diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2012-01-23 09:27:54 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2012-01-23 09:27:54 -0800 |
commit | 4f57d865f1d863346ac50db9c25859e73a86499c (patch) | |
tree | ac3cf5abdc3ce4b5c051f03c682f8b0668d66caf | |
parent | 46c5b83bcc5ab4db34716954fc64645eba7038ca (diff) | |
parent | c25a785d6647984505fa165b5cd84cfc9a95970b (diff) | |
download | op-kernel-dev-4f57d865f1d863346ac50db9c25859e73a86499c.zip op-kernel-dev-4f57d865f1d863346ac50db9c25859e73a86499c.tar.gz |
Merge branch 'akpm'
Quoth Andrew:
"Random fixes. And a simple new LED driver which I'm trying to sneak
in while you're not looking."
Sneaking successful.
* akpm:
score: fix off-by-one index into syscall table
mm: fix rss count leakage during migration
SHM_UNLOCK: fix Unevictable pages stranded after swap
SHM_UNLOCK: fix long unpreemptible section
kdump: define KEXEC_NOTE_BYTES arch specific for s390x
mm/hugetlb.c: undo change to page mapcount in fault handler
mm: memcg: update the correct soft limit tree during migration
proc: clear_refs: do not clear reserved pages
drivers/video/backlight/l4f00242t03.c: return proper error in l4f00242t03_probe if regulator_get() fails
drivers/video/backlight/adp88x0_bl.c: fix bit testing logic
kprobes: initialize before using a hlist
ipc/mqueue: simplify reading msgqueue limit
leds: add led driver for Bachmann's ot200
mm: __count_immobile_pages(): make sure the node is online
mm: fix NULL ptr dereference in __count_immobile_pages
mm: fix warnings regarding enum migrate_mode
-rw-r--r-- | arch/s390/include/asm/kexec.h | 18 | ||||
-rw-r--r-- | arch/score/kernel/entry.S | 2 | ||||
-rw-r--r-- | drivers/leds/Kconfig | 7 | ||||
-rw-r--r-- | drivers/leds/Makefile | 1 | ||||
-rw-r--r-- | drivers/leds/leds-ot200.c | 171 | ||||
-rw-r--r-- | drivers/video/backlight/adp8860_bl.c | 2 | ||||
-rw-r--r-- | drivers/video/backlight/adp8870_bl.c | 2 | ||||
-rw-r--r-- | drivers/video/backlight/l4f00242t03.c | 2 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 3 | ||||
-rw-r--r-- | include/linux/fs.h | 2 | ||||
-rw-r--r-- | include/linux/kexec.h | 2 | ||||
-rw-r--r-- | include/linux/migrate.h | 14 | ||||
-rw-r--r-- | include/linux/migrate_mode.h | 16 | ||||
-rw-r--r-- | include/linux/shmem_fs.h | 1 | ||||
-rw-r--r-- | include/linux/swap.h | 2 | ||||
-rw-r--r-- | ipc/mqueue.c | 3 | ||||
-rw-r--r-- | ipc/shm.c | 37 | ||||
-rw-r--r-- | kernel/kprobes.c | 2 | ||||
-rw-r--r-- | mm/hugetlb.c | 9 | ||||
-rw-r--r-- | mm/memcontrol.c | 2 | ||||
-rw-r--r-- | mm/memory.c | 37 | ||||
-rw-r--r-- | mm/page_alloc.c | 20 | ||||
-rw-r--r-- | mm/shmem.c | 53 | ||||
-rw-r--r-- | mm/vmscan.c | 124 |
24 files changed, 388 insertions, 144 deletions
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index cf4e47b..3f30dac 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -42,6 +42,24 @@ /* The native architecture */ #define KEXEC_ARCH KEXEC_ARCH_S390 +/* + * Size for s390x ELF notes per CPU + * + * Seven notes plus zero note at the end: prstatus, fpregset, timer, + * tod_cmp, tod_reg, control regs, and prefix + */ +#define KEXEC_NOTE_BYTES \ + (ALIGN(sizeof(struct elf_note), 4) * 8 + \ + ALIGN(sizeof("CORE"), 4) * 7 + \ + ALIGN(sizeof(struct elf_prstatus), 4) + \ + ALIGN(sizeof(elf_fpregset_t), 4) + \ + ALIGN(sizeof(u64), 4) + \ + ALIGN(sizeof(u64), 4) + \ + ALIGN(sizeof(u32), 4) + \ + ALIGN(sizeof(u64) * 16, 4) + \ + ALIGN(sizeof(u32), 4) \ + ) + /* Provide a dummy definition to avoid build failures. */ static inline void crash_setup_regs(struct pt_regs *newregs, struct pt_regs *oldregs) { } diff --git a/arch/score/kernel/entry.S b/arch/score/kernel/entry.S index 577abba..83bb960 100644 --- a/arch/score/kernel/entry.S +++ b/arch/score/kernel/entry.S @@ -408,7 +408,7 @@ ENTRY(handle_sys) sw r9, [r0, PT_EPC] cmpi.c r27, __NR_syscalls # check syscall number - bgtu illegal_syscall + bgeu illegal_syscall slli r8, r27, 2 # get syscall routine la r11, sys_call_table diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig index c957c34..9ca28fc 100644 --- a/drivers/leds/Kconfig +++ b/drivers/leds/Kconfig @@ -403,6 +403,13 @@ config LEDS_MAX8997 This option enables support for on-chip LED drivers on MAXIM MAX8997 PMIC. +config LEDS_OT200 + tristate "LED support for the Bachmann OT200" + depends on LEDS_CLASS && HAS_IOMEM + help + This option enables support for the LEDs on the Bachmann OT200. + Say Y to enable LEDs on the Bachmann OT200. + config LEDS_TRIGGERS bool "LED Trigger support" depends on LEDS_CLASS diff --git a/drivers/leds/Makefile b/drivers/leds/Makefile index b8a9723..1fc6875 100644 --- a/drivers/leds/Makefile +++ b/drivers/leds/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_LEDS_LP5523) += leds-lp5523.o obj-$(CONFIG_LEDS_TCA6507) += leds-tca6507.o obj-$(CONFIG_LEDS_CLEVO_MAIL) += leds-clevo-mail.o obj-$(CONFIG_LEDS_HP6XX) += leds-hp6xx.o +obj-$(CONFIG_LEDS_OT200) += leds-ot200.o obj-$(CONFIG_LEDS_FSG) += leds-fsg.o obj-$(CONFIG_LEDS_PCA955X) += leds-pca955x.o obj-$(CONFIG_LEDS_DA903X) += leds-da903x.o diff --git a/drivers/leds/leds-ot200.c b/drivers/leds/leds-ot200.c new file mode 100644 index 0000000..c464682 --- /dev/null +++ b/drivers/leds/leds-ot200.c @@ -0,0 +1,171 @@ +/* + * Bachmann ot200 leds driver. + * + * Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de> + * Christian Gmeiner <christian.gmeiner@gmail.com> + * + * License: GPL as published by the FSF. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/leds.h> +#include <linux/io.h> +#include <linux/module.h> + + +struct ot200_led { + struct led_classdev cdev; + const char *name; + unsigned long port; + u8 mask; +}; + +/* + * The device has three leds on the back panel (led_err, led_init and led_run) + * and can handle up to seven leds on the front panel. + */ + +static struct ot200_led leds[] = { + { + .name = "led_run", + .port = 0x5a, + .mask = BIT(0), + }, + { + .name = "led_init", + .port = 0x5a, + .mask = BIT(1), + }, + { + .name = "led_err", + .port = 0x5a, + .mask = BIT(2), + }, + { + .name = "led_1", + .port = 0x49, + .mask = BIT(7), + }, + { + .name = "led_2", + .port = 0x49, + .mask = BIT(6), + }, + { + .name = "led_3", + .port = 0x49, + .mask = BIT(5), + }, + { + .name = "led_4", + .port = 0x49, + .mask = BIT(4), + }, + { + .name = "led_5", + .port = 0x49, + .mask = BIT(3), + }, + { + .name = "led_6", + .port = 0x49, + .mask = BIT(2), + }, + { + .name = "led_7", + .port = 0x49, + .mask = BIT(1), + } +}; + +static DEFINE_SPINLOCK(value_lock); + +/* + * we need to store the current led states, as it is not + * possible to read the current led state via inb(). + */ +static u8 leds_back; +static u8 leds_front; + +static void ot200_led_brightness_set(struct led_classdev *led_cdev, + enum led_brightness value) +{ + struct ot200_led *led = container_of(led_cdev, struct ot200_led, cdev); + u8 *val; + unsigned long flags; + + spin_lock_irqsave(&value_lock, flags); + + if (led->port == 0x49) + val = &leds_front; + else if (led->port == 0x5a) + val = &leds_back; + else + BUG(); + + if (value == LED_OFF) + *val &= ~led->mask; + else + *val |= led->mask; + + outb(*val, led->port); + spin_unlock_irqrestore(&value_lock, flags); +} + +static int __devinit ot200_led_probe(struct platform_device *pdev) +{ + int i; + int ret; + + for (i = 0; i < ARRAY_SIZE(leds); i++) { + + leds[i].cdev.name = leds[i].name; + leds[i].cdev.brightness_set = ot200_led_brightness_set; + + ret = led_classdev_register(&pdev->dev, &leds[i].cdev); + if (ret < 0) + goto err; + } + + leds_front = 0; /* turn off all front leds */ + leds_back = BIT(1); /* turn on init led */ + outb(leds_front, 0x49); + outb(leds_back, 0x5a); + + return 0; + +err: + for (i = i - 1; i >= 0; i--) + led_classdev_unregister(&leds[i].cdev); + + return ret; +} + +static int __devexit ot200_led_remove(struct platform_device *pdev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(leds); i++) + led_classdev_unregister(&leds[i].cdev); + + return 0; +} + +static struct platform_driver ot200_led_driver = { + .probe = ot200_led_probe, + .remove = __devexit_p(ot200_led_remove), + .driver = { + .name = "leds-ot200", + .owner = THIS_MODULE, + }, +}; + +module_platform_driver(ot200_led_driver); + +MODULE_AUTHOR("Sebastian A. Siewior <bigeasy@linutronix.de>"); +MODULE_DESCRIPTION("ot200 LED driver"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:leds-ot200"); diff --git a/drivers/video/backlight/adp8860_bl.c b/drivers/video/backlight/adp8860_bl.c index 66bc74d..378276c 100644 --- a/drivers/video/backlight/adp8860_bl.c +++ b/drivers/video/backlight/adp8860_bl.c @@ -146,7 +146,7 @@ static int adp8860_set_bits(struct i2c_client *client, int reg, uint8_t bit_mask ret = adp8860_read(client, reg, ®_val); - if (!ret && ((reg_val & bit_mask) == 0)) { + if (!ret && ((reg_val & bit_mask) != bit_mask)) { reg_val |= bit_mask; ret = adp8860_write(client, reg, reg_val); } diff --git a/drivers/video/backlight/adp8870_bl.c b/drivers/video/backlight/adp8870_bl.c index 6c68a68..6735059 100644 --- a/drivers/video/backlight/adp8870_bl.c +++ b/drivers/video/backlight/adp8870_bl.c @@ -160,7 +160,7 @@ static int adp8870_set_bits(struct i2c_client *client, int reg, uint8_t bit_mask ret = adp8870_read(client, reg, ®_val); - if (!ret && ((reg_val & bit_mask) == 0)) { + if (!ret && ((reg_val & bit_mask) != bit_mask)) { reg_val |= bit_mask; ret = adp8870_write(client, reg, reg_val); } diff --git a/drivers/video/backlight/l4f00242t03.c b/drivers/video/backlight/l4f00242t03.c index 4f5d1c4..27d1d7a 100644 --- a/drivers/video/backlight/l4f00242t03.c +++ b/drivers/video/backlight/l4f00242t03.c @@ -190,6 +190,7 @@ static int __devinit l4f00242t03_probe(struct spi_device *spi) priv->io_reg = regulator_get(&spi->dev, "vdd"); if (IS_ERR(priv->io_reg)) { + ret = PTR_ERR(priv->io_reg); dev_err(&spi->dev, "%s: Unable to get the IO regulator\n", __func__); goto err3; @@ -197,6 +198,7 @@ static int __devinit l4f00242t03_probe(struct spi_device *spi) priv->core_reg = regulator_get(&spi->dev, "vcore"); if (IS_ERR(priv->core_reg)) { + ret = PTR_ERR(priv->core_reg); dev_err(&spi->dev, "%s: Unable to get the core regulator\n", __func__); goto err4; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e418c5a..7dcd2a2 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -518,6 +518,9 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, if (!page) continue; + if (PageReserved(page)) + continue; + /* Clear accessed and referenced bits. */ ptep_test_and_clear_young(vma, addr, pte); ClearPageReferenced(page); diff --git a/include/linux/fs.h b/include/linux/fs.h index 0244082..4b3a41f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -10,6 +10,7 @@ #include <linux/ioctl.h> #include <linux/blk_types.h> #include <linux/types.h> +#include <linux/migrate_mode.h> /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change @@ -526,7 +527,6 @@ enum positive_aop_returns { struct page; struct address_space; struct writeback_control; -enum migrate_mode; struct iov_iter { const struct iovec *iov; diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 2fa0901..0d7d6a1 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -50,9 +50,11 @@ * note header. For kdump, the code in vmcore.c runs in the context * of the second kernel to combine them into one note. */ +#ifndef KEXEC_NOTE_BYTES #define KEXEC_NOTE_BYTES ( (KEXEC_NOTE_HEAD_BYTES * 2) + \ KEXEC_CORE_NOTE_NAME_BYTES + \ KEXEC_CORE_NOTE_DESC_BYTES ) +#endif /* * This structure is used to hold the arguments that are used when loading diff --git a/include/linux/migrate.h b/include/linux/migrate.h index eaf8674..05ed282 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -3,22 +3,10 @@ #include <linux/mm.h> #include <linux/mempolicy.h> +#include <linux/migrate_mode.h> typedef struct page *new_page_t(struct page *, unsigned long private, int **); -/* - * MIGRATE_ASYNC means never block - * MIGRATE_SYNC_LIGHT in the current implementation means to allow blocking - * on most operations but not ->writepage as the potential stall time - * is too significant - * MIGRATE_SYNC will block when migrating pages - */ -enum migrate_mode { - MIGRATE_ASYNC, - MIGRATE_SYNC_LIGHT, - MIGRATE_SYNC, -}; - #ifdef CONFIG_MIGRATION #define PAGE_MIGRATION 1 diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h new file mode 100644 index 0000000..ebf3d89 --- /dev/null +++ b/include/linux/migrate_mode.h @@ -0,0 +1,16 @@ +#ifndef MIGRATE_MODE_H_INCLUDED +#define MIGRATE_MODE_H_INCLUDED +/* + * MIGRATE_ASYNC means never block + * MIGRATE_SYNC_LIGHT in the current implementation means to allow blocking + * on most operations but not ->writepage as the potential stall time + * is too significant + * MIGRATE_SYNC will block when migrating pages + */ +enum migrate_mode { + MIGRATE_ASYNC, + MIGRATE_SYNC_LIGHT, + MIGRATE_SYNC, +}; + +#endif /* MIGRATE_MODE_H_INCLUDED */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index e4c711c..79ab255 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -48,6 +48,7 @@ extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); diff --git a/include/linux/swap.h b/include/linux/swap.h index 06061a7..3e60228 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -273,7 +273,7 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order) #endif extern int page_evictable(struct page *page, struct vm_area_struct *vma); -extern void scan_mapping_unevictable_pages(struct address_space *); +extern void check_move_unevictable_pages(struct page **, int nr_pages); extern unsigned long scan_unevictable_pages; extern int scan_unevictable_handler(struct ctl_table *, int, diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 9b7c8ab..86ee272 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -128,7 +128,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb, if (S_ISREG(mode)) { struct mqueue_inode_info *info; - struct task_struct *p = current; unsigned long mq_bytes, mq_msg_tblsz; inode->i_fop = &mqueue_file_operations; @@ -159,7 +158,7 @@ static struct inode *mqueue_get_inode(struct super_block *sb, spin_lock(&mq_lock); if (u->mq_bytes + mq_bytes < u->mq_bytes || - u->mq_bytes + mq_bytes > task_rlimit(p, RLIMIT_MSGQUEUE)) { + u->mq_bytes + mq_bytes > rlimit(RLIMIT_MSGQUEUE)) { spin_unlock(&mq_lock); /* mqueue_evict_inode() releases info->messages */ ret = -EMFILE; @@ -870,9 +870,7 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) case SHM_LOCK: case SHM_UNLOCK: { - struct file *uninitialized_var(shm_file); - - lru_add_drain_all(); /* drain pagevecs to lru lists */ + struct file *shm_file; shp = shm_lock_check(ns, shmid); if (IS_ERR(shp)) { @@ -895,22 +893,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf) err = security_shm_shmctl(shp, cmd); if (err) goto out_unlock; - - if(cmd==SHM_LOCK) { + + shm_file = shp->shm_file; + if (is_file_hugepages(shm_file)) + goto out_unlock; + + if (cmd == SHM_LOCK) { struct user_struct *user = current_user(); - if (!is_file_hugepages(shp->shm_file)) { - err = shmem_lock(shp->shm_file, 1, user); - if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){ - shp->shm_perm.mode |= SHM_LOCKED; - shp->mlock_user = user; - } + err = shmem_lock(shm_file, 1, user); + if (!err && !(shp->shm_perm.mode & SHM_LOCKED)) { + shp->shm_perm.mode |= SHM_LOCKED; + shp->mlock_user = user; } - } else if (!is_file_hugepages(shp->shm_file)) { - shmem_lock(shp->shm_file, 0, shp->mlock_user); - shp->shm_perm.mode &= ~SHM_LOCKED; - shp->mlock_user = NULL; + goto out_unlock; } + + /* SHM_UNLOCK */ + if (!(shp->shm_perm.mode & SHM_LOCKED)) + goto out_unlock; + shmem_lock(shm_file, 0, shp->mlock_user); + shp->shm_perm.mode &= ~SHM_LOCKED; + shp->mlock_user = NULL; + get_file(shm_file); shm_unlock(shp); + shmem_unlock_mapping(shm_file->f_mapping); + fput(shm_file); goto out; } case IPC_RMID: diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 95dd721..29f5b65 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1077,6 +1077,7 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) /* Early boot. kretprobe_table_locks not yet initialized. */ return; + INIT_HLIST_HEAD(&empty_rp); hash = hash_ptr(tk, KPROBE_HASH_BITS); head = &kretprobe_inst_table[hash]; kretprobe_table_lock(hash, &flags); @@ -1085,7 +1086,6 @@ void __kprobes kprobe_flush_task(struct task_struct *tk) recycle_rp_inst(ri, &empty_rp); } kretprobe_table_unlock(hash, &flags); - INIT_HLIST_HEAD(&empty_rp); hlist_for_each_entry_safe(ri, node, tmp, &empty_rp, hlist) { hlist_del(&ri->hlist); kfree(ri); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ea8c3a4..5f34bd8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2508,6 +2508,7 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct hstate *h = hstate_vma(vma); int ret = VM_FAULT_SIGBUS; + int anon_rmap = 0; pgoff_t idx; unsigned long size; struct page *page; @@ -2562,14 +2563,13 @@ retry: spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); - page_dup_rmap(page); } else { lock_page(page); if (unlikely(anon_vma_prepare(vma))) { ret = VM_FAULT_OOM; goto backout_unlocked; } - hugepage_add_new_anon_rmap(page, vma, address); + anon_rmap = 1; } } else { /* @@ -2582,7 +2582,6 @@ retry: VM_FAULT_SET_HINDEX(h - hstates); goto backout_unlocked; } - page_dup_rmap(page); } /* @@ -2606,6 +2605,10 @@ retry: if (!huge_pte_none(huge_ptep_get(ptep))) goto backout; + if (anon_rmap) + hugepage_add_new_anon_rmap(page, vma, address); + else + page_dup_rmap(page); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, address, ptep, new_pte); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3dbff4d..4baddba 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3247,7 +3247,7 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype); + __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype); return ret; } diff --git a/mm/memory.c b/mm/memory.c index 5e30583..fa2f04e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -878,15 +878,24 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, } if (likely(!non_swap_entry(entry))) rss[MM_SWAPENTS]++; - else if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both parent - * and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - set_pte_at(src_mm, addr, src_pte, pte); + else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + set_pte_at(src_mm, addr, src_pte, pte); + } } } goto out_set_pte; @@ -1191,6 +1200,16 @@ again: if (!non_swap_entry(entry)) rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; + + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; + } if (unlikely(!free_swap_and_cache(entry))) print_bad_pte(vma, addr, ptent, NULL); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0027d8f..d2186ec 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5413,7 +5413,25 @@ __count_immobile_pages(struct zone *zone, struct page *page, int count) bool is_pageblock_removable_nolock(struct page *page) { - struct zone *zone = page_zone(page); + struct zone *zone; + unsigned long pfn; + + /* + * We have to be careful here because we are iterating over memory + * sections which are not zone aware so we might end up outside of + * the zone but still within the section. + * We have to take care about the node as well. If the node is offline + * its NODE_DATA will be NULL - see page_zone. + */ + if (!node_online(page_to_nid(page))) + return false; + + zone = page_zone(page); + pfn = page_to_pfn(page); + if (zone->zone_start_pfn > pfn || + zone->zone_start_pfn + zone->spanned_pages <= pfn) + return false; + return __count_immobile_pages(zone, page, 0); } @@ -379,7 +379,7 @@ static int shmem_free_swap(struct address_space *mapping, /* * Pagevec may contain swap entries, so shuffle up pages before releasing. */ -static void shmem_pagevec_release(struct pagevec *pvec) +static void shmem_deswap_pagevec(struct pagevec *pvec) { int i, j; @@ -389,7 +389,36 @@ static void shmem_pagevec_release(struct pagevec *pvec) pvec->pages[j++] = page; } pvec->nr = j; - pagevec_release(pvec); +} + +/* + * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists. + */ +void shmem_unlock_mapping(struct address_space *mapping) +{ + struct pagevec pvec; + pgoff_t indices[PAGEVEC_SIZE]; + pgoff_t index = 0; + + pagevec_init(&pvec, 0); + /* + * Minor point, but we might as well stop if someone else SHM_LOCKs it. + */ + while (!mapping_unevictable(mapping)) { + /* + * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it + * has finished, if it hits a row of PAGEVEC_SIZE swap entries. + */ + pvec.nr = shmem_find_get_pages_and_swap(mapping, index, + PAGEVEC_SIZE, pvec.pages, indices); + if (!pvec.nr) + break; + index = indices[pvec.nr - 1] + 1; + shmem_deswap_pagevec(&pvec); + check_move_unevictable_pages(pvec.pages, pvec.nr); + pagevec_release(&pvec); + cond_resched(); + } } /* @@ -440,7 +469,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } unlock_page(page); } - shmem_pagevec_release(&pvec); + shmem_deswap_pagevec(&pvec); + pagevec_release(&pvec); mem_cgroup_uncharge_end(); cond_resched(); index++; @@ -470,7 +500,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) continue; } if (index == start && indices[0] > end) { - shmem_pagevec_release(&pvec); + shmem_deswap_pagevec(&pvec); + pagevec_release(&pvec); break; } mem_cgroup_uncharge_start(); @@ -494,7 +525,8 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) } unlock_page(page); } - shmem_pagevec_release(&pvec); + shmem_deswap_pagevec(&pvec); + pagevec_release(&pvec); mem_cgroup_uncharge_end(); index++; } @@ -1068,13 +1100,6 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) user_shm_unlock(inode->i_size, user); info->flags &= ~VM_LOCKED; mapping_clear_unevictable(file->f_mapping); - /* - * Ensure that a racing putback_lru_page() can see - * the pages of this mapping are evictable when we - * skip them due to !PageLRU during the scan. - */ - smp_mb__after_clear_bit(); - scan_mapping_unevictable_pages(file->f_mapping); } retval = 0; @@ -2445,6 +2470,10 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user) return 0; } +void shmem_unlock_mapping(struct address_space *mapping) +{ +} + void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend) { truncate_inode_pages_range(inode->i_mapping, lstart, lend); diff --git a/mm/vmscan.c b/mm/vmscan.c index 2880396..c52b235 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -26,7 +26,6 @@ #include <linux/buffer_head.h> /* for try_to_release_page(), buffer_heads_over_limit */ #include <linux/mm_inline.h> -#include <linux/pagevec.h> #include <linux/backing-dev.h> #include <linux/rmap.h> #include <linux/topology.h> @@ -661,7 +660,7 @@ redo: * When racing with an mlock or AS_UNEVICTABLE clearing * (page is unlocked) make sure that if the other thread * does not observe our setting of PG_lru and fails - * isolation/check_move_unevictable_page, + * isolation/check_move_unevictable_pages, * we see PG_mlocked/AS_UNEVICTABLE cleared below and move * the page back to the evictable list. * @@ -3499,100 +3498,61 @@ int page_evictable(struct page *page, struct vm_area_struct *vma) return 1; } +#ifdef CONFIG_SHMEM /** - * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list - * @page: page to check evictability and move to appropriate lru list - * @zone: zone page is in + * check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list + * @pages: array of pages to check + * @nr_pages: number of pages to check * - * Checks a page for evictability and moves the page to the appropriate - * zone lru list. + * Checks pages for evictability and moves them to the appropriate lru list. * - * Restrictions: zone->lru_lock must be held, page must be on LRU and must - * have PageUnevictable set. + * This function is only used for SysV IPC SHM_UNLOCK. */ -static void check_move_unevictable_page(struct page *page, struct zone *zone) +void check_move_unevictable_pages(struct page **pages, int nr_pages) { struct lruvec *lruvec; + struct zone *zone = NULL; + int pgscanned = 0; + int pgrescued = 0; + int i; - VM_BUG_ON(PageActive(page)); -retry: - ClearPageUnevictable(page); - if (page_evictable(page, NULL)) { - enum lru_list l = page_lru_base_type(page); - - __dec_zone_state(zone, NR_UNEVICTABLE); - lruvec = mem_cgroup_lru_move_lists(zone, page, - LRU_UNEVICTABLE, l); - list_move(&page->lru, &lruvec->lists[l]); - __inc_zone_state(zone, NR_INACTIVE_ANON + l); - __count_vm_event(UNEVICTABLE_PGRESCUED); - } else { - /* - * rotate unevictable list - */ - SetPageUnevictable(page); - lruvec = mem_cgroup_lru_move_lists(zone, page, LRU_UNEVICTABLE, - LRU_UNEVICTABLE); - list_move(&page->lru, &lruvec->lists[LRU_UNEVICTABLE]); - if (page_evictable(page, NULL)) - goto retry; - } -} - -/** - * scan_mapping_unevictable_pages - scan an address space for evictable pages - * @mapping: struct address_space to scan for evictable pages - * - * Scan all pages in mapping. Check unevictable pages for - * evictability and move them to the appropriate zone lru list. - */ -void scan_mapping_unevictable_pages(struct address_space *mapping) -{ - pgoff_t next = 0; - pgoff_t end = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >> - PAGE_CACHE_SHIFT; - struct zone *zone; - struct pagevec pvec; - - if (mapping->nrpages == 0) - return; - - pagevec_init(&pvec, 0); - while (next < end && - pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { - int i; - int pg_scanned = 0; - - zone = NULL; - - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - pgoff_t page_index = page->index; - struct zone *pagezone = page_zone(page); + for (i = 0; i < nr_pages; i++) { + struct page *page = pages[i]; + struct zone *pagezone; - pg_scanned++; - if (page_index > next) - next = page_index; - next++; + pgscanned++; + pagezone = page_zone(page); + if (pagezone != zone) { + if (zone) + spin_unlock_irq(&zone->lru_lock); + zone = pagezone; + spin_lock_irq(&zone->lru_lock); + } - if (pagezone != zone) { - if (zone) - spin_unlock_irq(&zone->lru_lock); - zone = pagezone; - spin_lock_irq(&zone->lru_lock); - } + if (!PageLRU(page) || !PageUnevictable(page)) + continue; - if (PageLRU(page) && PageUnevictable(page)) - check_move_unevictable_page(page, zone); + if (page_evictable(page, NULL)) { + enum lru_list lru = page_lru_base_type(page); + + VM_BUG_ON(PageActive(page)); + ClearPageUnevictable(page); + __dec_zone_state(zone, NR_UNEVICTABLE); + lruvec = mem_cgroup_lru_move_lists(zone, page, + LRU_UNEVICTABLE, lru); + list_move(&page->lru, &lruvec->lists[lru]); + __inc_zone_state(zone, NR_INACTIVE_ANON + lru); + pgrescued++; } - if (zone) - spin_unlock_irq(&zone->lru_lock); - pagevec_release(&pvec); - - count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned); } + if (zone) { + __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); + __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); + spin_unlock_irq(&zone->lru_lock); + } } +#endif /* CONFIG_SHMEM */ static void warn_scan_unevictable_pages(void) { |