diff options
49 files changed, 381 insertions, 205 deletions
diff --git a/arch/alpha/include/asm/mmu_context.h b/arch/alpha/include/asm/mmu_context.h index 384bd47b5187..45c020a0fe76 100644 --- a/arch/alpha/include/asm/mmu_context.h +++ b/arch/alpha/include/asm/mmu_context.h @@ -8,6 +8,7 @@ */ #include <linux/mm_types.h> +#include <linux/sched.h> #include <asm/machvec.h> #include <asm/compiler.h> diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig index 87cde1e4b38c..0777f3a8a1f3 100644 --- a/arch/m32r/Kconfig +++ b/arch/m32r/Kconfig @@ -194,6 +194,10 @@ config TIMER_DIVIDE int "Timer divider (integer)" default "128" +config CPU_BIG_ENDIAN + bool "Generate big endian code" + default n + config CPU_LITTLE_ENDIAN bool "Generate little endian code" default n diff --git a/arch/m32r/kernel/traps.c b/arch/m32r/kernel/traps.c index 647dd94a0c39..72b96f282689 100644 --- a/arch/m32r/kernel/traps.c +++ b/arch/m32r/kernel/traps.c @@ -114,6 +114,15 @@ static void set_eit_vector_entries(void) _flush_cache_copyback_all(); } +void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} +EXPORT_SYMBOL(abort); + void __init trap_init(void) { set_eit_vector_entries(); diff --git a/arch/powerpc/sysdev/fsl_rio.c b/arch/powerpc/sysdev/fsl_rio.c index 9234be1e66f5..5011ffea4e4b 100644 --- a/arch/powerpc/sysdev/fsl_rio.c +++ b/arch/powerpc/sysdev/fsl_rio.c @@ -71,6 +71,8 @@ #define RIWAR_WRTYP_ALLOC 0x00006000 #define RIWAR_SIZE_MASK 0x0000003F +static DEFINE_SPINLOCK(fsl_rio_config_lock); + #define __fsl_read_rio_config(x, addr, err, op) \ __asm__ __volatile__( \ "1: "op" %1,0(%2)\n" \ @@ -184,6 +186,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 *val) { struct rio_priv *priv = mport->priv; + unsigned long flags; u8 *data; u32 rval, err = 0; @@ -197,6 +200,8 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len)) return -EINVAL; + spin_lock_irqsave(&fsl_rio_config_lock, flags); + out_be32(&priv->maint_atmu_regs->rowtar, (destid << 22) | (hopcount << 12) | (offset >> 12)); out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10)); @@ -213,6 +218,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, __fsl_read_rio_config(rval, data, err, "lwz"); break; default: + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); return -EINVAL; } @@ -221,6 +227,7 @@ fsl_rio_config_read(struct rio_mport *mport, int index, u16 destid, err, destid, hopcount, offset); } + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); *val = rval; return err; @@ -244,7 +251,10 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, u8 hopcount, u32 offset, int len, u32 val) { struct rio_priv *priv = mport->priv; + unsigned long flags; u8 *data; + int ret = 0; + pr_debug ("fsl_rio_config_write:" " index %d destid %d hopcount %d offset %8.8x len %d val %8.8x\n", @@ -255,6 +265,8 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, if (offset > (0x1000000 - len) || !IS_ALIGNED(offset, len)) return -EINVAL; + spin_lock_irqsave(&fsl_rio_config_lock, flags); + out_be32(&priv->maint_atmu_regs->rowtar, (destid << 22) | (hopcount << 12) | (offset >> 12)); out_be32(&priv->maint_atmu_regs->rowtear, (destid >> 10)); @@ -271,10 +283,11 @@ fsl_rio_config_write(struct rio_mport *mport, int index, u16 destid, out_be32((u32 *) data, val); break; default: - return -EINVAL; + ret = -EINVAL; } + spin_unlock_irqrestore(&fsl_rio_config_lock, flags); - return 0; + return ret; } static void fsl_rio_inbound_mem_init(struct rio_priv *priv) diff --git a/arch/powerpc/sysdev/fsl_rmu.c b/arch/powerpc/sysdev/fsl_rmu.c index ab7a74c75be8..88b35a3dcdc5 100644 --- a/arch/powerpc/sysdev/fsl_rmu.c +++ b/arch/powerpc/sysdev/fsl_rmu.c @@ -104,6 +104,8 @@ #define DOORBELL_MESSAGE_SIZE 0x08 +static DEFINE_SPINLOCK(fsl_rio_doorbell_lock); + struct rio_msg_regs { u32 omr; u32 osr; @@ -626,9 +628,13 @@ err_out: int fsl_rio_doorbell_send(struct rio_mport *mport, int index, u16 destid, u16 data) { + unsigned long flags; + pr_debug("fsl_doorbell_send: index %d destid %4.4x data %4.4x\n", index, destid, data); + spin_lock_irqsave(&fsl_rio_doorbell_lock, flags); + /* In the serial version silicons, such as MPC8548, MPC8641, * below operations is must be. */ @@ -638,6 +644,8 @@ int fsl_rio_doorbell_send(struct rio_mport *mport, out_be32(&dbell->dbell_regs->oddatr, (index << 20) | data); out_be32(&dbell->dbell_regs->odmr, 0x00000001); + spin_unlock_irqrestore(&fsl_rio_doorbell_lock, flags); + return 0; } diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7264.h b/arch/sh/include/cpu-sh2a/cpu/sh7264.h index 4d1ef6d74bd6..2ae0e938b657 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7264.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7264.h @@ -43,9 +43,7 @@ enum { GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4, GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0, - /* Port H */ - GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4, - GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0, + /* Port H - Port H does not have a Data Register */ /* Port I - not on device */ diff --git a/arch/sh/include/cpu-sh2a/cpu/sh7269.h b/arch/sh/include/cpu-sh2a/cpu/sh7269.h index 2a0ca8780f0d..13c495a9fc00 100644 --- a/arch/sh/include/cpu-sh2a/cpu/sh7269.h +++ b/arch/sh/include/cpu-sh2a/cpu/sh7269.h @@ -45,9 +45,7 @@ enum { GPIO_PG7, GPIO_PG6, GPIO_PG5, GPIO_PG4, GPIO_PG3, GPIO_PG2, GPIO_PG1, GPIO_PG0, - /* Port H */ - GPIO_PH7, GPIO_PH6, GPIO_PH5, GPIO_PH4, - GPIO_PH3, GPIO_PH2, GPIO_PH1, GPIO_PH0, + /* Port H - Port H does not have a Data Register */ /* Port I - not on device */ diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h index 3bb74e534d0f..78961ab78a5a 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7722.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h @@ -67,7 +67,7 @@ enum { GPIO_PTN3, GPIO_PTN2, GPIO_PTN1, GPIO_PTN0, /* PTQ */ - GPIO_PTQ7, GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4, + GPIO_PTQ6, GPIO_PTQ5, GPIO_PTQ4, GPIO_PTQ3, GPIO_PTQ2, GPIO_PTQ1, GPIO_PTQ0, /* PTR */ diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h index 5340f3bc1863..b40fb541e72a 100644 --- a/arch/sh/include/cpu-sh4/cpu/sh7757.h +++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h @@ -40,7 +40,7 @@ enum { /* PTJ */ GPIO_PTJ0, GPIO_PTJ1, GPIO_PTJ2, GPIO_PTJ3, - GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, GPIO_PTJ7_RESV, + GPIO_PTJ4, GPIO_PTJ5, GPIO_PTJ6, /* PTK */ GPIO_PTK0, GPIO_PTK1, GPIO_PTK2, GPIO_PTK3, @@ -48,7 +48,7 @@ enum { /* PTL */ GPIO_PTL0, GPIO_PTL1, GPIO_PTL2, GPIO_PTL3, - GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, GPIO_PTL7_RESV, + GPIO_PTL4, GPIO_PTL5, GPIO_PTL6, /* PTM */ GPIO_PTM0, GPIO_PTM1, GPIO_PTM2, GPIO_PTM3, @@ -56,7 +56,7 @@ enum { /* PTN */ GPIO_PTN0, GPIO_PTN1, GPIO_PTN2, GPIO_PTN3, - GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, GPIO_PTN7_RESV, + GPIO_PTN4, GPIO_PTN5, GPIO_PTN6, /* PTO */ GPIO_PTO0, GPIO_PTO1, GPIO_PTO2, GPIO_PTO3, @@ -68,7 +68,7 @@ enum { /* PTQ */ GPIO_PTQ0, GPIO_PTQ1, GPIO_PTQ2, GPIO_PTQ3, - GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, GPIO_PTQ7_RESV, + GPIO_PTQ4, GPIO_PTQ5, GPIO_PTQ6, /* PTR */ GPIO_PTR0, GPIO_PTR1, GPIO_PTR2, GPIO_PTR3, diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 8fe165844e47..064f5e31ec55 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -913,6 +913,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, struct binder_alloc *alloc; uintptr_t page_addr; size_t index; + struct vm_area_struct *vma; alloc = page->alloc; if (!mutex_trylock(&alloc->mutex)) @@ -923,16 +924,22 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - if (alloc->vma) { + vma = alloc->vma; + if (vma) { mm = get_task_mm(alloc->tsk); if (!mm) goto err_get_task_mm_failed; if (!down_write_trylock(&mm->mmap_sem)) goto err_down_write_mmap_sem_failed; + } + + list_lru_isolate(lru, item); + spin_unlock(lock); + if (vma) { trace_binder_unmap_user_start(alloc, index); - zap_page_range(alloc->vma, + zap_page_range(vma, page_addr + alloc->user_buffer_offset, PAGE_SIZE); @@ -950,13 +957,12 @@ enum lru_status binder_alloc_free_page(struct list_head *item, trace_binder_unmap_kernel_end(alloc, index); - list_lru_isolate(lru, item); - + spin_lock(lock); mutex_unlock(&alloc->mutex); - return LRU_REMOVED; + return LRU_REMOVED_RETRY; err_down_write_mmap_sem_failed: - mmput(mm); + mmput_async(mm); err_get_task_mm_failed: err_page_already_freed: mutex_unlock(&alloc->mutex); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2981c27d3aae..f149d3e61234 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -766,27 +766,6 @@ static void zram_slot_unlock(struct zram *zram, u32 index) bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value); } -static bool zram_same_page_read(struct zram *zram, u32 index, - struct page *page, - unsigned int offset, unsigned int len) -{ - zram_slot_lock(zram, index); - if (unlikely(!zram_get_handle(zram, index) || - zram_test_flag(zram, index, ZRAM_SAME))) { - void *mem; - - zram_slot_unlock(zram, index); - mem = kmap_atomic(page); - zram_fill_page(mem + offset, len, - zram_get_element(zram, index)); - kunmap_atomic(mem); - return true; - } - zram_slot_unlock(zram, index); - - return false; -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -884,11 +863,20 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, zram_slot_unlock(zram, index); } - if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE)) - return 0; - zram_slot_lock(zram, index); handle = zram_get_handle(zram, index); + if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) { + unsigned long value; + void *mem; + + value = handle ? zram_get_element(zram, index) : 0; + mem = kmap_atomic(page); + zram_fill_page(mem, PAGE_SIZE, value); + kunmap_atomic(mem); + zram_slot_unlock(zram, index); + return 0; + } + size = zram_get_obj_size(zram, index); src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); diff --git a/drivers/rapidio/devices/tsi721.c b/drivers/rapidio/devices/tsi721.c index 315a4be8dc1e..9a68914100ad 100644 --- a/drivers/rapidio/devices/tsi721.c +++ b/drivers/rapidio/devices/tsi721.c @@ -51,6 +51,8 @@ module_param(mbox_sel, byte, S_IRUGO); MODULE_PARM_DESC(mbox_sel, "RIO Messaging MBOX Selection Mask (default: 0x0f = all)"); +static DEFINE_SPINLOCK(tsi721_maint_lock); + static void tsi721_omsg_handler(struct tsi721_device *priv, int ch); static void tsi721_imsg_handler(struct tsi721_device *priv, int ch); @@ -124,12 +126,15 @@ static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size, void __iomem *regs = priv->regs + TSI721_DMAC_BASE(priv->mdma.ch_id); struct tsi721_dma_desc *bd_ptr; u32 rd_count, swr_ptr, ch_stat; + unsigned long flags; int i, err = 0; u32 op = do_wr ? MAINT_WR : MAINT_RD; if (offset > (RIO_MAINT_SPACE_SZ - len) || (len != sizeof(u32))) return -EINVAL; + spin_lock_irqsave(&tsi721_maint_lock, flags); + bd_ptr = priv->mdma.bd_base; rd_count = ioread32(regs + TSI721_DMAC_DRDCNT); @@ -197,7 +202,9 @@ static int tsi721_maint_dma(struct tsi721_device *priv, u32 sys_size, */ swr_ptr = ioread32(regs + TSI721_DMAC_DSWP); iowrite32(swr_ptr, regs + TSI721_DMAC_DSRP); + err_out: + spin_unlock_irqrestore(&tsi721_maint_lock, flags); return err; } diff --git a/drivers/rapidio/rio-access.c b/drivers/rapidio/rio-access.c index a3824baca2e5..3ee9af83b638 100644 --- a/drivers/rapidio/rio-access.c +++ b/drivers/rapidio/rio-access.c @@ -14,16 +14,8 @@ #include <linux/module.h> /* - * These interrupt-safe spinlocks protect all accesses to RIO - * configuration space and doorbell access. - */ -static DEFINE_SPINLOCK(rio_config_lock); -static DEFINE_SPINLOCK(rio_doorbell_lock); - -/* * Wrappers for all RIO configuration access functions. They just check - * alignment, do locking and call the low-level functions pointed to - * by rio_mport->ops. + * alignment and call the low-level functions pointed to by rio_mport->ops. */ #define RIO_8_BAD 0 @@ -44,13 +36,10 @@ int __rio_local_read_config_##size \ (struct rio_mport *mport, u32 offset, type *value) \ { \ int res; \ - unsigned long flags; \ u32 data = 0; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ res = mport->ops->lcread(mport, mport->id, offset, len, &data); \ *value = (type)data; \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ return res; \ } @@ -67,13 +56,8 @@ int __rio_local_read_config_##size \ int __rio_local_write_config_##size \ (struct rio_mport *mport, u32 offset, type value) \ { \ - int res; \ - unsigned long flags; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ - res = mport->ops->lcwrite(mport, mport->id, offset, len, value);\ - spin_unlock_irqrestore(&rio_config_lock, flags); \ - return res; \ + return mport->ops->lcwrite(mport, mport->id, offset, len, value);\ } RIO_LOP_READ(8, u8, 1) @@ -104,13 +88,10 @@ int rio_mport_read_config_##size \ (struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type *value) \ { \ int res; \ - unsigned long flags; \ u32 data = 0; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ res = mport->ops->cread(mport, mport->id, destid, hopcount, offset, len, &data); \ *value = (type)data; \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ return res; \ } @@ -127,13 +108,9 @@ int rio_mport_read_config_##size \ int rio_mport_write_config_##size \ (struct rio_mport *mport, u16 destid, u8 hopcount, u32 offset, type value) \ { \ - int res; \ - unsigned long flags; \ if (RIO_##size##_BAD) return RIO_BAD_SIZE; \ - spin_lock_irqsave(&rio_config_lock, flags); \ - res = mport->ops->cwrite(mport, mport->id, destid, hopcount, offset, len, value); \ - spin_unlock_irqrestore(&rio_config_lock, flags); \ - return res; \ + return mport->ops->cwrite(mport, mport->id, destid, hopcount, \ + offset, len, value); \ } RIO_OP_READ(8, u8, 1) @@ -162,14 +139,7 @@ EXPORT_SYMBOL_GPL(rio_mport_write_config_32); */ int rio_mport_send_doorbell(struct rio_mport *mport, u16 destid, u16 data) { - int res; - unsigned long flags; - - spin_lock_irqsave(&rio_doorbell_lock, flags); - res = mport->ops->dsend(mport, mport->id, destid, data); - spin_unlock_irqrestore(&rio_doorbell_lock, flags); - - return res; + return mport->ops->dsend(mport, mport->id, destid, data); } EXPORT_SYMBOL_GPL(rio_mport_send_doorbell); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index ce7181ea60fa..2a46762def31 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -54,7 +54,7 @@ typedef struct { int size; /* size of magic/mask */ char *magic; /* magic or filename extension */ char *mask; /* mask, NULL for exact match */ - char *interpreter; /* filename of interpreter */ + const char *interpreter; /* filename of interpreter */ char *name; struct dentry *dentry; struct file *interp_file; @@ -131,27 +131,26 @@ static int load_misc_binary(struct linux_binprm *bprm) { Node *fmt; struct file *interp_file = NULL; - char iname[BINPRM_BUF_SIZE]; - const char *iname_addr = iname; int retval; int fd_binary = -1; retval = -ENOEXEC; if (!enabled) - goto ret; + return retval; /* to keep locking time low, we copy the interpreter string */ read_lock(&entries_lock); fmt = check_file(bprm); if (fmt) - strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE); + dget(fmt->dentry); read_unlock(&entries_lock); if (!fmt) - goto ret; + return retval; /* Need to be able to load the file after exec */ + retval = -ENOENT; if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) - return -ENOENT; + goto ret; if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) { retval = remove_arg_zero(bprm); @@ -195,22 +194,22 @@ static int load_misc_binary(struct linux_binprm *bprm) bprm->argc++; /* add the interp as argv[0] */ - retval = copy_strings_kernel(1, &iname_addr, bprm); + retval = copy_strings_kernel(1, &fmt->interpreter, bprm); if (retval < 0) goto error; bprm->argc++; /* Update interp in case binfmt_script needs it. */ - retval = bprm_change_interp(iname, bprm); + retval = bprm_change_interp(fmt->interpreter, bprm); if (retval < 0) goto error; - if (fmt->flags & MISC_FMT_OPEN_FILE && fmt->interp_file) { + if (fmt->flags & MISC_FMT_OPEN_FILE) { interp_file = filp_clone_open(fmt->interp_file); if (!IS_ERR(interp_file)) deny_write_access(interp_file); } else { - interp_file = open_exec(iname); + interp_file = open_exec(fmt->interpreter); } retval = PTR_ERR(interp_file); if (IS_ERR(interp_file)) @@ -238,6 +237,7 @@ static int load_misc_binary(struct linux_binprm *bprm) goto error; ret: + dput(fmt->dentry); return retval; error: if (fd_binary > 0) @@ -594,8 +594,13 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) static void bm_evict_inode(struct inode *inode) { + Node *e = inode->i_private; + + if (e->flags & MISC_FMT_OPEN_FILE) + filp_close(e->interp_file, NULL); + clear_inode(inode); - kfree(inode->i_private); + kfree(e); } static void kill_node(Node *e) @@ -603,24 +608,14 @@ static void kill_node(Node *e) struct dentry *dentry; write_lock(&entries_lock); - dentry = e->dentry; - if (dentry) { - list_del_init(&e->list); - e->dentry = NULL; - } + list_del_init(&e->list); write_unlock(&entries_lock); - if ((e->flags & MISC_FMT_OPEN_FILE) && e->interp_file) { - filp_close(e->interp_file, NULL); - e->interp_file = NULL; - } - - if (dentry) { - drop_nlink(d_inode(dentry)); - d_drop(dentry); - dput(dentry); - simple_release_fs(&bm_mnt, &entry_count); - } + dentry = e->dentry; + drop_nlink(d_inode(dentry)); + d_drop(dentry); + dput(dentry); + simple_release_fs(&bm_mnt, &entry_count); } /* /<entry> */ @@ -665,7 +660,8 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, root = file_inode(file)->i_sb->s_root; inode_lock(d_inode(root)); - kill_node(e); + if (!list_empty(&e->list)) + kill_node(e); inode_unlock(d_inode(root)); break; @@ -794,7 +790,7 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, inode_lock(d_inode(root)); while (!list_empty(&entries)) - kill_node(list_entry(entries.next, Node, list)); + kill_node(list_first_entry(&entries, Node, list)); inode_unlock(d_inode(root)); break; diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index afdf4e3cafc2..7cde3f46ad26 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -19,7 +19,6 @@ static int load_script(struct linux_binprm *bprm) const char *i_arg, *i_name; char *cp; struct file *file; - char interp[BINPRM_BUF_SIZE]; int retval; if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) @@ -55,7 +54,7 @@ static int load_script(struct linux_binprm *bprm) break; } for (cp = bprm->buf+2; (*cp == ' ') || (*cp == '\t'); cp++); - if (*cp == '\0') + if (*cp == '\0') return -ENOEXEC; /* No interpreter name found */ i_name = cp; i_arg = NULL; @@ -65,7 +64,6 @@ static int load_script(struct linux_binprm *bprm) *cp++ = '\0'; if (*cp) i_arg = cp; - strcpy (interp, i_name); /* * OK, we've parsed out the interpreter name and * (optional) argument. @@ -80,24 +78,27 @@ static int load_script(struct linux_binprm *bprm) if (retval) return retval; retval = copy_strings_kernel(1, &bprm->interp, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; if (i_arg) { retval = copy_strings_kernel(1, &i_arg, bprm); - if (retval < 0) return retval; + if (retval < 0) + return retval; bprm->argc++; } retval = copy_strings_kernel(1, &i_name, bprm); - if (retval) return retval; + if (retval) + return retval; bprm->argc++; - retval = bprm_change_interp(interp, bprm); + retval = bprm_change_interp(i_name, bprm); if (retval < 0) return retval; /* * OK, now restart the process with the interpreter's dentry. */ - file = open_exec(interp); + file = open_exec(i_name); if (IS_ERR(file)) return PTR_ERR(file); diff --git a/fs/exec.c b/fs/exec.c index ac34d9724684..5470d3c1892a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1410,7 +1410,7 @@ static void free_bprm(struct linux_binprm *bprm) kfree(bprm); } -int bprm_change_interp(char *interp, struct linux_binprm *bprm) +int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index ef4b48d1ea42..1c713fd5b3e6 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -588,6 +588,12 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, break; if (ACCESS_ONCE(ctx->released) || fatal_signal_pending(current)) { + /* + * &ewq->wq may be queued in fork_event, but + * __remove_wait_queue ignores the head + * parameter. It would be a problem if it + * didn't. + */ __remove_wait_queue(&ctx->event_wqh, &ewq->wq); if (ewq->msg.event == UFFD_EVENT_FORK) { struct userfaultfd_ctx *new; @@ -1061,6 +1067,12 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, (unsigned long) uwq->msg.arg.reserved.reserved1; list_move(&uwq->wq.entry, &fork_event); + /* + * fork_nctx can be freed as soon as + * we drop the lock, unless we take a + * reference on it. + */ + userfaultfd_ctx_get(fork_nctx); spin_unlock(&ctx->event_wqh.lock); ret = 0; break; @@ -1091,19 +1103,53 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait, if (!ret && msg->event == UFFD_EVENT_FORK) { ret = resolve_userfault_fork(ctx, fork_nctx, msg); + spin_lock(&ctx->event_wqh.lock); + if (!list_empty(&fork_event)) { + /* + * The fork thread didn't abort, so we can + * drop the temporary refcount. + */ + userfaultfd_ctx_put(fork_nctx); + + uwq = list_first_entry(&fork_event, + typeof(*uwq), + wq.entry); + /* + * If fork_event list wasn't empty and in turn + * the event wasn't already released by fork + * (the event is allocated on fork kernel + * stack), put the event back to its place in + * the event_wq. fork_event head will be freed + * as soon as we return so the event cannot + * stay queued there no matter the current + * "ret" value. + */ + list_del(&uwq->wq.entry); + __add_wait_queue(&ctx->event_wqh, &uwq->wq); - if (!ret) { - spin_lock(&ctx->event_wqh.lock); - if (!list_empty(&fork_event)) { - uwq = list_first_entry(&fork_event, - typeof(*uwq), - wq.entry); - list_del(&uwq->wq.entry); - __add_wait_queue(&ctx->event_wqh, &uwq->wq); + /* + * Leave the event in the waitqueue and report + * error to userland if we failed to resolve + * the userfault fork. + */ + if (likely(!ret)) userfaultfd_event_complete(ctx, uwq); - } - spin_unlock(&ctx->event_wqh.lock); + } else { + /* + * Here the fork thread aborted and the + * refcount from the fork thread on fork_nctx + * has already been released. We still hold + * the reference we took before releasing the + * lock above. If resolve_userfault_fork + * failed we've to drop it because the + * fork_nctx has to be freed in such case. If + * it succeeded we'll hold it because the new + * uffd references it. + */ + if (ret) + userfaultfd_ctx_put(fork_nctx); } + spin_unlock(&ctx->event_wqh.lock); } return ret; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fb44d6180ca0..18d05b5491f3 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -131,7 +131,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, int executable_stack); extern int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location); -extern int bprm_change_interp(char *interp, struct linux_binprm *bprm); +extern int bprm_change_interp(const char *interp, struct linux_binprm *bprm); extern int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm); extern int prepare_bprm_creds(struct linux_binprm *bprm); diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 8b9d6fff002d..f2deb71958b2 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -92,7 +92,7 @@ /** * FIELD_GET() - extract a bitfield element * @_mask: shifted mask defining the field's length and position - * @_reg: 32bit value of entire bitfield + * @_reg: value of entire bitfield * * FIELD_GET() extracts the field specified by @_mask from the * bitfield passed in as @_reg by masking and shifting it down. diff --git a/include/linux/fs.h b/include/linux/fs.h index 339e73742e73..13dab191a23e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -403,7 +403,7 @@ struct address_space { unsigned long flags; /* error bits */ spinlock_t private_lock; /* for use by the address_space */ gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* ditto */ + struct list_head private_list; /* for use by the address_space */ void *private_data; /* ditto */ errseq_t wb_err; } __attribute__((aligned(sizeof(long)))) __randomize_layout; diff --git a/include/linux/mm.h b/include/linux/mm.h index f8c10d336e42..065d99deb847 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -240,7 +240,7 @@ extern unsigned int kobjsize(const void *objp); #if defined(CONFIG_X86_INTEL_MPX) /* MPX specific bounds table or bounds directory */ -# define VM_MPX VM_HIGH_ARCH_BIT_4 +# define VM_MPX VM_HIGH_ARCH_4 #else # define VM_MPX VM_NONE #endif diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 7b2e31b1745a..6866e8126982 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -400,6 +400,11 @@ extern void mmu_notifier_synchronize(void); #else /* CONFIG_MMU_NOTIFIER */ +static inline int mm_has_notifiers(struct mm_struct *mm) +{ + return 0; +} + static inline void mmu_notifier_release(struct mm_struct *mm) { } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 356a814e7c8e..c8f89417740b 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1094,8 +1094,14 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #error Allocator MAX_ORDER exceeds SECTION_SIZE #endif -#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT) -#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT) +static inline unsigned long pfn_to_section_nr(unsigned long pfn) +{ + return pfn >> PFN_SECTION_SHIFT; +} +static inline unsigned long section_nr_to_pfn(unsigned long sec) +{ + return sec << PFN_SECTION_SHIFT; +} #define SECTION_ALIGN_UP(pfn) (((pfn) + PAGES_PER_SECTION - 1) & PAGE_SECTION_MASK) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 3a19c253bdb1..ae53e413fb13 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -84,6 +84,12 @@ static inline bool mmget_not_zero(struct mm_struct *mm) /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); +#ifdef CONFIG_MMU +/* same as above but performs the slow path from the async context. Can + * be called from the atomic context as well + */ +void mmput_async(struct mm_struct *); +#endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); diff --git a/kernel/fork.c b/kernel/fork.c index 10646182440f..e702cb9ffbd8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -946,6 +946,24 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); +#ifdef CONFIG_MMU +static void mmput_async_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, + async_put_work); + + __mmput(mm); +} + +void mmput_async(struct mm_struct *mm) +{ + if (atomic_dec_and_test(&mm->mm_users)) { + INIT_WORK(&mm->async_put_work, mmput_async_fn); + schedule_work(&mm->async_put_work); + } +} +#endif + /** * set_mm_exe_file - change a reference to the mm's executable file * diff --git a/kernel/kcmp.c b/kernel/kcmp.c index ea34ed8bb952..055bb2962a0b 100644 --- a/kernel/kcmp.c +++ b/kernel/kcmp.c @@ -131,7 +131,7 @@ static int kcmp_epoll_target(struct task_struct *task1, if (filp_epoll) { filp_tgt = get_epoll_tfile_raw_ptr(filp_epoll, slot.tfd, slot.toff); fput(filp_epoll); - } else + } if (IS_ERR(filp_tgt)) return PTR_ERR(filp_tgt); diff --git a/kernel/memremap.c b/kernel/memremap.c index 6bcbfbf1a8fd..403ab9cdb949 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -350,7 +350,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; - int error, nid, is_ram; + int error, nid, is_ram, i = 0; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -448,6 +448,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, list_del(&page->lru); page->pgmap = pgmap; percpu_ref_get(ref); + if (!(++i % 1024)) + cond_resched(); } devres_add(dev, page_map); return __va(res->start); diff --git a/kernel/params.c b/kernel/params.c index 60b2d8101355..cc9108c2a1fd 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -224,7 +224,7 @@ char *parse_args(const char *doing, } \ int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ - return scnprintf(buffer, PAGE_SIZE, format, \ + return scnprintf(buffer, PAGE_SIZE, format "\n", \ *((type *)kp->arg)); \ } \ const struct kernel_param_ops param_ops_##name = { \ @@ -236,14 +236,14 @@ char *parse_args(const char *doing, EXPORT_SYMBOL(param_ops_##name) -STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); -STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); -STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); -STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); -STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); -STANDARD_PARAM_DEF(long, long, "%li", kstrtol); -STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); -STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); +STANDARD_PARAM_DEF(byte, unsigned char, "%hhu", kstrtou8); +STANDARD_PARAM_DEF(short, short, "%hi", kstrtos16); +STANDARD_PARAM_DEF(ushort, unsigned short, "%hu", kstrtou16); +STANDARD_PARAM_DEF(int, int, "%i", kstrtoint); +STANDARD_PARAM_DEF(uint, unsigned int, "%u", kstrtouint); +STANDARD_PARAM_DEF(long, long, "%li", kstrtol); +STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", kstrtoul); +STANDARD_PARAM_DEF(ullong, unsigned long long, "%llu", kstrtoull); int param_set_charp(const char *val, const struct kernel_param *kp) { @@ -270,7 +270,7 @@ EXPORT_SYMBOL(param_set_charp); int param_get_charp(char *buffer, const struct kernel_param *kp) { - return scnprintf(buffer, PAGE_SIZE, "%s", *((char **)kp->arg)); + return scnprintf(buffer, PAGE_SIZE, "%s\n", *((char **)kp->arg)); } EXPORT_SYMBOL(param_get_charp); @@ -301,7 +301,7 @@ EXPORT_SYMBOL(param_set_bool); int param_get_bool(char *buffer, const struct kernel_param *kp) { /* Y and N chosen as being relatively non-coder friendly */ - return sprintf(buffer, "%c", *(bool *)kp->arg ? 'Y' : 'N'); + return sprintf(buffer, "%c\n", *(bool *)kp->arg ? 'Y' : 'N'); } EXPORT_SYMBOL(param_get_bool); @@ -360,7 +360,7 @@ EXPORT_SYMBOL(param_set_invbool); int param_get_invbool(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); + return sprintf(buffer, "%c\n", (*(bool *)kp->arg) ? 'N' : 'Y'); } EXPORT_SYMBOL(param_get_invbool); @@ -460,8 +460,9 @@ static int param_array_get(char *buffer, const struct kernel_param *kp) struct kernel_param p = *kp; for (i = off = 0; i < (arr->num ? *arr->num : arr->max); i++) { + /* Replace \n with comma */ if (i) - buffer[off++] = ','; + buffer[off - 1] = ','; p.arg = arr->elem + arr->elemsize * i; check_kparam_locked(p.mod); ret = arr->ops->get(buffer + off, &p); @@ -507,7 +508,7 @@ EXPORT_SYMBOL(param_set_copystring); int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - return strlcpy(buffer, kps->string, kps->maxlen); + return scnprintf(buffer, PAGE_SIZE, "%s\n", kps->string); } EXPORT_SYMBOL(param_get_string); @@ -549,10 +550,6 @@ static ssize_t param_attr_show(struct module_attribute *mattr, kernel_param_lock(mk->mod); count = attribute->param->ops->get(buf, attribute->param); kernel_param_unlock(mk->mod); - if (count > 0) { - strcat(buf, "\n"); - ++count; - } return count; } @@ -600,7 +597,7 @@ EXPORT_SYMBOL(kernel_param_unlock); /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject - * @kparam: the actual parameter definition to add to sysfs + * @kp: the actual parameter definition to add to sysfs * @name: name of parameter * * Create a kobject if for a (per-module) parameter if mp NULL, and diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 423554ad3610..4da9e622471f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2188,8 +2188,6 @@ static int do_proc_douintvec_conv(unsigned long *lvalp, if (write) { if (*lvalp > UINT_MAX) return -EINVAL; - if (*lvalp > UINT_MAX) - return -EINVAL; *valp = *lvalp; } else { unsigned int val = *valp; diff --git a/lib/idr.c b/lib/idr.c index f9adf4805fd7..edd9b2be1651 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -146,8 +146,8 @@ EXPORT_SYMBOL(idr_get_next_ext); * idr_alloc() and idr_remove() (as long as the ID being removed is not * the one being replaced!). * - * Returns: 0 on success. %-ENOENT indicates that @id was not found. - * %-EINVAL indicates that @id or @ptr were not valid. + * Returns: the old value on success. %-ENOENT indicates that @id was not + * found. %-EINVAL indicates that @id or @ptr were not valid. */ void *idr_replace(struct idr *idr, void *ptr, int id) { diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index bd3574312b82..141734d255e4 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -85,8 +85,8 @@ static FORCE_INLINE int LZ4_decompress_generic( const BYTE * const lowLimit = lowPrefix - dictSize; const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize; - const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; - const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 }; + static const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; + static const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 }; const int safeDecode = (endOnInput == endOnInputSize); const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB))); diff --git a/lib/ratelimit.c b/lib/ratelimit.c index 08f8043cac61..d01f47135239 100644 --- a/lib/ratelimit.c +++ b/lib/ratelimit.c @@ -48,7 +48,9 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func) if (time_is_before_jiffies(rs->begin + rs->interval)) { if (rs->missed) { if (!(rs->flags & RATELIMIT_MSG_ON_RELEASE)) { - pr_warn("%s: %d callbacks suppressed\n", func, rs->missed); + printk_deferred(KERN_WARNING + "%s: %d callbacks suppressed\n", + func, rs->missed); rs->missed = 0; } } diff --git a/mm/compaction.c b/mm/compaction.c index fb548e4c7bd4..03d31a875341 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1999,17 +1999,14 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx) if (pgdat->kcompactd_max_order < order) pgdat->kcompactd_max_order = order; - /* - * Pairs with implicit barrier in wait_event_freezable() - * such that wakeups are not missed in the lockless - * waitqueue_active() call. - */ - smp_acquire__after_ctrl_dep(); - if (pgdat->kcompactd_classzone_idx > classzone_idx) pgdat->kcompactd_classzone_idx = classzone_idx; - if (!waitqueue_active(&pgdat->kcompactd_wait)) + /* + * Pairs with implicit barrier in wait_event_freezable() + * such that wakeups are not missed. + */ + if (!wq_has_sleeper(&pgdat->kcompactd_wait)) return; if (!kcompactd_node_suitable(pgdat)) diff --git a/mm/filemap.c b/mm/filemap.c index db250d0e0565..594d73fef8b4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -620,6 +620,14 @@ int file_check_and_advance_wb_err(struct file *file) trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } + + /* + * We're mostly using this function as a drop in replacement for + * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect + * that the legacy code would have had on these flags. + */ + clear_bit(AS_EIO, &mapping->flags); + clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); @@ -1990,6 +1990,7 @@ static void stable_tree_append(struct rmap_item *rmap_item, */ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) { + struct mm_struct *mm = rmap_item->mm; struct rmap_item *tree_rmap_item; struct page *tree_page = NULL; struct stable_node *stable_node; @@ -2062,9 +2063,11 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item) if (ksm_use_zero_pages && (checksum == zero_checksum)) { struct vm_area_struct *vma; - vma = find_mergeable_vma(rmap_item->mm, rmap_item->address); + down_read(&mm->mmap_sem); + vma = find_mergeable_vma(mm, rmap_item->address); err = try_to_merge_one_page(vma, page, ZERO_PAGE(rmap_item->address)); + up_read(&mm->mmap_sem); /* * In case of failure, the page was not really empty, so we * need to continue. Otherwise we're done. diff --git a/mm/list_lru.c b/mm/list_lru.c index 7a40fa2be858..f141f0c80ff3 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -325,12 +325,12 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) { int size = memcg_nr_cache_ids; - nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL); + nlru->memcg_lrus = kvmalloc(size * sizeof(void *), GFP_KERNEL); if (!nlru->memcg_lrus) return -ENOMEM; if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) { - kfree(nlru->memcg_lrus); + kvfree(nlru->memcg_lrus); return -ENOMEM; } @@ -340,7 +340,7 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru) static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) { __memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids); - kfree(nlru->memcg_lrus); + kvfree(nlru->memcg_lrus); } static int memcg_update_list_lru_node(struct list_lru_node *nlru, @@ -351,12 +351,12 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, BUG_ON(old_size > new_size); old = nlru->memcg_lrus; - new = kmalloc(new_size * sizeof(void *), GFP_KERNEL); + new = kvmalloc(new_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; if (__memcg_init_list_lru_node(new, old_size, new_size)) { - kfree(new); + kvfree(new); return -ENOMEM; } @@ -373,7 +373,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru, nlru->memcg_lrus = new; spin_unlock_irq(&nlru->lock); - kfree(old); + kvfree(old); return 0; } diff --git a/mm/madvise.c b/mm/madvise.c index 21261ff0466f..25bade36e9ca 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -625,18 +625,26 @@ static int madvise_inject_error(int behavior, { struct page *page; struct zone *zone; + unsigned int order; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - for (; start < end; start += PAGE_SIZE << - compound_order(compound_head(page))) { + + for (; start < end; start += PAGE_SIZE << order) { int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; + /* + * When soft offlining hugepages, after migrating the page + * we dissolve it, therefore in the second loop "page" will + * no longer be a compound page, and order will be 0. + */ + order = compound_order(compound_head(page)); + if (PageHWPoison(page)) { put_page(page); continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 15af3da5af02..d5f3a62887cf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1777,6 +1777,10 @@ static void drain_local_stock(struct work_struct *dummy) struct memcg_stock_pcp *stock; unsigned long flags; + /* + * The only protection from memory hotplug vs. drain_stock races is + * that we always operate on local CPU stock here with IRQ disabled + */ local_irq_save(flags); stock = this_cpu_ptr(&memcg_stock); @@ -1821,27 +1825,33 @@ static void drain_all_stock(struct mem_cgroup *root_memcg) /* If someone's already draining, avoid adding running more workers. */ if (!mutex_trylock(&percpu_charge_mutex)) return; - /* Notify other cpus that system-wide "drain" is running */ - get_online_cpus(); + /* + * Notify other cpus that system-wide "drain" is running + * We do not care about races with the cpu hotplug because cpu down + * as well as workers from this path always operate on the local + * per-cpu data. CPU up doesn't touch memcg_stock at all. + */ curcpu = get_cpu(); for_each_online_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); struct mem_cgroup *memcg; memcg = stock->cached; - if (!memcg || !stock->nr_pages) + if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css)) continue; - if (!mem_cgroup_is_descendant(memcg, root_memcg)) + if (!mem_cgroup_is_descendant(memcg, root_memcg)) { + css_put(&memcg->css); continue; + } if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) { if (cpu == curcpu) drain_local_stock(&stock->work); else schedule_work_on(cpu, &stock->work); } + css_put(&memcg->css); } put_cpu(); - put_online_cpus(); mutex_unlock(&percpu_charge_mutex); } @@ -5648,7 +5658,8 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page); + VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) && + !PageHWPoison(page) , page); if (!page->mem_cgroup) return; diff --git a/mm/memory.c b/mm/memory.c index ec4e15494901..a728bed16c20 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -845,7 +845,7 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr, * vm_normal_page() so that we do not have to special case all * call site of vm_normal_page(). */ - if (likely(pfn < highest_memmap_pfn)) { + if (likely(pfn <= highest_memmap_pfn)) { struct page *page = pfn_to_page(pfn); if (is_device_public_page(page)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e882cb6da994..d4b5f29906b9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -328,6 +328,7 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn, if (err && (err != -EEXIST)) break; err = 0; + cond_resched(); } vmemmap_populate_print_last(); out: @@ -337,7 +338,7 @@ EXPORT_SYMBOL_GPL(__add_pages); #ifdef CONFIG_MEMORY_HOTREMOVE /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ -static int find_smallest_section_pfn(int nid, struct zone *zone, +static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { @@ -362,7 +363,7 @@ static int find_smallest_section_pfn(int nid, struct zone *zone, } /* find the biggest valid pfn in the range [start_pfn, end_pfn). */ -static int find_biggest_section_pfn(int nid, struct zone *zone, +static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, unsigned long end_pfn) { @@ -550,7 +551,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms, return ret; scn_nr = __section_nr(ms); - start_pfn = section_nr_to_pfn(scn_nr); + start_pfn = section_nr_to_pfn((unsigned long)scn_nr); __remove_zone(zone, start_pfn); sparse_remove_one_section(zone, ms, map_offset); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 99736e026712..dee0f75c3013 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -40,6 +40,7 @@ #include <linux/ratelimit.h> #include <linux/kthread.h> #include <linux/init.h> +#include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" @@ -495,6 +496,21 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) } /* + * If the mm has notifiers then we would need to invalidate them around + * unmap_page_range and that is risky because notifiers can sleep and + * what they do is basically undeterministic. So let's have a short + * sleep to give the oom victim some more time. + * TODO: we really want to get rid of this ugly hack and make sure that + * notifiers cannot block for unbounded amount of time and add + * mmu_notifier_invalidate_range_{start,end} around unmap_page_range + */ + if (mm_has_notifiers(mm)) { + up_read(&mm->mmap_sem); + schedule_timeout_idle(HZ); + goto unlock_oom; + } + + /* * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't * work on the mm anymore. The check for MMF_OOM_SKIP must run * under mmap_sem for reading because it serializes against the diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c841af88836a..77e4d3c5c57b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1190,7 +1190,7 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone, } #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT -static void init_reserved_page(unsigned long pfn) +static void __meminit init_reserved_page(unsigned long pfn) { pg_data_t *pgdat; int nid, zid; @@ -5367,6 +5367,7 @@ not_early: __init_single_page(page, pfn, zone, nid); set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); } else { __init_single_pfn(pfn, zone, nid); } diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 6bb4deb12e78..d908c8769b48 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -14,7 +14,7 @@ #include <linux/uaccess.h> #include <asm/sections.h> -const int rodata_test_data = 0xC3; +static const int rodata_test_data = 0xC3; void rodata_test(void) { diff --git a/mm/slab_common.c b/mm/slab_common.c index 904a83be82de..80164599ca5d 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -165,9 +165,9 @@ static int init_memcg_params(struct kmem_cache *s, if (!memcg_nr_cache_ids) return 0; - arr = kzalloc(sizeof(struct memcg_cache_array) + - memcg_nr_cache_ids * sizeof(void *), - GFP_KERNEL); + arr = kvzalloc(sizeof(struct memcg_cache_array) + + memcg_nr_cache_ids * sizeof(void *), + GFP_KERNEL); if (!arr) return -ENOMEM; @@ -178,15 +178,23 @@ static int init_memcg_params(struct kmem_cache *s, static void destroy_memcg_params(struct kmem_cache *s) { if (is_root_cache(s)) - kfree(rcu_access_pointer(s->memcg_params.memcg_caches)); + kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); +} + +static void free_memcg_params(struct rcu_head *rcu) +{ + struct memcg_cache_array *old; + + old = container_of(rcu, struct memcg_cache_array, rcu); + kvfree(old); } static int update_memcg_params(struct kmem_cache *s, int new_array_size) { struct memcg_cache_array *old, *new; - new = kzalloc(sizeof(struct memcg_cache_array) + - new_array_size * sizeof(void *), GFP_KERNEL); + new = kvzalloc(sizeof(struct memcg_cache_array) + + new_array_size * sizeof(void *), GFP_KERNEL); if (!new) return -ENOMEM; @@ -198,7 +206,7 @@ static int update_memcg_params(struct kmem_cache *s, int new_array_size) rcu_assign_pointer(s->memcg_params.memcg_caches, new); if (old) - kfree_rcu(old, rcu); + call_rcu(&old->rcu, free_memcg_params); return 0; } diff --git a/mm/swap.c b/mm/swap.c index 9295ae960d66..a77d68f2c1b6 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -575,7 +575,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, void *arg) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageUnevictable(page)) { + !PageSwapCache(page) && !PageUnevictable(page)) { bool active = PageActive(page); del_page_from_lru_list(page, lruvec, @@ -665,7 +665,7 @@ void deactivate_file_page(struct page *page) void mark_page_lazyfree(struct page *page) { if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && - !PageUnevictable(page)) { + !PageSwapCache(page) && !PageUnevictable(page)) { struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); get_page(page); diff --git a/mm/swap_state.c b/mm/swap_state.c index 71ce2d1ccbf7..ed91091d1e68 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -242,6 +242,17 @@ int add_to_swap(struct page *page) * clear SWAP_HAS_CACHE flag. */ goto fail; + /* + * Normally the page will be dirtied in unmap because its pte should be + * dirty. A special case is MADV_FREE page. The page'e pte could have + * dirty bit cleared but the page's SwapBacked bit is still set because + * clearing the dirty bit and SwapBacked bit has no lock protected. For + * such page, unmap will not set dirty bit for it, so page reclaim will + * not write the page out. This can cause data corruption when the page + * is swap in later. Always setting the dirty bit for the page solves + * the problem. + */ + set_page_dirty(page); return 1; diff --git a/mm/z3fold.c b/mm/z3fold.c index 486550df32be..b2ba2ba585f3 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -250,6 +250,7 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked) WARN_ON(!list_empty(&zhdr->buddy)); set_bit(PAGE_STALE, &page->private); + clear_bit(NEEDS_COMPACTING, &page->private); spin_lock(&pool->lock); if (!list_empty(&page->lru)) list_del(&page->lru); @@ -303,7 +304,6 @@ static void free_pages_work(struct work_struct *w) list_del(&zhdr->buddy); if (WARN_ON(!test_bit(PAGE_STALE, &page->private))) continue; - clear_bit(NEEDS_COMPACTING, &page->private); spin_unlock(&pool->stale_lock); cancel_work_sync(&zhdr->work); free_z3fold_page(page); @@ -624,10 +624,8 @@ lookup: * stale pages list. cancel_work_sync() can sleep so we must make * sure it won't be called in case we're in atomic context. */ - if (zhdr && (can_sleep || !work_pending(&zhdr->work) || - !unlikely(work_busy(&zhdr->work)))) { + if (zhdr && (can_sleep || !work_pending(&zhdr->work))) { list_del(&zhdr->buddy); - clear_bit(NEEDS_COMPACTING, &page->private); spin_unlock(&pool->stale_lock); if (can_sleep) cancel_work_sync(&zhdr->work); @@ -875,16 +873,18 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) goto next; } next: + spin_lock(&pool->lock); if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { + spin_unlock(&pool->lock); free_z3fold_page(page); return 0; } } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { atomic64_dec(&pool->pages_nr); + spin_unlock(&pool->lock); return 0; } - spin_lock(&pool->lock); /* * Add to the beginning of LRU. diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index dd2c262aebbf..8b80bac055e4 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -6390,7 +6390,7 @@ sub process { exit(0); } - if (!$is_patch && $file !~ /cover-letter\.patch$/) { + if (!$is_patch && $filename !~ /cover-letter\.patch$/) { ERROR("NOT_UNIFIED_DIFF", "Does not appear to be a unified-diff format patch\n"); } diff --git a/scripts/spelling.txt b/scripts/spelling.txt index 400ef35169c5..aa0cc49ad1ad 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -53,6 +53,7 @@ acumulator||accumulator adapater||adapter addional||additional additionaly||additionally +additonal||additional addres||address adddress||address addreses||addresses @@ -67,6 +68,8 @@ adviced||advised afecting||affecting againt||against agaist||against +aggreataon||aggregation +aggreation||aggregation albumns||albums alegorical||allegorical algined||aligned @@ -80,6 +83,8 @@ aligment||alignment alignement||alignment allign||align alligned||aligned +alllocate||allocate +alloated||allocated allocatote||allocate allocatrd||allocated allocte||allocate @@ -171,6 +176,7 @@ availale||available availavility||availability availble||available availiable||available +availible||available avalable||available avaliable||available aysnc||async @@ -203,6 +209,7 @@ broadcat||broadcast cacluated||calculated caculation||calculation calender||calendar +calescing||coalescing calle||called callibration||calibration calucate||calculate @@ -210,6 +217,7 @@ calulate||calculate cancelation||cancellation cancle||cancel capabilites||capabilities +capabilty||capability capabitilies||capabilities capatibilities||capabilities capapbilities||capabilities @@ -302,6 +310,7 @@ containts||contains contaisn||contains contant||contact contence||contents +continious||continuous continous||continuous continously||continuously continueing||continuing @@ -393,6 +402,7 @@ differrence||difference diffrent||different diffrentiate||differentiate difinition||definition +dimesions||dimensions diplay||display direectly||directly disassocation||disassociation @@ -449,6 +459,7 @@ equiped||equipped equivelant||equivalent equivilant||equivalent eror||error +errorr||error estbalishment||establishment etsablishment||establishment etsbalishment||establishment @@ -481,6 +492,7 @@ failied||failed faillure||failure failue||failure failuer||failure +failng||failing faireness||fairness falied||failed faliure||failure @@ -493,6 +505,7 @@ fetaure||feature fetaures||features fileystem||filesystem fimware||firmware +firware||firmware finanize||finalize findn||find finilizes||finalizes @@ -502,6 +515,7 @@ folloing||following followign||following followings||following follwing||following +fonud||found forseeable||foreseeable forse||force fortan||fortran @@ -532,6 +546,7 @@ grabing||grabbing grahical||graphical grahpical||graphical grapic||graphic +grranted||granted guage||gauge guarenteed||guaranteed guarentee||guarantee @@ -543,6 +558,7 @@ happend||happened harware||hardware heirarchically||hierarchically helpfull||helpful +hybernate||hibernate hierachy||hierarchy hierarchie||hierarchy howver||however @@ -565,16 +581,19 @@ implemenation||implementation implementaiton||implementation implementated||implemented implemention||implementation +implementd||implemented implemetation||implementation implemntation||implementation implentation||implementation implmentation||implementation implmenting||implementing +incative||inactive incomming||incoming incompatabilities||incompatibilities incompatable||incompatible inconsistant||inconsistent increas||increase +incremeted||incremented incrment||increment indendation||indentation indended||intended @@ -619,6 +638,7 @@ interger||integer intermittant||intermittent internel||internal interoprability||interoperability +interuupt||interrupt interrface||interface interrrupt||interrupt interrup||interrupt @@ -638,8 +658,10 @@ intrrupt||interrupt intterrupt||interrupt intuative||intuitive invaid||invalid +invald||invalid invalde||invalid invalide||invalid +invalidiate||invalidate invalud||invalid invididual||individual invokation||invocation @@ -713,6 +735,7 @@ misformed||malformed mispelled||misspelled mispelt||misspelt mising||missing +mismactch||mismatch missmanaged||mismanaged missmatch||mismatch miximum||maximum @@ -731,6 +754,7 @@ multidimensionnal||multidimensional multple||multiple mumber||number muticast||multicast +mutilcast||multicast mutiple||multiple mutli||multi nams||names @@ -834,6 +858,7 @@ posible||possible positon||position possibilites||possibilities powerfull||powerful +preample||preamble preapre||prepare preceeded||preceded preceeding||preceding @@ -1059,6 +1084,7 @@ sturcture||structure subdirectoires||subdirectories suble||subtle substract||subtract +submition||submission succesfully||successfully succesful||successful successed||succeeded @@ -1078,6 +1104,7 @@ suppoted||supported suppported||supported suppport||support supress||suppress +surpressed||suppressed surpresses||suppresses susbsystem||subsystem suspeneded||suspended @@ -1091,6 +1118,7 @@ swithced||switched swithcing||switching swithed||switched swithing||switching +swtich||switch symetric||symmetric synax||syntax synchonized||synchronized @@ -1111,7 +1139,9 @@ therfore||therefore thier||their threds||threads threshhold||threshold +thresold||threshold throught||through +troughput||throughput thses||these tiggered||triggered tipically||typically @@ -1120,6 +1150,7 @@ tmis||this torerable||tolerable tramsmitted||transmitted tramsmit||transmit +tranasction||transaction tranfer||transfer transciever||transceiver transferd||transferred @@ -1133,6 +1164,7 @@ trasmission||transmission treshold||threshold trigerring||triggering trun||turn +tunning||tuning ture||true tyep||type udpate||update @@ -1199,6 +1231,7 @@ visiters||visitors vitual||virtual wakeus||wakeups wating||waiting +wiat||wait wether||whether whataver||whatever whcih||which |