diff options
28 files changed, 283 insertions, 111 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 557a3ed..b4ca955 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4411,6 +4411,7 @@ K: fmc_d.*register FPGA MANAGER FRAMEWORK M: Alan Tull <atull@opensource.altera.com> +R: Moritz Fischer <moritz.fischer@ettus.com> S: Maintained F: drivers/fpga/ F: include/linux/fpga/fpga-mgr.h @@ -7904,6 +7905,18 @@ S: Maintained F: net/openvswitch/ F: include/uapi/linux/openvswitch.h +OPERATING PERFORMANCE POINTS (OPP) +M: Viresh Kumar <vireshk@kernel.org> +M: Nishanth Menon <nm@ti.com> +M: Stephen Boyd <sboyd@codeaurora.org> +L: linux-pm@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git +F: drivers/base/power/opp/ +F: include/linux/pm_opp.h +F: Documentation/power/opp.txt +F: Documentation/devicetree/bindings/opp/ + OPL4 DRIVER M: Clemens Ladisch <clemens@ladisch.de> L: alsa-devel@alsa-project.org (moderated for non-subscribers) diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c index 35759a9..e8f8472 100644 --- a/drivers/media/pci/cx23885/cx23885-core.c +++ b/drivers/media/pci/cx23885/cx23885-core.c @@ -1992,9 +1992,9 @@ static int cx23885_initdev(struct pci_dev *pci_dev, (unsigned long long)pci_resource_start(pci_dev, 0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + err = pci_set_dma_mask(pci_dev, 0xffffffff); + if (err) { printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail_context; } diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c index dbc695f..0042803 100644 --- a/drivers/media/pci/cx25821/cx25821-core.c +++ b/drivers/media/pci/cx25821/cx25821-core.c @@ -1319,7 +1319,8 @@ static int cx25821_initdev(struct pci_dev *pci_dev, dev->pci_lat, (unsigned long long)dev->base_io_addr); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + err = pci_set_dma_mask(pci_dev, 0xffffffff); + if (err) { pr_err("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); err = -EIO; goto fail_irq; diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c index 0ed1b65..1b5268f 100644 --- a/drivers/media/pci/cx88/cx88-alsa.c +++ b/drivers/media/pci/cx88/cx88-alsa.c @@ -890,9 +890,9 @@ static int snd_cx88_create(struct snd_card *card, struct pci_dev *pci, return err; } - if (!pci_set_dma_mask(pci,DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci,DMA_BIT_MASK(32)); + if (err) { dprintk(0, "%s/1: Oops: no 32bit PCI DMA ???\n",core->name); - err = -EIO; cx88_core_put(core, pci); return err; } diff --git a/drivers/media/pci/cx88/cx88-mpeg.c b/drivers/media/pci/cx88/cx88-mpeg.c index 9db7767..f34c229 100644 --- a/drivers/media/pci/cx88/cx88-mpeg.c +++ b/drivers/media/pci/cx88/cx88-mpeg.c @@ -393,7 +393,8 @@ static int cx8802_init_common(struct cx8802_dev *dev) if (pci_enable_device(dev->pci)) return -EIO; pci_set_master(dev->pci); - if (!pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(dev->pci,DMA_BIT_MASK(32)); + if (err) { printk("%s/2: Oops: no 32bit PCI DMA ???\n",dev->core->name); return -EIO; } diff --git a/drivers/media/pci/cx88/cx88-video.c b/drivers/media/pci/cx88/cx88-video.c index 0de1ad5..aef9acf 100644 --- a/drivers/media/pci/cx88/cx88-video.c +++ b/drivers/media/pci/cx88/cx88-video.c @@ -1314,9 +1314,9 @@ static int cx8800_initdev(struct pci_dev *pci_dev, dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci_dev,DMA_BIT_MASK(32)); + if (err) { printk("%s/0: Oops: no 32bit PCI DMA ???\n",core->name); - err = -EIO; goto fail_core; } dev->alloc_ctx = vb2_dma_sg_init_ctx(&pci_dev->dev); diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c index 60b2d46..3fdbd81 100644 --- a/drivers/media/pci/netup_unidvb/netup_unidvb_core.c +++ b/drivers/media/pci/netup_unidvb/netup_unidvb_core.c @@ -810,7 +810,7 @@ static int netup_unidvb_initdev(struct pci_dev *pci_dev, "%s(): board vendor 0x%x, revision 0x%x\n", __func__, board_vendor, board_revision); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + if (pci_set_dma_mask(pci_dev, 0xffffffff) < 0) { dev_err(&pci_dev->dev, "%s(): 32bit PCI DMA is not supported\n", __func__); goto pci_detect_err; diff --git a/drivers/media/pci/saa7134/saa7134-core.c b/drivers/media/pci/saa7134/saa7134-core.c index e79d63e..f720cea 100644 --- a/drivers/media/pci/saa7134/saa7134-core.c +++ b/drivers/media/pci/saa7134/saa7134-core.c @@ -951,9 +951,9 @@ static int saa7134_initdev(struct pci_dev *pci_dev, pci_name(pci_dev), dev->pci_rev, pci_dev->irq, dev->pci_lat,(unsigned long long)pci_resource_start(pci_dev,0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); + if (err) { pr_warn("%s: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail1; } diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c index 8f36b48..8bbd092 100644 --- a/drivers/media/pci/saa7164/saa7164-core.c +++ b/drivers/media/pci/saa7164/saa7164-core.c @@ -1264,9 +1264,9 @@ static int saa7164_initdev(struct pci_dev *pci_dev, pci_set_master(pci_dev); /* TODO */ - if (!pci_set_dma_mask(pci_dev, 0xffffffff)) { + err = pci_set_dma_mask(pci_dev, 0xffffffff); + if (err) { printk("%s/0: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail_irq; } diff --git a/drivers/media/pci/tw68/tw68-core.c b/drivers/media/pci/tw68/tw68-core.c index 8c5655d..4e77618 100644 --- a/drivers/media/pci/tw68/tw68-core.c +++ b/drivers/media/pci/tw68/tw68-core.c @@ -257,9 +257,9 @@ static int tw68_initdev(struct pci_dev *pci_dev, dev->name, pci_name(pci_dev), dev->pci_rev, pci_dev->irq, dev->pci_lat, (u64)pci_resource_start(pci_dev, 0)); pci_set_master(pci_dev); - if (!pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32))) { + err = pci_set_dma_mask(pci_dev, DMA_BIT_MASK(32)); + if (err) { pr_info("%s: Oops: no 32bit PCI DMA ???\n", dev->name); - err = -EIO; goto fail1; } diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index e2afabf..7ccebae 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1500,10 +1500,11 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) return -ENODEV; } - if (!pci_set_dma_mask(pdev, PCNET32_DMA_MASK)) { + err = pci_set_dma_mask(pdev, PCNET32_DMA_MASK); + if (err) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("architecture does not support 32bit PCI busmaster DMA\n"); - return -ENODEV; + return err; } if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) { if (pcnet32_debug & NETIF_MSG_PROBE) diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index c81ce7f..a7a1b21 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1636,6 +1636,116 @@ const struct file_operations configfs_dir_operations = { .iterate = configfs_readdir, }; +/** + * configfs_register_group - creates a parent-child relation between two groups + * @parent_group: parent group + * @group: child group + * + * link groups, creates dentry for the child and attaches it to the + * parent dentry. + * + * Return: 0 on success, negative errno code on error + */ +int configfs_register_group(struct config_group *parent_group, + struct config_group *group) +{ + struct configfs_subsystem *subsys = parent_group->cg_subsys; + struct dentry *parent; + int ret; + + mutex_lock(&subsys->su_mutex); + link_group(parent_group, group); + mutex_unlock(&subsys->su_mutex); + + parent = parent_group->cg_item.ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + ret = create_default_group(parent_group, group); + if (!ret) { + spin_lock(&configfs_dirent_lock); + configfs_dir_set_ready(group->cg_item.ci_dentry->d_fsdata); + spin_unlock(&configfs_dirent_lock); + } + mutex_unlock(&d_inode(parent)->i_mutex); + return ret; +} +EXPORT_SYMBOL(configfs_register_group); + +/** + * configfs_unregister_group() - unregisters a child group from its parent + * @group: parent group to be unregistered + * + * Undoes configfs_register_group() + */ +void configfs_unregister_group(struct config_group *group) +{ + struct configfs_subsystem *subsys = group->cg_subsys; + struct dentry *dentry = group->cg_item.ci_dentry; + struct dentry *parent = group->cg_item.ci_parent->ci_dentry; + + mutex_lock_nested(&d_inode(parent)->i_mutex, I_MUTEX_PARENT); + spin_lock(&configfs_dirent_lock); + configfs_detach_prep(dentry, NULL); + spin_unlock(&configfs_dirent_lock); + + configfs_detach_group(&group->cg_item); + d_inode(dentry)->i_flags |= S_DEAD; + dont_mount(dentry); + d_delete(dentry); + mutex_unlock(&d_inode(parent)->i_mutex); + + dput(dentry); + + mutex_lock(&subsys->su_mutex); + unlink_group(group); + mutex_unlock(&subsys->su_mutex); +} +EXPORT_SYMBOL(configfs_unregister_group); + +/** + * configfs_register_default_group() - allocates and registers a child group + * @parent_group: parent group + * @name: child group name + * @item_type: child item type description + * + * boilerplate to allocate and register a child group with its parent. We need + * kzalloc'ed memory because child's default_group is initially empty. + * + * Return: allocated config group or ERR_PTR() on error + */ +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type) +{ + int ret; + struct config_group *group; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + config_group_init_type_name(group, name, item_type); + + ret = configfs_register_group(parent_group, group); + if (ret) { + kfree(group); + return ERR_PTR(ret); + } + return group; +} +EXPORT_SYMBOL(configfs_register_default_group); + +/** + * configfs_unregister_default_group() - unregisters and frees a child group + * @group: the group to act on + */ +void configfs_unregister_default_group(struct config_group *group) +{ + configfs_unregister_group(group); + kfree(group); +} +EXPORT_SYMBOL(configfs_unregister_default_group); + int configfs_register_subsystem(struct configfs_subsystem *subsys) { int err; diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 4afc4d9..8b2127f 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -610,9 +610,9 @@ parse_record: int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); if (status < 0) { - ctx->pos = cpos; + bh = NULL; ret = status; - goto out; + goto end_of_dir; } else if (status == PARSE_INVALID) goto record_end; else if (status == PARSE_NOT_LONGNAME) @@ -654,8 +654,9 @@ parse_record: fill_len = short_len; start_filldir: - if (!fake_offset) - ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + if (fake_offset && ctx->pos < 2) + ctx->pos = 2; if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) { if (!dir_emit_dot(file, ctx)) @@ -681,14 +682,19 @@ record_end: fake_offset = 0; ctx->pos = cpos; goto get_new; + end_of_dir: - ctx->pos = cpos; + if (fake_offset && cpos < 2) + ctx->pos = 2; + else + ctx->pos = cpos; fill_failed: brelse(bh); if (unicode) __putname(unicode); out: mutex_unlock(&sbi->s_lock); + return ret; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 316adb9..de4bdfa 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -332,12 +332,17 @@ static void remove_huge_page(struct page *page) * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserv - * maps and global counts. + * maps and global counts. Page faults can not race with truncation + * in this routine. hugetlb_no_page() prevents page faults in the + * truncated range. It checks i_size before allocation, and again after + * with the page table lock for the page held. The same lock must be + * acquired to unmap a page. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserv map * deleted. The region/reserv map for ranges without associated - * pages are not modified. + * pages are not modified. Page faults can race with hole punch. + * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ @@ -361,46 +366,37 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, next = start; while (next < end) { /* - * Make sure to never grab more pages that we - * might possibly need. + * Don't grab more pages than the number left in the range. */ if (end - next < lookup_nr) lookup_nr = end - next; /* - * This pagevec_lookup() may return pages past 'end', - * so we must check for page->index > end. + * When no more pages are found, we are done. */ - if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) { - if (next == start) - break; - next = start; - continue; - } + if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) + break; for (i = 0; i < pagevec_count(&pvec); ++i) { struct page *page = pvec.pages[i]; u32 hash; + /* + * The page (index) could be beyond end. This is + * only possible in the punch hole case as end is + * max page offset in the truncate case. + */ + next = page->index; + if (next >= end) + break; + hash = hugetlb_fault_mutex_hash(h, current->mm, &pseudo_vma, mapping, next, 0); mutex_lock(&hugetlb_fault_mutex_table[hash]); lock_page(page); - if (page->index >= end) { - unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); - next = end; /* we are done */ - break; - } - - /* - * If page is mapped, it was faulted in after being - * unmapped. Do nothing in this race case. In the - * normal case page is not mapped. - */ - if (!page_mapped(page)) { + if (likely(!page_mapped(page))) { bool rsv_on_error = !PagePrivate(page); /* * We must free the huge page and remove @@ -421,17 +417,23 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, hugetlb_fix_reserve_counts( inode, rsv_on_error); } + } else { + /* + * If page is mapped, it was faulted in after + * being unmapped. It indicates a race between + * hole punch and page fault. Do nothing in + * this case. Getting here in a truncate + * operation is a bug. + */ + BUG_ON(truncate_op); } - if (page->index > next) - next = page->index; - - ++next; unlock_page(page); - mutex_unlock(&hugetlb_fault_mutex_table[hash]); } + ++next; huge_pagevec_release(&pvec); + cond_resched(); } if (truncate_op) @@ -647,9 +649,6 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode->i_ctime = CURRENT_TIME; - spin_lock(&inode->i_lock); - inode->i_private = NULL; - spin_unlock(&inode->i_lock); out: mutex_unlock(&inode->i_mutex); return error; diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 79b1130..0a3f9b5 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -525,6 +525,8 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg switch (rqdata.cmd) { case NCP_LOCK_EX: case NCP_LOCK_SH: + if (rqdata.timeout < 0) + return -EINVAL; if (rqdata.timeout == 0) rqdata.timeout = NCP_LOCK_DEFAULT_TIMEOUT; else if (rqdata.timeout > NCP_LOCK_MAX_TIMEOUT) diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 3b48ac2..a03f6f4 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -372,6 +372,8 @@ static int ocfs2_mknod(struct inode *dir, mlog_errno(status); goto leave; } + /* update inode->i_mode after mask with "umask". */ + inode->i_mode = mode; handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb, S_ISDIR(mode), diff --git a/include/linux/configfs.h b/include/linux/configfs.h index a8a335b..758a029 100644 --- a/include/linux/configfs.h +++ b/include/linux/configfs.h @@ -197,6 +197,16 @@ static inline struct configfs_subsystem *to_configfs_subsystem(struct config_gro int configfs_register_subsystem(struct configfs_subsystem *subsys); void configfs_unregister_subsystem(struct configfs_subsystem *subsys); +int configfs_register_group(struct config_group *parent_group, + struct config_group *group); +void configfs_unregister_group(struct config_group *group); + +struct config_group * +configfs_register_default_group(struct config_group *parent_group, + const char *name, + struct config_item_type *item_type); +void configfs_unregister_default_group(struct config_group *group); + /* These functions can sleep and can alloc with GFP_KERNEL */ /* WARNING: These cannot be called underneath configfs callbacks!! */ int configfs_depend_item(struct configfs_subsystem *subsys, struct config_item *target); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6523109..8942af0 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -271,7 +271,7 @@ static inline int gfpflags_to_migratetype(const gfp_t gfp_flags) static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags) { - return gfp_flags & __GFP_DIRECT_RECLAIM; + return (bool __force)(gfp_flags & __GFP_DIRECT_RECLAIM); } #ifdef CONFIG_HIGHMEM diff --git a/include/linux/signal.h b/include/linux/signal.h index ab1e039..92557bb 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -239,7 +239,6 @@ extern int sigprocmask(int, sigset_t *, sigset_t *); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; -extern int sigsuspend(sigset_t *); struct sigaction { #ifndef __ARCH_HAS_IRIX_SIGACTION diff --git a/include/linux/slab.h b/include/linux/slab.h index 7c82e3b..9694077 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -158,6 +158,24 @@ size_t ksize(const void *); #endif /* + * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. + * Intended for arches that get misalignment faults even for 64 bit integer + * aligned buffers. + */ +#ifndef ARCH_SLAB_MINALIGN +#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) +#endif + +/* + * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned + * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN + * aligned pointers. + */ +#define __assume_kmalloc_alignment __assume_aligned(ARCH_KMALLOC_MINALIGN) +#define __assume_slab_alignment __assume_aligned(ARCH_SLAB_MINALIGN) +#define __assume_page_alignment __assume_aligned(PAGE_SIZE) + +/* * Kmalloc array related definitions */ @@ -286,8 +304,8 @@ static __always_inline int kmalloc_index(size_t size) } #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags); -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags); +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment; +void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment; void kmem_cache_free(struct kmem_cache *, void *); /* @@ -301,8 +319,8 @@ void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); bool kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node); -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node); +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment; +void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -316,12 +334,12 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t); +extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment; #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size); + int node, size_t size) __assume_slab_alignment; #else static __always_inline void * kmem_cache_alloc_node_trace(struct kmem_cache *s, @@ -354,10 +372,10 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order); +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment; #else static __always_inline void * kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) @@ -482,15 +500,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) return __kmalloc_node(size, flags, node); } -/* - * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment. - * Intended for arches that get misalignment faults even for 64 bit integer - * aligned buffers. - */ -#ifndef ARCH_SLAB_MINALIGN -#define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) -#endif - struct memcg_cache_array { struct rcu_head rcu; struct kmem_cache *entries[0]; diff --git a/kernel/panic.c b/kernel/panic.c index 4579dbb..4b150bc 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -152,8 +152,11 @@ void panic(const char *fmt, ...) * We may have ended up stopping the CPU holding the lock (in * smp_send_stop()) while still having some valuable data in the console * buffer. Try to acquire the lock then release it regardless of the - * result. The release will also print the buffers out. + * result. The release will also print the buffers out. Locks debug + * should be disabled to avoid reporting bad unlock balance when + * panic() is not being callled from OOPS. */ + debug_locks_off(); console_trylock(); console_unlock(); diff --git a/kernel/signal.c b/kernel/signal.c index c0b01fe..f3f1f7a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3503,7 +3503,7 @@ SYSCALL_DEFINE0(pause) #endif -int sigsuspend(sigset_t *set) +static int sigsuspend(sigset_t *set) { current->saved_sigmask = current->blocked; set_current_blocked(set); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c29ddeb..62fe06b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2009,7 +2009,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) + if (*vm_flags & VM_NO_THP) return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; @@ -2025,7 +2025,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_NOHUGEPAGE | VM_NO_THP)) + if (*vm_flags & VM_NO_THP) return -EINVAL; *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index d41b21b..bc0a8d8 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -19,6 +19,7 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/kmemleak.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/mm.h> @@ -444,6 +445,7 @@ int kasan_module_alloc(void *addr, size_t size) if (ret) { find_vm_area(addr)->flags |= VM_KASAN; + kmemleak_ignore(ret); return 0; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2c90357..3e4d654 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1542,7 +1542,9 @@ static void balance_dirty_pages(struct address_space *mapping, for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; - unsigned long m_dirty, m_thresh, m_bg_thresh; + unsigned long m_dirty = 0; /* stop bogus uninit warnings */ + unsigned long m_thresh = 0; + unsigned long m_bg_thresh = 0; /* * Unstable writes are a feature of certain networked @@ -1204,7 +1204,7 @@ unsigned long kmem_cache_flags(unsigned long object_size, return flags; } -#else +#else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} @@ -2295,23 +2295,15 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * And if we were unable to get a new slab from the partial slab lists then * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. + * + * Version of __slab_alloc to use when we know that interrupts are + * already disabled (which is the case for bulk allocation). */ -static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void *freelist; struct page *page; - unsigned long flags; - - local_irq_save(flags); -#ifdef CONFIG_PREEMPT - /* - * We may have been preempted and rescheduled on a different - * cpu before disabling interrupts. Need to reload cpu area - * pointer. - */ - c = this_cpu_ptr(s->cpu_slab); -#endif page = c->page; if (!page) @@ -2369,7 +2361,6 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); - local_irq_restore(flags); return freelist; new_slab: @@ -2386,7 +2377,6 @@ new_slab: if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); return NULL; } @@ -2402,11 +2392,35 @@ new_slab: deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); return freelist; } /* + * Another one that disabled interrupt and compensates for possible + * cpu changes by refetching the per cpu area pointer. + */ +static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) +{ + void *p; + unsigned long flags; + + local_irq_save(flags); +#ifdef CONFIG_PREEMPT + /* + * We may have been preempted and rescheduled on a different + * cpu before disabling interrupts. Need to reload cpu area + * pointer. + */ + c = this_cpu_ptr(s->cpu_slab); +#endif + + p = ___slab_alloc(s, gfpflags, node, addr, c); + local_irq_restore(flags); + return p; +} + +/* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. @@ -2804,30 +2818,23 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void *object = c->freelist; if (unlikely(!object)) { - local_irq_enable(); /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist */ - p[i] = __slab_alloc(s, flags, NUMA_NO_NODE, + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_, c); - if (unlikely(!p[i])) { - __kmem_cache_free_bulk(s, i, p); - return false; - } - local_irq_disable(); + if (unlikely(!p[i])) + goto error; + c = this_cpu_ptr(s->cpu_slab); continue; /* goto for-loop */ } /* kmem_cache debug support */ s = slab_pre_alloc_hook(s, flags); - if (unlikely(!s)) { - __kmem_cache_free_bulk(s, i, p); - c->tid = next_tid(c->tid); - local_irq_enable(); - return false; - } + if (unlikely(!s)) + goto error; c->freelist = get_freepointer(s, object); p[i] = object; @@ -2847,6 +2854,11 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, } return true; + +error: + __kmem_cache_free_bulk(s, i, p); + local_irq_enable(); + return false; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d045634..8e3c9c5 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1443,7 +1443,6 @@ struct vm_struct *remove_vm_area(const void *addr) vmap_debug_free_range(va->va_start, va->va_end); kasan_free_shadow(vm); free_unmap_vmap_area(va); - vm->size -= PAGE_SIZE; return vm; } @@ -1468,8 +1467,8 @@ static void __vunmap(const void *addr, int deallocate_pages) return; } - debug_check_no_locks_freed(addr, area->size); - debug_check_no_obj_freed(addr, area->size); + debug_check_no_locks_freed(addr, get_vm_area_size(area)); + debug_check_no_obj_freed(addr, get_vm_area_size(area)); if (deallocate_pages) { int i; diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index bcf5ec7..5a60162 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -128,6 +128,7 @@ static const char * const page_flag_names[] = { [KPF_THP] = "t:thp", [KPF_BALLOON] = "o:balloon", [KPF_ZERO_PAGE] = "z:zero_page", + [KPF_IDLE] = "i:idle_page", [KPF_RESERVED] = "r:reserved", [KPF_MLOCKED] = "m:mlocked", |