From 68f23b89067fdf187763e75a56087550624fdbee Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Thu, 30 Jan 2020 22:11:04 -0800 Subject: memcg: fix a crash in wb_workfn when a device disappears Without memcg, there is a one-to-one mapping between the bdi and bdi_writeback structures. In this world, things are fairly straightforward; the first thing bdi_unregister() does is to shutdown the bdi_writeback structure (or wb), and part of that writeback ensures that no other work queued against the wb, and that the wb is fully drained. With memcg, however, there is a one-to-many relationship between the bdi and bdi_writeback structures; that is, there are multiple wb objects which can all point to a single bdi. There is a refcount which prevents the bdi object from being released (and hence, unregistered). So in theory, the bdi_unregister() *should* only get called once its refcount goes to zero (bdi_put will drop the refcount, and when it is zero, release_bdi gets called, which calls bdi_unregister). Unfortunately, del_gendisk() in block/gen_hd.c never got the memo about the Brave New memcg World, and calls bdi_unregister directly. It does this without informing the file system, or the memcg code, or anything else. This causes the root wb associated with the bdi to be unregistered, but none of the memcg-specific wb's are shutdown. So when one of these wb's are woken up to do delayed work, they try to dereference their wb->bdi->dev to fetch the device name, but unfortunately bdi->dev is now NULL, thanks to the bdi_unregister() called by del_gendisk(). As a result, *boom*. Fortunately, it looks like the rest of the writeback path is perfectly happy with bdi->dev and bdi->owner being NULL, so the simplest fix is to create a bdi_dev_name() function which can handle bdi->dev being NULL. This also allows us to bulletproof the writeback tracepoints to prevent them from dereferencing a NULL pointer and crashing the kernel if one is tracing with memcg's enabled, and an iSCSI device dies or a USB storage stick is pulled. The most common way of triggering this will be hotremoval of a device while writeback with memcg enabled is going on. It was triggering several times a day in a heavily loaded production environment. Google Bug Id: 145475544 Link: https://lore.kernel.org/r/20191227194829.150110-1-tytso@mit.edu Link: http://lkml.kernel.org/r/20191228005211.163952-1-tytso@mit.edu Signed-off-by: Theodore Ts'o Cc: Chris Mason Cc: Tejun Heo Cc: Jens Axboe Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 10 ++++++++++ include/trace/events/writeback.h | 37 +++++++++++++++++-------------------- 2 files changed, 27 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 97967ce06de3..f88197c1ffc2 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -504,4 +505,13 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } +extern const char *bdi_unknown_name; + +static inline const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return dev_name(bdi->dev); +} + #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index ef50be4e5e6c..d94def25e4dc 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -67,8 +67,8 @@ DECLARE_EVENT_CLASS(writeback_page_template, TP_fast_assign( strscpy_pad(__entry->name, - mapping ? dev_name(inode_to_bdi(mapping->host)->dev) : "(unknown)", - 32); + bdi_dev_name(mapping ? inode_to_bdi(mapping->host) : + NULL), 32); __entry->ino = mapping ? mapping->host->i_ino : 0; __entry->index = page->index; ), @@ -111,8 +111,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, struct backing_dev_info *bdi = inode_to_bdi(inode); /* may be called for files on pseudo FSes w/ unregistered bdi */ - strscpy_pad(__entry->name, - bdi->dev ? dev_name(bdi->dev) : "(unknown)", 32); + strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->flags = flags; @@ -193,7 +192,7 @@ TRACE_EVENT(inode_foreign_history, ), TP_fast_assign( - strncpy(__entry->name, dev_name(inode_to_bdi(inode)->dev), 32); + strncpy(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); __entry->history = history; @@ -222,7 +221,7 @@ TRACE_EVENT(inode_switch_wbs, ), TP_fast_assign( - strncpy(__entry->name, dev_name(old_wb->bdi->dev), 32); + strncpy(__entry->name, bdi_dev_name(old_wb->bdi), 32); __entry->ino = inode->i_ino; __entry->old_cgroup_ino = __trace_wb_assign_cgroup(old_wb); __entry->new_cgroup_ino = __trace_wb_assign_cgroup(new_wb); @@ -255,7 +254,7 @@ TRACE_EVENT(track_foreign_dirty, struct address_space *mapping = page_mapping(page); struct inode *inode = mapping ? mapping->host : NULL; - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->bdi_id = wb->bdi->id; __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; @@ -288,7 +287,7 @@ TRACE_EVENT(flush_foreign, ), TP_fast_assign( - strncpy(__entry->name, dev_name(wb->bdi->dev), 32); + strncpy(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); __entry->frn_bdi_id = frn_bdi_id; __entry->frn_memcg_id = frn_memcg_id; @@ -318,7 +317,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template, TP_fast_assign( strscpy_pad(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->sync_mode = wbc->sync_mode; __entry->cgroup_ino = __trace_wbc_assign_cgroup(wbc); @@ -361,9 +360,7 @@ DECLARE_EVENT_CLASS(writeback_work_class, __field(ino_t, cgroup_ino) ), TP_fast_assign( - strscpy_pad(__entry->name, - wb->bdi->dev ? dev_name(wb->bdi->dev) : - "(unknown)", 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->nr_pages = work->nr_pages; __entry->sb_dev = work->sb ? work->sb->s_dev : 0; __entry->sync_mode = work->sync_mode; @@ -416,7 +413,7 @@ DECLARE_EVENT_CLASS(writeback_class, __field(ino_t, cgroup_ino) ), TP_fast_assign( - strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); ), TP_printk("bdi %s: cgroup_ino=%lu", @@ -438,7 +435,7 @@ TRACE_EVENT(writeback_bdi_register, __array(char, name, 32) ), TP_fast_assign( - strscpy_pad(__entry->name, dev_name(bdi->dev), 32); + strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); ), TP_printk("bdi %s", __entry->name @@ -463,7 +460,7 @@ DECLARE_EVENT_CLASS(wbc_class, ), TP_fast_assign( - strscpy_pad(__entry->name, dev_name(bdi->dev), 32); + strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->nr_to_write = wbc->nr_to_write; __entry->pages_skipped = wbc->pages_skipped; __entry->sync_mode = wbc->sync_mode; @@ -514,7 +511,7 @@ TRACE_EVENT(writeback_queue_io, ), TP_fast_assign( unsigned long *older_than_this = work->older_than_this; - strscpy_pad(__entry->name, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); __entry->older = older_than_this ? *older_than_this : 0; __entry->age = older_than_this ? (jiffies - *older_than_this) * 1000 / HZ : -1; @@ -600,7 +597,7 @@ TRACE_EVENT(bdi_dirty_ratelimit, ), TP_fast_assign( - strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->write_bw = KBps(wb->write_bandwidth); __entry->avg_write_bw = KBps(wb->avg_write_bandwidth); __entry->dirty_rate = KBps(dirty_rate); @@ -665,7 +662,7 @@ TRACE_EVENT(balance_dirty_pages, TP_fast_assign( unsigned long freerun = (thresh + bg_thresh) / 2; - strscpy_pad(__entry->bdi, dev_name(wb->bdi->dev), 32); + strscpy_pad(__entry->bdi, bdi_dev_name(wb->bdi), 32); __entry->limit = global_wb_domain.dirty_limit; __entry->setpoint = (global_wb_domain.dirty_limit + @@ -726,7 +723,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue, TP_fast_assign( strscpy_pad(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; @@ -800,7 +797,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_fast_assign( strscpy_pad(__entry->name, - dev_name(inode_to_bdi(inode)->dev), 32); + bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; __entry->state = inode->i_state; __entry->dirtied_when = inode->dirtied_when; -- cgit v1.2.3 From dd3e7cba16274831f5a69f071ed3cf13ffb352ea Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Jan 2020 22:11:47 -0800 Subject: ocfs2/dlm: move BITS_TO_BYTES() to bitops.h for wider use There are users already and will be more of BITS_TO_BYTES() macro. Move it to bitops.h for wider use. In the case of ocfs2 the replacement is identical. As for bnx2x, there are two places where floor version is used. In the first case to calculate the amount of structures that can fit one memory page. In this case obviously the ceiling variant is correct and original code might have a potential bug, if amount of bits % 8 is not 0. In the second case the macro is used to calculate bytes transmitted in one microsecond. This will work for all speeds which is multiply of 1Gbps without any change, for the rest new code will give ceiling value, for instance 100Mbps will give 13 bytes, while old code gives 12 bytes and the arithmetically correct one is 12.5 bytes. Further the value is used to setup timer threshold which in any case has its own margins due to certain resolution. I don't see here an issue with slightly shifting thresholds for low speed connections, the card is supposed to utilize highest available rate, which is usually 10Gbps. Link: http://lkml.kernel.org/r/20200108121316.22411-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Joseph Qi Acked-by: Sudarsana Reddy Kalluru Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: Changwei Ge Cc: Gang He Cc: Jun Piao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index e479067c202c..6c7c4133c25c 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -13,6 +13,7 @@ #define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE) #define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long)) +#define BITS_TO_BYTES(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(char)) extern unsigned int __sw_hweight8(unsigned int w); extern unsigned int __sw_hweight16(unsigned int w); -- cgit v1.2.3 From ddf8f376d137ba41ca67347a0b80ba0c357a1018 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Thu, 30 Jan 2020 22:12:07 -0800 Subject: mm/filemap.c: clean up filemap_write_and_wait() At some point filemap_write_and_wait() and filemap_write_and_wait_range() got the exact same implementation with the exception of the range being specified in *_range() Similar to other functions in fs.h which call *_range(..., 0, LLONG_MAX), change filemap_write_and_wait() to be a static inline which calls filemap_write_and_wait_range() Link: http://lkml.kernel.org/r/20191129160713.30892-1-ira.weiny@intel.com Signed-off-by: Ira Weiny Reviewed-by: Nikolay Borisov Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/fs.h b/include/linux/fs.h index 40be2ccb87f3..41584f50af0d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2737,7 +2737,6 @@ static inline int filemap_fdatawait(struct address_space *mapping) extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); -extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); extern int __filemap_fdatawrite_range(struct address_space *mapping, @@ -2747,6 +2746,11 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_check_errors(struct address_space *mapping); extern void __filemap_set_wb_err(struct address_space *mapping, int err); +static inline int filemap_write_and_wait(struct address_space *mapping) +{ + return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); +} + extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, loff_t lend); extern int __must_check file_check_and_advance_wb_err(struct file *file); -- cgit v1.2.3 From 07d8026995287c2a2f03e28c69cdd8152fa69107 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 30 Jan 2020 22:12:28 -0800 Subject: mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An upcoming patch changes and complicates the refcounting and especially the "put page" aspects of it. In order to keep everything clean, refactor the devmap page release routines: * Rename put_devmap_managed_page() to page_is_devmap_managed(), and limit the functionality to "read only": return a bool, with no side effects. * Add a new routine, put_devmap_managed_page(), to handle decrementing the refcount for ZONE_DEVICE pages. * Change callers (just release_pages() and put_page()) to check page_is_devmap_managed() before calling the new put_devmap_managed_page() routine. This is a performance point: put_page() is a hot path, so we need to avoid non- inline function calls where possible. * Rename __put_devmap_managed_page() to free_devmap_managed_page(), and limit the functionality to unconditionally freeing a devmap page. This is originally based on a separate patch by Ira Weiny, which applied to an early version of the put_user_page() experiments. Since then, Jérôme Glisse suggested the refactoring described above. Link: http://lkml.kernel.org/r/20200107224558.2362728-5-jhubbard@nvidia.com Signed-off-by: Ira Weiny Signed-off-by: John Hubbard Suggested-by: Jérôme Glisse Reviewed-by: Dan Williams Reviewed-by: Jan Kara Cc: Christoph Hellwig Cc: Kirill A. Shutemov Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Björn Töpel Cc: Daniel Vetter Cc: Hans Verkuil Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Jonathan Corbet Cc: Leon Romanovsky Cc: Mauro Carvalho Chehab Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1233bf45164d..3b88618e361a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -947,9 +947,10 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void __put_devmap_managed_page(struct page *page); +void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool put_devmap_managed_page(struct page *page) + +static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; @@ -958,7 +959,6 @@ static inline bool put_devmap_managed_page(struct page *page) switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: - __put_devmap_managed_page(page); return true; default: break; @@ -966,11 +966,17 @@ static inline bool put_devmap_managed_page(struct page *page) return false; } +void put_devmap_managed_page(struct page *page); + #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool put_devmap_managed_page(struct page *page) +static inline bool page_is_devmap_managed(struct page *page) { return false; } + +static inline void put_devmap_managed_page(struct page *page) +{ +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) @@ -1023,8 +1029,10 @@ static inline void put_page(struct page *page) * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (put_devmap_managed_page(page)) + if (page_is_devmap_managed(page)) { + put_devmap_managed_page(page); return; + } if (put_page_testzero(page)) __put_page(page); -- cgit v1.2.3 From eddb1c228f7951d399240a0cc57455dccc7f8777 Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 30 Jan 2020 22:12:54 -0800 Subject: mm/gup: introduce pin_user_pages*() and FOLL_PIN MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce pin_user_pages*() variations of get_user_pages*() calls, and also pin_longterm_pages*() variations. For now, these are placeholder calls, until the various call sites are converted to use the correct get_user_pages*() or pin_user_pages*() API. These variants will eventually all set FOLL_PIN, which is also introduced, and thoroughly documented. pin_user_pages() pin_user_pages_remote() pin_user_pages_fast() All pages that are pinned via the above calls, must be unpinned via put_user_page(). The underlying rules are: * FOLL_PIN is a gup-internal flag, so the call sites should not directly set it. That behavior is enforced with assertions. * Call sites that want to indicate that they are going to do DirectIO ("DIO") or something with similar characteristics, should call a get_user_pages()-like wrapper call that sets FOLL_PIN. These wrappers will: * Start with "pin_user_pages" instead of "get_user_pages". That makes it easy to find and audit the call sites. * Set FOLL_PIN * For pages that are received via FOLL_PIN, those pages must be returned via put_user_page(). Thanks to Jan Kara and Vlastimil Babka for explaining the 4 cases in this documentation. (I've reworded it and expanded upon it.) Link: http://lkml.kernel.org/r/20200107224558.2362728-12-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Jan Kara Reviewed-by: Mike Rapoport [Documentation] Reviewed-by: Jérôme Glisse Cc: Jonathan Corbet Cc: Ira Weiny Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Björn Töpel Cc: Christoph Hellwig Cc: Daniel Vetter Cc: Dan Williams Cc: Hans Verkuil Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Kirill A. Shutemov Cc: Leon Romanovsky Cc: Mauro Carvalho Chehab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 63 +++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 50 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3b88618e361a..79ca557349c6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1042,16 +1042,14 @@ static inline void put_page(struct page *page) * put_user_page() - release a gup-pinned page * @page: pointer to page to be released * - * Pages that were pinned via get_user_pages*() must be released via - * either put_user_page(), or one of the put_user_pages*() routines - * below. This is so that eventually, pages that are pinned via - * get_user_pages*() can be separately tracked and uniquely handled. In - * particular, interactions with RDMA and filesystems need special - * handling. + * Pages that were pinned via pin_user_pages*() must be released via either + * put_user_page(), or one of the put_user_pages*() routines. This is so that + * eventually such pages can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special handling. * * put_user_page() and put_page() are not interchangeable, despite this early * implementation that makes them look the same. put_user_page() calls must - * be perfectly matched up with get_user_page() calls. + * be perfectly matched up with pin*() calls. */ static inline void put_user_page(struct page *page) { @@ -1509,9 +1507,16 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1519,6 +1524,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, @@ -2583,13 +2590,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ +#define FOLL_PIN 0x40000 /* pages must be released via put_user_page() */ /* - * NOTE on FOLL_LONGTERM: + * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each + * other. Here is what they mean, and how to use them: * * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is contrasted with - * iov_iter_get_pages() where usages which are transient. + * period _often_ under userspace control. This is in contrast to + * iov_iter_get_pages(), whose usages are transient. * * FIXME: For pages which are part of a filesystem, mappings are subject to the * lifetime enforced by the filesystem and we need guarantees that longterm @@ -2604,11 +2613,39 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * Currently only get_user_pages() and get_user_pages_fast() support this flag * and calls to get_user_pages_[un]locked are specifically not allowed. This * is due to an incompatibility with the FS DAX check and - * FAULT_FLAG_ALLOW_RETRY + * FAULT_FLAG_ALLOW_RETRY. * - * In the CMA case: longterm pins in a CMA region would unnecessarily fragment - * that region. And so CMA attempts to migrate the page before pinning when + * In the CMA case: long term pins in a CMA region would unnecessarily fragment + * that region. And so, CMA attempts to migrate the page before pinning, when * FOLL_LONGTERM is specified. + * + * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, + * but an additional pin counting system) will be invoked. This is intended for + * anything that gets a page reference and then touches page data (for example, + * Direct IO). This lets the filesystem know that some non-file-system entity is + * potentially changing the pages' data. In contrast to FOLL_GET (whose pages + * are released via put_page()), FOLL_PIN pages must be released, ultimately, by + * a call to put_user_page(). + * + * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different + * and separate refcounting mechanisms, however, and that means that each has + * its own acquire and release mechanisms: + * + * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. + * + * FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release. + * + * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. + * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based + * calls applied to them, and that's perfectly OK. This is a constraint on the + * callers, not on the pages.) + * + * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never + * directly by the caller. That's in order to help avoid mismatches when + * releasing pages: get_user_pages*() pages must be released via put_page(), + * while pin_user_pages*() pages must be released via put_user_page(). + * + * Please see Documentation/vm/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) -- cgit v1.2.3 From f1f6a7dd9b53aafd81b696b9017036e7b08e57ea Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Thu, 30 Jan 2020 22:13:35 -0800 Subject: mm, tree-wide: rename put_user_page*() to unpin_user_page*() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In order to provide a clearer, more symmetric API for pinning and unpinning DMA pages. This way, pin_user_pages*() calls match up with unpin_user_pages*() calls, and the API is a lot closer to being self-explanatory. Link: http://lkml.kernel.org/r/20200107224558.2362728-23-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Jan Kara Cc: Alex Williamson Cc: Aneesh Kumar K.V Cc: Björn Töpel Cc: Christoph Hellwig Cc: Daniel Vetter Cc: Dan Williams Cc: Hans Verkuil Cc: Ira Weiny Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: Jens Axboe Cc: Jerome Glisse Cc: Jonathan Corbet Cc: Kirill A. Shutemov Cc: Leon Romanovsky Cc: Mauro Carvalho Chehab Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index 79ca557349c6..fc543eb45de1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1039,27 +1039,27 @@ static inline void put_page(struct page *page) } /** - * put_user_page() - release a gup-pinned page + * unpin_user_page() - release a gup-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either - * put_user_page(), or one of the put_user_pages*() routines. This is so that - * eventually such pages can be separately tracked and uniquely handled. In + * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so + * that eventually such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. * - * put_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. put_user_page() calls must + * unpin_user_page() and put_page() are not interchangeable, despite this early + * implementation that makes them look the same. unpin_user_page() calls must * be perfectly matched up with pin*() calls. */ -static inline void put_user_page(struct page *page) +static inline void unpin_user_page(struct page *page) { put_page(page); } -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages, - bool make_dirty); +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty); -void put_user_pages(struct page **pages, unsigned long npages); +void unpin_user_pages(struct page **pages, unsigned long npages); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS @@ -2590,7 +2590,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_ANON 0x8000 /* don't do file mappings */ #define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ #define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ -#define FOLL_PIN 0x40000 /* pages must be released via put_user_page() */ +#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ /* * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each @@ -2625,7 +2625,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * Direct IO). This lets the filesystem know that some non-file-system entity is * potentially changing the pages' data. In contrast to FOLL_GET (whose pages * are released via put_page()), FOLL_PIN pages must be released, ultimately, by - * a call to put_user_page(). + * a call to unpin_user_page(). * * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different * and separate refcounting mechanisms, however, and that means that each has @@ -2633,7 +2633,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. * - * FOLL_PIN: pin_user_pages*() to acquire, and put_user_pages to release. + * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. * * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based @@ -2643,7 +2643,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never * directly by the caller. That's in order to help avoid mismatches when * releasing pages: get_user_pages*() pages must be released via put_page(), - * while pin_user_pages*() pages must be released via put_user_page(). + * while pin_user_pages*() pages must be released via unpin_user_page(). * * Please see Documentation/vm/pin_user_pages.rst for more information. */ -- cgit v1.2.3 From 7e168b9babab254c3f9a6c7ed100faee73d493f8 Mon Sep 17 00:00:00 2001 From: Junyong Sun Date: Thu, 30 Jan 2020 22:13:48 -0800 Subject: mm, tracing: print symbol name for kmem_alloc_node call_site events Print the call_site ip of kmem_alloc_node using '%pS' to improve the readability of raw slab trace points. Link: http://lkml.kernel.org/r/1577949568-4518-1-git-send-email-sunjunyong@xiaomi.com Signed-off-by: Junyong Sun Acked-by: Steven Rostedt (VMware) Cc: Ingo Molnar Cc: Joel Fernandes (Google) Cc: Changbin Du Cc: Tim Murray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/kmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index ad7e642bd497..f65b1f6db22d 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -88,8 +88,8 @@ DECLARE_EVENT_CLASS(kmem_alloc_node, __entry->node = node; ), - TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d", - __entry->call_site, + TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d", + (void *)__entry->call_site, __entry->ptr, __entry->bytes_req, __entry->bytes_alloc, -- cgit v1.2.3 From 3f9903b9ca5e981b5862d7b10086d0e8caa20298 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:01 -0800 Subject: mm: remove the memory isolate notifier Luckily, we have no users left, so we can get rid of it. Cleanup set_migratetype_isolate() a little bit. Link: http://lkml.kernel.org/r/20191114131911.11783-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Greg Kroah-Hartman Acked-by: Michal Hocko Cc: "Rafael J. Wysocki" Cc: Pavel Tatashin Cc: Dan Williams Cc: Oscar Salvador Cc: Qian Cai Cc: Anshuman Khandual Cc: Pingfan Liu Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 27 --------------------------- 1 file changed, 27 deletions(-) (limited to 'include') diff --git a/include/linux/memory.h b/include/linux/memory.h index 4c75dae8dd29..de6bccb28f07 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -55,19 +55,6 @@ struct memory_notify { int status_change_nid; }; -/* - * During pageblock isolation, count the number of pages within the - * range [start_pfn, start_pfn + nr_pages) which are owned by code - * in the notifier chain. - */ -#define MEM_ISOLATE_COUNT (1<<0) - -struct memory_isolate_notify { - unsigned long start_pfn; /* Start of range to check */ - unsigned int nr_pages; /* # pages in range to check */ - unsigned int pages_found; /* # pages owned found by callbacks */ -}; - struct notifier_block; struct mem_section; @@ -94,27 +81,13 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -static inline int register_memory_isolate_notifier(struct notifier_block *nb) -{ - return 0; -} -static inline void unregister_memory_isolate_notifier(struct notifier_block *nb) -{ -} -static inline int memory_isolate_notify(unsigned long val, void *v) -{ - return 0; -} #else extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); -extern int register_memory_isolate_notifier(struct notifier_block *nb); -extern void unregister_memory_isolate_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size); void remove_memory_block_devices(unsigned long start, unsigned long size); extern void memory_dev_init(void); extern int memory_notify(unsigned long val, void *v); -extern int memory_isolate_notify(unsigned long val, void *v); extern struct memory_block *find_memory_block(struct mem_section *); typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, -- cgit v1.2.3 From fe4c86c916d9151113372369f322e7436167e6f3 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:04 -0800 Subject: mm: remove "count" parameter from has_unmovable_pages() Now that the memory isolate notifier is gone, the parameter is always 0. Drop it and cleanup has_unmovable_pages(). Link: http://lkml.kernel.org/r/20191114131911.11783-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Michal Hocko Cc: Oscar Salvador Cc: Anshuman Khandual Cc: Qian Cai Cc: Pingfan Liu Cc: Stephen Rothwell Cc: Dan Williams Cc: Pavel Tatashin Cc: Vlastimil Babka Cc: Mel Gorman Cc: Mike Rapoport Cc: Wei Yang Cc: Alexander Duyck Cc: Alexander Potapenko Cc: Arun KS Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-isolation.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 6861df759fad..148e65a9c606 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -bool has_unmovable_pages(struct zone *zone, struct page *page, int count, - int migratetype, int flags); +bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, + int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -- cgit v1.2.3 From 02634a44b8aba2d4f16ea09d3c17400d9320327e Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 30 Jan 2020 22:14:20 -0800 Subject: mm/memblock: define memblock_physmem_add() On the s390 platform memblock.physmem array is being built by directly calling into memblock_add_range() which is a low level function not intended to be used outside of memblock. Hence lets conditionally add helper functions for physmem array when HAVE_MEMBLOCK_PHYS_MAP is enabled. Also use MAX_NUMNODES instead of 0 as node ID similar to memblock_add() and memblock_reserve(). Make memblock_add_range() a static function as it is no longer getting used outside of memblock. Link: http://lkml.kernel.org/r/1578283835-21969-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Mike Rapoport Acked-by: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Martin Schwidefsky Cc: Collin Walling Cc: Gerald Schaefer Cc: Philipp Rudo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b38bbefabfab..079d17d96410 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -113,6 +113,9 @@ int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +int memblock_physmem_add(phys_addr_t base, phys_addr_t size); +#endif void memblock_trim_memory(phys_addr_t align); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); @@ -127,10 +130,6 @@ void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); /* Low level functions */ -int memblock_add_range(struct memblock_type *type, - phys_addr_t base, phys_addr_t size, - int nid, enum memblock_flags flags); - void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_a, struct memblock_type *type_b, phys_addr_t *out_start, -- cgit v1.2.3 From bd5c2344f9eb1ebf7ff2501ddb13d83151939780 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 30 Jan 2020 22:14:54 -0800 Subject: mm/memory_hotplug: pass in nid to online_pages() Patch series "mm/memory_hotplug: pass in nid to online_pages()". Simplify onlining code and get rid of find_memory_block(). Pass in the nid from the memory block we are trying to online directly, instead of manually looking it up. This patch (of 2): No need to lookup the memory block, we can directly pass in the nid. Link: http://lkml.kernel.org/r/20200113113354.6341-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Andrew Morton Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Michal Hocko Cc: Oscar Salvador Cc: Anshuman Khandual Cc: Dan Williams Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index ba0dca6aac6e..ffa6ad12d84a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -94,7 +94,8 @@ extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); /* VM interface that may be used by firmware interface */ -extern int online_pages(unsigned long, unsigned long, int); +extern int online_pages(unsigned long pfn, unsigned long nr_pages, + int online_type, int nid); extern int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, unsigned long *valid_start, unsigned long *valid_end); extern unsigned long __offline_isolated_pages(unsigned long start_pfn, -- cgit v1.2.3 From 4a55c0474a92d5c418bcbbe122368de0910aeac2 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Thu, 30 Jan 2020 22:14:57 -0800 Subject: mm/hotplug: silence a lockdep splat with printk() It is not that hard to trigger lockdep splats by calling printk from under zone->lock. Most of them are false positives caused by lock chains introduced early in the boot process and they do not cause any real problems (although most of the early boot lock dependencies could happen after boot as well). There are some console drivers which do allocate from the printk context as well and those should be fixed. In any case, false positives are not that trivial to workaround and it is far from optimal to lose lockdep functionality for something that is a non-issue. So change has_unmovable_pages() so that it no longer calls dump_page() itself - instead it returns a "struct page *" of the unmovable page back to the caller so that in the case of a has_unmovable_pages() failure, the caller can call dump_page() after releasing zone->lock. Also, make dump_page() is able to report a CMA page as well, so the reason string from has_unmovable_pages() can be removed. Even though has_unmovable_pages doesn't hold any reference to the returned page this should be reasonably safe for the purpose of reporting the page (dump_page) because it cannot be hotremoved in the context of memory unplug. The state of the page might change but that is the case even with the existing code as zone->lock only plays role for free pages. While at it, remove a similar but unnecessary debug-only printk() as well. A sample of one of those lockdep splats is, WARNING: possible circular locking dependency detected ------------------------------------------------------ test.sh/8653 is trying to acquire lock: ffffffff865a4460 (console_owner){-.-.}, at: console_unlock+0x207/0x750 but task is already holding lock: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 (&(&zone->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock+0x2f/0x40 rmqueue_bulk.constprop.21+0xb6/0x1160 get_page_from_freelist+0x898/0x22c0 __alloc_pages_nodemask+0x2f3/0x1cd0 alloc_pages_current+0x9c/0x110 allocate_slab+0x4c6/0x19c0 new_slab+0x46/0x70 ___slab_alloc+0x58b/0x960 __slab_alloc+0x43/0x70 __kmalloc+0x3ad/0x4b0 __tty_buffer_request_room+0x100/0x250 tty_insert_flip_string_fixed_flag+0x67/0x110 pty_write+0xa2/0xf0 n_tty_write+0x36b/0x7b0 tty_write+0x284/0x4c0 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 redirected_tty_write+0x6a/0xc0 do_iter_write+0x248/0x2a0 vfs_writev+0x106/0x1e0 do_writev+0xd4/0x180 __x64_sys_writev+0x45/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #2 (&(&port->lock)->rlock){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 tty_port_tty_get+0x20/0x60 tty_port_default_wakeup+0xf/0x30 tty_port_tty_wakeup+0x39/0x40 uart_write_wakeup+0x2a/0x40 serial8250_tx_chars+0x22e/0x440 serial8250_handle_irq.part.8+0x14a/0x170 serial8250_default_handle_irq+0x5c/0x90 serial8250_interrupt+0xa6/0x130 __handle_irq_event_percpu+0x78/0x4f0 handle_irq_event_percpu+0x70/0x100 handle_irq_event+0x5a/0x8b handle_edge_irq+0x117/0x370 do_IRQ+0x9e/0x1e0 ret_from_intr+0x0/0x2a cpuidle_enter_state+0x156/0x8e0 cpuidle_enter+0x41/0x70 call_cpuidle+0x5e/0x90 do_idle+0x333/0x370 cpu_startup_entry+0x1d/0x1f start_secondary+0x290/0x330 secondary_startup_64+0xb6/0xc0 -> #1 (&port_lock_key){-.-.}: __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 _raw_spin_lock_irqsave+0x3a/0x50 serial8250_console_write+0x3e4/0x450 univ8250_console_write+0x4b/0x60 console_unlock+0x501/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 -> #0 (console_owner){-.-.}: check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Chain exists of: console_owner --> &(&port->lock)->rlock --> &(&zone->lock)->rlock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&zone->lock)->rlock); lock(&(&port->lock)->rlock); lock(&(&zone->lock)->rlock); lock(console_owner); *** DEADLOCK *** 9 locks held by test.sh/8653: #0: ffff88839ba7d408 (sb_writers#4){.+.+}, at: vfs_write+0x25f/0x290 #1: ffff888277618880 (&of->mutex){+.+.}, at: kernfs_fop_write+0x128/0x240 #2: ffff8898131fc218 (kn->count#115){.+.+}, at: kernfs_fop_write+0x138/0x240 #3: ffffffff86962a80 (device_hotplug_lock){+.+.}, at: lock_device_hotplug_sysfs+0x16/0x50 #4: ffff8884374f4990 (&dev->mutex){....}, at: device_offline+0x70/0x110 #5: ffffffff86515250 (cpu_hotplug_lock.rw_sem){++++}, at: __offline_pages+0xbf/0xa10 #6: ffffffff867405f0 (mem_hotplug_lock.rw_sem){++++}, at: percpu_down_write+0x87/0x2f0 #7: ffff88883fff3c58 (&(&zone->lock)->rlock){-.-.}, at: __offline_isolated_pages+0x179/0x3e0 #8: ffffffff865a4920 (console_lock){+.+.}, at: vprintk_emit+0x100/0x340 stack backtrace: Hardware name: HPE ProLiant DL560 Gen10/ProLiant DL560 Gen10, BIOS U34 05/21/2019 Call Trace: dump_stack+0x86/0xca print_circular_bug.cold.31+0x243/0x26e check_noncircular+0x29e/0x2e0 check_prev_add+0x107/0xea0 validate_chain+0x8fc/0x1200 __lock_acquire+0x5b3/0xb40 lock_acquire+0x126/0x280 console_unlock+0x269/0x750 vprintk_emit+0x10d/0x340 vprintk_default+0x1f/0x30 vprintk_func+0x44/0xd4 printk+0x9f/0xc5 __offline_isolated_pages.cold.52+0x2f/0x30a offline_isolated_pages_cb+0x17/0x30 walk_system_ram_range+0xda/0x160 __offline_pages+0x79c/0xa10 offline_pages+0x11/0x20 memory_subsys_offline+0x7e/0xc0 device_offline+0xd5/0x110 state_store+0xc6/0xe0 dev_attr_store+0x3f/0x60 sysfs_kf_write+0x89/0xb0 kernfs_fop_write+0x188/0x240 __vfs_write+0x50/0xa0 vfs_write+0x105/0x290 ksys_write+0xc6/0x160 __x64_sys_write+0x43/0x50 do_syscall_64+0xcc/0x76c entry_SYSCALL_64_after_hwframe+0x49/0xbe Link: http://lkml.kernel.org/r/20200117181200.20299-1-cai@lca.pw Signed-off-by: Qian Cai Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Sergey Senozhatsky Cc: Petr Mladek Cc: Steven Rostedt (VMware) Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-isolation.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 148e65a9c606..572458016331 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -33,8 +33,8 @@ static inline bool is_migrate_isolate(int migratetype) #define MEMORY_OFFLINE 0x1 #define REPORT_FAILURE 0x2 -bool has_unmovable_pages(struct zone *zone, struct page *page, int migratetype, - int flags); +struct page *has_unmovable_pages(struct zone *zone, struct page *page, + int migratetype, int flags); void set_pageblock_migratetype(struct page *page, int migratetype); int move_freepages_block(struct zone *zone, struct page *page, int migratetype, int *num_movable); -- cgit v1.2.3 From 26b56e116a69e70cc13976a1b0b818036f539f53 Mon Sep 17 00:00:00 2001 From: Yu Zhao Date: Thu, 30 Jan 2020 22:15:10 -0800 Subject: include/linux/mm.h: clean up obsolete check on space in page->flags The check was intended to make sure we don't overrun page flags. But it's obsolete because it doesn't include LAST_CPUPID_WIDTH nor KASAN_TAG_WIDTH. Just remove check since we already have it covered in linux/page-flags-layout.h (near the end of the file). Link: http://lkml.kernel.org/r/20191208183508.89177-1-yuzhao@google.com Signed-off-by: Yu Zhao Reviewed-by: David Hildenbrand Cc: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index fc543eb45de1..ddfc217bc026 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -916,10 +916,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) -#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS -#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS -#endif - #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) -- cgit v1.2.3 From ca023a92c8f753a78c37cc8290bd8e3c54f1a936 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Thu, 30 Jan 2020 22:15:13 -0800 Subject: include/linux/mm.h: remove dead code totalram_pages_set() totalram_pages_set() was introduced in commit ca79b0c211af ("mm: convert totalram_pages and totalhigh_pages variables to atomic"), but no one uses it. Link: http://lkml.kernel.org/r/20191218005543.24146-1-richardw.yang@linux.intel.com Signed-off-by: Wei Yang Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include') diff --git a/include/linux/mm.h b/include/linux/mm.h index ddfc217bc026..73a044ed6981 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -70,11 +70,6 @@ static inline void totalram_pages_add(long count) atomic_long_add(count, &_totalram_pages); } -static inline void totalram_pages_set(long val) -{ - atomic_long_set(&_totalram_pages, val); -} - extern void * high_memory; extern int page_cluster; -- cgit v1.2.3 From 068964541db6dbacce26e75b390e87e63ad1c100 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Thu, 30 Jan 2020 22:15:16 -0800 Subject: include/linux/memory.h: drop fields 'hw' and 'phys_callback' from struct memory_block memory_block structure elements 'hw' and 'phys_callback' are not getting used. This was originally added with commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") but never seem to have been used. Just drop them now. Link: http://lkml.kernel.org/r/1576728650-13867-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Reviewed-by: Dan Williams Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Pavel Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include') diff --git a/include/linux/memory.h b/include/linux/memory.h index de6bccb28f07..0b8d791b6669 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -29,8 +29,6 @@ struct memory_block { int section_count; /* serialized by mem_sysfs_mutex */ int online_type; /* for passing data to online routine */ int phys_device; /* to which fru does this belong? */ - void *hw; /* optional pointer to fw/hw data */ - int (*phys_callback)(struct memory_block *); struct device dev; int nid; /* NID for this memory block */ }; -- cgit v1.2.3 From 0a3c57729768e08de690ba872dd52ee9c3c11e8b Mon Sep 17 00:00:00 2001 From: Hao Lee Date: Thu, 30 Jan 2020 22:15:19 -0800 Subject: mm: fix comments related to node reclaim As zone reclaim has been replaced by node reclaim, this patch fixes related comments. Link: http://lkml.kernel.org/r/20191126141346.GA22665@haolee.github.io Signed-off-by: Hao Lee Reviewed-by: Andrew Morton Cc: Anshuman Khandual Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 2 +- include/uapi/linux/sysctl.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5334ad8fc7bd..c2bc309d1634 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -758,7 +758,7 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA /* - * zone reclaim becomes active if more unmapped pages exist. + * node reclaim becomes active if more unmapped pages exist. */ unsigned long min_unmapped_pages; unsigned long min_slab_pages; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 87aa2a6d9125..27c1ed2822e6 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -195,7 +195,7 @@ enum VM_MIN_UNMAPPED=32, /* Set min percent of unmapped pages */ VM_PANIC_ON_OOM=33, /* panic at out-of-memory */ VM_VDSO_ENABLED=34, /* map VDSO into new processes? */ - VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */ + VM_MIN_SLAB=35, /* Percent pages ignored by node reclaim */ }; -- cgit v1.2.3 From 23331e4893614deb555c65cdf115c8a28ed32471 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 30 Jan 2020 22:15:28 -0800 Subject: include/linux/units.h: add helpers for kelvin to/from Celsius conversion Patch series "add header file for kelvin to/from Celsius conversion helpers", v4. There are several helper macros to convert kelvin to/from Celsius in for thermal drivers. These are useful for any other drivers or subsystems, but it's odd to include just for the helpers. This adds a new that provides the equivalent inline functions for any drivers or subsystems, and switches all the users of conversion helpers in to use helpers. This patch (of 12): There are several helper macros to convert kelvin to/from Celsius in for thermal drivers. These are useful for any other drivers or subsystems, but it's odd to include just for the helpers. This adds a new that provides the equivalent inline functions for any drivers or subsystems. It is intended to replace the helpers in . Link: http://lkml.kernel.org/r/1576386975-7941-2-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita Reviewed-by: Andy Shevchenko Cc: Sujith Thomas Cc: Darren Hart Cc: Zhang Rui Cc: Daniel Lezcano Cc: Amit Kucheria Cc: Jean Delvare Cc: Guenter Roeck Cc: Keith Busch Cc: Jens Axboe Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Kalle Valo Cc: Stanislaw Gruszka Cc: Johannes Berg Cc: Emmanuel Grumbach Cc: Luca Coelho Cc: Jonathan Cameron Cc: Hartmut Knaack Cc: Lars-Peter Clausen Cc: Peter Meerwald-Stadler Cc: Andy Shevchenko Cc: Jonathan Cameron Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/units.h | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) create mode 100644 include/linux/units.h (limited to 'include') diff --git a/include/linux/units.h b/include/linux/units.h new file mode 100644 index 000000000000..aaf716364ec3 --- /dev/null +++ b/include/linux/units.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_UNITS_H +#define _LINUX_UNITS_H + +#include + +#define ABSOLUTE_ZERO_MILLICELSIUS -273150 + +static inline long milli_kelvin_to_millicelsius(long t) +{ + return t + ABSOLUTE_ZERO_MILLICELSIUS; +} + +static inline long millicelsius_to_milli_kelvin(long t) +{ + return t - ABSOLUTE_ZERO_MILLICELSIUS; +} + +#define MILLIDEGREE_PER_DEGREE 1000 +#define MILLIDEGREE_PER_DECIDEGREE 100 + +static inline long kelvin_to_millicelsius(long t) +{ + return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DEGREE); +} + +static inline long millicelsius_to_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE); +} + +static inline long deci_kelvin_to_celsius(long t) +{ + t = milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DEGREE); +} + +static inline long celsius_to_deci_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t * MILLIDEGREE_PER_DEGREE); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE); +} + +/** + * deci_kelvin_to_millicelsius_with_offset - convert Kelvin to Celsius + * @t: temperature value in decidegrees Kelvin + * @offset: difference between Kelvin and Celsius in millidegrees + * + * Return: temperature value in millidegrees Celsius + */ +static inline long deci_kelvin_to_millicelsius_with_offset(long t, long offset) +{ + return t * MILLIDEGREE_PER_DECIDEGREE - offset; +} + +static inline long deci_kelvin_to_millicelsius(long t) +{ + return milli_kelvin_to_millicelsius(t * MILLIDEGREE_PER_DECIDEGREE); +} + +static inline long millicelsius_to_deci_kelvin(long t) +{ + t = millicelsius_to_milli_kelvin(t); + + return DIV_ROUND_CLOSEST(t, MILLIDEGREE_PER_DECIDEGREE); +} + +static inline long kelvin_to_celsius(long t) +{ + return t + DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS, + MILLIDEGREE_PER_DEGREE); +} + +static inline long celsius_to_kelvin(long t) +{ + return t - DIV_ROUND_CLOSEST(ABSOLUTE_ZERO_MILLICELSIUS, + MILLIDEGREE_PER_DEGREE); +} + +#endif /* _LINUX_UNITS_H */ -- cgit v1.2.3 From cdf309fb38ad419aadb8f5856a088864688fad90 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Thu, 30 Jan 2020 22:15:57 -0800 Subject: thermal: remove kelvin to/from Celsius conversion helpers from This removes the kelvin to/from Celsius conversion helper macros in which were switched to the inline helper functions in . Link: http://lkml.kernel.org/r/1576386975-7941-9-git-send-email-akinobu.mita@gmail.com Signed-off-by: Akinobu Mita Reviewed-by: Andy Shevchenko Cc: Sujith Thomas Cc: Darren Hart Cc: Andy Shevchenko Cc: Zhang Rui Cc: Daniel Lezcano Cc: Amit Kucheria Cc: Jean Delvare Cc: Guenter Roeck Cc: Keith Busch Cc: Jens Axboe Cc: Christoph Hellwig Cc: Sagi Grimberg Cc: Emmanuel Grumbach Cc: Hartmut Knaack Cc: Johannes Berg Cc: Jonathan Cameron Cc: Jonathan Cameron Cc: Kalle Valo Cc: Lars-Peter Clausen Cc: Luca Coelho Cc: Peter Meerwald-Stadler Cc: Stanislaw Gruszka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thermal.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include') diff --git a/include/linux/thermal.h b/include/linux/thermal.h index d9111aebb97d..126913c6a53b 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -32,17 +32,6 @@ /* use value, which < 0K, to indicate an invalid/uninitialized temperature */ #define THERMAL_TEMP_INVALID -274000 -/* Unit conversion macros */ -#define DECI_KELVIN_TO_CELSIUS(t) ({ \ - long _t = (t); \ - ((_t-2732 >= 0) ? (_t-2732+5)/10 : (_t-2732-5)/10); \ -}) -#define CELSIUS_TO_DECI_KELVIN(t) ((t)*10+2732) -#define DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, off) (((t) - (off)) * 100) -#define DECI_KELVIN_TO_MILLICELSIUS(t) DECI_KELVIN_TO_MILLICELSIUS_WITH_OFFSET(t, 2732) -#define MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, off) (((t) / 100) + (off)) -#define MILLICELSIUS_TO_DECI_KELVIN(t) MILLICELSIUS_TO_DECI_KELVIN_WITH_OFFSET(t, 2732) - /* Default Thermal Governor */ #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE) #define DEFAULT_THERMAL_GOVERNOR "step_wise" -- cgit v1.2.3 From 803521b149c8c71a712445a32bd9316e074df76a Mon Sep 17 00:00:00 2001 From: Mikhail Zaslonko Date: Thu, 30 Jan 2020 22:16:30 -0800 Subject: lib/zlib: add zlib_deflate_dfltcc_enabled() function Add a new function to zlib.h checking if s390 Deflate-Conversion facility is installed and enabled. Link: http://lkml.kernel.org/r/20200103223334.20669-6-zaslonko@linux.ibm.com Signed-off-by: Mikhail Zaslonko Cc: Chris Mason Cc: Christian Borntraeger Cc: David Sterba Cc: Eduard Shishkin Cc: Heiko Carstens Cc: Ilya Leoshkevich Cc: Josef Bacik Cc: Richard Purdie Cc: Vasily Gorbik Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zlib.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/zlib.h b/include/linux/zlib.h index 92dbbd3f6c75..c757d848a758 100644 --- a/include/linux/zlib.h +++ b/include/linux/zlib.h @@ -191,6 +191,12 @@ extern int zlib_deflate_workspacesize (int windowBits, int memLevel); exceed those passed here. */ +extern int zlib_deflate_dfltcc_enabled (void); +/* + Returns 1 if Deflate-Conversion facility is installed and enabled, + otherwise 0. +*/ + /* extern int deflateInit (z_streamp strm, int level); -- cgit v1.2.3 From d5767057c9a76a29f073dad66b7fa12a90e8c748 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Thu, 30 Jan 2020 22:16:40 -0800 Subject: uapi: rename ext2_swab() to swab() and share globally in swab.h ext2_swab() is defined locally in lib/find_bit.c However it is not specific to ext2, neither to bitmaps. There are many potential users of it, so rename it to just swab() and move to include/uapi/linux/swab.h ABI guarantees that size of unsigned long corresponds to BITS_PER_LONG, therefore drop unneeded cast. Link: http://lkml.kernel.org/r/20200103202846.21616-1-yury.norov@gmail.com Signed-off-by: Yury Norov Cc: Allison Randal Cc: Joe Perches Cc: Thomas Gleixner Cc: William Breathitt Gray Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swab.h | 1 + include/uapi/linux/swab.h | 10 ++++++++++ 2 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/linux/swab.h b/include/linux/swab.h index e466fd159c85..bcff5149861a 100644 --- a/include/linux/swab.h +++ b/include/linux/swab.h @@ -7,6 +7,7 @@ # define swab16 __swab16 # define swab32 __swab32 # define swab64 __swab64 +# define swab __swab # define swahw32 __swahw32 # define swahb32 __swahb32 # define swab16p __swab16p diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 23cd84868cc3..fa7f97da5b76 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -4,6 +4,7 @@ #include #include +#include #include /* @@ -132,6 +133,15 @@ static inline __attribute_const__ __u32 __fswahb32(__u32 val) __fswab64(x)) #endif +static __always_inline unsigned long __swab(const unsigned long y) +{ +#if BITS_PER_LONG == 64 + return __swab64(y); +#else /* BITS_PER_LONG == 32 */ + return __swab32(y); +#endif +} + /** * __swahw32 - return a word-swapped 32-bit value * @x: value to wordswap -- cgit v1.2.3 From 2b755626cad6d9dcbad09d022ba7bdfc39ed773d Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Jan 2020 22:17:32 -0800 Subject: include/linux/io-mapping.h-mapping: use PHYS_PFN() macro in io_mapping_map_atomic_wc() Use PHYS_PFN() macro in io_mapping_map_atomic_wc() instead of open coded variant. Link: http://lkml.kernel.org/r/20191209165624.56351-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io-mapping.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index 6e125e9b4187..837058bc1c9f 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -28,6 +28,7 @@ struct io_mapping { #ifdef CONFIG_HAVE_ATOMIC_IOMAP +#include #include /* * For small address space machines, mapping large objects @@ -64,12 +65,10 @@ io_mapping_map_atomic_wc(struct io_mapping *mapping, unsigned long offset) { resource_size_t phys_addr; - unsigned long pfn; BUG_ON(offset >= mapping->size); phys_addr = mapping->base + offset; - pfn = (unsigned long) (phys_addr >> PAGE_SHIFT); - return iomap_atomic_prot_pfn(pfn, mapping->prot); + return iomap_atomic_prot_pfn(PHYS_PFN(phys_addr), mapping->prot); } static inline void -- cgit v1.2.3