_MAC_IOCB_RSP_OI 0x01 /* Overide intr delay */
#define IB_MAC_IOCB_RSP_I 0x02 /* Disble Intr Generation */
#define IB_MAC_IOCB_RSP_OI 0x01 /* Override intr delay */
#define IB_MAC_IOCB_RSP_I 0x02 /* Disable Intr Generation */
#define IB_MAC_CSUM_ERR_MASK 0x1c /* A mask to use for csum errs */
#define IB_MAC_IOCB_RSP_TE 0x04 /* Checksum error */
#define IB_MAC_IOCB_RSP_NU 0x08 /* No checksum rcvd */

View File

@ -6278,7 +6278,7 @@ ahd_reset(struct ahd_softc *ahd, int reinit)
* does not disable its parity logic prior to
* the start of the reset. This may cause a
* parity error to be detected and thus a
* spurious SERR or PERR assertion. Disble
* spurious SERR or PERR assertion. Disable
* PERR and SERR responses during the CHIPRST.
*/
mod_cmd = cmd & ~(PCIM_CMD_PERRESPEN|PCIM_CMD_SERRESPEN);

View File

@ -84,8 +84,7 @@ static int ep_open(struct inode *, struct file *);
/* /dev/gadget/$CHIP represents ep0 and the whole device */
enum ep0_state {
/* DISBLED is the initial state.
*/
/* DISABLED is the initial state. */
STATE_DEV_DISABLED = 0,
/* Only one open() of /dev/gadget/$CHIP; only one file tracks

View File

@ -868,7 +868,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
spin_lock_irqsave(&xhci->lock, flags);
/* disble usb3 ports Wake bits*/
/* disable usb3 ports Wake bits */
port_index = xhci->num_usb3_ports;
port_array = xhci->usb3_ports;
while (port_index--) {
@ -879,7 +879,7 @@ static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
writel(t2, port_array[port_index]);
}
/* disble usb2 ports Wake bits*/
/* disable usb2 ports Wake bits */
port_index = xhci->num_usb2_ports;
port_array = xhci->usb2_ports;
while (port_index--) {

View File

@ -1359,6 +1359,16 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
return 0;
}
static void fat_dummy_inode_init(struct inode *inode)
{
/* Initialize this dummy inode to work as no-op. */
MSDOS_I(inode)->mmu_private = 0;
MSDOS_I(inode)->i_start = 0;
MSDOS_I(inode)->i_logstart = 0;
MSDOS_I(inode)->i_attrs = 0;
MSDOS_I(inode)->i_pos = 0;
}
static int fat_read_root(struct inode *inode)
{
struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
fat_inode = new_inode(sb);
if (!fat_inode)
goto out_fail;
MSDOS_I(fat_inode)->i_pos = 0;
fat_dummy_inode_init(fat_inode);
sbi->fat_inode = fat_inode;
fsinfo_inode = new_inode(sb);
if (!fsinfo_inode)
goto out_fail;
fat_dummy_inode_init(fsinfo_inode);
fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
sbi->fsinfo_inode = fsinfo_inode;
insert_inode_hash(fsinfo_inode);

View File

@ -138,8 +138,6 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
* userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
* context.
* @ctx: [in] Pointer to the userfaultfd context.
*
* Returns: In case of success, returns not zero.
*/
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
{
@ -490,7 +488,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
* in such case.
*/
down_read(&mm->mmap_sem);
ret = 0;
ret = VM_FAULT_NOPAGE;
}
}
@ -527,10 +525,11 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
return ret;
}
static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
struct userfaultfd_wait_queue *ewq)
static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
struct userfaultfd_wait_queue *ewq)
{
int ret = 0;
if (WARN_ON_ONCE(current->flags & PF_EXITING))
goto out;
ewq->ctx = ctx;
init_waitqueue_entry(&ewq->wq, current);
@ -547,8 +546,16 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
break;
if (ACCESS_ONCE(ctx->released) ||
fatal_signal_pending(current)) {
ret = -1;
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
if (ewq->msg.event == UFFD_EVENT_FORK) {
struct userfaultfd_ctx *new;
new = (struct userfaultfd_ctx *)
(unsigned long)
ewq->msg.arg.reserved.reserved1;
userfaultfd_ctx_put(new);
}
break;
}
@ -566,9 +573,8 @@ static int userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
* ctx may go away after this if the userfault pseudo fd is
* already released.
*/
out:
userfaultfd_ctx_put(ctx);
return ret;
}
static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
@ -626,7 +632,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
return 0;
}
static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
{
struct userfaultfd_ctx *ctx = fctx->orig;
struct userfaultfd_wait_queue ewq;
@ -636,17 +642,15 @@ static int dup_fctx(struct userfaultfd_fork_ctx *fctx)
ewq.msg.event = UFFD_EVENT_FORK;
ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
return userfaultfd_event_wait_completion(ctx, &ewq);
userfaultfd_event_wait_completion(ctx, &ewq);
}
void dup_userfaultfd_complete(struct list_head *fcs)
{
int ret = 0;
struct userfaultfd_fork_ctx *fctx, *n;
list_for_each_entry_safe(fctx, n, fcs, list) {
if (!ret)
ret = dup_fctx(fctx);
dup_fctx(fctx);
list_del(&fctx->list);
kfree(fctx);
}
@ -689,8 +693,7 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
userfaultfd_event_wait_completion(ctx, &ewq);
}
void userfaultfd_remove(struct vm_area_struct *vma,
struct vm_area_struct **prev,
bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
@ -699,13 +702,11 @@ void userfaultfd_remove(struct vm_area_struct *vma,
ctx = vma->vm_userfaultfd_ctx.ctx;
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
return;
return true;
userfaultfd_ctx_get(ctx);
up_read(&mm->mmap_sem);
*prev = NULL; /* We wait for ACK w/o the mmap semaphore */
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_REMOVE;
@ -714,7 +715,7 @@ void userfaultfd_remove(struct vm_area_struct *vma,
userfaultfd_event_wait_completion(ctx, &ewq);
down_read(&mm->mmap_sem);
return false;
}
static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
@ -775,34 +776,6 @@ void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
}
}
void userfaultfd_exit(struct mm_struct *mm)
{
struct vm_area_struct *vma = mm->mmap;
/*
* We can do the vma walk without locking because the caller
* (exit_mm) knows it now has exclusive access
*/
while (vma) {
struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
if (ctx && (ctx->features & UFFD_FEATURE_EVENT_EXIT)) {
struct userfaultfd_wait_queue ewq;
userfaultfd_ctx_get(ctx);
msg_init(&ewq.msg);
ewq.msg.event = UFFD_EVENT_EXIT;
userfaultfd_event_wait_completion(ctx, &ewq);
ctx->features &= ~UFFD_FEATURE_EVENT_EXIT;
}
vma = vma->vm_next;
}
}
static int userfaultfd_release(struct inode *inode, struct file *file)
{
struct userfaultfd_ctx *ctx = file->private_data;

View File

@ -20,7 +20,7 @@
#define CS42L42_HPOUT_LOAD_1NF 0
#define CS42L42_HPOUT_LOAD_10NF 1
/* HPOUT Clamp to GND Overide */
/* HPOUT Clamp to GND Override */
#define CS42L42_HPOUT_CLAMP_EN 0
#define CS42L42_HPOUT_CLAMP_DIS 1

View File

@ -2678,7 +2678,7 @@ static const char * const kernel_read_file_str[] = {
static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id)
{
if (id < 0 || id >= READING_MAX_ID)
if ((unsigned)id >= READING_MAX_ID)
return kernel_read_file_str[READING_UNKNOWN];
return kernel_read_file_str[id];

View File

@ -65,7 +65,7 @@ struct regulator_state {
int uV; /* suspend voltage */
unsigned int mode; /* suspend regulator operating mode */
int enabled; /* is regulator enabled in this suspend state */
int disabled; /* is the regulator disbled in this suspend state */
int disabled; /* is the regulator disabled in this suspend state */
};
/**

View File

@ -61,8 +61,7 @@ extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
unsigned long from, unsigned long to,
unsigned long len);
extern void userfaultfd_remove(struct vm_area_struct *vma,
struct vm_area_struct **prev,
extern bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start,
unsigned long end);
@ -72,8 +71,6 @@ extern int userfaultfd_unmap_prep(struct vm_area_struct *vma,
extern void userfaultfd_unmap_complete(struct mm_struct *mm,
struct list_head *uf);
extern void userfaultfd_exit(struct mm_struct *mm);
#else /* CONFIG_USERFAULTFD */
/* mm helpers */
@ -120,11 +117,11 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
{
}
static inline void userfaultfd_remove(struct vm_area_struct *vma,
struct vm_area_struct **prev,
static inline bool userfaultfd_remove(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
return true;
}
static inline int userfaultfd_unmap_prep(struct vm_area_struct *vma,
@ -139,10 +136,6 @@ static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
{
}
static inline void userfaultfd_exit(struct mm_struct *mm)
{
}
#endif /* CONFIG_USERFAULTFD */
#endif /* _LINUX_USERFAULTFD_K_H */

View File

@ -79,6 +79,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
THP_SPLIT_PAGE_FAILED,
THP_DEFERRED_SPLIT_PAGE,
THP_SPLIT_PMD,
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
THP_SPLIT_PUD,
#endif
THP_ZERO_PAGE_ALLOC,
THP_ZERO_PAGE_ALLOC_FAILED,
#endif

View File

@ -59,7 +59,7 @@ struct lap_cb;
* Slot timer must never exceed 85 ms, and must always be at least 25 ms,
* suggested to 75-85 msec by IrDA lite. This doesn't work with a lot of
* devices, and other stackes uses a lot more, so it's best we do it as well
* (Note : this is the default value and sysctl overides it - Jean II)
* (Note : this is the default value and sysctl overrides it - Jean II)
*/
#define SLOT_TIMEOUT (90*HZ/1000)

View File

@ -18,8 +18,7 @@
* means the userland is reading).
*/
#define UFFD_API ((__u64)0xAA)
#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_EXIT | \
UFFD_FEATURE_EVENT_FORK | \
#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \
UFFD_FEATURE_EVENT_REMAP | \
UFFD_FEATURE_EVENT_REMOVE | \
UFFD_FEATURE_EVENT_UNMAP | \
@ -113,7 +112,6 @@ struct uffd_msg {
#define UFFD_EVENT_REMAP 0x14
#define UFFD_EVENT_REMOVE 0x15
#define UFFD_EVENT_UNMAP 0x16
#define UFFD_EVENT_EXIT 0x17
/* flags for UFFD_EVENT_PAGEFAULT */
#define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */
@ -163,7 +161,6 @@ struct uffdio_api {
#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4)
#define UFFD_FEATURE_MISSING_SHMEM (1<<5)
#define UFFD_FEATURE_EVENT_UNMAP (1<<6)
#define UFFD_FEATURE_EVENT_EXIT (1<<7)
__u64 features;
__u64 ioctls;

View File

@ -2669,7 +2669,7 @@ static bool css_visible(struct cgroup_subsys_state *css)
*
* Returns 0 on success, -errno on failure. On failure, csses which have
* been processed already aren't cleaned up. The caller is responsible for
* cleaning up with cgroup_apply_control_disble().
* cleaning up with cgroup_apply_control_disable().
*/
static int cgroup_apply_control_enable(struct cgroup *cgrp)
{

View File

@ -998,7 +998,7 @@ list_update_cgroup_event(struct perf_event *event,
*/
#define PERF_CPU_HRTIMER (1000 / HZ)
/*
* function must be called with interrupts disbled
* function must be called with interrupts disabled
*/
static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr)
{

View File

@ -554,7 +554,6 @@ static void exit_mm(void)
enter_lazy_tlb(mm, current);
task_unlock(current);
mm_update_next_owner(mm);
userfaultfd_exit(mm);
mmput(mm);
if (test_thread_flag(TIF_MEMDIE))
exit_oom_victim();

View File

@ -65,7 +65,7 @@ void stack_trace_print(void)
}
/*
* When arch-specific code overides this function, the following
* When arch-specific code overrides this function, the following
* data should be filled up, assuming stack_trace_max_lock is held to
* prevent concurrent updates.
* stack_trace_index[]

View File

@ -1828,7 +1828,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
count_vm_event(THP_SPLIT_PMD);
count_vm_event(THP_SPLIT_PUD);
pudp_huge_clear_flush_notify(vma, haddr, pud);
}

View File

@ -25,6 +25,7 @@
#include <linux/printk.h>
#include <linux/shrinker.h>
#include <linux/slab.h>
#include <linux/srcu.h>
#include <linux/string.h>
#include <linux/types.h>
@ -103,6 +104,7 @@ static int quarantine_tail;
/* Total size of all objects in global_quarantine across all batches. */
static unsigned long quarantine_size;
static DEFINE_SPINLOCK(quarantine_lock);
DEFINE_STATIC_SRCU(remove_cache_srcu);
/* Maximum size of the global queue. */
static unsigned long quarantine_max_size;
@ -173,17 +175,22 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
struct qlist_head *q;
struct qlist_head temp = QLIST_INIT;
/*
* Note: irq must be disabled until after we move the batch to the
* global quarantine. Otherwise quarantine_remove_cache() can miss
* some objects belonging to the cache if they are in our local temp
* list. quarantine_remove_cache() executes on_each_cpu() at the
* beginning which ensures that it either sees the objects in per-cpu
* lists or in the global quarantine.
*/
local_irq_save(flags);
q = this_cpu_ptr(&cpu_quarantine);
qlist_put(q, &info->quarantine_link, cache->size);
if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE))
if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) {
qlist_move_all(q, &temp);
local_irq_restore(flags);
if (unlikely(!qlist_empty(&temp))) {
spin_lock_irqsave(&quarantine_lock, flags);
spin_lock(&quarantine_lock);
WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes);
qlist_move_all(&temp, &global_quarantine[quarantine_tail]);
if (global_quarantine[quarantine_tail].bytes >=
@ -196,20 +203,33 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
if (new_tail != quarantine_head)
quarantine_tail = new_tail;
}
spin_unlock_irqrestore(&quarantine_lock, flags);
spin_unlock(&quarantine_lock);
}
local_irq_restore(flags);
}
void quarantine_reduce(void)
{
size_t total_size, new_quarantine_size, percpu_quarantines;
unsigned long flags;
int srcu_idx;
struct qlist_head to_free = QLIST_INIT;
if (likely(READ_ONCE(quarantine_size) <=
READ_ONCE(quarantine_max_size)))
return;
/*
* srcu critical section ensures that quarantine_remove_cache()
* will not miss objects belonging to the cache while they are in our
* local to_free list. srcu is chosen because (1) it gives us private
* grace period domain that does not interfere with anything else,
* and (2) it allows synchronize_srcu() to return without waiting
* if there are no pending read critical sections (which is the
* expected case).
*/
srcu_idx = srcu_read_lock(&remove_cache_srcu);
spin_lock_irqsave(&quarantine_lock, flags);
/*
@ -237,6 +257,7 @@ void quarantine_reduce(void)
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, NULL);
srcu_read_unlock(&remove_cache_srcu, srcu_idx);
}
static void qlist_move_cache(struct qlist_head *from,
@ -280,12 +301,28 @@ void quarantine_remove_cache(struct kmem_cache *cache)
unsigned long flags, i;
struct qlist_head to_free = QLIST_INIT;
/*
* Must be careful to not miss any objects that are being moved from
* per-cpu list to the global quarantine in quarantine_put(),
* nor objects being freed in quarantine_reduce(). on_each_cpu()
* achieves the first goal, while synchronize_srcu() achieves the
* second.
*/
on_each_cpu(per_cpu_remove_cache, cache, 1);
spin_lock_irqsave(&quarantine_lock, flags);
for (i = 0; i < QUARANTINE_BATCHES; i++)
for (i = 0; i < QUARANTINE_BATCHES; i++) {
if (qlist_empty(&global_quarantine[i]))
continue;
qlist_move_cache(&global_quarantine[i], &to_free, cache);
/* Scanning whole quarantine can take a while. */
spin_unlock_irqrestore(&quarantine_lock, flags);
cond_resched();
spin_lock_irqsave(&quarantine_lock, flags);
}
spin_unlock_irqrestore(&quarantine_lock, flags);
qlist_free_all(&to_free, cache);
synchronize_srcu(&remove_cache_srcu);
}

View File

@ -513,7 +513,43 @@ static long madvise_dontneed(struct vm_area_struct *vma,
if (!can_madv_dontneed_vma(vma))
return -EINVAL;
userfaultfd_remove(vma, prev, start, end);
if (!userfaultfd_remove(vma, start, end)) {
*prev = NULL; /* mmap_sem has been dropped, prev is stale */
down_read(&current->mm->mmap_sem);
vma = find_vma(current->mm, start);
if (!vma)
return -ENOMEM;
if (start < vma->vm_start) {
/*
* This "vma" under revalidation is the one
* with the lowest vma->vm_start where start
* is also < vma->vm_end. If start <
* vma->vm_start it means an hole materialized
* in the user address space within the
* virtual range passed to MADV_DONTNEED.
*/
return -ENOMEM;
}
if (!can_madv_dontneed_vma(vma))
return -EINVAL;
if (end > vma->vm_end) {
/*
* Don't fail if end > vma->vm_end. If the old
* vma was splitted while the mmap_sem was
* released the effect of the concurrent
* operation may not cause MADV_DONTNEED to
* have an undefined result. There may be an
* adjacent next vma that we'll walk
* next. userfaultfd_remove() will generate an
* UFFD_EVENT_REMOVE repetition on the
* end-vma->vm_end range, but the manager can
* handle a repetition fine.
*/
end = vma->vm_end;
}
VM_WARN_ON(start >= end);
}
zap_page_range(vma, start, end - start);
return 0;
}
@ -554,8 +590,10 @@ static long madvise_remove(struct vm_area_struct *vma,
* mmap_sem.
*/
get_file(f);
userfaultfd_remove(vma, prev, start, end);
up_read(&current->mm->mmap_sem);
if (userfaultfd_remove(vma, start, end)) {
/* mmap_sem was not released by userfaultfd_remove() */
up_read(&current->mm->mmap_sem);
}
error = vfs_fallocate(f,
FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
offset, end - start);

View File

@ -1118,7 +1118,10 @@ unsigned long __init_memblock memblock_next_valid_pfn(unsigned long pfn,
}
} while (left < right);
return min(PHYS_PFN(type->regions[right].base), max_pfn);
if (right == type->cnt)
return max_pfn;
else
return min(PHYS_PFN(type->regions[right].base), max_pfn);
}
/**

View File

@ -466,6 +466,8 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
struct mem_cgroup_tree_per_node *mctz;
mctz = soft_limit_tree_from_page(page);
if (!mctz)
return;
/*
* Necessary to update all ancestors when hierarchy is used.
* because their event counter is not touched.
@ -503,7 +505,8 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
for_each_node(nid) {
mz = mem_cgroup_nodeinfo(memcg, nid);
mctz = soft_limit_tree_node(nid);
mem_cgroup_remove_exceeded(mz, mctz);
if (mctz)
mem_cgroup_remove_exceeded(mz, mctz);
}
}
@ -2558,7 +2561,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
* is empty. Do it lockless to prevent lock bouncing. Races
* are acceptable as soft limit is best effort anyway.
*/
if (RB_EMPTY_ROOT(&mctz->rb_root))
if (!mctz || RB_EMPTY_ROOT(&mctz->rb_root))
return 0;
/*
@ -4135,17 +4138,22 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
kfree(memcg->nodeinfo[node]);
}
static void mem_cgroup_free(struct mem_cgroup *memcg)
static void __mem_cgroup_free(struct mem_cgroup *memcg)
{
int node;
memcg_wb_domain_exit(memcg);
for_each_node(node)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->stat);
kfree(memcg);
}
static void mem_cgroup_free(struct mem_cgroup *memcg)
{
memcg_wb_domain_exit(memcg);
__mem_cgroup_free(memcg);
}
static struct mem_cgroup *mem_cgroup_alloc(void)
{
struct mem_cgroup *memcg;
@ -4196,7 +4204,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
fail:
if (memcg->id.id > 0)
idr_remove(&mem_cgroup_idr, memcg->id.id);
mem_cgroup_free(memcg);
__mem_cgroup_free(memcg);
return NULL;
}

View File

@ -442,7 +442,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
while (start < end) {
struct page *page;
unsigned int page_mask;
unsigned int page_mask = 0;
unsigned long page_increm;
struct pagevec pvec;
struct zone *zone;
@ -456,8 +456,7 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
* suits munlock very well (and if somehow an abnormal page
* has sneaked into the range, we won't oops here: great).
*/
page = follow_page_mask(vma, start, FOLL_GET | FOLL_DUMP,
&page_mask);
page = follow_page(vma, start, FOLL_GET | FOLL_DUMP);
if (page && !IS_ERR(page)) {
if (PageTransTail(page)) {
@ -468,8 +467,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
/*
* Any THP page found by follow_page_mask() may
* have gotten split before reaching
* munlock_vma_page(), so we need to recompute
* the page_mask here.
* munlock_vma_page(), so we need to compute
* the page_mask here instead.
*/
page_mask = munlock_vma_page(page);
unlock_page(page);

View File

@ -1316,12 +1316,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
while (page_vma_mapped_walk(&pvmw)) {
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
/* Unexpected PMD-mapped THP? */
VM_BUG_ON_PAGE(!pvmw.pte, page);
/*
* If the page is mlock()d, we cannot swap it out.
* If it's recently referenced (perhaps page_referenced
@ -1345,6 +1339,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
continue;
}
/* Unexpected PMD-mapped THP? */
VM_BUG_ON_PAGE(!pvmw.pte, page);
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
address = pvmw.address;
if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address,
pvmw.pte)) {

View File

@ -1065,6 +1065,9 @@ const char * const vmstat_text[] = {
"thp_split_page_failed",
"thp_deferred_split_page",
"thp_split_pmd",
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
"thp_split_pud",
#endif
"thp_zero_page_alloc",
"thp_zero_page_alloc_failed",
#endif

View File

@ -372,6 +372,8 @@ disassocation||disassociation
disapear||disappear
disapeared||disappeared
disappared||disappeared
disble||disable
disbled||disabled
disconnet||disconnect
discontinous||discontinuous
dispertion||dispersion
@ -732,6 +734,7 @@ oustanding||outstanding
overaall||overall
overhread||overhead
overlaping||overlapping
overide||override
overrided||overridden
overriden||overridden
overun||overrun

View File

@ -89,7 +89,7 @@ static void acp_reg_write(u32 val, void __iomem *acp_mmio, u32 reg)
writel(val, acp_mmio + (reg * 4));
}
/* Configure a given dma channel parameters - enable/disble,
/* Configure a given dma channel parameters - enable/disable,
* number of descriptors, priority
*/
static void config_acp_dma_channel(void __iomem *acp_mmio, u8 ch_num,

View File

@ -1387,7 +1387,7 @@ static bool pci_data_iowrite(u16 port, u32 mask, u32 val)
/* Allow writing to any other BAR, or expansion ROM */
iowrite(portoff, val, mask, &d->config_words[reg]);
return true;
/* We let them overide latency timer and cacheline size */
/* We let them override latency timer and cacheline size */
} else if (&d->config_words[reg] == (void *)&d->config.cacheline_size) {
/* Only let them change the first two fields. */
if (mask == 0xFFFFFFFF)

View File

@ -132,7 +132,7 @@ else
Q = @
endif
# Disable command line variables (CFLAGS) overide from top
# Disable command line variables (CFLAGS) override from top
# level Makefile (perf), otherwise build Makefile will get
# the same command line setup.
MAKEOVERRIDES=

View File

@ -135,7 +135,7 @@ else
Q = @
endif
# Disable command line variables (CFLAGS) overide from top
# Disable command line variables (CFLAGS) override from top
# level Makefile (perf), otherwise build Makefile will get
# the same command line setup.
MAKEOVERRIDES=

View File

@ -140,7 +140,7 @@ struct pevent_plugin_option {
* struct pevent_plugin_option PEVENT_PLUGIN_OPTIONS[] = {
* {
* .name = "option-name",
* .plugin_alias = "overide-file-name", (optional)
* .plugin_alias = "override-file-name", (optional)
* .description = "description of option to show users",
* },
* {

View File

@ -1,5 +1,9 @@
# Makefile for vm selftests
ifndef OUTPUT
OUTPUT := $(shell pwd)
endif
CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
LDLIBS = -lrt
TEST_GEN_FILES = compaction_test