From b80d5ccca3a012e91ca64a2a0b13049163a6a698 Mon Sep 17 00:00:00 2001 From: Haiyan Hu Date: Tue, 10 Sep 2013 11:25:37 +0800 Subject: NVMe: Avoid shift operation when writing cq head doorbell Changes the type of dev->db_stride to unsigned and changes the value stored there to be 1 << the current value. Then there is less calculation to be done at completion time. Signed-off-by: Haiyan Hu Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 26ebcf41c213..8119a476cb29 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -80,7 +80,7 @@ struct nvme_dev { struct dma_pool *prp_small_pool; int instance; int queue_count; - int db_stride; + u32 db_stride; u32 ctrl_config; struct msix_entry *entry; struct nvme_bar __iomem *bar; -- cgit v1.2.3 From 4f024f3797c43cb4b73cd2c50cec728842d0e49e Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 11 Oct 2013 15:44:27 -0700 Subject: block: Abstract out bvec iterator MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Geert Uytterhoeven Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Ed L. Cashin" Cc: Nick Piggin Cc: Lars Ellenberg Cc: Jiri Kosina Cc: Matthew Wilcox Cc: Geoff Levand Cc: Yehuda Sadeh Cc: Sage Weil Cc: Alex Elder Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris Cc: Philip Kelleher Cc: Rusty Russell Cc: "Michael S. Tsirkin" Cc: Konrad Rzeszutek Wilk Cc: Jeremy Fitzhardinge Cc: Neil Brown Cc: Alasdair Kergon Cc: Mike Snitzer Cc: dm-devel@redhat.com Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux390@de.ibm.com Cc: Boaz Harrosh Cc: Benny Halevy Cc: "James E.J. Bottomley" Cc: Greg Kroah-Hartman Cc: "Nicholas A. Bellinger" Cc: Alexander Viro Cc: Chris Mason Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: Jaegeuk Kim Cc: Steven Whitehouse Cc: Dave Kleikamp Cc: Joern Engel Cc: Prasad Joshi Cc: Trond Myklebust Cc: KONISHI Ryusuke Cc: Mark Fasheh Cc: Joel Becker Cc: Ben Myers Cc: xfs@oss.sgi.com Cc: Steven Rostedt Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Len Brown Cc: Pavel Machek Cc: "Rafael J. Wysocki" Cc: Herton Ronaldo Krzesinski Cc: Ben Hutchings Cc: Andrew Morton Cc: Guo Chao Cc: Tejun Heo Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Wei Yongjun Cc: "Roger Pau MonnĂ©" Cc: Jan Beulich Cc: Stefano Stabellini Cc: Ian Campbell Cc: Sebastian Ott Cc: Christian Borntraeger Cc: Minchan Kim Cc: Jiang Liu Cc: Nitin Gupta Cc: Jerome Marchand Cc: Joe Perches Cc: Peng Tao Cc: Andy Adamson Cc: fanchaoting Cc: Jie Liu Cc: Sunil Mushran Cc: "Martin K. Petersen" Cc: Namjae Jeon Cc: Pankaj Kumar Cc: Dan Magenheimer Cc: Mel Gorman 6 --- include/linux/bio.h | 16 ++++++++-------- include/linux/blk_types.h | 19 ++++++++++++------- 2 files changed, 20 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 060ff695085c..e2e0bc642ed1 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -62,19 +62,19 @@ * on highmem page vectors */ #define bio_iovec_idx(bio, idx) (&((bio)->bi_io_vec[(idx)])) -#define bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_idx) +#define bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) #define bio_page(bio) bio_iovec((bio))->bv_page #define bio_offset(bio) bio_iovec((bio))->bv_offset -#define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_idx) -#define bio_sectors(bio) ((bio)->bi_size >> 9) -#define bio_end_sector(bio) ((bio)->bi_sector + bio_sectors((bio))) +#define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_iter.bi_idx) +#define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) +#define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio))) static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio->bi_vcnt) return bio_iovec(bio)->bv_len; else /* dataless requests such as discard */ - return bio->bi_size; + return bio->bi_iter.bi_size; } static inline void *bio_data(struct bio *bio) @@ -108,7 +108,7 @@ static inline void *bio_data(struct bio *bio) */ #define __BVEC_END(bio) bio_iovec_idx((bio), (bio)->bi_vcnt - 1) -#define __BVEC_START(bio) bio_iovec_idx((bio), (bio)->bi_idx) +#define __BVEC_START(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) /* Default implementation of BIOVEC_PHYS_MERGEABLE */ #define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ @@ -150,7 +150,7 @@ static inline void *bio_data(struct bio *bio) i++) #define bio_for_each_segment(bvl, bio, i) \ - for (i = (bio)->bi_idx; \ + for (i = (bio)->bi_iter.bi_idx; \ bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ i++) @@ -365,7 +365,7 @@ static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx, #define __bio_kunmap_irq(buf, flags) bvec_kunmap_irq(buf, flags) #define bio_kmap_irq(bio, flags) \ - __bio_kmap_irq((bio), (bio)->bi_idx, (flags)) + __bio_kmap_irq((bio), (bio)->bi_iter.bi_idx, (flags)) #define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags) /* diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 238ef0ed62f8..29b5b84d8a29 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -28,13 +28,19 @@ struct bio_vec { unsigned int bv_offset; }; +struct bvec_iter { + sector_t bi_sector; /* device address in 512 byte + sectors */ + unsigned int bi_size; /* residual I/O count */ + + unsigned int bi_idx; /* current index into bvl_vec */ +}; + /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) */ struct bio { - sector_t bi_sector; /* device address in 512 byte - sectors */ struct bio *bi_next; /* request queue link */ struct block_device *bi_bdev; unsigned long bi_flags; /* status, command, etc */ @@ -42,16 +48,13 @@ struct bio { * top bits priority */ - unsigned short bi_vcnt; /* how many bio_vec's */ - unsigned short bi_idx; /* current index into bvl_vec */ + struct bvec_iter bi_iter; /* Number of segments in this BIO after * physical address coalescing is performed. */ unsigned int bi_phys_segments; - unsigned int bi_size; /* residual I/O count */ - /* * To keep track of the max segment size, we account for the * sizes of the first and last mergeable segments in this bio. @@ -74,11 +77,13 @@ struct bio { struct bio_integrity_payload *bi_integrity; /* data integrity */ #endif + unsigned short bi_vcnt; /* how many bio_vec's */ + /* * Everything starting with bi_max_vecs will be preserved by bio_reset() */ - unsigned int bi_max_vecs; /* max bvl_vecs we can hold */ + unsigned short bi_max_vecs; /* max bvl_vecs we can hold */ atomic_t bi_cnt; /* pin count */ -- cgit v1.2.3 From a4ad39b1d10584dfcfcfb0d510faab2c7f034399 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2013 14:24:32 -0700 Subject: block: Convert bio_iovec() to bvec_iter For immutable biovecs, we'll be introducing a new bio_iovec() that uses our new bvec iterator to construct a biovec, taking into account bvec_iter->bi_bvec_done - this patch updates existing users for the new usage. Some of the existing users really do need a pointer into the bvec array - those uses are all going to be removed, but we'll need the functionality from immutable to remove them - so for now rename the existing bio_iovec() -> __bio_iovec(), and it'll be removed in a couple patches. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: "Ed L. Cashin" Cc: Alasdair Kergon Cc: dm-devel@redhat.com Cc: "James E.J. Bottomley" --- include/linux/bio.h | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index e2e0bc642ed1..9f182fcbe714 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -62,9 +62,11 @@ * on highmem page vectors */ #define bio_iovec_idx(bio, idx) (&((bio)->bi_io_vec[(idx)])) -#define bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) -#define bio_page(bio) bio_iovec((bio))->bv_page -#define bio_offset(bio) bio_iovec((bio))->bv_offset +#define __bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) +#define bio_iovec(bio) (*__bio_iovec(bio)) + +#define bio_page(bio) (bio_iovec((bio)).bv_page) +#define bio_offset(bio) (bio_iovec((bio)).bv_offset) #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_iter.bi_idx) #define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) #define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio))) @@ -72,7 +74,7 @@ static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio->bi_vcnt) - return bio_iovec(bio)->bv_len; + return bio_iovec(bio).bv_len; else /* dataless requests such as discard */ return bio->bi_iter.bi_size; } -- cgit v1.2.3 From 7988613b0e5b2638caf6cd493cc78e9595eba19c Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Nov 2013 17:19:00 -0800 Subject: block: Convert bio_for_each_segment() to bvec_iter More prep work for immutable biovecs - with immutable bvecs drivers won't be able to use the biovec directly, they'll need to use helpers that take into account bio->bi_iter.bi_bvec_done. This updates callers for the new usage without changing the implementation yet. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Geert Uytterhoeven Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "Ed L. Cashin" Cc: Nick Piggin Cc: Lars Ellenberg Cc: Jiri Kosina Cc: Paul Clements Cc: Jim Paris Cc: Geoff Levand Cc: Yehuda Sadeh Cc: Sage Weil Cc: Alex Elder Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris Cc: Philip Kelleher Cc: Konrad Rzeszutek Wilk Cc: Jeremy Fitzhardinge Cc: Neil Brown Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux390@de.ibm.com Cc: Nagalakshmi Nandigama Cc: Sreekanth Reddy Cc: support@lsi.com Cc: "James E.J. Bottomley" Cc: Greg Kroah-Hartman Cc: Alexander Viro Cc: Steven Whitehouse Cc: Herton Ronaldo Krzesinski Cc: Tejun Heo Cc: Andrew Morton Cc: Guo Chao Cc: Asai Thambi S P Cc: Selvan Mani Cc: Sam Bradshaw Cc: Matthew Wilcox Cc: Keith Busch Cc: Stephen Hemminger Cc: Quoc-Son Anh Cc: Sebastian Ott Cc: Nitin Gupta Cc: Minchan Kim Cc: Jerome Marchand Cc: Seth Jennings Cc: "Martin K. Petersen" Cc: Mike Snitzer Cc: Vivek Goyal Cc: "Darrick J. Wong" Cc: Chris Metcalf Cc: Jan Kara Cc: linux-m68k@lists.linux-m68k.org Cc: linuxppc-dev@lists.ozlabs.org Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net Cc: cbe-oss-dev@lists.ozlabs.org Cc: xen-devel@lists.xensource.com Cc: virtualization@lists.linux-foundation.org Cc: linux-raid@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: DL-MPTFusionLinux@lsi.com Cc: linux-scsi@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: linux-fsdevel@vger.kernel.org Cc: cluster-devel@redhat.com Cc: linux-mm@kvack.org Acked-by: Geoff Levand --- include/linux/bio.h | 28 ++++++++++++++-------------- include/linux/blkdev.h | 7 ++++--- 2 files changed, 18 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9f182fcbe714..c16adb5f69f8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -63,10 +63,13 @@ */ #define bio_iovec_idx(bio, idx) (&((bio)->bi_io_vec[(idx)])) #define __bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) -#define bio_iovec(bio) (*__bio_iovec(bio)) + +#define bio_iter_iovec(bio, iter) ((bio)->bi_io_vec[(iter).bi_idx]) #define bio_page(bio) (bio_iovec((bio)).bv_page) #define bio_offset(bio) (bio_iovec((bio)).bv_offset) +#define bio_iovec(bio) (*__bio_iovec(bio)) + #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_iter.bi_idx) #define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) #define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio))) @@ -133,15 +136,6 @@ static inline void *bio_data(struct bio *bio) #define bio_io_error(bio) bio_endio((bio), -EIO) -/* - * drivers should not use the __ version unless they _really_ know what - * they're doing - */ -#define __bio_for_each_segment(bvl, bio, i, start_idx) \ - for (bvl = bio_iovec_idx((bio), (start_idx)), i = (start_idx); \ - i < (bio)->bi_vcnt; \ - bvl++, i++) - /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it @@ -151,10 +145,16 @@ static inline void *bio_data(struct bio *bio) bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ i++) -#define bio_for_each_segment(bvl, bio, i) \ - for (i = (bio)->bi_iter.bi_idx; \ - bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ - i++) +#define __bio_for_each_segment(bvl, bio, iter, start) \ + for (iter = (start); \ + bvl = bio_iter_iovec((bio), (iter)), \ + (iter).bi_idx < (bio)->bi_vcnt; \ + (iter).bi_idx++) + +#define bio_for_each_segment(bvl, bio, iter) \ + __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) + +#define bio_iter_last(bio, iter) ((iter).bi_idx == (bio)->bi_vcnt - 1) /* * get a reference to a bio, so it won't disappear. the intended use is diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1b135d49b279..337b92a54658 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -735,7 +735,7 @@ struct rq_map_data { }; struct req_iterator { - int i; + struct bvec_iter iter; struct bio *bio; }; @@ -748,10 +748,11 @@ struct req_iterator { #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ - bio_for_each_segment(bvl, _iter.bio, _iter.i) + bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_iter_last(rq, _iter) \ - (_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1) + (_iter.bio->bi_next == NULL && \ + bio_iter_last(_iter.bio, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" -- cgit v1.2.3 From 4550dd6c6b062fc5e5b647296d55da22616123c3 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2013 14:26:21 -0700 Subject: block: Immutable bio vecs This adds a mechanism by which we can advance a bio by an arbitrary number of bytes without modifying the biovec: bio->bi_iter.bi_bvec_done indicates the number of bytes completed in the current bvec. Various driver code still needs to be updated to not refer to the bvec directly before we can use this for interesting things, like efficient bio splitting. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Lars Ellenberg Cc: Paul Clements Cc: drbd-user@lists.linbit.com Cc: nbd-general@lists.sourceforge.net --- include/linux/bio.h | 81 ++++++++++++++++++++++++++++++++++++++++++----- include/linux/blk_types.h | 3 ++ include/linux/blkdev.h | 4 +-- 3 files changed, 78 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index c16adb5f69f8..04e592e74c92 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -64,11 +64,38 @@ #define bio_iovec_idx(bio, idx) (&((bio)->bi_io_vec[(idx)])) #define __bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) -#define bio_iter_iovec(bio, iter) ((bio)->bi_io_vec[(iter).bi_idx]) +#define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) -#define bio_page(bio) (bio_iovec((bio)).bv_page) -#define bio_offset(bio) (bio_iovec((bio)).bv_offset) -#define bio_iovec(bio) (*__bio_iovec(bio)) +#define bvec_iter_page(bvec, iter) \ + (__bvec_iter_bvec((bvec), (iter))->bv_page) + +#define bvec_iter_len(bvec, iter) \ + min((iter).bi_size, \ + __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) + +#define bvec_iter_offset(bvec, iter) \ + (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) + +#define bvec_iter_bvec(bvec, iter) \ +((struct bio_vec) { \ + .bv_page = bvec_iter_page((bvec), (iter)), \ + .bv_len = bvec_iter_len((bvec), (iter)), \ + .bv_offset = bvec_iter_offset((bvec), (iter)), \ +}) + +#define bio_iter_iovec(bio, iter) \ + bvec_iter_bvec((bio)->bi_io_vec, (iter)) + +#define bio_iter_page(bio, iter) \ + bvec_iter_page((bio)->bi_io_vec, (iter)) +#define bio_iter_len(bio, iter) \ + bvec_iter_len((bio)->bi_io_vec, (iter)) +#define bio_iter_offset(bio, iter) \ + bvec_iter_offset((bio)->bi_io_vec, (iter)) + +#define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter) +#define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) +#define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) #define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_iter.bi_idx) #define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) @@ -145,16 +172,54 @@ static inline void *bio_data(struct bio *bio) bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ i++) +static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter, + unsigned bytes) +{ + WARN_ONCE(bytes > iter->bi_size, + "Attempted to advance past end of bvec iter\n"); + + while (bytes) { + unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + + bytes -= len; + iter->bi_size -= len; + iter->bi_bvec_done += len; + + if (iter->bi_bvec_done == __bvec_iter_bvec(bv, *iter)->bv_len) { + iter->bi_bvec_done = 0; + iter->bi_idx++; + } + } +} + +#define for_each_bvec(bvl, bio_vec, iter, start) \ + for ((iter) = start; \ + (bvl) = bvec_iter_bvec((bio_vec), (iter)), \ + (iter).bi_size; \ + bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) + + +static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, + unsigned bytes) +{ + iter->bi_sector += bytes >> 9; + + if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK) + iter->bi_size -= bytes; + else + bvec_iter_advance(bio->bi_io_vec, iter, bytes); +} + #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ - bvl = bio_iter_iovec((bio), (iter)), \ - (iter).bi_idx < (bio)->bi_vcnt; \ - (iter).bi_idx++) + (iter).bi_size && \ + ((bvl = bio_iter_iovec((bio), (iter))), 1); \ + bio_advance_iter((bio), &(iter), (bvl).bv_len)) #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) -#define bio_iter_last(bio, iter) ((iter).bi_idx == (bio)->bi_vcnt - 1) +#define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) /* * get a reference to a bio, so it won't disappear. the intended use is diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 29b5b84d8a29..d369f8f6af79 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -34,6 +34,9 @@ struct bvec_iter { unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ + + unsigned int bi_bvec_done; /* number of bytes completed in + current bvec */ }; /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 337b92a54658..02cb6f0ea71d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -750,9 +750,9 @@ struct req_iterator { __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) -#define rq_iter_last(rq, _iter) \ +#define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ - bio_iter_last(_iter.bio, _iter.iter)) + bio_iter_last(bvec, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" -- cgit v1.2.3 From d57a5f7c6605f15f3b5134837e68b448a7cea88e Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Nov 2013 17:20:16 -0800 Subject: bio-integrity: Convert to bvec_iter The bio integrity is also stored in a bvec array, so if we use the bvec iter code we just added, the integrity code won't need to implement its own iteration stuff (bio_integrity_mark_head(), bio_integrity_mark_tail()) Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: "Martin K. Petersen" Cc: "James E.J. Bottomley" --- include/linux/bio.h | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 04e592e74c92..930cb73c894b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -244,16 +244,15 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ - sector_t bip_sector; /* virtual start sector */ + struct bvec_iter bip_iter; + /* kill - should just use bip_vec */ void *bip_buf; /* generated integrity data */ - bio_end_io_t *bip_end_io; /* saved I/O completion fn */ - unsigned int bip_size; + bio_end_io_t *bip_end_io; /* saved I/O completion fn */ unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ - unsigned short bip_idx; /* current bip_vec index */ unsigned bip_owns_buf:1; /* should free bip_buf */ struct work_struct bip_work; /* I/O completion */ @@ -626,16 +625,12 @@ struct biovec_slab { #if defined(CONFIG_BLK_DEV_INTEGRITY) -#define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) -#define bip_vec(bip) bip_vec_idx(bip, 0) -#define __bip_for_each_vec(bvl, bip, i, start_idx) \ - for (bvl = bip_vec_idx((bip), (start_idx)), i = (start_idx); \ - i < (bip)->bip_vcnt; \ - bvl++, i++) -#define bip_for_each_vec(bvl, bip, i) \ - __bip_for_each_vec(bvl, bip, i, (bip)->bip_idx) +#define bip_vec_idx(bip, idx) (&(bip->bip_vec[(idx)])) + +#define bip_for_each_vec(bvl, bip, iter) \ + for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) #define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ for_each_bio(_bio) \ -- cgit v1.2.3 From 458b76ed2f9517becb74dcc8eedd70d3068ea6e4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 24 Sep 2013 16:26:05 -0700 Subject: block: Kill bio_segments()/bi_vcnt usage When we start sharing biovecs, keeping bi_vcnt accurate for splits is going to be error prone - and unnecessary, if we refactor some code. So bio_segments() has to go - but most of the existing users just needed to know if the bio had multiple segments, which is easier - add a bio_multiple_segments() for them. (Two of the current uses of bio_segments() are going to go away in a couple patches, but the current implementation of bio_segments() is unsafe as soon as we start doing driver conversions for immutable biovecs - so implement a dumb version for bisectability, it'll go away in a couple patches) Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Neil Brown Cc: Nagalakshmi Nandigama Cc: Sreekanth Reddy Cc: "James E.J. Bottomley" --- include/linux/bio.h | 81 +++++++++++++++++++++++++++++++---------------------- 1 file changed, 48 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 930cb73c894b..aea9896a6289 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -97,13 +97,46 @@ #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) -#define bio_segments(bio) ((bio)->bi_vcnt - (bio)->bi_iter.bi_idx) +#define bio_multiple_segments(bio) \ + ((bio)->bi_iter.bi_size != bio_iovec(bio).bv_len) #define bio_sectors(bio) ((bio)->bi_iter.bi_size >> 9) #define bio_end_sector(bio) ((bio)->bi_iter.bi_sector + bio_sectors((bio))) +/* + * Check whether this bio carries any data or not. A NULL bio is allowed. + */ +static inline bool bio_has_data(struct bio *bio) +{ + if (bio && + bio->bi_iter.bi_size && + !(bio->bi_rw & REQ_DISCARD)) + return true; + + return false; +} + +static inline bool bio_is_rw(struct bio *bio) +{ + if (!bio_has_data(bio)) + return false; + + if (bio->bi_rw & BIO_NO_ADVANCE_ITER_MASK) + return false; + + return true; +} + +static inline bool bio_mergeable(struct bio *bio) +{ + if (bio->bi_rw & REQ_NOMERGE_FLAGS) + return false; + + return true; +} + static inline unsigned int bio_cur_bytes(struct bio *bio) { - if (bio->bi_vcnt) + if (bio_has_data(bio)) return bio_iovec(bio).bv_len; else /* dataless requests such as discard */ return bio->bi_iter.bi_size; @@ -111,7 +144,7 @@ static inline unsigned int bio_cur_bytes(struct bio *bio) static inline void *bio_data(struct bio *bio) { - if (bio->bi_vcnt) + if (bio_has_data(bio)) return page_address(bio_page(bio)) + bio_offset(bio); return NULL; @@ -221,6 +254,18 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) +static inline unsigned bio_segments(struct bio *bio) +{ + unsigned segs = 0; + struct bio_vec bv; + struct bvec_iter iter; + + bio_for_each_segment(bv, bio, iter) + segs++; + + return segs; +} + /* * get a reference to a bio, so it won't disappear. the intended use is * something like: @@ -434,36 +479,6 @@ static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx, __bio_kmap_irq((bio), (bio)->bi_iter.bi_idx, (flags)) #define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags) -/* - * Check whether this bio carries any data or not. A NULL bio is allowed. - */ -static inline bool bio_has_data(struct bio *bio) -{ - if (bio && bio->bi_vcnt) - return true; - - return false; -} - -static inline bool bio_is_rw(struct bio *bio) -{ - if (!bio_has_data(bio)) - return false; - - if (bio->bi_rw & REQ_WRITE_SAME) - return false; - - return true; -} - -static inline bool bio_mergeable(struct bio *bio) -{ - if (bio->bi_rw & REQ_NOMERGE_FLAGS) - return false; - - return true; -} - /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * -- cgit v1.2.3 From 003b5c5719f159f4f4bf97511c4702a0638313dd Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Fri, 11 Oct 2013 15:45:43 -0700 Subject: block: Convert drivers to immutable biovecs Now that we've got a mechanism for immutable biovecs - bi_iter.bi_bvec_done - we need to convert drivers to use primitives that respect it instead of using the bvec array directly. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: NeilBrown Cc: Alasdair Kergon Cc: dm-devel@redhat.com --- include/linux/dm-io.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h index f4b0aa3126f5..a68cbe59e6ad 100644 --- a/include/linux/dm-io.h +++ b/include/linux/dm-io.h @@ -29,7 +29,7 @@ typedef void (*io_notify_fn)(unsigned long error, void *context); enum dm_io_mem_type { DM_IO_PAGE_LIST,/* Page list */ - DM_IO_BVEC, /* Bio vector */ + DM_IO_BIO, /* Bio vector */ DM_IO_VMA, /* Virtual memory area */ DM_IO_KMEM, /* Kernel memory */ }; @@ -41,7 +41,7 @@ struct dm_io_memory { union { struct page_list *pl; - struct bio_vec *bvec; + struct bio *bio; void *vma; void *addr; } ptr; -- cgit v1.2.3 From f38a5181d9f3e004b1f50f9d7e1f2a8492ce240a Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2013 14:30:24 -0700 Subject: ceph: Convert to immutable biovecs Now that we've got a mechanism for immutable biovecs - bi_iter.bi_bvec_done - we need to convert drivers to use primitives that respect it instead of using the bvec array directly. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Sage Weil Cc: ceph-devel@vger.kernel.org --- include/linux/ceph/messenger.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 7c1420bb1dce..091fdb600d55 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -1,6 +1,7 @@ #ifndef __FS_CEPH_MESSENGER_H #define __FS_CEPH_MESSENGER_H +#include #include #include #include @@ -119,8 +120,7 @@ struct ceph_msg_data_cursor { #ifdef CONFIG_BLOCK struct { /* bio */ struct bio *bio; /* bio from list */ - unsigned int vector_index; /* vector from bio */ - unsigned int vector_offset; /* bytes from vector */ + struct bvec_iter bvec_iter; }; #endif /* CONFIG_BLOCK */ struct { /* pages */ -- cgit v1.2.3 From f619d25460473788944e3b71b030398681e8809b Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2013 14:30:33 -0700 Subject: block: Kill bio_iovec_idx(), __bio_iovec() bio_iovec_idx() and __bio_iovec() don't have any valid uses anymore - previous users have been converted to bio_iovec_iter() or other methods. __BVEC_END() has to go too - the bvec array can't be used directly for the last biovec because we might only be using the first portion of it, we have to iterate over the bvec array with bio_for_each_segment() which checks against the current value of bi_iter.bi_size. Signed-off-by: Kent Overstreet Cc: Jens Axboe --- include/linux/bio.h | 26 ++++++++------------------ 1 file changed, 8 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index aea9896a6289..1a31f9d9e057 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -61,9 +61,6 @@ * various member access, note that bio_data should of course not be used * on highmem page vectors */ -#define bio_iovec_idx(bio, idx) (&((bio)->bi_io_vec[(idx)])) -#define __bio_iovec(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) - #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) #define bvec_iter_page(bvec, iter) \ @@ -162,19 +159,16 @@ static inline void *bio_data(struct bio *bio) * permanent PIO fall back, user is probably better off disabling highmem * I/O completely on that queue (see ide-dma for example) */ -#define __bio_kmap_atomic(bio, idx) \ - (kmap_atomic(bio_iovec_idx((bio), (idx))->bv_page) + \ - bio_iovec_idx((bio), (idx))->bv_offset) +#define __bio_kmap_atomic(bio, iter) \ + (kmap_atomic(bio_iter_iovec((bio), (iter)).bv_page) + \ + bio_iter_iovec((bio), (iter)).bv_offset) -#define __bio_kunmap_atomic(addr) kunmap_atomic(addr) +#define __bio_kunmap_atomic(addr) kunmap_atomic(addr) /* * merge helpers etc */ -#define __BVEC_END(bio) bio_iovec_idx((bio), (bio)->bi_vcnt - 1) -#define __BVEC_START(bio) bio_iovec_idx((bio), (bio)->bi_iter.bi_idx) - /* Default implementation of BIOVEC_PHYS_MERGEABLE */ #define __BIOVEC_PHYS_MERGEABLE(vec1, vec2) \ ((bvec_to_phys((vec1)) + (vec1)->bv_len) == bvec_to_phys((vec2))) @@ -191,8 +185,6 @@ static inline void *bio_data(struct bio *bio) (((addr1) | (mask)) == (((addr2) - 1) | (mask))) #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \ __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q))) -#define BIO_SEG_BOUNDARY(q, b1, b2) \ - BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2))) #define bio_io_error(bio) bio_endio((bio), -EIO) @@ -201,9 +193,7 @@ static inline void *bio_data(struct bio *bio) * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, i) \ - for (i = 0; \ - bvl = bio_iovec_idx((bio), (i)), i < (bio)->bi_vcnt; \ - i++) + for (i = 0, bvl = (bio)->bi_io_vec; i < (bio)->bi_vcnt; i++, bvl++) static inline void bvec_iter_advance(struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) @@ -468,15 +458,15 @@ static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) } #endif -static inline char *__bio_kmap_irq(struct bio *bio, unsigned short idx, +static inline char *__bio_kmap_irq(struct bio *bio, struct bvec_iter iter, unsigned long *flags) { - return bvec_kmap_irq(bio_iovec_idx(bio, idx), flags); + return bvec_kmap_irq(&bio_iter_iovec(bio, iter), flags); } #define __bio_kunmap_irq(buf, flags) bvec_kunmap_irq(buf, flags) #define bio_kmap_irq(bio, flags) \ - __bio_kmap_irq((bio), (bio)->bi_iter.bi_idx, (flags)) + __bio_kmap_irq((bio), (bio)->bi_iter, (flags)) #define bio_kunmap_irq(buf,flags) __bio_kunmap_irq(buf, flags) /* -- cgit v1.2.3 From 59d276fe02d7e887a4825ef05c80b8f8c54ba60a Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Nov 2013 18:19:27 -0800 Subject: block: Add bio_clone_fast() bio_clone() just got more expensive - however, most users of bio_clone() don't actually need to modify the biovec. If they aren't modifying the biovec, and they can guarantee that the original bio isn't freed before the clone (also true in most cases), we can just point the clone at the original bio's biovec. Signed-off-by: Kent Overstreet --- include/linux/bio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1a31f9d9e057..1f83f4a3083e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -328,6 +328,8 @@ extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries); extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *); extern void bio_put(struct bio *); +extern void __bio_clone_fast(struct bio *, struct bio *); +extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern void __bio_clone(struct bio *, struct bio *); extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs); -- cgit v1.2.3 From 1c3b13e64cf70d652fb04e32d13ae3e36810c2e4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Tue, 29 Oct 2013 17:17:49 -0700 Subject: dm: Refactor for new bio cloning/splitting We need to convert the dm code to the new bvec_iter primitives which respect bi_bvec_done; they also allow us to drastically simplify dm's bio splitting code. Also, it's no longer necessary to save/restore the bvec array anymore - driver conversions for immutable bvecs are done, so drivers should never be modifying it. Also kill bio_sector_offset(), dm was the only user and it doesn't make much sense anymore. Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Alasdair Kergon Cc: dm-devel@redhat.com Reviewed-by: Mike Snitzer --- include/linux/bio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 1f83f4a3083e..0c32a45a419c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -330,7 +330,6 @@ extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); -extern void __bio_clone(struct bio *, struct bio *); extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs); extern struct bio_set *fs_bio_set; @@ -370,7 +369,6 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); extern int bio_get_nr_vecs(struct block_device *); -extern sector_t bio_sector_offset(struct bio *, unsigned short, unsigned int); extern struct bio *bio_map_user(struct request_queue *, struct block_device *, unsigned long, unsigned int, int, gfp_t); struct sg_iovec; -- cgit v1.2.3 From 196d38bccfcfa32faed8c561868336fdfa0fe8e4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Nov 2013 18:34:15 -0800 Subject: block: Generic bio chaining This adds a generic mechanism for chaining bio completions. This is going to be used for a bio_split() replacement, and it turns out to be very useful in a fair amount of driver code - a fair number of drivers were implementing this in their own roundabout ways, often painfully. Note that this means it's no longer to call bio_endio() more than once on the same bio! This can cause problems for drivers that save/restore bi_end_io. Arguably they shouldn't be saving/restoring bi_end_io at all - in all but the simplest cases they'd be better off just cloning the bio, and immutable biovecs is making bio cloning cheaper. But for now, we add a bio_endio_nodec() for these cases. Signed-off-by: Kent Overstreet Cc: Jens Axboe --- include/linux/bio.h | 2 ++ include/linux/blk_types.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0c32a45a419c..64f5169c224b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -356,6 +356,7 @@ static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask) } extern void bio_endio(struct bio *, int); +extern void bio_endio_nodec(struct bio *, int); struct request_queue; extern int bio_phys_segments(struct request_queue *, struct bio *); @@ -364,6 +365,7 @@ extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *); extern void bio_reset(struct bio *); +void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index d369f8f6af79..bbc3a6c88fce 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -65,6 +65,8 @@ struct bio { unsigned int bi_seg_front_size; unsigned int bi_seg_back_size; + atomic_t bi_remaining; + bio_end_io_t *bi_end_io; void *bi_private; -- cgit v1.2.3 From ee67891bf132612feb7b999ee1f3350b40867cb4 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2013 14:32:45 -0700 Subject: block: Rename bio_split() -> bio_pair_split() This is prep work for introducing a more general bio_split(). Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: NeilBrown Cc: Alasdair Kergon Cc: Lars Ellenberg Cc: Peter Osterlund Cc: Sage Weil --- include/linux/bio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 64f5169c224b..aa67af0b31ac 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -317,7 +317,7 @@ struct bio_pair { atomic_t cnt; int error; }; -extern struct bio_pair *bio_split(struct bio *bi, int first_sectors); +extern struct bio_pair *bio_pair_split(struct bio *bi, int first_sectors); extern void bio_pair_release(struct bio_pair *dbio); extern void bio_trim(struct bio *bio, int offset, int size); -- cgit v1.2.3 From 20d0189b1012a37d2533a87fb451f7852f2418d1 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sat, 23 Nov 2013 18:21:01 -0800 Subject: block: Introduce new bio_split() The new bio_split() can split arbitrary bios - it's not restricted to single page bios, like the old bio_split() (previously renamed to bio_pair_split()). It also has different semantics - it doesn't allocate a struct bio_pair, leaving it up to the caller to handle completions. Then convert the existing bio_pair_split() users to the new bio_split() - and also nvme, which was open coding bio splitting. (We have to take that BUG_ON() out of bio_integrity_trim() because this bio_split() needs to use it, and there's no reason it has to be used on bios marked as cloned; BIO_CLONED doesn't seem to have clearly documented semantics anyways.) Signed-off-by: Kent Overstreet Cc: Jens Axboe Cc: Martin K. Petersen Cc: Matthew Wilcox Cc: Keith Busch Cc: Vishal Verma Cc: Jiri Kosina Cc: Neil Brown --- include/linux/bio.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index aa67af0b31ac..19e31b2f5b2c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -321,6 +321,28 @@ extern struct bio_pair *bio_pair_split(struct bio *bi, int first_sectors); extern void bio_pair_release(struct bio_pair *dbio); extern void bio_trim(struct bio *bio, int offset, int size); +extern struct bio *bio_split(struct bio *bio, int sectors, + gfp_t gfp, struct bio_set *bs); + +/** + * bio_next_split - get next @sectors from a bio, splitting if necessary + * @bio: bio to split + * @sectors: number of sectors to split from the front of @bio + * @gfp: gfp mask + * @bs: bio set to allocate from + * + * Returns a bio representing the next @sectors of @bio - if the bio is smaller + * than @sectors, returns the original bio unchanged. + */ +static inline struct bio *bio_next_split(struct bio *bio, int sectors, + gfp_t gfp, struct bio_set *bs) +{ + if (sectors >= bio_sectors(bio)) + return bio; + + return bio_split(bio, sectors, gfp, bs); +} + extern struct bio_set *bioset_create(unsigned int, unsigned int); extern void bioset_free(struct bio_set *); extern mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries); -- cgit v1.2.3 From 4b1faf931650d4a35b2a570318862821d6a962e3 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Wed, 7 Aug 2013 14:33:00 -0700 Subject: block: Kill bio_pair_split() Signed-off-by: Kent Overstreet Cc: Jens Axboe --- include/linux/bio.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 19e31b2f5b2c..70654521dab6 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -297,30 +297,7 @@ struct bio_integrity_payload { }; #endif /* CONFIG_BLK_DEV_INTEGRITY */ -/* - * A bio_pair is used when we need to split a bio. - * This can only happen for a bio that refers to just one - * page of data, and in the unusual situation when the - * page crosses a chunk/device boundary - * - * The address of the master bio is stored in bio1.bi_private - * The address of the pool the pair was allocated from is stored - * in bio2.bi_private - */ -struct bio_pair { - struct bio bio1, bio2; - struct bio_vec bv1, bv2; -#if defined(CONFIG_BLK_DEV_INTEGRITY) - struct bio_integrity_payload bip1, bip2; - struct bio_vec iv1, iv2; -#endif - atomic_t cnt; - int error; -}; -extern struct bio_pair *bio_pair_split(struct bio *bi, int first_sectors); -extern void bio_pair_release(struct bio_pair *dbio); extern void bio_trim(struct bio *bio, int offset, int size); - extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); @@ -677,7 +654,6 @@ extern int bio_integrity_prep(struct bio *); extern void bio_integrity_endio(struct bio *, int); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *, unsigned int, unsigned int); -extern void bio_integrity_split(struct bio *, struct bio_pair *, int); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); @@ -721,12 +697,6 @@ static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, return 0; } -static inline void bio_integrity_split(struct bio *bio, struct bio_pair *bp, - int sectors) -{ - return; -} - static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { -- cgit v1.2.3 From 4b9a445e3eeb8bd9278b1ae51c1b3a651e370cd6 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 14 Nov 2013 07:25:17 -0500 Subject: sunrpc: create a new dummy pipe for gssd to hold open rpc.gssd will naturally hold open any pipe named */clnt*/gssd that shows up under rpc_pipefs. That behavior gives us a reliable mechanism to tell whether it's actually running or not. Create a new toplevel "gssd" directory in rpc_pipefs when it's mounted. Under that directory create another directory called "clntXX", and then within that a pipe called "gssd". We'll never send an upcall along that pipe, and any downcall written to it will just return -EINVAL. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index a353e0300b54..85f13424647c 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -84,7 +84,8 @@ enum { extern struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name); -extern void rpc_pipefs_init_net(struct net *net); +extern int rpc_pipefs_init_net(struct net *net); +extern void rpc_pipefs_exit_net(struct net *net); extern struct super_block *rpc_get_sb_net(const struct net *net); extern void rpc_put_sb_net(const struct net *net); -- cgit v1.2.3 From 89f842435c630f8426f414e6030bc2ffea0d6f81 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Thu, 14 Nov 2013 07:25:18 -0500 Subject: sunrpc: replace sunrpc_net->gssd_running flag with a more reliable check Now that we have a more reliable method to tell if gssd is running, we can replace the sn->gssd_running flag with a function that will query to see if it's up and running. There's also no need to attempt an upcall that we know will fail, so just return -EACCES if gssd isn't running. Finally, fix the warn_gss() message not to claim that that the upcall timed out since we don't necesarily perform one now when gssd isn't running, and remove the extraneous newline from the message. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/sunrpc/rpc_pipe_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h index 85f13424647c..7f490bef9e99 100644 --- a/include/linux/sunrpc/rpc_pipe_fs.h +++ b/include/linux/sunrpc/rpc_pipe_fs.h @@ -131,5 +131,7 @@ extern int rpc_unlink(struct dentry *); extern int register_rpc_pipefs(void); extern void unregister_rpc_pipefs(void); +extern bool gssd_running(struct net *net); + #endif #endif -- cgit v1.2.3 From 5877231f646bbd6d1d545e7af83aaa6e6b746013 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 6 Dec 2013 00:08:22 +0530 Subject: mm: Move change_prot_numa outside CONFIG_ARCH_USES_NUMA_PROT_NONE change_prot_numa should work even if _PAGE_NUMA != _PAGE_PROTNONE. On archs like ppc64 that don't use _PAGE_PROTNONE and also have a separate page table outside linux pagetable, we just need to make sure that when calling change_prot_numa we flush the hardware page table entry so that next page access result in a numa fault. We still need to make sure we use the numa faulting logic only when CONFIG_NUMA_BALANCING is set. This implies the migrate-on-fault (Lazy migration) via mbind will only work if CONFIG_NUMA_BALANCING is set. Signed-off-by: Aneesh Kumar K.V Reviewed-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Benjamin Herrenschmidt --- include/linux/mm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 1cedd000cf29..a7b4e310bf42 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1842,7 +1842,7 @@ static inline pgprot_t vm_get_page_prot(unsigned long vm_flags) } #endif -#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE +#ifdef CONFIG_NUMA_BALANCING unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long start, unsigned long end); #endif -- cgit v1.2.3 From 28303ca3090c0aa0dbbb72714c51fceb4b939f6d Mon Sep 17 00:00:00 2001 From: Weng Meiling Date: Sat, 30 Nov 2013 17:56:44 +0800 Subject: sunrpc: fix some typos Signed-off-by: Weng Meiling Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6eecfc2e4f98..b631642318c5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -368,7 +368,7 @@ struct svc_program { struct svc_program * pg_next; /* other programs (same xprt) */ u32 pg_prog; /* program number */ unsigned int pg_lovers; /* lowest version */ - unsigned int pg_hivers; /* lowest version */ + unsigned int pg_hivers; /* highest version */ unsigned int pg_nvers; /* number of versions */ struct svc_version ** pg_vers; /* version array */ char * pg_name; /* service name */ -- cgit v1.2.3 From a626e64e0bee4fb26848dbed92223dde488f3d93 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 10 Jul 2013 12:03:30 -0300 Subject: [media] v4l: vsp1: Add SRU support The Super Resolution Unit performs super resolution processing with optional upscaling by a factor of two. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/vsp1.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/vsp1.h b/include/linux/platform_data/vsp1.h index a73a456d7f11..27c0ede1a53f 100644 --- a/include/linux/platform_data/vsp1.h +++ b/include/linux/platform_data/vsp1.h @@ -14,6 +14,7 @@ #define __PLATFORM_VSP1_H__ #define VSP1_HAS_LIF (1 << 0) +#define VSP1_HAS_SRU (1 << 1) struct vsp1_platform_data { unsigned int features; -- cgit v1.2.3 From 989af88339db26345e23271dae1089d949c4a0f1 Mon Sep 17 00:00:00 2001 From: Laurent Pinchart Date: Wed, 10 Jul 2013 12:03:30 -0300 Subject: [media] v4l: vsp1: Add LUT support The Look-Up Table looks up values in 8-bit indexed tables separately for each color component. Signed-off-by: Laurent Pinchart Signed-off-by: Mauro Carvalho Chehab --- include/linux/platform_data/vsp1.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/vsp1.h b/include/linux/platform_data/vsp1.h index 27c0ede1a53f..63170e2614b3 100644 --- a/include/linux/platform_data/vsp1.h +++ b/include/linux/platform_data/vsp1.h @@ -14,7 +14,8 @@ #define __PLATFORM_VSP1_H__ #define VSP1_HAS_LIF (1 << 0) -#define VSP1_HAS_SRU (1 << 1) +#define VSP1_HAS_LUT (1 << 1) +#define VSP1_HAS_SRU (1 << 2) struct vsp1_platform_data { unsigned int features; -- cgit v1.2.3 From d29adb34a94715174c88ca93e8aba955850c9bde Mon Sep 17 00:00:00 2001 From: Josh Durgin Date: Mon, 2 Dec 2013 19:11:48 -0800 Subject: libceph: block I/O when PAUSE or FULL osd map flags are set The PAUSEWR and PAUSERD flags are meant to stop the cluster from processing writes and reads, respectively. The FULL flag is set when the cluster determines that it is out of space, and will no longer process writes. PAUSEWR and PAUSERD are purely client-side settings already implemented in userspace clients. The osd does nothing special with these flags. When the FULL flag is set, however, the osd responds to all writes with -ENOSPC. For cephfs, this makes sense, but for rbd the block layer translates this into EIO. If a cluster goes from full to non-full quickly, a filesystem on top of rbd will not behave well, since some writes succeed while others get EIO. Fix this by blocking any writes when the FULL flag is set in the osd client. This is the same strategy used by userspace, so apply it by default. A follow-on patch makes this configurable. __map_request() is called to re-target osd requests in case the available osds changed. Add a paused field to a ceph_osd_request, and set it whenever an appropriate osd map flag is set. Avoid queueing paused requests in __map_request(), but force them to be resent if they become unpaused. Also subscribe to the next osd map from the monitor if any of these flags are set, so paused requests can be unblocked as soon as possible. Fixes: http://tracker.ceph.com/issues/6079 Reviewed-by: Sage Weil Signed-off-by: Josh Durgin --- include/linux/ceph/osd_client.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 8f47625a0661..4fb6a8938957 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -138,6 +138,7 @@ struct ceph_osd_request { __le64 *r_request_pool; void *r_request_pgid; __le32 *r_request_attempts; + bool r_paused; struct ceph_eversion *r_request_reassert_version; int r_result; -- cgit v1.2.3 From cd72b8462a2ebbf9524e726c65c2770f0bf70d22 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Wed, 13 Nov 2013 22:55:24 +0800 Subject: dma: imx-sdma: Add sdma firmware version 2 support On i.MX5/6 series, SDMA is using new version firmware to support SSI dual FIFO feature and HDMI Audio (i.MX6Q/DL only). Thus add it. Signed-off-by: Nicolin Chen Acked-by: Sascha Hauer Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-imx-sdma.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h index 3a3942823c20..eabac4e2fc99 100644 --- a/include/linux/platform_data/dma-imx-sdma.h +++ b/include/linux/platform_data/dma-imx-sdma.h @@ -43,6 +43,11 @@ struct sdma_script_start_addrs { s32 dptc_dvfs_addr; s32 utra_addr; s32 ram_code_start_addr; + /* End of v1 array */ + s32 mcu_2_ssish_addr; + s32 ssish_2_mcu_addr; + s32 hdmi_dma_addr; + /* End of v2 array */ }; /** -- cgit v1.2.3 From 1a895578d4e50577bb6aa79bd194b502f09dd768 Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Wed, 13 Nov 2013 22:55:25 +0800 Subject: dma: imx-sdma: Add new dma type for ssi dual fifo script This patch adds a new DMA_TYPE for SSI dual FIFO script, included in SDMA firmware version 2. This script would allow SSI use dual fifo mode to transimit/receive data without occasional hardware underrun/overrun. Signed-off-by: Nicolin Chen Acked-by: Kumar Gala Acked-by: Sascha Hauer Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-imx.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-imx.h b/include/linux/platform_data/dma-imx.h index beac6b8b6a7b..bcbc6c3c14c0 100644 --- a/include/linux/platform_data/dma-imx.h +++ b/include/linux/platform_data/dma-imx.h @@ -39,6 +39,7 @@ enum sdma_peripheral_type { IMX_DMATYPE_IPU_MEMORY, /* IPU Memory */ IMX_DMATYPE_ASRC, /* ASRC */ IMX_DMATYPE_ESAI, /* ESAI */ + IMX_DMATYPE_SSI_DUAL, /* SSI Dual FIFO */ }; enum imx_dma_prio { -- cgit v1.2.3 From ca13bb3d4e54f5c30089e55d5b8f4bb80c8f05e2 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Tue, 5 Nov 2013 15:59:53 +0000 Subject: iommu: add IOMMU_EXEC flag for safely allowing XN mappings Whilst most IOMMU mappings should probably be non-executable, there may be cases (HSA?) where executable mappings are required. This patch introduces a new mapping flag, IOMMU_EXEC, to indicate that the mapping should be mapped as executable. Signed-off-by: Will Deacon --- include/linux/iommu.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a444c790fa72..709a697c4e02 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -24,9 +24,10 @@ #include #include -#define IOMMU_READ (1) -#define IOMMU_WRITE (2) -#define IOMMU_CACHE (4) /* DMA cache coherency */ +#define IOMMU_READ (1 << 0) +#define IOMMU_WRITE (1 << 1) +#define IOMMU_CACHE (1 << 2) /* DMA cache coherency */ +#define IOMMU_EXEC (1 << 3) struct iommu_ops; struct iommu_group; -- cgit v1.2.3 From 320a382746e0ab1304476ea7e986a8d416ab99db Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 23 Oct 2013 13:07:34 -0600 Subject: NVMe: compat SG_IO ioctl For 32-bit versions of sg3-utils running on a 64-bit system. This is mostly a copy from the relevent portions of fs/compat_ioctl.c, with slight modifications for going through block_device_operations. Signed-off-by: Keith Busch Reviewed-by: Vishal Verma [fixed up CONFIG_COMPAT=n build problems] Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 8119a476cb29..5bc29197d90e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -165,6 +165,7 @@ int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11, struct sg_io_hdr; int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr); +int nvme_sg_io32(struct nvme_ns *ns, unsigned long arg); int nvme_sg_get_version_num(int __user *ip); #endif /* _LINUX_NVME_H */ -- cgit v1.2.3 From 9a6b94584de1a0467d85b435df9c744c5c45a270 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 10 Dec 2013 13:10:36 -0700 Subject: NVMe: Device resume error handling Adds controller error handling on resume power management. If the device fails to initialize, the device is queued for a reset. If the reset fails, a thread is spawned to remove the pci device. If the device resumes as "busy", the device is responding to admin commands but will not create IO queues. In this case, we need to remove the gendisks and free the IO queues since they can't be used and may be holding bios in their lists. From testing, the dma pools require a pci device so this had to change the pci driver 'remove' to release the dma resources in line with that call instead of after all references to the device are released. Signed-off-by: Keith Busch Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 5bc29197d90e..eed81cc56d7e 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -87,6 +87,7 @@ struct nvme_dev { struct list_head namespaces; struct kref kref; struct miscdevice miscdev; + struct work_struct reset_work; char name[12]; char serial[20]; char model[40]; -- cgit v1.2.3 From 46eeb2c144956e88197439b5ee5cf221a91b0a81 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Mon, 16 Dec 2013 15:57:39 +0000 Subject: video/fb: Propagate error code from failing to unregister conflicting fb If we fail to remove a conflicting fb driver, we need to abort the loading of the second driver to avoid likely kernel panics. Signed-off-by: Chris Wilson Cc: Jean-Christophe Plagniol-Villard Cc: Tomi Valkeinen Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Reviewed-by: Jani Nikula Signed-off-by: Dave Airlie --- include/linux/fb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fb.h b/include/linux/fb.h index 70c4836e4a9f..fe6ac956550e 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -613,8 +613,8 @@ extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf, extern int register_framebuffer(struct fb_info *fb_info); extern int unregister_framebuffer(struct fb_info *fb_info); extern int unlink_framebuffer(struct fb_info *fb_info); -extern void remove_conflicting_framebuffers(struct apertures_struct *a, - const char *name, bool primary); +extern int remove_conflicting_framebuffers(struct apertures_struct *a, + const char *name, bool primary); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -- cgit v1.2.3 From e1168c2cc4a5a5e495a53e067a6be6b4f29abfe0 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 22 Nov 2013 18:14:38 -0800 Subject: slab.h: remove duplicate kmalloc declaration and fix kernel-doc warnings Fix kernel-doc warning for duplicate definition of 'kmalloc': Documentation/DocBook/kernel-api.xml:9483: element refentry: validity error : ID API-kmalloc already defined Also combine the kernel-doc info from the 2 kmalloc definitions into one block and remove the "see kcalloc" comment since kmalloc now contains the @flags info. Signed-off-by: Randy Dunlap Acked-by: Christoph Lameter Signed-off-by: Pekka Enberg --- include/linux/slab.h | 102 +++++++++++++++++++++++---------------------------- 1 file changed, 46 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c2bba248fa63..1e2f4fe12773 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -388,10 +388,55 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) /** * kmalloc - allocate memory * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate (see kcalloc). + * @flags: the type of memory to allocate. * * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. + * + * The @flags argument may be one of: + * + * %GFP_USER - Allocate memory on behalf of user. May sleep. + * + * %GFP_KERNEL - Allocate normal kernel ram. May sleep. + * + * %GFP_ATOMIC - Allocation will not sleep. May use emergency pools. + * For example, use this inside interrupt handlers. + * + * %GFP_HIGHUSER - Allocate pages from high memory. + * + * %GFP_NOIO - Do not do any I/O at all while trying to get memory. + * + * %GFP_NOFS - Do not make any fs calls while trying to get memory. + * + * %GFP_NOWAIT - Allocation will not sleep. + * + * %GFP_THISNODE - Allocate node-local memory only. + * + * %GFP_DMA - Allocation suitable for DMA. + * Should only be used for kmalloc() caches. Otherwise, use a + * slab created with SLAB_DMA. + * + * Also it is possible to set different flags by OR'ing + * in one or more of the following additional @flags: + * + * %__GFP_COLD - Request cache-cold pages instead of + * trying to return cache-warm pages. + * + * %__GFP_HIGH - This allocation has high priority and may use emergency pools. + * + * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail + * (think twice before using). + * + * %__GFP_NORETRY - If memory is not immediately available, + * then give up at once. + * + * %__GFP_NOWARN - If allocation fails, don't issue any warnings. + * + * %__GFP_REPEAT - If allocation fails initially, try once more before failing. + * + * There are other flags available as well, but these are not intended + * for general use, and so are not documented here. For a full list of + * potential flags, always refer to linux/gfp.h. */ static __always_inline void *kmalloc(size_t size, gfp_t flags) { @@ -501,61 +546,6 @@ struct seq_file; int cache_show(struct kmem_cache *s, struct seq_file *m); void print_slabinfo_header(struct seq_file *m); -/** - * kmalloc - allocate memory - * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate. - * - * The @flags argument may be one of: - * - * %GFP_USER - Allocate memory on behalf of user. May sleep. - * - * %GFP_KERNEL - Allocate normal kernel ram. May sleep. - * - * %GFP_ATOMIC - Allocation will not sleep. May use emergency pools. - * For example, use this inside interrupt handlers. - * - * %GFP_HIGHUSER - Allocate pages from high memory. - * - * %GFP_NOIO - Do not do any I/O at all while trying to get memory. - * - * %GFP_NOFS - Do not make any fs calls while trying to get memory. - * - * %GFP_NOWAIT - Allocation will not sleep. - * - * %GFP_THISNODE - Allocate node-local memory only. - * - * %GFP_DMA - Allocation suitable for DMA. - * Should only be used for kmalloc() caches. Otherwise, use a - * slab created with SLAB_DMA. - * - * Also it is possible to set different flags by OR'ing - * in one or more of the following additional @flags: - * - * %__GFP_COLD - Request cache-cold pages instead of - * trying to return cache-warm pages. - * - * %__GFP_HIGH - This allocation has high priority and may use emergency pools. - * - * %__GFP_NOFAIL - Indicate that this allocation is in no way allowed to fail - * (think twice before using). - * - * %__GFP_NORETRY - If memory is not immediately available, - * then give up at once. - * - * %__GFP_NOWARN - If allocation fails, don't issue any warnings. - * - * %__GFP_REPEAT - If allocation fails initially, try once more before failing. - * - * There are other flags available as well, but these are not intended - * for general use, and so are not documented here. For a full list of - * potential flags, always refer to linux/gfp.h. - * - * kmalloc is the normal method of allocating memory - * in the kernel. - */ -static __always_inline void *kmalloc(size_t size, gfp_t flags); - /** * kmalloc_array - allocate memory for an array. * @n: number of elements. -- cgit v1.2.3 From 397321f45d31159c84982978106f3165be44bc2b Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Mon, 16 Dec 2013 12:12:17 +0400 Subject: dmaengine: fix incorrect kernel-doc comment for struct dma_slave_config The 'direction' member of 'struct dma_slave_config' is of data type 'enum dma_transfer_direction', so update the kernel-doc comment for 'struct dma_slave_config' to refer to appropriate values. Signed-off-by: Alexander Popov Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 41cf0c399288..bd6b88222ced 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -305,9 +305,8 @@ enum dma_slave_buswidth { /** * struct dma_slave_config - dma slave channel runtime config * @direction: whether the data shall go in or out on this slave - * channel, right now. DMA_TO_DEVICE and DMA_FROM_DEVICE are - * legal values, DMA_BIDIRECTIONAL is not acceptable since we - * need to differentiate source and target addresses. + * channel, right now. DMA_MEM_TO_DEV and DMA_DEV_TO_MEM are + * legal values. * @src_addr: this is the physical address where DMA slave data * should be read (RX), if the source is memory this argument is * ignored. -- cgit v1.2.3 From 4de6a2d6acb0e2a840f07db17def7e674b9d2bb4 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 2 Sep 2013 09:48:53 +0200 Subject: gpu: host1x: Add MIPI pad calibration support This driver adds support to perform calibration of the MIPI pads for CSI and DSI. Signed-off-by: Thierry Reding --- include/linux/host1x.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/host1x.h b/include/linux/host1x.h index f5b9b87ac9a9..3af847273277 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -281,4 +281,10 @@ int host1x_device_exit(struct host1x_device *device); int host1x_client_register(struct host1x_client *client); int host1x_client_unregister(struct host1x_client *client); +struct tegra_mipi_device; + +struct tegra_mipi_device *tegra_mipi_request(struct device *device); +void tegra_mipi_free(struct tegra_mipi_device *device); +int tegra_mipi_calibrate(struct tegra_mipi_device *device); + #endif -- cgit v1.2.3 From b62dfd29eeaf12f8bc79a50f680901e84b351851 Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Thu, 21 Nov 2013 17:41:14 +1100 Subject: iommu: Add empty stub for iommu_group_get_by_id() Almost every function in include/linux/iommu.h has an empty stub but the iommu_group_get_by_id() did not get one by mistake. This adds an empty stub for iommu_group_get_by_id() for IOMMU_API disabled config. Signed-off-by: Alexey Kardashevskiy Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a444c790fa72..01ed7345f508 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -247,6 +247,11 @@ static inline struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) return NULL; } +static inline struct iommu_group *iommu_group_get_by_id(int id) +{ + return NULL; +} + static inline void iommu_domain_free(struct iommu_domain *domain) { } -- cgit v1.2.3 From 3edcc0ce85c59d45d6dfc6a36a6b3f8b31ba9887 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 26 Dec 2013 21:31:38 +0800 Subject: block: blk-mq: don't export blk_mq_free_queue() blk_mq_free_queue() is called from release handler of queue kobject, so it needn't be called from drivers. Cc: Jens Axboe Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ab0e9b2025b3..851d34b7ac26 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -113,7 +113,6 @@ enum { }; struct request_queue *blk_mq_init_queue(struct blk_mq_reg *, void *); -void blk_mq_free_queue(struct request_queue *); int blk_mq_register_disk(struct gendisk *); void blk_mq_unregister_disk(struct gendisk *); void blk_mq_init_commands(struct request_queue *, void (*init)(void *data, struct blk_mq_hw_ctx *, struct request *, unsigned int), void *data); -- cgit v1.2.3 From 12b4629a9fb80fecaebadc217b13b8776ed8dbef Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:23 +0200 Subject: libceph: all features fields must be u64 In preparation for ceph_features.h update, change all features fields from unsigned int/u32 to u64. (ceph.git has ~40 feature bits at this point.) Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/libceph.h | 8 ++++---- include/linux/ceph/messenger.h | 10 +++++----- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 2e3024881a5e..7d704db60cbb 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -122,8 +122,8 @@ struct ceph_client { int (*extra_mon_dispatch)(struct ceph_client *, struct ceph_msg *); - u32 supported_features; - u32 required_features; + u64 supported_features; + u64 required_features; struct ceph_messenger msgr; /* messenger instance */ struct ceph_mon_client monc; @@ -192,8 +192,8 @@ extern int ceph_compare_options(struct ceph_options *new_opt, struct ceph_client *client); extern struct ceph_client *ceph_create_client(struct ceph_options *opt, void *private, - unsigned supported_features, - unsigned required_features); + u64 supported_features, + u64 required_features); extern u64 ceph_client_id(struct ceph_client *client); extern void ceph_destroy_client(struct ceph_client *client); extern int __ceph_open_session(struct ceph_client *client, diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 7c1420bb1dce..c1d3f5a65273 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -60,8 +60,8 @@ struct ceph_messenger { u32 global_seq; spinlock_t global_seq_lock; - u32 supported_features; - u32 required_features; + u64 supported_features; + u64 required_features; }; enum ceph_msg_data_type { @@ -192,7 +192,7 @@ struct ceph_connection { struct ceph_entity_name peer_name; /* peer name */ - unsigned peer_features; + u64 peer_features; u32 connect_seq; /* identify the most recent connection attempt for this connection, client */ u32 peer_global_seq; /* peer's global seq for this connection */ @@ -256,8 +256,8 @@ extern void ceph_msgr_flush(void); extern void ceph_messenger_init(struct ceph_messenger *msgr, struct ceph_entity_addr *myaddr, - u32 supported_features, - u32 required_features, + u64 supported_features, + u64 required_features, bool nocrc); extern void ceph_con_init(struct ceph_connection *con, void *private, -- cgit v1.2.3 From 2b3e0c905af43cfe402a2ef3f800be5dc1684005 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:24 +0200 Subject: libceph: update ceph_features.h This updates ceph_features.h so that it has all feature bits defined in ceph.git. In the interim since the last update, ceph.git crossed the "32 feature bits" point, and, the addition of the 33rd bit wasn't handled correctly. The work-around is squashed into this commit and reflects ceph.git commit 053659d05e0349053ef703b414f44965f368b9f0. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 96 +++++++++++++++++++++++++------------- 1 file changed, 64 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 4c42080347af..003ea719be65 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -4,42 +4,73 @@ /* * feature bits */ -#define CEPH_FEATURE_UID (1<<0) -#define CEPH_FEATURE_NOSRCADDR (1<<1) -#define CEPH_FEATURE_MONCLOCKCHECK (1<<2) -#define CEPH_FEATURE_FLOCK (1<<3) -#define CEPH_FEATURE_SUBSCRIBE2 (1<<4) -#define CEPH_FEATURE_MONNAMES (1<<5) -#define CEPH_FEATURE_RECONNECT_SEQ (1<<6) -#define CEPH_FEATURE_DIRLAYOUTHASH (1<<7) -#define CEPH_FEATURE_OBJECTLOCATOR (1<<8) -#define CEPH_FEATURE_PGID64 (1<<9) -#define CEPH_FEATURE_INCSUBOSDMAP (1<<10) -#define CEPH_FEATURE_PGPOOL3 (1<<11) -#define CEPH_FEATURE_OSDREPLYMUX (1<<12) -#define CEPH_FEATURE_OSDENC (1<<13) -#define CEPH_FEATURE_OMAP (1<<14) -#define CEPH_FEATURE_MONENC (1<<15) -#define CEPH_FEATURE_QUERY_T (1<<16) -#define CEPH_FEATURE_INDEP_PG_MAP (1<<17) -#define CEPH_FEATURE_CRUSH_TUNABLES (1<<18) -#define CEPH_FEATURE_CHUNKY_SCRUB (1<<19) -#define CEPH_FEATURE_MON_NULLROUTE (1<<20) -#define CEPH_FEATURE_MON_GV (1<<21) -#define CEPH_FEATURE_BACKFILL_RESERVATION (1<<22) -#define CEPH_FEATURE_MSG_AUTH (1<<23) -#define CEPH_FEATURE_RECOVERY_RESERVATION (1<<24) -#define CEPH_FEATURE_CRUSH_TUNABLES2 (1<<25) -#define CEPH_FEATURE_CREATEPOOLID (1<<26) -#define CEPH_FEATURE_REPLY_CREATE_INODE (1<<27) -#define CEPH_FEATURE_OSD_HBMSGS (1<<28) -#define CEPH_FEATURE_MDSENC (1<<29) -#define CEPH_FEATURE_OSDHASHPSPOOL (1<<30) +#define CEPH_FEATURE_UID (1ULL<<0) +#define CEPH_FEATURE_NOSRCADDR (1ULL<<1) +#define CEPH_FEATURE_MONCLOCKCHECK (1ULL<<2) +#define CEPH_FEATURE_FLOCK (1ULL<<3) +#define CEPH_FEATURE_SUBSCRIBE2 (1ULL<<4) +#define CEPH_FEATURE_MONNAMES (1ULL<<5) +#define CEPH_FEATURE_RECONNECT_SEQ (1ULL<<6) +#define CEPH_FEATURE_DIRLAYOUTHASH (1ULL<<7) +#define CEPH_FEATURE_OBJECTLOCATOR (1ULL<<8) +#define CEPH_FEATURE_PGID64 (1ULL<<9) +#define CEPH_FEATURE_INCSUBOSDMAP (1ULL<<10) +#define CEPH_FEATURE_PGPOOL3 (1ULL<<11) +#define CEPH_FEATURE_OSDREPLYMUX (1ULL<<12) +#define CEPH_FEATURE_OSDENC (1ULL<<13) +#define CEPH_FEATURE_OMAP (1ULL<<14) +#define CEPH_FEATURE_MONENC (1ULL<<15) +#define CEPH_FEATURE_QUERY_T (1ULL<<16) +#define CEPH_FEATURE_INDEP_PG_MAP (1ULL<<17) +#define CEPH_FEATURE_CRUSH_TUNABLES (1ULL<<18) +#define CEPH_FEATURE_CHUNKY_SCRUB (1ULL<<19) +#define CEPH_FEATURE_MON_NULLROUTE (1ULL<<20) +#define CEPH_FEATURE_MON_GV (1ULL<<21) +#define CEPH_FEATURE_BACKFILL_RESERVATION (1ULL<<22) +#define CEPH_FEATURE_MSG_AUTH (1ULL<<23) +#define CEPH_FEATURE_RECOVERY_RESERVATION (1ULL<<24) +#define CEPH_FEATURE_CRUSH_TUNABLES2 (1ULL<<25) +#define CEPH_FEATURE_CREATEPOOLID (1ULL<<26) +#define CEPH_FEATURE_REPLY_CREATE_INODE (1ULL<<27) +#define CEPH_FEATURE_OSD_HBMSGS (1ULL<<28) +#define CEPH_FEATURE_MDSENC (1ULL<<29) +#define CEPH_FEATURE_OSDHASHPSPOOL (1ULL<<30) +#define CEPH_FEATURE_MON_SINGLE_PAXOS (1ULL<<31) +#define CEPH_FEATURE_OSD_SNAPMAPPER (1ULL<<32) +#define CEPH_FEATURE_MON_SCRUB (1ULL<<33) +#define CEPH_FEATURE_OSD_PACKED_RECOVERY (1ULL<<34) +#define CEPH_FEATURE_OSD_CACHEPOOL (1ULL<<35) +#define CEPH_FEATURE_CRUSH_V2 (1ULL<<36) /* new indep; SET_* steps */ +#define CEPH_FEATURE_EXPORT_PEER (1ULL<<37) +#define CEPH_FEATURE_OSD_ERASURE_CODES (1ULL<<38) + +/* + * The introduction of CEPH_FEATURE_OSD_SNAPMAPPER caused the feature + * vector to evaluate to 64 bit ~0. To cope, we designate 1ULL << 63 + * to mean 33 bit ~0, and introduce a helper below to do the + * translation. + * + * This was introduced by ceph.git commit + * 9ea02b84104045c2ffd7e7f4e7af512953855ecd v0.58-657-g9ea02b8 + * and fixed by ceph.git commit + * 4255b5c2fb54ae40c53284b3ab700fdfc7e61748 v0.65-263-g4255b5c + */ +#define CEPH_FEATURE_RESERVED (1ULL<<63) + +static inline u64 ceph_sanitize_features(u64 features) +{ + if (features & CEPH_FEATURE_RESERVED) { + /* everything through OSD_SNAPMAPPER */ + return 0x1ffffffffull; + } else { + return features; + } +} /* * Features supported. */ -#define CEPH_FEATURES_SUPPORTED_DEFAULT \ +#define CEPH_FEATURES_SUPPORTED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ CEPH_FEATURE_RECONNECT_SEQ | \ CEPH_FEATURE_PGID64 | \ @@ -56,4 +87,5 @@ CEPH_FEATURE_PGID64 | \ CEPH_FEATURE_PGPOOL3 | \ CEPH_FEATURE_OSDENC) + #endif -- cgit v1.2.3 From b3b33b0e43323af4fb697f4378218d3c268d02cd Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:24 +0200 Subject: crush: pass weight vector size to map function Pass the size of the weight vector into crush_do_rule() to ensure that we don't access values past the end. This can happen if the caller misbehaves and passes a weight vector that is smaller than max_devices. Currently the monitor tries to prevent that from happening, but this will gracefully tolerate previous bad osdmaps that got into this state. It's also a bit more defensive. Reflects ceph.git commit 5922e2c2b8335b5e46c9504349c3a55b7434c01a. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/mapper.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index 5772dee3ecbf..69310b031875 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -14,6 +14,6 @@ extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, i extern int crush_do_rule(const struct crush_map *map, int ruleno, int x, int *result, int result_max, - const __u32 *weights); + const __u32 *weights, int weight_max); #endif -- cgit v1.2.3 From bfb16d7d69f0272451ad85a6e50aab3c4262fbc0 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:24 +0200 Subject: crush: factor out (trivial) crush_destroy_rule() Reflects ceph.git commit 43a01c9973c4b83f2eaa98be87429941a227ddde. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 6a1101f24cfb..09561a04c127 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -174,6 +174,7 @@ extern void crush_destroy_bucket_list(struct crush_bucket_list *b); extern void crush_destroy_bucket_tree(struct crush_bucket_tree *b); extern void crush_destroy_bucket_straw(struct crush_bucket_straw *b); extern void crush_destroy_bucket(struct crush_bucket *b); +extern void crush_destroy_rule(struct crush_rule *r); extern void crush_destroy(struct crush_map *map); static inline int crush_calc_tree_node(int i) -- cgit v1.2.3 From e8ef19c4ad161768e1d8309d5ae18481c098eb81 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:24 +0200 Subject: crush: eliminate CRUSH_MAX_SET result size limitation This is only present to size the temporary scratch arrays that we put on the stack. Let the caller allocate them as they wish and remove the limitation. Reflects ceph.git commit 1cfe140bf2dab99517589a82a916f4c75b9492d1. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 1 - include/linux/crush/mapper.h | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 09561a04c127..83543c504b5a 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -21,7 +21,6 @@ #define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ -#define CRUSH_MAX_SET 10 /* max size of a mapping result */ /* diff --git a/include/linux/crush/mapper.h b/include/linux/crush/mapper.h index 69310b031875..eab367446eea 100644 --- a/include/linux/crush/mapper.h +++ b/include/linux/crush/mapper.h @@ -14,6 +14,7 @@ extern int crush_find_rule(const struct crush_map *map, int ruleset, int type, i extern int crush_do_rule(const struct crush_map *map, int ruleno, int x, int *result, int result_max, - const __u32 *weights, int weight_max); + const __u32 *weights, int weight_max, + int *scratch); #endif -- cgit v1.2.3 From c6d98a603a02594f6ecf16d0a0af989ae9fa7abd Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:25 +0200 Subject: crush: return CRUSH_ITEM_UNDEF for failed placements with indep For firstn mode, if we fail to make a valid placement choice, we just continue and return a short result to the caller. For indep mode, however, we need to make the position stable, and return an undefined value on failed placements to avoid shifting later results to the left. Reflects ceph.git commit b1d4dd4eb044875874a1d01c01c7d766db5d0a80. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 83543c504b5a..3d6a12928560 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -19,10 +19,11 @@ #define CRUSH_MAGIC 0x00010000ul /* for detecting algorithm revisions */ - #define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ +#define CRUSH_ITEM_UNDEF 0x7fffffff /* undefined result */ + /* * CRUSH uses user-defined "rules" to describe how inputs should be * mapped to devices. A rule consists of sequence of steps to perform -- cgit v1.2.3 From 9a3b490a20e06368c81d7a81506e99388e733379 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:25 +0200 Subject: crush: use breadth-first search for indep mode Reflects ceph.git commit 86e978036a4ecbac4c875e7c00f6c5bbe37282d3. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 3d6a12928560..4023b1b52296 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -22,7 +22,8 @@ #define CRUSH_MAX_DEPTH 10 /* max crush hierarchy depth */ -#define CRUSH_ITEM_UNDEF 0x7fffffff /* undefined result */ +#define CRUSH_ITEM_UNDEF 0x7ffffffe /* undefined result (internal use only) */ +#define CRUSH_ITEM_NONE 0x7fffffff /* no result */ /* * CRUSH uses user-defined "rules" to describe how inputs should be -- cgit v1.2.3 From be3226acc5544bcc91e756eb3ee6ca7b74f6f0a8 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:26 +0200 Subject: crush: new SET_CHOOSE_LEAF_TRIES command Explicitly control the number of sample attempts, and allow the number of tries in the recursive call to be explicitly controlled via the rule. This is important because the amount of time we want to spend looking for a solution may be rule dependent (e.g., higher for the wide indep pool than the rep pools). (We should do the same for the other tunables, by the way!) Reflects ceph.git commit c43c893be872f709c787bc57f46c0e97876ff681. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 4023b1b52296..2e50bab91655 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -46,6 +46,8 @@ enum { CRUSH_RULE_EMIT = 4, /* no args */ CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6, CRUSH_RULE_CHOOSE_LEAF_INDEP = 7, + + CRUSH_RULE_SET_CHOOSE_LEAF_TRIES = 9, }; /* -- cgit v1.2.3 From f18650ace38ef200dd1578257c75e9407297953c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:26 +0200 Subject: crush: apply chooseleaf_tries to firstn mode too Parameterize the attempts for the _firstn choose method, and apply the rule-specified tries count to firstn mode as well. Note that we have slightly different behavior here than with indep: If the firstn value is not specified for firstn, we pass through the normal attempt count. This maintains compatibility with legacy behavior. Note that this is usually *not* actually N^2 work, though, because of the descend_once tunable. However, descend_once is unfortunately *not* the same thing as 1 chooseleaf try because it is only checked on a reject but not on a collision. Sigh. In contrast, for indep, if tries is not specified we default to 1 recursive attempt, because that is simply more sane, and we have the option to do so. The descend_once tunable has no effect for indep. Reflects ceph.git commit 64aeded50d80942d66a5ec7b604ff2fcbf5d7b63. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 2e50bab91655..07b8fd4f81fc 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -165,7 +165,10 @@ struct crush_map { __u32 choose_local_fallback_tries; /* choose attempts before giving up */ __u32 choose_total_tries; - /* attempt chooseleaf inner descent once; on failure retry outer descent */ + /* attempt chooseleaf inner descent once for firstn mode; on + * reject retry outer descent. Note that this does *not* + * apply to a collision: in that case we will retry as we used + * to. */ __u32 chooseleaf_descend_once; }; -- cgit v1.2.3 From cc10df4a3a5c34cb1d5b635ac70dd1fc406153ce Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:26 +0200 Subject: crush: add SET_CHOOSE_TRIES rule step Since we can specify the recursive retries in a rule, we may as well also specify the non-recursive tries too for completeness. Reflects ceph.git commit d1b97462cffccc871914859eaee562f2786abfd1. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 07b8fd4f81fc..5f95969347ec 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -47,7 +47,8 @@ enum { CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6, CRUSH_RULE_CHOOSE_LEAF_INDEP = 7, - CRUSH_RULE_SET_CHOOSE_LEAF_TRIES = 9, + CRUSH_RULE_SET_CHOOSE_TRIES = 8, /* override choose_total_tries */ + CRUSH_RULE_SET_CHOOSE_LEAF_TRIES = 9, /* override chooseleaf_descend_once */ }; /* -- cgit v1.2.3 From 917edad5d1d62070436b74ecbf5ea019b651ff69 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:26 +0200 Subject: crush: CHOOSE_LEAF -> CHOOSELEAF throughout This aligns the internal identifier names with the user-visible names in the decompiled crush map language. Reflects ceph.git commit caa0e22e15e4226c3671318ba1f61314bf6da2a6. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 5f95969347ec..7b0fc4aba75b 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -44,11 +44,11 @@ enum { /* arg2 = type */ CRUSH_RULE_CHOOSE_INDEP = 3, /* same */ CRUSH_RULE_EMIT = 4, /* no args */ - CRUSH_RULE_CHOOSE_LEAF_FIRSTN = 6, - CRUSH_RULE_CHOOSE_LEAF_INDEP = 7, + CRUSH_RULE_CHOOSELEAF_FIRSTN = 6, + CRUSH_RULE_CHOOSELEAF_INDEP = 7, CRUSH_RULE_SET_CHOOSE_TRIES = 8, /* override choose_total_tries */ - CRUSH_RULE_SET_CHOOSE_LEAF_TRIES = 9, /* override chooseleaf_descend_once */ + CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */ }; /* -- cgit v1.2.3 From f046bf92080cbdc4a94c6e86698c5a3f10716445 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:27 +0200 Subject: crush: add set_choose_local_[fallback_]tries steps This allows all of the tunables to be overridden by a specific rule. Reflects ceph.git commits d129e09e57fbc61cfd4f492e3ee77d0750c9d292, 0497db49e5973b50df26251ed0e3f4ac7578e66e. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/crush/crush.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/crush/crush.h b/include/linux/crush/crush.h index 7b0fc4aba75b..acaa5615d634 100644 --- a/include/linux/crush/crush.h +++ b/include/linux/crush/crush.h @@ -49,6 +49,8 @@ enum { CRUSH_RULE_SET_CHOOSE_TRIES = 8, /* override choose_total_tries */ CRUSH_RULE_SET_CHOOSELEAF_TRIES = 9, /* override chooseleaf_descend_once */ + CRUSH_RULE_SET_CHOOSE_LOCAL_TRIES = 10, + CRUSH_RULE_SET_CHOOSE_LOCAL_FALLBACK_TRIES = 11, }; /* -- cgit v1.2.3 From cdff49918c8286ac18593e742ead25242c76c81d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 24 Dec 2013 21:19:27 +0200 Subject: crush: support new indep mode and SET_* steps (crush v2) by default Add CRUSH_V2 feature (new indep mode and SET_* steps) to a set of features supported by default. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 003ea719be65..5f42e4412909 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -79,7 +79,8 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES | \ CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ - CEPH_FEATURE_OSDHASHPSPOOL) + CEPH_FEATURE_OSDHASHPSPOOL | \ + CEPH_FEATURE_CRUSH_V2) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ -- cgit v1.2.3 From 26a6d240e2a1480a33d76ac4db8855b6a7f2bd89 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 12 Nov 2013 20:11:26 +0100 Subject: mtd: make mtd_partition.name const This allows to drop a few casts. Signed-off-by: Geert Uytterhoeven Signed-off-by: Brian Norris --- include/linux/mtd/partitions.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 1f8d24bdafda..335ffca10c10 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -37,7 +37,7 @@ */ struct mtd_partition { - char *name; /* identifier string */ + const char *name; /* identifier string */ uint64_t size; /* partition size */ uint64_t offset; /* offset within the master MTD space */ uint32_t mask_flags; /* master MTD flags to mask out for this partition */ @@ -80,7 +80,7 @@ extern int register_mtd_parser(struct mtd_part_parser *parser); extern int deregister_mtd_parser(struct mtd_part_parser *parser); int mtd_is_partition(const struct mtd_info *mtd); -int mtd_add_partition(struct mtd_info *master, char *name, +int mtd_add_partition(struct mtd_info *master, const char *name, long long offset, long long length); int mtd_del_partition(struct mtd_info *master, int partno); uint64_t mtd_get_device_size(const struct mtd_info *mtd); -- cgit v1.2.3 From 776f265e279744e3f327ccd3e7eb378046311373 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 14 Nov 2013 18:25:28 -0300 Subject: mtd: nand: pxa3xx: Add bad block handling Add support for flash-based bad block table using Marvell's custom in-flash bad block table layout. The support is enabled a 'flash_bbt' platform data or device tree parameter. Signed-off-by: Ezequiel Garcia Tested-by: Daniel Mack Signed-off-by: Brian Norris --- include/linux/platform_data/mtd-nand-pxa3xx.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-nand-pxa3xx.h b/include/linux/platform_data/mtd-nand-pxa3xx.h index ffb801998e5d..a94147124929 100644 --- a/include/linux/platform_data/mtd-nand-pxa3xx.h +++ b/include/linux/platform_data/mtd-nand-pxa3xx.h @@ -55,6 +55,9 @@ struct pxa3xx_nand_platform_data { /* indicate how many chip selects will be used */ int num_cs; + /* use an flash-based bad block table */ + bool flash_bbt; + const struct mtd_partition *parts[NUM_CHIP_SELECT]; unsigned int nr_parts[NUM_CHIP_SELECT]; -- cgit v1.2.3 From a55e85ce9bee97df63f85547a5e72df14851b338 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 2 Dec 2013 11:12:22 -0800 Subject: mtd: nand: fix misspelling in ONFI parameter field name s/strenght/strength/ This field isn't used anywhere, so this rename is safe. Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 9e6c8f9f306e..f3ea8daf08ee 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -279,7 +279,7 @@ struct nand_onfi_params { __le16 io_pin_capacitance_typ; __le16 input_pin_capacitance_typ; u8 input_pin_capacitance_max; - u8 driver_strenght_support; + u8 driver_strength_support; __le16 t_int_r; __le16 t_ald; u8 reserved4[7]; -- cgit v1.2.3 From e0b6047b73278d165ae0ad448177209a3c2067ad Mon Sep 17 00:00:00 2001 From: Philipp Rosenberger Date: Thu, 28 Nov 2013 12:36:52 +0100 Subject: of_mtd: fix header file include guard It seems the include guard was copied from of_net.h. Signed-off-by: Philipp Rosenberger Signed-off-by: Brian Norris --- include/linux/of_mtd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_mtd.h b/include/linux/of_mtd.h index 6f10e938ff7e..cb32d9c1e8dc 100644 --- a/include/linux/of_mtd.h +++ b/include/linux/of_mtd.h @@ -7,7 +7,7 @@ */ #ifndef __LINUX_OF_MTD_H -#define __LINUX_OF_NET_H +#define __LINUX_OF_MTD_H #ifdef CONFIG_OF_MTD -- cgit v1.2.3 From cf3b2b1e24998ba67ca6defa71899bee2432046f Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sun, 1 Dec 2013 18:59:15 +0800 Subject: mtd: make deregister_mtd_parser return void deregister_mtd_parser never fails; hence make it return void. Signed-off-by: Axel Lin Signed-off-by: Brian Norris --- include/linux/mtd/partitions.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 335ffca10c10..d513ffbd8043 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -77,7 +77,7 @@ struct mtd_part_parser { }; extern int register_mtd_parser(struct mtd_part_parser *parser); -extern int deregister_mtd_parser(struct mtd_part_parser *parser); +extern void deregister_mtd_parser(struct mtd_part_parser *parser); int mtd_is_partition(const struct mtd_info *mtd); int mtd_add_partition(struct mtd_info *master, const char *name, -- cgit v1.2.3 From 6e14a61d412eb87ef7bdcec8b08a95bead771a78 Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Sun, 1 Dec 2013 19:01:06 +0800 Subject: mtd: make register_mtd_parser return void register_mtd_parser never fails; hence make it return void. Signed-off-by: Axel Lin Signed-off-by: Brian Norris --- include/linux/mtd/partitions.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index d513ffbd8043..6a35e6de5da1 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -76,7 +76,7 @@ struct mtd_part_parser { struct mtd_part_parser_data *); }; -extern int register_mtd_parser(struct mtd_part_parser *parser); +extern void register_mtd_parser(struct mtd_part_parser *parser); extern void deregister_mtd_parser(struct mtd_part_parser *parser); int mtd_is_partition(const struct mtd_info *mtd); -- cgit v1.2.3 From 7e55b59b2f32afc83452ae250dfd6173c9a7b515 Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Tue, 31 Dec 2013 13:17:20 +0800 Subject: SUNRPC/NFSD: Support a new option for ignoring the result of svc_register NFSv4 clients can contact port 2049 directly instead of needing the portmapper. Therefore a failure to register to the portmapper when starting an NFSv4-only server isn't really a problem. But Gareth Williams reports that an attempt to start an NFSv4-only server without starting portmap fails: #rpc.nfsd -N 2 -N 3 rpc.nfsd: writing fd to kernel failed: errno 111 (Connection refused) rpc.nfsd: unable to set any sockets for nfsd Add a flag to svc_version to tell the rpc layer it can safely ignore an rpcbind failure in the NFSv4-only case. Reported-by: Gareth Williams Reviewed-by: Chuck Lever Signed-off-by: Kinglong Mee Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index b631642318c5..04e763221246 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -386,8 +386,10 @@ struct svc_version { struct svc_procedure * vs_proc; /* per-procedure info */ u32 vs_xdrsize; /* xdrsize needed for this version */ - unsigned int vs_hidden : 1; /* Don't register with portmapper. + unsigned int vs_hidden : 1, /* Don't register with portmapper. * Only used for nfsacl so far. */ + vs_rpcb_optnl:1;/* Don't care the result of register. + * Only used for nfsv4. */ /* Override dispatch function (e.g. when caching replies). * A return value of 0 means drop the request. -- cgit v1.2.3 From 5b5c13996ff115599e13b719fc7e4c39746d3b30 Mon Sep 17 00:00:00 2001 From: "Upinder Malhi (umalhi)" Date: Wed, 11 Dec 2013 20:19:56 +0000 Subject: iommu: Rename domain_has_cap to iommu_domain_has_cap domain_has_cap is a misnomer bc the func name should be the same for CONFIG_IOMMU_API and !CONFIG_IOMMU_API. Signed-off-by: Upinder Malhi Signed-off-by: Joerg Roedel --- include/linux/iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a444c790fa72..8876ef982169 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -291,8 +291,8 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_ad return 0; } -static inline int domain_has_cap(struct iommu_domain *domain, - unsigned long cap) +static inline int iommu_domain_has_cap(struct iommu_domain *domain, + unsigned long cap) { return 0; } -- cgit v1.2.3 From 360eb3c5687e2df23e29e97878238765bfe6a756 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 6 Jan 2014 14:18:08 +0800 Subject: iommu/vt-d: use dedicated bitmap to track remapping entry allocation status Currently Intel interrupt remapping drivers uses the "present" flag bit in remapping entry to track whether an entry is allocated or not. It works as follow: 1) allocate a remapping entry and set its "present" flag bit to 1 2) compose other fields for the entry 3) update the remapping entry with the composed value The remapping hardware may access the entry between step 1 and step 3, which then observers an entry with the "present" flag set but random values in all other fields. This patch introduces a dedicated bitmap to track remapping entry allocation status instead of sharing the "present" flag with hardware, thus eliminate the race window. It also simplifies the implementation. Tested-and-reviewed-by: Yijing Wang Signed-off-by: Jiang Liu Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index d380c5e68008..de1e5e936420 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -288,6 +288,7 @@ struct q_inval { struct ir_table { struct irte *base; + unsigned long *bitmap; }; #endif -- cgit v1.2.3 From c78afc6261b09f74abff8c0719b80692a4959768 Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Thu, 11 Jul 2013 22:39:53 -0700 Subject: bcache/md: Use raid stripe size Now that we've got code for raid5/6 stripe awareness, bcache just needs to know about the stripes and when writing partial stripes is expensive - we probably don't want to enable this optimization for raid1 or 10, even though they have stripes. So add a flag to queue_limits. Signed-off-by: Kent Overstreet --- include/linux/blkdev.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 02cb6f0ea71d..0375654adb28 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -291,6 +291,7 @@ struct queue_limits { unsigned char discard_misaligned; unsigned char cluster; unsigned char discard_zeroes_data; + unsigned char raid_partial_stripes_expensive; }; struct request_queue { -- cgit v1.2.3 From ada4d4b2a32e9f63d4dcb9f69578473408f4622c Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 6 Jan 2014 14:18:09 +0800 Subject: iommu/vt-d: fix PCI device reference leakage on error recovery path Function dmar_parse_dev_scope() should release the PCI device reference count gained in function dmar_parse_one_dev_scope() on error recovery, otherwise it will cause PCI device object leakage. This patch also introduces dmar_free_dev_scope(), which will be used to support DMAR device hotplug. Reviewed-by: Yijing Wang Signed-off-by: Jiang Liu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index b029d1aa2d12..205ee37eed73 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -62,6 +62,9 @@ extern struct list_head dmar_drhd_units; extern int dmar_table_init(void); extern int dmar_dev_scope_init(void); +extern int dmar_parse_dev_scope(void *start, void *end, int *cnt, + struct pci_dev ***devices, u16 segment); +extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt); /* Intel IOMMU detection */ extern int detect_intel_iommu(void); @@ -157,8 +160,6 @@ struct dmar_atsr_unit { int dmar_parse_rmrr_atsr_dev(void); extern int dmar_parse_one_rmrr(struct acpi_dmar_header *header); extern int dmar_parse_one_atsr(struct acpi_dmar_header *header); -extern int dmar_parse_dev_scope(void *start, void *end, int *cnt, - struct pci_dev ***devices, u16 segment); extern int intel_iommu_init(void); #else /* !CONFIG_INTEL_IOMMU: */ static inline int intel_iommu_init(void) { return -ENODEV; } -- cgit v1.2.3 From 694835dc227ad203886457aa447025d09b2f7523 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 6 Jan 2014 14:18:16 +0800 Subject: iommu/vt-d: mark internal functions as static Functions alloc_iommu() and parse_ioapics_under_ir() are only used internally, so mark them as static. [Joerg: Made detect_intel_iommu() non-static again for IA64] Signed-off-by: Jiang Liu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 4 +--- include/linux/intel-iommu.h | 1 - 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 205ee37eed73..1a60dd630bb4 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -33,6 +33,7 @@ struct acpi_dmar_header; #define DMAR_X2APIC_OPT_OUT 0x2 struct intel_iommu; + #ifdef CONFIG_DMAR_TABLE extern struct acpi_table_header *dmar_tbl; struct dmar_drhd_unit { @@ -69,9 +70,6 @@ extern void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt); /* Intel IOMMU detection */ extern int detect_intel_iommu(void); extern int enable_drhd_fault_handling(void); - -extern int parse_ioapics_under_ir(void); -extern int alloc_iommu(struct dmar_drhd_unit *); #else static inline int detect_intel_iommu(void) { diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index de1e5e936420..f2c4114b8665 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -348,7 +348,6 @@ static inline void __iommu_flush_cache( extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); -extern int alloc_iommu(struct dmar_drhd_unit *drhd); extern void free_iommu(struct intel_iommu *iommu); extern int dmar_enable_qi(struct intel_iommu *iommu); extern void dmar_disable_qi(struct intel_iommu *iommu); -- cgit v1.2.3 From 7c9197791a0cbbbb0f74aade3339f8e5890fbd15 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 6 Jan 2014 14:18:18 +0800 Subject: iommu/vt-d, trivial: simplify code with existing macros Simplify vt-d related code with existing macros and introduce a new macro for_each_active_drhd_unit() to enumerate all active DRHD unit. Signed-off-by: Jiang Liu Signed-off-by: Joerg Roedel --- include/linux/dmar.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dmar.h b/include/linux/dmar.h index 1a60dd630bb4..eccb0c0c6cf6 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -53,6 +53,10 @@ extern struct list_head dmar_drhd_units; #define for_each_drhd_unit(drhd) \ list_for_each_entry(drhd, &dmar_drhd_units, list) +#define for_each_active_drhd_unit(drhd) \ + list_for_each_entry(drhd, &dmar_drhd_units, list) \ + if (drhd->ignored) {} else + #define for_each_active_iommu(i, drhd) \ list_for_each_entry(drhd, &dmar_drhd_units, list) \ if (i=drhd->iommu, drhd->ignored) {} else -- cgit v1.2.3 From a868e6b7b661c3d3e7e681a16d0b205971987c99 Mon Sep 17 00:00:00 2001 From: Jiang Liu Date: Mon, 6 Jan 2014 14:18:20 +0800 Subject: iommu/vt-d: keep shared resources when failed to initialize iommu devices Data structure drhd->iommu is shared between DMA remapping driver and interrupt remapping driver, so DMA remapping driver shouldn't release drhd->iommu when it failed to initialize IOMMU devices. Otherwise it may cause invalid memory access to the interrupt remapping driver. Sample stack dump: [ 13.315090] BUG: unable to handle kernel paging request at ffffc9000605a088 [ 13.323221] IP: [] qi_submit_sync+0x15c/0x400 [ 13.330107] PGD 82f81e067 PUD c2f81e067 PMD 82e846067 PTE 0 [ 13.336818] Oops: 0002 [#1] SMP [ 13.340757] Modules linked in: [ 13.344422] CPU: 0 PID: 4 Comm: kworker/0:0 Not tainted 3.13.0-rc1-gerry+ #7 [ 13.352474] Hardware name: Intel Corporation LH Pass ........../SVRBD-ROW_T, BIOS SE5C600.86B.99.99.x059.091020121352 09/10/2012 [ 13.365659] Workqueue: events work_for_cpu_fn [ 13.370774] task: ffff88042ddf00d0 ti: ffff88042ddee000 task.ti: ffff88042dde e000 [ 13.379389] RIP: 0010:[] [] qi_submit_sy nc+0x15c/0x400 [ 13.389055] RSP: 0000:ffff88042ddef940 EFLAGS: 00010002 [ 13.395151] RAX: 00000000000005e0 RBX: 0000000000000082 RCX: 0000000200000025 [ 13.403308] RDX: ffffc9000605a000 RSI: 0000000000000010 RDI: ffff88042ddb8610 [ 13.411446] RBP: ffff88042ddef9a0 R08: 00000000000005d0 R09: 0000000000000001 [ 13.419599] R10: 0000000000000000 R11: 000000000000005d R12: 000000000000005c [ 13.427742] R13: ffff88102d84d300 R14: 0000000000000174 R15: ffff88042ddb4800 [ 13.435877] FS: 0000000000000000(0000) GS:ffff88043de00000(0000) knlGS:00000 00000000000 [ 13.445168] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 13.451749] CR2: ffffc9000605a088 CR3: 0000000001a0b000 CR4: 00000000000407f0 [ 13.459895] Stack: [ 13.462297] ffff88042ddb85d0 000000000000005d ffff88042ddef9b0 0000000000000 5d0 [ 13.471147] 00000000000005c0 ffff88042ddb8000 000000000000005c 0000000000000 015 [ 13.480001] ffff88042ddb4800 0000000000000282 ffff88042ddefa40 ffff88042ddef ac0 [ 13.488855] Call Trace: [ 13.491771] [] modify_irte+0x9d/0xd0 [ 13.497778] [] intel_setup_ioapic_entry+0x10d/0x290 [ 13.505250] [] ? trace_hardirqs_on_caller+0x16/0x1e0 [ 13.512824] [] ? default_init_apic_ldr+0x60/0x60 [ 13.519998] [] setup_ioapic_remapped_entry+0x20/0x30 [ 13.527566] [] io_apic_setup_irq_pin+0x12a/0x2c0 [ 13.534742] [] ? acpi_pci_irq_find_prt_entry+0x2b9/0x2d8 [ 13.544102] [] io_apic_setup_irq_pin_once+0x85/0xa0 [ 13.551568] [] ? mp_find_ioapic_pin+0x8f/0xf0 [ 13.558434] [] io_apic_set_pci_routing+0x34/0x70 [ 13.565621] [] mp_register_gsi+0xaf/0x1c0 [ 13.572111] [] acpi_register_gsi_ioapic+0xe/0x10 [ 13.579286] [] acpi_register_gsi+0xf/0x20 [ 13.585779] [] acpi_pci_irq_enable+0x171/0x1e3 [ 13.592764] [] pcibios_enable_device+0x31/0x40 [ 13.599744] [] do_pci_enable_device+0x3b/0x60 [ 13.606633] [] pci_enable_device_flags+0xc8/0x120 [ 13.613887] [] pci_enable_device+0x13/0x20 [ 13.620484] [] pcie_port_device_register+0x1e/0x510 [ 13.627947] [] ? trace_hardirqs_on_caller+0x16/0x1e0 [ 13.635510] [] ? trace_hardirqs_on+0xd/0x10 [ 13.642189] [] pcie_portdrv_probe+0x58/0xc0 [ 13.648877] [] local_pci_probe+0x45/0xa0 [ 13.655266] [] work_for_cpu_fn+0x14/0x20 [ 13.661656] [] process_one_work+0x369/0x710 [ 13.668334] [] ? process_one_work+0x2f2/0x710 [ 13.675215] [] ? worker_thread+0x46/0x690 [ 13.681714] [] worker_thread+0x484/0x690 [ 13.688109] [] ? cancel_delayed_work_sync+0x20/0x20 [ 13.695576] [] kthread+0xf0/0x110 [ 13.701300] [] ? local_clock+0x3f/0x50 [ 13.707492] [] ? kthread_create_on_node+0x250/0x250 [ 13.714959] [] ret_from_fork+0x7c/0xb0 [ 13.721152] [] ? kthread_create_on_node+0x250/0x250 Signed-off-by: Jiang Liu Signed-off-by: Joerg Roedel --- include/linux/dma_remapping.h | 4 ---- include/linux/intel-iommu.h | 1 - 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h index 57c9a8ae4f2d..7ac17f57250e 100644 --- a/include/linux/dma_remapping.h +++ b/include/linux/dma_remapping.h @@ -27,7 +27,6 @@ struct root_entry; #ifdef CONFIG_INTEL_IOMMU -extern void free_dmar_iommu(struct intel_iommu *iommu); extern int iommu_calculate_agaw(struct intel_iommu *iommu); extern int iommu_calculate_max_sagaw(struct intel_iommu *iommu); extern int dmar_disabled; @@ -41,9 +40,6 @@ static inline int iommu_calculate_max_sagaw(struct intel_iommu *iommu) { return 0; } -static inline void free_dmar_iommu(struct intel_iommu *iommu) -{ -} #define dmar_disabled (1) #define intel_iommu_enabled (0) #endif diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index f2c4114b8665..2c4bed593b32 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -348,7 +348,6 @@ static inline void __iommu_flush_cache( extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); -extern void free_iommu(struct intel_iommu *iommu); extern int dmar_enable_qi(struct intel_iommu *iommu); extern void dmar_disable_qi(struct intel_iommu *iommu); extern int dmar_reenable_qi(struct intel_iommu *iommu); -- cgit v1.2.3 From b27652dd2174df1a7e0a7c5f00d1c8e3ed9287a7 Mon Sep 17 00:00:00 2001 From: Kevin Hao Date: Tue, 24 Dec 2013 15:12:08 +0800 Subject: powerpc: introduce early_get_first_memblock_info For a relocatable kernel since it can be loaded at any place, there is no any relation between the kernel start addr and the memstart_addr. So we can't calculate the memstart_addr from kernel start addr. And also we can't wait to do the relocation after we get the real memstart_addr from device tree because it is so late. So introduce a new function we can use to get the first memblock address and size in a very early stage (before machine_init). Signed-off-by: Kevin Hao Signed-off-by: Scott Wood --- include/linux/of_fdt.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 0beaee9dac1f..2b77058a7335 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -116,6 +116,7 @@ extern const void *of_flat_dt_match_machine(const void *default_match, extern void unflatten_device_tree(void); extern void unflatten_and_copy_device_tree(void); extern void early_init_devtree(void *); +extern void early_get_first_memblock_info(void *, phys_addr_t *); #else /* CONFIG_OF_FLATTREE */ static inline const char *of_flat_dt_get_machine_name(void) { return NULL; } static inline void unflatten_device_tree(void) {} -- cgit v1.2.3 From 111b5a317677d09fd6e2a1dc532f32b4df745166 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Mon, 30 Dec 2013 12:00:20 +0530 Subject: mtd: omap2: Cleanup header files Commit 2203747c9771 ("ARM: omap: move platform_data definitions") moved the files to the current location but forgot to remove the pointer to its previous location. Clean it up. Signed-off-by: Sachin Kamat Acked-by: Pekon Gupta Signed-off-by: Brian Norris --- include/linux/platform_data/mtd-nand-omap2.h | 2 -- include/linux/platform_data/mtd-onenand-omap2.h | 2 -- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h index 4da5bfa2147f..3e9dd6676b97 100644 --- a/include/linux/platform_data/mtd-nand-omap2.h +++ b/include/linux/platform_data/mtd-nand-omap2.h @@ -1,6 +1,4 @@ /* - * arch/arm/plat-omap/include/mach/nand.h - * * Copyright (C) 2006 Micron Technology Inc. * * This program is free software; you can redistribute it and/or modify diff --git a/include/linux/platform_data/mtd-onenand-omap2.h b/include/linux/platform_data/mtd-onenand-omap2.h index e9a9fb188f97..56ff0e6f5ad1 100644 --- a/include/linux/platform_data/mtd-onenand-omap2.h +++ b/include/linux/platform_data/mtd-onenand-omap2.h @@ -1,6 +1,4 @@ /* - * arch/arm/plat-omap/include/mach/onenand.h - * * Copyright (C) 2006 Nokia Corporation * Author: Juha Yrjola * -- cgit v1.2.3 From 6bd8c02753bc0bb8dc14e23004a8effc46906638 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Mon, 30 Dec 2013 12:00:21 +0530 Subject: mtd: orion: Cleanup mtd-orion_nand.h header Commit c02cecb92ed4 ("ARM: orion: move platform_data definitions") moved the file to the current location but forgot to remove the pointer to its previous location. Clean it up. While at it also change the header file protection macros appropriately. Signed-off-by: Sachin Kamat Signed-off-by: Brian Norris --- include/linux/platform_data/mtd-orion_nand.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/mtd-orion_nand.h b/include/linux/platform_data/mtd-orion_nand.h index 9f3c180834d1..a7ce77c7c1a8 100644 --- a/include/linux/platform_data/mtd-orion_nand.h +++ b/include/linux/platform_data/mtd-orion_nand.h @@ -1,13 +1,11 @@ /* - * arch/arm/plat-orion/include/plat/orion_nand.h - * * This file is licensed under the terms of the GNU General Public * License version 2. This program is licensed "as is" without any * warranty of any kind, whether express or implied. */ -#ifndef __PLAT_ORION_NAND_H -#define __PLAT_ORION_NAND_H +#ifndef __MTD_ORION_NAND_H +#define __MTD_ORION_NAND_H /* * Device bus NAND private data -- cgit v1.2.3 From 6d8cdb68249d2a5d2504a7bc79a8cfb517e07020 Mon Sep 17 00:00:00 2001 From: Gerhard Sittig Date: Sat, 30 Nov 2013 23:51:24 +0100 Subject: clk: mpc512x: introduce COMMON_CLK for MPC512x (disabled) this change implements a clock driver for the MPC512x PowerPC platform which follows the COMMON_CLK approach and uses common clock drivers shared with other platforms this driver implements the publicly announced set of clocks (those listed in the dt-bindings header file), as well as generates additional 'struct clk' items where the SoC hardware cannot easily get mapped to the common primitives (shared code) of the clock API, or requires "intermediate clock nodes" to represent clocks that have both gates and dividers the previous PPC_CLOCK implementation is kept in place and remains active for the moment, the newly introduced CCF clock driver will receive additional support for backwards compatibility in a subsequent patch before it gets enabled and will replace the PPC_CLOCK approach some of the clock items get pre-enabled in the clock driver to not have them automatically disabled by the underlying clock subsystem because of their being unused -- this approach is desirable because - some of the clocks are useful to have for diagnostics and information despite their not getting claimed by any drivers (CPU, internal and external RAM, internal busses, boot media) - some of the clocks aren't claimed by their peripheral drivers yet, either because of missing driver support or because device tree specs aren't available yet (but the workarounds will get removed as the drivers get adjusted and the device tree provides the clock specs) clkdev registration provides "alias names" for few clock items - to not break those peripheral drivers which encode their component index into the name that is used for clock lookup (UART, SPI, USB) - to not break those drivers which use names for the clock lookup which were encoded in the previous PPC_CLOCK implementation (NFC, VIU, CAN) this workaround will get removed as these drivers get adjusted after device tree based clock lookup has become available the COMMON_CLK implementation copes with device trees which lack an oscillator node (backwards compat), the REF clock is then derived from the IPS bus frequency and multiplier values fetched from hardware Cc: Mike Turquette Cc: Anatolij Gustschin Cc: linux-arm-kernel@lists.infradead.org Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Gerhard Sittig Signed-off-by: Anatolij Gustschin --- include/linux/clk-provider.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 7e59253b8603..534dc618f2d7 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -512,6 +512,20 @@ static inline const char *of_clk_get_parent_name(struct device_node *np, * for improved portability across platforms */ +#if IS_ENABLED(CONFIG_PPC) + +static inline u32 clk_readl(u32 __iomem *reg) +{ + return ioread32be(reg); +} + +static inline void clk_writel(u32 val, u32 __iomem *reg) +{ + iowrite32be(val, reg); +} + +#else /* platform dependent I/O accessors */ + static inline u32 clk_readl(u32 __iomem *reg) { return readl(reg); @@ -522,5 +536,7 @@ static inline void clk_writel(u32 val, u32 __iomem *reg) writel(val, reg); } +#endif /* platform dependent I/O accessors */ + #endif /* CONFIG_COMMON_CLK */ #endif /* CLK_PROVIDER_H */ -- cgit v1.2.3 From 61310a3659befaad3edfababcf7b4352c1df2b3e Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Mon, 30 Dec 2013 10:46:31 +0530 Subject: dma: Cleanup dma-mmp_tdma.h header Commit 293b2da1b611 ("ARM: pxa: move platform_data definitions") moved the file to the current location but forgot to remove the pointer to its previous location. Clean it up. While at it also change the header file protection macros appropriately. Signed-off-by: Sachin Kamat Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-mmp_tdma.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-mmp_tdma.h b/include/linux/platform_data/dma-mmp_tdma.h index 239e0fc1bb1f..66574ea39f97 100644 --- a/include/linux/platform_data/dma-mmp_tdma.h +++ b/include/linux/platform_data/dma-mmp_tdma.h @@ -1,6 +1,4 @@ /* - * linux/arch/arm/mach-mmp/include/mach/sram.h - * * SRAM Memory Management * * Copyright (c) 2011 Marvell Semiconductors Inc. @@ -11,8 +9,8 @@ * */ -#ifndef __ASM_ARCH_SRAM_H -#define __ASM_ARCH_SRAM_H +#ifndef __DMA_MMP_TDMA_H +#define __DMA_MMP_TDMA_H #include @@ -32,4 +30,4 @@ struct sram_platdata { extern struct gen_pool *sram_get_gpool(char *pool_name); -#endif /* __ASM_ARCH_SRAM_H */ +#endif /* __DMA_MMP_TDMA_H */ -- cgit v1.2.3 From 6fb9063ca2237956e80135700275cdc471ce7233 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Mon, 30 Dec 2013 10:46:32 +0530 Subject: dma: mv_xor: Cleanup in dma-mv_xor.h header Commit c02cecb92ed4 ("ARM: orion: move platform_data definitions") moved the file to the current location but forgot to remove the pointer to its previous location. Clean it up. While at it also change the header file protection macros appropriately. Signed-off-by: Sachin Kamat Cc: Thomas Petazzoni Signed-off-by: Vinod Koul --- include/linux/platform_data/dma-mv_xor.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/dma-mv_xor.h b/include/linux/platform_data/dma-mv_xor.h index 8ec18f64e396..92ffd3245f76 100644 --- a/include/linux/platform_data/dma-mv_xor.h +++ b/include/linux/platform_data/dma-mv_xor.h @@ -1,11 +1,9 @@ /* - * arch/arm/plat-orion/include/plat/mv_xor.h - * * Marvell XOR platform device data definition file. */ -#ifndef __PLAT_MV_XOR_H -#define __PLAT_MV_XOR_H +#ifndef __DMA_MV_XOR_H +#define __DMA_MV_XOR_H #include #include -- cgit v1.2.3 From 6f0065b0124bef5e66869ec0b813d251797be439 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 3 Dec 2013 12:02:20 -0800 Subject: mtd: nand: add ONFI vendor block for Micron Signed-off-by: Brian Norris Acked-by: Huang Shijie --- include/linux/mtd/nand.h | 23 ++++++++++++++++++++++- 1 file changed, 22 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index f3ea8daf08ee..029fe5948dc4 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -285,7 +285,8 @@ struct nand_onfi_params { u8 reserved4[7]; /* vendor */ - u8 reserved5[90]; + __le16 vendor_revision; + u8 vendor[88]; __le16 crc; } __attribute__((packed)); @@ -326,6 +327,26 @@ struct onfi_ext_param_page { */ } __packed; +struct nand_onfi_vendor_micron { + u8 two_plane_read; + u8 read_cache; + u8 read_unique_id; + u8 dq_imped; + u8 dq_imped_num_settings; + u8 dq_imped_feat_addr; + u8 rb_pulldown_strength; + u8 rb_pulldown_strength_feat_addr; + u8 rb_pulldown_strength_num_settings; + u8 otp_mode; + u8 otp_page_start; + u8 otp_data_prot_addr; + u8 otp_num_pages; + u8 otp_feat_addr; + u8 read_retry_options; + u8 reserved[72]; + u8 param_revision; +} __packed; + /** * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices * @lock: protection lock -- cgit v1.2.3 From ba84fb5952af114e28ac82adcdef75297701ccc1 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Fri, 3 Jan 2014 15:13:33 -0800 Subject: mtd: nand: add generic READ RETRY support Modern MLC (and even SLC?) NAND can experience a large number of bitflips (beyond the recommended correctability capacity) due to drifts in the voltage threshold (Vt). These bitflips can cause ECC errors to occur well within the expected lifetime of the flash. To account for this, some manufacturers provide a mechanism for shifting the Vt threshold after a corrupted read. The generic pattern seems to be that a particular flash has N read retry modes (where N = 0, traditionally), and after an ECC failure, the host should reconfigure the flash to use the next available mode, then retry the read operation. This process repeats until all bitfips can be corrected or until the host has tried all available retry modes. This patch adds the infrastructure support for a vendor-specific/flash-specific callback, used for setting the read-retry mode (i.e., voltage threshold). For now, this patch always returns the flash to mode 0 (the default mode) after a successful read-retry, according to the flowchart found in Micron's datasheets. This may need to change in the future if it is determined that eventually, mode 0 is insufficient for the majority of the flash cells (and so for performance reasons, we should leave the flash in mode 1, 2, etc.). Signed-off-by: Brian Norris Acked-by: Huang Shijie --- include/linux/mtd/nand.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 029fe5948dc4..267d61dd89dd 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -472,6 +472,8 @@ struct nand_buffers { * commands to the chip. * @waitfunc: [REPLACEABLE] hardwarespecific function for wait on * ready. + * @setup_read_retry: [FLASHSPECIFIC] flash (vendor) specific function for + * setting the read-retry mode. Mostly needed for MLC NAND. * @ecc: [BOARDSPECIFIC] ECC control structure * @buffers: buffer structure for read/write * @hwcontrol: platform-specific hardware control structure @@ -518,6 +520,7 @@ struct nand_buffers { * non 0 if ONFI supported. * @onfi_params: [INTERN] holds the ONFI page parameter when ONFI is * supported, 0 otherwise. + * @read_retries: [INTERN] the number of read retry modes supported * @onfi_set_features: [REPLACEABLE] set the features for ONFI nand * @onfi_get_features: [REPLACEABLE] get the features for ONFI nand * @bbt: [INTERN] bad block table pointer @@ -565,6 +568,7 @@ struct nand_chip { int feature_addr, uint8_t *subfeature_para); int (*onfi_get_features)(struct mtd_info *mtd, struct nand_chip *chip, int feature_addr, uint8_t *subfeature_para); + int (*setup_read_retry)(struct mtd_info *mtd, int retry_mode); int chip_delay; unsigned int options; @@ -589,6 +593,8 @@ struct nand_chip { int onfi_version; struct nand_onfi_params onfi_params; + int read_retries; + flstate_t state; uint8_t *oob_poi; -- cgit v1.2.3 From 8429bb3975ef81c114cde4da111e64d224d19f83 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Tue, 3 Dec 2013 15:51:09 -0800 Subject: mtd: nand: support Micron READ RETRY Micron provides READ RETRY support via the ONFI vendor-specific parameter block (to indicate how many read-retry modes are available) and the ONFI {GET,SET}_FEATURES commands with a vendor-specific feature address (to support reading/switching the current read-retry mode). The recommended sequence is as follows: 1. Perform PAGE_READ operation 2. If no ECC error, we are done 3. Run SET_FEATURES with feature address 89h, mode 1 4. Retry PAGE_READ operation 5. If ECC error and there are remaining supported modes, increment the mode and return to step 3. Otherwise, this is a true ECC error. 6. Run SET_FEATURES with feature address 89h, mode 0, to return to the default state. This patch implements the chip->setup_read_retry() callback for Micron and fills in the chip->read_retries. Tested on Micron MT29F32G08CBADA, which supports 8 read-retry modes. The Micron vendor-specific table was checked against the datasheets for the following Micron NAND: Needs retry Cell-type Part number Vendor revision Byte 180 ----------- --------- ---------------- --------------- ------------ No SLC MT29F16G08ABABA 1 Reserved (0) No MLC MT29F32G08CBABA 1 Reserved (0) No SLC MT29F1G08AACWP 1 0 Yes MLC MT29F32G08CBADA 1 08h Yes MLC MT29F64G08CBABA 2 08h Signed-off-by: Brian Norris Acked-by: Huang Shijie --- include/linux/mtd/nand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 267d61dd89dd..3080a8c8b62e 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -219,6 +219,9 @@ struct nand_chip; /* ONFI feature address */ #define ONFI_FEATURE_ADDR_TIMING_MODE 0x1 +/* Vendor-specific feature address (Micron) */ +#define ONFI_FEATURE_ADDR_READ_RETRY 0x89 + /* ONFI subfeature parameters length */ #define ONFI_SUBFEATURE_PARAM_LEN 4 -- cgit v1.2.3 From e2e6b7b7d64baeac1c38fa5eb0d3ec85f3d123f5 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Thu, 5 Dec 2013 12:06:54 -0800 Subject: mtd: nand: use __packed shorthand To be consistent with the rest of include/linux/mtd/nand.h, we should use the __packed shorthand instead of __attribute__((packed)). Signed-off-by: Brian Norris Acked-by: Huang Shijie --- include/linux/mtd/nand.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 3080a8c8b62e..05fcdfea640b 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -292,7 +292,7 @@ struct nand_onfi_params { u8 vendor[88]; __le16 crc; -} __attribute__((packed)); +} __packed; #define ONFI_CRC_BASE 0x4F4E -- cgit v1.2.3 From 3cea4c3071d4e55e9d7356efe9d0ebf92f0c2204 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 9 Jan 2014 20:08:21 +0200 Subject: libceph: rename ceph_msg::front_max to front_alloc_len Rename front_max field of struct ceph_msg to front_alloc_len to make its purpose more clear. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/messenger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index c1d3f5a65273..861138f7c161 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -157,7 +157,7 @@ struct ceph_msg { bool front_is_vmalloc; bool more_to_follow; bool needs_out_seq; - int front_max; + int front_alloc_len; unsigned long ack_stamp; /* tx: when we were acked */ struct ceph_msgpool *pool; -- cgit v1.2.3 From 05f7835975dad6b3b517f9e23415985e648fb875 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Uwe=20Kleine-K=C3=B6nig?= Date: Thu, 5 Dec 2013 22:22:04 +0100 Subject: mtd: nand: don't use {read,write}_buf for 8-bit transfers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to the Open NAND Flash Interface Specification (ONFI) Revision 3.1 "Parameters are always transferred on the lower 8-bits of the data bus." for the Get Features and Set Features commands. So using read_buf and write_buf is wrong for 16-bit wide nand chips as they use I/O[15:0]. The Get Features command is easily fixed using 4 times the read_byte callback. For Set Features implement a new overwritable callback "write_byte". Still I expect the default to work just fine for all controllers and making it overwriteable was just done for symmetry. Signed-off-by: Uwe Kleine-König [Brian: fixed warning] Tested-by: Brian Norris Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 05fcdfea640b..352e23891f58 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -456,6 +456,8 @@ struct nand_buffers { * flash device. * @read_byte: [REPLACEABLE] read one byte from the chip * @read_word: [REPLACEABLE] read one word from the chip + * @write_byte: [REPLACEABLE] write a single byte to the chip on the + * low 8 I/O lines * @write_buf: [REPLACEABLE] write data from the buffer to the chip * @read_buf: [REPLACEABLE] read data from the chip into the buffer * @select_chip: [REPLACEABLE] select chip nr @@ -548,6 +550,7 @@ struct nand_chip { uint8_t (*read_byte)(struct mtd_info *mtd); u16 (*read_word)(struct mtd_info *mtd); + void (*write_byte)(struct mtd_info *mtd, uint8_t byte); void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len); void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len); void (*select_chip)(struct mtd_info *mtd, int chip); -- cgit v1.2.3 From 5acac1be499d979e3aa463ea73a498888faefcbe Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 4 Dec 2013 18:28:20 +0100 Subject: tick: Rename tick_check_idle() to tick_irq_enter() This makes the code more symetric against the existing tick functions called on irq exit: tick_irq_exit() and tick_nohz_irq_exit(). These function are also symetric as they mirror each other's action: we start to account idle time on irq exit and we stop this accounting on irq entry. Also the tick is stopped on irq exit and timekeeping catches up with the tickless time elapsed until we reach irq entry. This rename was suggested by Peter Zijlstra a long while ago but it got forgotten in the mass. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Alex Shi Cc: Steven Rostedt Cc: Paul E. McKenney Cc: John Stultz Cc: Kevin Hilman Link: http://lkml.kernel.org/r/1387320692-28460-2-git-send-email-fweisbec@gmail.com Signed-off-by: Frederic Weisbecker --- include/linux/tick.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 0175d8663b6c..b84773cb9f4c 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -104,7 +104,7 @@ extern struct cpumask *tick_get_broadcast_oneshot_mask(void); extern void tick_clock_notify(void); extern int tick_check_oneshot_change(int allow_nohz); extern struct tick_sched *tick_get_tick_sched(int cpu); -extern void tick_check_idle(void); +extern void tick_irq_enter(void); extern int tick_oneshot_mode_active(void); # ifndef arch_needs_cpu # define arch_needs_cpu(cpu) (0) @@ -112,7 +112,7 @@ extern int tick_oneshot_mode_active(void); # else static inline void tick_clock_notify(void) { } static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } -static inline void tick_check_idle(void) { } +static inline void tick_irq_enter(void) { } static inline int tick_oneshot_mode_active(void) { return 0; } # endif @@ -121,7 +121,7 @@ static inline void tick_init(void) { } static inline void tick_cancel_sched_timer(int cpu) { } static inline void tick_clock_notify(void) { } static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } -static inline void tick_check_idle(void) { } +static inline void tick_irq_enter(void) { } static inline int tick_oneshot_mode_active(void) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ -- cgit v1.2.3 From 8fe8ff09ce3b5750e1f3e45a1f4a81d59c7ff1f1 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Wed, 15 Jan 2014 14:51:38 +0100 Subject: sched/nohz: Fix overflow error in scheduler_tick_max_deferment() While calculating the scheduler tick max deferment, the delta is converted from microseconds to nanoseconds through a multiplication against NSEC_PER_USEC. But this microseconds operand is an unsigned int, thus the result may likely overflow. The result is cast to u64 but only once the operation is completed, which is too late to avoid overflown result. This is currently not a problem because the scheduler tick max deferment is 1 second. But this may become an issue as we plan to make this value tunable. So lets fix this by casting the usecs value to u64 before multiplying by NSECS_PER_USEC. Also to prevent from this kind of mistake to happen again, move this ad-hoc jiffies -> nsecs conversion to a new helper. Signed-off-by: Kevin Hilman Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Alex Shi Cc: Steven Rostedt Cc: Paul E. McKenney Cc: John Stultz Cc: Kevin Hilman Link: http://lkml.kernel.org/r/1387315388-31676-2-git-send-email-khilman@linaro.org [move ad-hoc conversion to jiffies_to_nsecs helper] Signed-off-by: Frederic Weisbecker --- include/linux/jiffies.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index d235e88cfd7c..1f44466c1e9d 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -294,6 +294,12 @@ extern unsigned long preset_lpj; */ extern unsigned int jiffies_to_msecs(const unsigned long j); extern unsigned int jiffies_to_usecs(const unsigned long j); + +static inline u64 jiffies_to_nsecs(const unsigned long j) +{ + return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC; +} + extern unsigned long msecs_to_jiffies(const unsigned int m); extern unsigned long usecs_to_jiffies(const unsigned int u); extern unsigned long timespec_to_jiffies(const struct timespec *value); -- cgit v1.2.3 From a8aceccb4d5db0acb476b74051525fb26f57f8ae Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 18 Jul 2013 11:52:33 +0300 Subject: CLK: TI: add DT alias clock registration mechanism Some devices require their clocks to be available with a specific dev-id con-id mapping. With DT, the clocks can be found by default only with their name, or alternatively through the device node of the consumer. With drivers, that don't support DT fully yet, add mechanism to register specific clock names. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 include/linux/clk/ti.h (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h new file mode 100644 index 000000000000..df94c243205e --- /dev/null +++ b/include/linux/clk/ti.h @@ -0,0 +1,42 @@ +/* + * TI clock drivers support + * + * Copyright (C) 2013 Texas Instruments, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#ifndef __LINUX_CLK_TI_H__ +#define __LINUX_CLK_TI_H__ + +#include + +/** + * struct ti_dt_clk - OMAP DT clock alias declarations + * @lk: clock lookup definition + * @node_name: clock DT node to map to + */ +struct ti_dt_clk { + struct clk_lookup lk; + char *node_name; +}; + +#define DT_CLK(dev, con, name) \ + { \ + .lk = { \ + .dev_id = dev, \ + .con_id = con, \ + }, \ + .node_name = name, \ + } + + +void ti_dt_clocks_register(struct ti_dt_clk *oclks); + +#endif -- cgit v1.2.3 From 819b4861c18d602463cfe815041d11fd81002654 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Tue, 22 Oct 2013 11:39:36 +0300 Subject: CLK: ti: add init support for clock IP blocks ti_dt_clk_init_provider() can now be used to initialize the contents of a single clock IP block. This parses all the clocks under the IP block and calls the corresponding init function for them. This patch also introduces a helper function for the TI clock drivers to get register info from DT and append the master IP info to this. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk-provider.h | 2 ++ include/linux/clk/ti.h | 35 +++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 999b28ba38f7..448b2294820f 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -488,6 +488,8 @@ struct clk_onecell_data { unsigned int clk_num; }; +extern struct of_device_id __clk_of_table; + #define CLK_OF_DECLARE(name, compat, fn) \ static const struct of_device_id __clk_of_table_##name \ __used __section(__clk_of_table) \ diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index df94c243205e..c6eded5eea76 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -36,7 +36,42 @@ struct ti_dt_clk { .node_name = name, \ } +/* Maximum number of clock memmaps */ +#define CLK_MAX_MEMMAPS 4 +typedef void (*ti_of_clk_init_cb_t)(struct clk_hw *, struct device_node *); + +/** + * struct clk_omap_reg - OMAP register declaration + * @offset: offset from the master IP module base address + * @index: index of the master IP module + */ +struct clk_omap_reg { + u16 offset; + u16 index; +}; + +/** + * struct ti_clk_ll_ops - low-level register access ops for a clock + * @clk_readl: pointer to register read function + * @clk_writel: pointer to register write function + * + * Low-level register access ops are generally used by the basic clock types + * (clk-gate, clk-mux, clk-divider etc.) to provide support for various + * low-level hardware interfaces (direct MMIO, regmap etc.), but can also be + * used by other hardware-specific clock drivers if needed. + */ +struct ti_clk_ll_ops { + u32 (*clk_readl)(void __iomem *reg); + void (*clk_writel)(u32 val, void __iomem *reg); +}; + +extern struct ti_clk_ll_ops *ti_clk_ll_ops; + +void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index); void ti_dt_clocks_register(struct ti_dt_clk *oclks); +void ti_dt_clk_init_provider(struct device_node *np, int index); +int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, + ti_of_clk_init_cb_t func); #endif -- cgit v1.2.3 From f38b0dd63f0d0cca753bf0997eefdfb23dcc9518 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 12 Jun 2013 16:04:34 +0300 Subject: CLK: TI: Add DPLL clock support The OMAP clock driver now supports DPLL clock type. This patch also adds support for DT DPLL nodes. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 172 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 172 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index c6eded5eea76..3f9de3973582 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -17,6 +17,153 @@ #include +/** + * struct dpll_data - DPLL registers and integration data + * @mult_div1_reg: register containing the DPLL M and N bitfields + * @mult_mask: mask of the DPLL M bitfield in @mult_div1_reg + * @div1_mask: mask of the DPLL N bitfield in @mult_div1_reg + * @clk_bypass: struct clk pointer to the clock's bypass clock input + * @clk_ref: struct clk pointer to the clock's reference clock input + * @control_reg: register containing the DPLL mode bitfield + * @enable_mask: mask of the DPLL mode bitfield in @control_reg + * @last_rounded_rate: cache of the last rate result of omap2_dpll_round_rate() + * @last_rounded_m: cache of the last M result of omap2_dpll_round_rate() + * @last_rounded_m4xen: cache of the last M4X result of + * omap4_dpll_regm4xen_round_rate() + * @last_rounded_lpmode: cache of the last lpmode result of + * omap4_dpll_lpmode_recalc() + * @max_multiplier: maximum valid non-bypass multiplier value (actual) + * @last_rounded_n: cache of the last N result of omap2_dpll_round_rate() + * @min_divider: minimum valid non-bypass divider value (actual) + * @max_divider: maximum valid non-bypass divider value (actual) + * @modes: possible values of @enable_mask + * @autoidle_reg: register containing the DPLL autoidle mode bitfield + * @idlest_reg: register containing the DPLL idle status bitfield + * @autoidle_mask: mask of the DPLL autoidle mode bitfield in @autoidle_reg + * @freqsel_mask: mask of the DPLL jitter correction bitfield in @control_reg + * @idlest_mask: mask of the DPLL idle status bitfield in @idlest_reg + * @lpmode_mask: mask of the DPLL low-power mode bitfield in @control_reg + * @m4xen_mask: mask of the DPLL M4X multiplier bitfield in @control_reg + * @auto_recal_bit: bitshift of the driftguard enable bit in @control_reg + * @recal_en_bit: bitshift of the PRM_IRQENABLE_* bit for recalibration IRQs + * @recal_st_bit: bitshift of the PRM_IRQSTATUS_* bit for recalibration IRQs + * @flags: DPLL type/features (see below) + * + * Possible values for @flags: + * DPLL_J_TYPE: "J-type DPLL" (only some 36xx, 4xxx DPLLs) + * + * @freqsel_mask is only used on the OMAP34xx family and AM35xx. + * + * XXX Some DPLLs have multiple bypass inputs, so it's not technically + * correct to only have one @clk_bypass pointer. + * + * XXX The runtime-variable fields (@last_rounded_rate, @last_rounded_m, + * @last_rounded_n) should be separated from the runtime-fixed fields + * and placed into a different structure, so that the runtime-fixed data + * can be placed into read-only space. + */ +struct dpll_data { + void __iomem *mult_div1_reg; + u32 mult_mask; + u32 div1_mask; + struct clk *clk_bypass; + struct clk *clk_ref; + void __iomem *control_reg; + u32 enable_mask; + unsigned long last_rounded_rate; + u16 last_rounded_m; + u8 last_rounded_m4xen; + u8 last_rounded_lpmode; + u16 max_multiplier; + u8 last_rounded_n; + u8 min_divider; + u16 max_divider; + u8 modes; + void __iomem *autoidle_reg; + void __iomem *idlest_reg; + u32 autoidle_mask; + u32 freqsel_mask; + u32 idlest_mask; + u32 dco_mask; + u32 sddiv_mask; + u32 lpmode_mask; + u32 m4xen_mask; + u8 auto_recal_bit; + u8 recal_en_bit; + u8 recal_st_bit; + u8 flags; +}; + +struct clk_hw_omap_ops; + +/** + * struct clk_hw_omap - OMAP struct clk + * @node: list_head connecting this clock into the full clock list + * @enable_reg: register to write to enable the clock (see @enable_bit) + * @enable_bit: bitshift to write to enable/disable the clock (see @enable_reg) + * @flags: see "struct clk.flags possibilities" above + * @clksel_reg: for clksel clks, register va containing src/divisor select + * @clksel_mask: bitmask in @clksel_reg for the src/divisor selector + * @clksel: for clksel clks, pointer to struct clksel for this clock + * @dpll_data: for DPLLs, pointer to struct dpll_data for this clock + * @clkdm_name: clockdomain name that this clock is contained in + * @clkdm: pointer to struct clockdomain, resolved from @clkdm_name at runtime + * @ops: clock ops for this clock + */ +struct clk_hw_omap { + struct clk_hw hw; + struct list_head node; + unsigned long fixed_rate; + u8 fixed_div; + void __iomem *enable_reg; + u8 enable_bit; + u8 flags; + void __iomem *clksel_reg; + u32 clksel_mask; + const struct clksel *clksel; + struct dpll_data *dpll_data; + const char *clkdm_name; + struct clockdomain *clkdm; + const struct clk_hw_omap_ops *ops; +}; + +/* + * struct clk_hw_omap.flags possibilities + * + * XXX document the rest of the clock flags here + * + * ENABLE_REG_32BIT: (OMAP1 only) clock control register must be accessed + * with 32bit ops, by default OMAP1 uses 16bit ops. + * CLOCK_IDLE_CONTROL: (OMAP1 only) clock has autoidle support. + * CLOCK_NO_IDLE_PARENT: (OMAP1 only) when clock is enabled, its parent + * clock is put to no-idle mode. + * ENABLE_ON_INIT: Clock is enabled on init. + * INVERT_ENABLE: By default, clock enable bit behavior is '1' enable, '0' + * disable. This inverts the behavior making '0' enable and '1' disable. + * CLOCK_CLKOUTX2: (OMAP4 only) DPLL CLKOUT and CLKOUTX2 GATE_CTRL + * bits share the same register. This flag allows the + * omap4_dpllmx*() code to determine which GATE_CTRL bit field + * should be used. This is a temporary solution - a better approach + * would be to associate clock type-specific data with the clock, + * similar to the struct dpll_data approach. + * MEMMAP_ADDRESSING: Use memmap addressing to access clock registers. + */ +#define ENABLE_REG_32BIT (1 << 0) /* Use 32-bit access */ +#define CLOCK_IDLE_CONTROL (1 << 1) +#define CLOCK_NO_IDLE_PARENT (1 << 2) +#define ENABLE_ON_INIT (1 << 3) /* Enable upon framework init */ +#define INVERT_ENABLE (1 << 4) /* 0 enables, 1 disables */ +#define CLOCK_CLKOUTX2 (1 << 5) +#define MEMMAP_ADDRESSING (1 << 6) + +/* CM_CLKEN_PLL*.EN* bit values - not all are available for every DPLL */ +#define DPLL_LOW_POWER_STOP 0x1 +#define DPLL_LOW_POWER_BYPASS 0x5 +#define DPLL_LOCKED 0x7 + +/* DPLL Type and DCO Selection Flags */ +#define DPLL_J_TYPE 0x1 + /** * struct ti_dt_clk - OMAP DT clock alias declarations * @lk: clock lookup definition @@ -68,10 +215,35 @@ struct ti_clk_ll_ops { extern struct ti_clk_ll_ops *ti_clk_ll_ops; +#define to_clk_hw_omap(_hw) container_of(_hw, struct clk_hw_omap, hw) + +void omap2_init_clk_hw_omap_clocks(struct clk *clk); +int omap3_noncore_dpll_enable(struct clk_hw *hw); +void omap3_noncore_dpll_disable(struct clk_hw *hw); +int omap3_noncore_dpll_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate); +unsigned long omap4_dpll_regm4xen_recalc(struct clk_hw *hw, + unsigned long parent_rate); +long omap4_dpll_regm4xen_round_rate(struct clk_hw *hw, + unsigned long target_rate, + unsigned long *parent_rate); +u8 omap2_init_dpll_parent(struct clk_hw *hw); +unsigned long omap3_dpll_recalc(struct clk_hw *hw, unsigned long parent_rate); +long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate, + unsigned long *parent_rate); +void omap2_init_clk_clkdm(struct clk_hw *clk); +unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, + unsigned long parent_rate); +int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, + unsigned long parent_rate); + void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index); void ti_dt_clocks_register(struct ti_dt_clk *oclks); void ti_dt_clk_init_provider(struct device_node *np, int index); int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, ti_of_clk_init_cb_t func); +extern const struct clk_hw_omap_ops clkhwops_omap3_dpll; +extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx; + #endif -- cgit v1.2.3 From b1a07b478b63f0a8f971b3a82ce34a67a9324547 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Tue, 18 Jun 2013 16:27:57 +0300 Subject: CLK: TI: add autoidle support TI clk driver now routes some of the basic clocks through own registration routine to allow autoidle support. This routine just checks a couple of device node properties and adds autoidle support if required, and just passes the registration forward to basic clocks. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 3f9de3973582..ca38ee3620b1 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -242,6 +242,15 @@ void ti_dt_clocks_register(struct ti_dt_clk *oclks); void ti_dt_clk_init_provider(struct device_node *np, int index); int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, ti_of_clk_init_cb_t func); +int of_ti_clk_autoidle_setup(struct device_node *node); + +#ifdef CONFIG_OF +void of_ti_clk_allow_autoidle_all(void); +void of_ti_clk_deny_autoidle_all(void); +#else +static inline void of_ti_clk_allow_autoidle_all(void) { } +static inline void of_ti_clk_deny_autoidle_all(void) { } +#endif extern const struct clk_hw_omap_ops clkhwops_omap3_dpll; extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx; -- cgit v1.2.3 From 975e15487d5abfd5f33fea9c1ba0b987604f0d0f Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Mon, 9 Sep 2013 15:46:45 +0300 Subject: clk: ti: add composite clock support This is a multipurpose clock node, which contains support for multiple sub-clocks. Uses basic composite clock type to implement the actual functionality, and TI specific gate, mux and divider clocks. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index ca38ee3620b1..c8c591dd3261 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -164,6 +164,14 @@ struct clk_hw_omap { /* DPLL Type and DCO Selection Flags */ #define DPLL_J_TYPE 0x1 +/* Composite clock component types */ +enum { + CLK_COMPONENT_TYPE_GATE = 0, + CLK_COMPONENT_TYPE_DIVIDER, + CLK_COMPONENT_TYPE_MUX, + CLK_COMPONENT_TYPE_MAX, +}; + /** * struct ti_dt_clk - OMAP DT clock alias declarations * @lk: clock lookup definition @@ -236,6 +244,9 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long parent_rate); int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, unsigned long parent_rate); +int omap2_dflt_clk_enable(struct clk_hw *hw); +void omap2_dflt_clk_disable(struct clk_hw *hw); +int omap2_dflt_clk_is_enabled(struct clk_hw *hw); void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index); void ti_dt_clocks_register(struct ti_dt_clk *oclks); @@ -243,6 +254,7 @@ void ti_dt_clk_init_provider(struct device_node *np, int index); int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, ti_of_clk_init_cb_t func); int of_ti_clk_autoidle_setup(struct device_node *node); +int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); #ifdef CONFIG_OF void of_ti_clk_allow_autoidle_all(void); -- cgit v1.2.3 From b4761198bfaf29649dc58a48e8b123ea4174ba95 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 13 Sep 2013 12:02:15 +0300 Subject: CLK: ti: add support for ti divider-clock This patch adds support for TI divider clock binding, which simply uses the basic clock divider to provide the features needed. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index c8c591dd3261..17fb49e4ff5e 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -223,6 +223,8 @@ struct ti_clk_ll_ops { extern struct ti_clk_ll_ops *ti_clk_ll_ops; +extern const struct clk_ops ti_clk_divider_ops; + #define to_clk_hw_omap(_hw) container_of(_hw, struct clk_hw_omap, hw) void omap2_init_clk_hw_omap_clocks(struct clk *clk); -- cgit v1.2.3 From f60b1ea5ea7ab1aee34a5ba55520b84b6e6d482e Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Tue, 18 Jun 2013 18:55:59 +0300 Subject: CLK: TI: add support for gate clock This patch adds support for TI specific gate clocks. These behave as basic gate-clock, but have different ops / hw-ops for controlling the actual gate, for example waiting until the clock is ready. Several sub-types are supported: - ti,gate-clock: basic gate clock with default ops/hwops - ti,clkdm-gate-clock: clockdomain level gate control - ti,dss-gate-clock: gate clock with DSS specific hardware handling - ti,am35xx-gate-clock: gate clock with AM35xx specific hardware handling - ti,hsdiv-gate-clock: gate clock with OMAP36xx hardware errata handling Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 17fb49e4ff5e..d94feb3b5519 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -244,6 +244,8 @@ long omap2_dpll_round_rate(struct clk_hw *hw, unsigned long target_rate, void omap2_init_clk_clkdm(struct clk_hw *clk); unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long parent_rate); +int omap2_clkops_enable_clkdm(struct clk_hw *hw); +void omap2_clkops_disable_clkdm(struct clk_hw *hw); int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, unsigned long parent_rate); int omap2_dflt_clk_enable(struct clk_hw *hw); @@ -268,5 +270,9 @@ static inline void of_ti_clk_deny_autoidle_all(void) { } extern const struct clk_hw_omap_ops clkhwops_omap3_dpll; extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx; +extern const struct clk_hw_omap_ops clkhwops_wait; +extern const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait; +extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait; +extern const struct clk_hw_omap_ops clkhwops_iclk_wait; #endif -- cgit v1.2.3 From 3cd4a596224565cff00b69a02d4b5fa7432ea6d3 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Wed, 21 Aug 2013 19:39:15 +0300 Subject: CLK: TI: add support for clockdomain binding Some OMAP clocks require knowledge about their parent clockdomain for book keeping purposes. This patch creates a new DT binding for TI clockdomains, which act as a collection of device clocks. Clockdomain itself is rather misleading name for the hardware functionality, as at least on OMAP4 / OMAP5 / DRA7 the clockdomains can be collections of either clocks and/or IP blocks, thus idle-domain or such might be more appropriate. For most cases on these SoCs, the kernel doesn't even need the information and the mappings can be ignored. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index d94feb3b5519..a3f89a60de07 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -255,6 +255,7 @@ int omap2_dflt_clk_is_enabled(struct clk_hw *hw); void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index); void ti_dt_clocks_register(struct ti_dt_clk *oclks); void ti_dt_clk_init_provider(struct device_node *np, int index); +void ti_dt_clockdomains_setup(void); int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, ti_of_clk_init_cb_t func); int of_ti_clk_autoidle_setup(struct device_node *node); -- cgit v1.2.3 From 6a369c584fbe98264458b9442e780f8078f2f7ad Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 13 Sep 2013 20:22:27 +0300 Subject: clk: ti: add support for basic mux clock ti,mux-clock provides now a binding for basic mux support. This is just using the basic clock type. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index a3f89a60de07..6e205b140071 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -224,6 +224,7 @@ struct ti_clk_ll_ops { extern struct ti_clk_ll_ops *ti_clk_ll_ops; extern const struct clk_ops ti_clk_divider_ops; +extern const struct clk_ops ti_clk_mux_ops; #define to_clk_hw_omap(_hw) container_of(_hw, struct clk_hw_omap, hw) -- cgit v1.2.3 From 21876ea566fedadd56453af5a1a91eb667c25422 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 18 Jul 2013 15:57:51 +0300 Subject: CLK: TI: add omap4 clock init file clk-44xx.c now contains the clock init functionality for omap4, including DT clock registration and adding of static clkdev entries. Signed-off-by: Tero Kristo Tested-by: Nishanth Menon Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 6e205b140071..a56ff1216f8d 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -247,6 +247,7 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, unsigned long parent_rate); int omap2_clkops_enable_clkdm(struct clk_hw *hw); void omap2_clkops_disable_clkdm(struct clk_hw *hw); +int omap2_clk_disable_autoidle_all(void); int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, unsigned long parent_rate); int omap2_dflt_clk_enable(struct clk_hw *hw); @@ -262,6 +263,8 @@ int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, int of_ti_clk_autoidle_setup(struct device_node *node); int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); +int omap4xxx_dt_clk_init(void); + #ifdef CONFIG_OF void of_ti_clk_allow_autoidle_all(void); void of_ti_clk_deny_autoidle_all(void); -- cgit v1.2.3 From 52b14728dd890f8a62bffce8dfece496434c2b41 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 18 Jul 2013 17:15:51 +0300 Subject: CLK: TI: add omap5 clock init file clk-54xx.c now contains the clock init functionality for omap5, including DT clock registration and adding of static clkdev entries. Signed-off-by: Tero Kristo Tested-by: Nishanth Menon Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index a56ff1216f8d..6647f28b445d 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -264,6 +264,7 @@ int of_ti_clk_autoidle_setup(struct device_node *node); int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); int omap4xxx_dt_clk_init(void); +int omap5xxx_dt_clk_init(void); #ifdef CONFIG_OF void of_ti_clk_allow_autoidle_all(void); -- cgit v1.2.3 From 251a449dd3290d5af35da1113e155a37bf8b3ece Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Thu, 18 Jul 2013 17:41:00 +0300 Subject: CLK: TI: add dra7 clock init file clk-7xx.c now contains the clock init functionality for dra7, including DT clock registration and adding of static clkdev entries. Signed-off-by: Tero Kristo Tested-by: Nishanth Menon Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 6647f28b445d..506155b1fd1f 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -265,6 +265,7 @@ int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); int omap4xxx_dt_clk_init(void); int omap5xxx_dt_clk_init(void); +int dra7xx_dt_clk_init(void); #ifdef CONFIG_OF void of_ti_clk_allow_autoidle_all(void); -- cgit v1.2.3 From 45622e2162b6d5907006f4595f2ac862afe1dfb5 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 19 Jul 2013 11:36:01 +0300 Subject: CLK: TI: add am33xx clock init file clk-33xx.c now contains the clock init functionality for am33xx, including DT clock registration and adding of static clkdev entries. This patch also moves the omap2_clk_enable_init_clocks declaration to the driver include, as this is needed by the am33xx clock init code. Signed-off-by: Tero Kristo Tested-by: Nishanth Menon Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 506155b1fd1f..0e7c8d956f2b 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -248,6 +248,7 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw, int omap2_clkops_enable_clkdm(struct clk_hw *hw); void omap2_clkops_disable_clkdm(struct clk_hw *hw); int omap2_clk_disable_autoidle_all(void); +void omap2_clk_enable_init_clocks(const char **clk_names, u8 num_clocks); int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, unsigned long parent_rate); int omap2_dflt_clk_enable(struct clk_hw *hw); @@ -266,6 +267,7 @@ int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); int omap4xxx_dt_clk_init(void); int omap5xxx_dt_clk_init(void); int dra7xx_dt_clk_init(void); +int am33xx_dt_clk_init(void); #ifdef CONFIG_OF void of_ti_clk_allow_autoidle_all(void); -- cgit v1.2.3 From 24582b3407775d57f06becfccd8cd202bc01eda6 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Mon, 15 Jul 2013 13:14:20 +0300 Subject: CLK: TI: add interface clock support for OMAP3 OMAP3 has interface clocks in addition to functional clocks, which require special handling for the autoidle and idle status register offsets mainly. Signed-off-by: Tero Kristo Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 0e7c8d956f2b..17c034ea03ad 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -282,6 +282,11 @@ extern const struct clk_hw_omap_ops clkhwops_omap4_dpllmx; extern const struct clk_hw_omap_ops clkhwops_wait; extern const struct clk_hw_omap_ops clkhwops_omap3430es2_dss_usbhost_wait; extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_module_wait; +extern const struct clk_hw_omap_ops clkhwops_am35xx_ipss_wait; +extern const struct clk_hw_omap_ops clkhwops_iclk; extern const struct clk_hw_omap_ops clkhwops_iclk_wait; +extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_ssi_wait; +extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_dss_usbhost_wait; +extern const struct clk_hw_omap_ops clkhwops_omap3430es2_iclk_hsotgusb_wait; #endif -- cgit v1.2.3 From aafd900cab87d339dc3004c241eebc854005124b Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 2 Aug 2013 14:04:19 +0300 Subject: CLK: TI: add omap3 clock init file clk-3xxx.c now contains the clock init functionality for omap3, including DT clock registration and adding of static clkdev entries. Signed-off-by: Tero Kristo Tested-by: Nishanth Menon Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 17c034ea03ad..3d2ba57446cd 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -254,6 +254,7 @@ int omap3_dpll4_set_rate(struct clk_hw *clk, unsigned long rate, int omap2_dflt_clk_enable(struct clk_hw *hw); void omap2_dflt_clk_disable(struct clk_hw *hw); int omap2_dflt_clk_is_enabled(struct clk_hw *hw); +void omap3_clk_lock_dpll5(void); void __iomem *ti_clk_get_reg_addr(struct device_node *node, int index); void ti_dt_clocks_register(struct ti_dt_clk *oclks); @@ -264,6 +265,10 @@ int ti_clk_retry_init(struct device_node *node, struct clk_hw *hw, int of_ti_clk_autoidle_setup(struct device_node *node); int ti_clk_add_component(struct device_node *node, struct clk_hw *hw, int type); +int omap3430_dt_clk_init(void); +int omap3630_dt_clk_init(void); +int am35xx_dt_clk_init(void); +int ti81xx_dt_clk_init(void); int omap4xxx_dt_clk_init(void); int omap5xxx_dt_clk_init(void); int dra7xx_dt_clk_init(void); -- cgit v1.2.3 From ffab239956613be7b81d00999128fd05fd096762 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 20 Sep 2013 17:02:40 +0300 Subject: CLK: TI: add am43xx clock init file clk-43xx.c now contains the clock init functionality for am43xx, including DT clock registration and adding of static clkdev entries. Signed-off-by: Tero Kristo Tested-by: Nishanth Menon Acked-by: Tony Lindgren Signed-off-by: Mike Turquette --- include/linux/clk/ti.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h index 3d2ba57446cd..092b64168d7f 100644 --- a/include/linux/clk/ti.h +++ b/include/linux/clk/ti.h @@ -273,6 +273,7 @@ int omap4xxx_dt_clk_init(void); int omap5xxx_dt_clk_init(void); int dra7xx_dt_clk_init(void); int am33xx_dt_clk_init(void); +int am43xx_dt_clk_init(void); #ifdef CONFIG_OF void of_ti_clk_allow_autoidle_all(void); -- cgit v1.2.3 From 868d2ee252918e7640df80156df9e1299f8118f5 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Wed, 18 Dec 2013 21:39:39 +0530 Subject: dmaengine: fix kernel-doc style typos for few comments Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index fa6b4285d8d2..188108c36313 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -257,7 +257,7 @@ struct dma_chan_percpu { * @dev: class device for sysfs * @device_node: used to add this to the device chan list * @local: per-cpu pointer to a struct dma_chan_percpu - * @client-count: how many clients are using this channel + * @client_count: how many clients are using this channel * @table_count: number of appearances in the mem-to-mem allocation table * @private: private data for certain client-channel associations */ @@ -279,10 +279,10 @@ struct dma_chan { /** * struct dma_chan_dev - relate sysfs device node to backing channel device - * @chan - driver channel device - * @device - sysfs device - * @dev_id - parent dma_device dev_id - * @idr_ref - reference count to gate release of dma_device dev_id + * @chan: driver channel device + * @device: sysfs device + * @dev_id: parent dma_device dev_id + * @idr_ref: reference count to gate release of dma_device dev_id */ struct dma_chan_dev { struct dma_chan *chan; -- cgit v1.2.3 From 3f97c6ff6de8a657e4d4d826e502698004cfc2ae Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Thu, 26 Dec 2013 15:37:45 +0800 Subject: mtd: nand: add SanDisk manufacturer ID Add the manufactor ID for SanDisk. Make preparation for SanDisk SDTNRGAMA-008G. Signed-off-by: Huang Shijie Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 352e23891f58..e03a78c70de1 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -633,6 +633,7 @@ struct nand_chip { #define NAND_MFR_AMD 0x01 #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 +#define NAND_MFR_SANDISK 0x45 /* The maximum expected count of bytes in the NAND ID sequence */ #define NAND_MAX_ID_LEN 8 -- cgit v1.2.3 From 4968a4124cf2df4b3672eed4714c6755f10f400c Mon Sep 17 00:00:00 2001 From: Huang Shijie Date: Fri, 3 Jan 2014 16:50:39 +0800 Subject: mtd: nand: add Intel manufacturer ID Add the Intel manufacturer Id. Tested with Intel JS29F32G08ACMD1(4096 + 224) which is ONFI 2.0 compliant nand. Signed-off-by: Huang Shijie Signed-off-by: Brian Norris --- include/linux/mtd/nand.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index e03a78c70de1..32f8612469d8 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -634,6 +634,7 @@ struct nand_chip { #define NAND_MFR_MACRONIX 0xc2 #define NAND_MFR_EON 0x92 #define NAND_MFR_SANDISK 0x45 +#define NAND_MFR_INTEL 0x89 /* The maximum expected count of bytes in the NAND ID sequence */ #define NAND_MAX_ID_LEN 8 -- cgit v1.2.3 From 0a8899b31a7d6c4a3bc7fdbd7c8c1fc79e726363 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Sat, 11 Jan 2014 15:51:45 -0800 Subject: mtd: mtdram: add missing 'const' mtdram_init_device() wasn't updated along with mtd_partition.name. Signed-off-by: Brian Norris Cc: Geert Uytterhoeven --- include/linux/mtd/mtdram.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtdram.h b/include/linux/mtd/mtdram.h index 68891313875d..628a6a21ddf0 100644 --- a/include/linux/mtd/mtdram.h +++ b/include/linux/mtd/mtdram.h @@ -3,6 +3,6 @@ #include int mtdram_init_device(struct mtd_info *mtd, void *mapped_address, - unsigned long size, char *name); + unsigned long size, const char *name); #endif /* __MTD_MTDRAM_H__ */ -- cgit v1.2.3 From 186e4f7a4b1883f3f46aa15366c0bcebc28fdda7 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 22 Nov 2013 14:48:37 +0800 Subject: ceph: handle session flush message Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 2ad7b860f062..26bb587deb78 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -282,6 +282,8 @@ enum { CEPH_SESSION_RENEWCAPS, CEPH_SESSION_STALE, CEPH_SESSION_RECALL_STATE, + CEPH_SESSION_FLUSHMSG, + CEPH_SESSION_FLUSHMSG_ACK, }; extern const char *ceph_session_op_name(int op); -- cgit v1.2.3 From 4ee6a914edbbd2543884f0ad7d58ea471136be32 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Sun, 24 Nov 2013 14:43:46 +0800 Subject: ceph: remove exported caps when handling cap import message Version 3 cap import message includes the ID of the exported caps. It allow us to remove the exported caps if we still haven't received the corresponding cap export message. We remove the exported caps because they are stale, keeping them can compromise consistence. Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_fs.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 26bb587deb78..0a37b989b52f 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -459,7 +459,8 @@ struct ceph_mds_reply_cap { __u8 flags; /* CEPH_CAP_FLAG_* */ } __attribute__ ((packed)); -#define CEPH_CAP_FLAG_AUTH 1 /* cap is issued by auth mds */ +#define CEPH_CAP_FLAG_AUTH (1 << 0) /* cap is issued by auth mds */ +#define CEPH_CAP_FLAG_RELEASE (1 << 1) /* release the cap */ /* inode record, for bundling with mds reply */ struct ceph_mds_reply_inode { @@ -660,6 +661,14 @@ struct ceph_mds_caps { __le32 time_warp_seq; } __attribute__ ((packed)); +struct ceph_mds_cap_peer { + __le64 cap_id; + __le32 seq; + __le32 mseq; + __le32 mds; + __u8 flags; +} __attribute__ ((packed)); + /* cap release msg head */ struct ceph_mds_cap_release { __le32 num; /* number of cap_items that follow */ -- cgit v1.2.3 From 80213a84a96c3040f5824bce646a184d5dd3dd2b Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Tue, 21 Jan 2014 11:07:16 +0800 Subject: libceph: support CEPH_FEATURE_EXPORT_PEER Signed-off-by: Yan, Zheng --- include/linux/ceph/ceph_features.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 5f42e4412909..d21b34d94436 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -80,7 +80,8 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ CEPH_FEATURE_OSDHASHPSPOOL | \ - CEPH_FEATURE_CRUSH_V2) + CEPH_FEATURE_CRUSH_V2 | \ + CEPH_FEATURE_EXPORT_PEER) #define CEPH_FEATURES_REQUIRED_DEFAULT \ (CEPH_FEATURE_NOSRCADDR | \ -- cgit v1.2.3 From bca266b3886b8bc587db044750c8a00d674b4d09 Mon Sep 17 00:00:00 2001 From: CaiZhiyong Date: Tue, 21 Jan 2014 14:39:25 -0800 Subject: block: remove unrelated header files and export symbol Fix up the following items: - remove unrelated header files. - export interface function. - modify function cmdline_parts_parse return value, this will make it more friendly for the caller. Signed-off-by: CaiZhiyong Cc: Ezequiel Garcia CC: Brian Norris Cc: "Wanglin (Albert)" Cc: Artem Bityutskiy Cc: Karel Zak Cc: Shmulik Ladkani Cc: David Woodhouse Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Jens Axboe --- include/linux/cmdline-parser.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cmdline-parser.h b/include/linux/cmdline-parser.h index a0f9280421ec..2e6dce6e5c2a 100644 --- a/include/linux/cmdline-parser.h +++ b/include/linux/cmdline-parser.h @@ -37,9 +37,9 @@ int cmdline_parts_parse(struct cmdline_parts **parts, const char *cmdline); struct cmdline_parts *cmdline_parts_find(struct cmdline_parts *parts, const char *bdev); -void cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, - int slot, - int (*add_part)(int, struct cmdline_subpart *, void *), - void *param); +int cmdline_parts_set(struct cmdline_parts *parts, sector_t disk_size, + int slot, + int (*add_part)(int, struct cmdline_subpart *, void *), + void *param); #endif /* CMDLINEPARSEH */ -- cgit v1.2.3 From 74e200c781501fc7a551ae04e2d4171ba0a60d9b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 5 Dec 2013 18:26:06 -0800 Subject: MIPS: BCM63XX: move UART register definitions Move the BCM63XX UART driver definitions to include/linux/serial_bcm63xx.h such that we do not rely on the MIPS BCM63XX code to provide these for us. Signed-off-by: Florian Fainelli Signed-off-by: John Crispin Patchwork: http://patchwork.linux-mips.org/patch/6202/ --- include/linux/serial_bcm63xx.h | 119 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 119 insertions(+) create mode 100644 include/linux/serial_bcm63xx.h (limited to 'include/linux') diff --git a/include/linux/serial_bcm63xx.h b/include/linux/serial_bcm63xx.h new file mode 100644 index 000000000000..570e964dc899 --- /dev/null +++ b/include/linux/serial_bcm63xx.h @@ -0,0 +1,119 @@ +#ifndef _LINUX_SERIAL_BCM63XX_H +#define _LINUX_SERIAL_BCM63XX_H + +/* UART Control Register */ +#define UART_CTL_REG 0x0 +#define UART_CTL_RXTMOUTCNT_SHIFT 0 +#define UART_CTL_RXTMOUTCNT_MASK (0x1f << UART_CTL_RXTMOUTCNT_SHIFT) +#define UART_CTL_RSTTXDN_SHIFT 5 +#define UART_CTL_RSTTXDN_MASK (1 << UART_CTL_RSTTXDN_SHIFT) +#define UART_CTL_RSTRXFIFO_SHIFT 6 +#define UART_CTL_RSTRXFIFO_MASK (1 << UART_CTL_RSTRXFIFO_SHIFT) +#define UART_CTL_RSTTXFIFO_SHIFT 7 +#define UART_CTL_RSTTXFIFO_MASK (1 << UART_CTL_RSTTXFIFO_SHIFT) +#define UART_CTL_STOPBITS_SHIFT 8 +#define UART_CTL_STOPBITS_MASK (0xf << UART_CTL_STOPBITS_SHIFT) +#define UART_CTL_STOPBITS_1 (0x7 << UART_CTL_STOPBITS_SHIFT) +#define UART_CTL_STOPBITS_2 (0xf << UART_CTL_STOPBITS_SHIFT) +#define UART_CTL_BITSPERSYM_SHIFT 12 +#define UART_CTL_BITSPERSYM_MASK (0x3 << UART_CTL_BITSPERSYM_SHIFT) +#define UART_CTL_XMITBRK_SHIFT 14 +#define UART_CTL_XMITBRK_MASK (1 << UART_CTL_XMITBRK_SHIFT) +#define UART_CTL_RSVD_SHIFT 15 +#define UART_CTL_RSVD_MASK (1 << UART_CTL_RSVD_SHIFT) +#define UART_CTL_RXPAREVEN_SHIFT 16 +#define UART_CTL_RXPAREVEN_MASK (1 << UART_CTL_RXPAREVEN_SHIFT) +#define UART_CTL_RXPAREN_SHIFT 17 +#define UART_CTL_RXPAREN_MASK (1 << UART_CTL_RXPAREN_SHIFT) +#define UART_CTL_TXPAREVEN_SHIFT 18 +#define UART_CTL_TXPAREVEN_MASK (1 << UART_CTL_TXPAREVEN_SHIFT) +#define UART_CTL_TXPAREN_SHIFT 18 +#define UART_CTL_TXPAREN_MASK (1 << UART_CTL_TXPAREN_SHIFT) +#define UART_CTL_LOOPBACK_SHIFT 20 +#define UART_CTL_LOOPBACK_MASK (1 << UART_CTL_LOOPBACK_SHIFT) +#define UART_CTL_RXEN_SHIFT 21 +#define UART_CTL_RXEN_MASK (1 << UART_CTL_RXEN_SHIFT) +#define UART_CTL_TXEN_SHIFT 22 +#define UART_CTL_TXEN_MASK (1 << UART_CTL_TXEN_SHIFT) +#define UART_CTL_BRGEN_SHIFT 23 +#define UART_CTL_BRGEN_MASK (1 << UART_CTL_BRGEN_SHIFT) + +/* UART Baudword register */ +#define UART_BAUD_REG 0x4 + +/* UART Misc Control register */ +#define UART_MCTL_REG 0x8 +#define UART_MCTL_DTR_SHIFT 0 +#define UART_MCTL_DTR_MASK (1 << UART_MCTL_DTR_SHIFT) +#define UART_MCTL_RTS_SHIFT 1 +#define UART_MCTL_RTS_MASK (1 << UART_MCTL_RTS_SHIFT) +#define UART_MCTL_RXFIFOTHRESH_SHIFT 8 +#define UART_MCTL_RXFIFOTHRESH_MASK (0xf << UART_MCTL_RXFIFOTHRESH_SHIFT) +#define UART_MCTL_TXFIFOTHRESH_SHIFT 12 +#define UART_MCTL_TXFIFOTHRESH_MASK (0xf << UART_MCTL_TXFIFOTHRESH_SHIFT) +#define UART_MCTL_RXFIFOFILL_SHIFT 16 +#define UART_MCTL_RXFIFOFILL_MASK (0x1f << UART_MCTL_RXFIFOFILL_SHIFT) +#define UART_MCTL_TXFIFOFILL_SHIFT 24 +#define UART_MCTL_TXFIFOFILL_MASK (0x1f << UART_MCTL_TXFIFOFILL_SHIFT) + +/* UART External Input Configuration register */ +#define UART_EXTINP_REG 0xc +#define UART_EXTINP_RI_SHIFT 0 +#define UART_EXTINP_RI_MASK (1 << UART_EXTINP_RI_SHIFT) +#define UART_EXTINP_CTS_SHIFT 1 +#define UART_EXTINP_CTS_MASK (1 << UART_EXTINP_CTS_SHIFT) +#define UART_EXTINP_DCD_SHIFT 2 +#define UART_EXTINP_DCD_MASK (1 << UART_EXTINP_DCD_SHIFT) +#define UART_EXTINP_DSR_SHIFT 3 +#define UART_EXTINP_DSR_MASK (1 << UART_EXTINP_DSR_SHIFT) +#define UART_EXTINP_IRSTAT(x) (1 << (x + 4)) +#define UART_EXTINP_IRMASK(x) (1 << (x + 8)) +#define UART_EXTINP_IR_RI 0 +#define UART_EXTINP_IR_CTS 1 +#define UART_EXTINP_IR_DCD 2 +#define UART_EXTINP_IR_DSR 3 +#define UART_EXTINP_RI_NOSENSE_SHIFT 16 +#define UART_EXTINP_RI_NOSENSE_MASK (1 << UART_EXTINP_RI_NOSENSE_SHIFT) +#define UART_EXTINP_CTS_NOSENSE_SHIFT 17 +#define UART_EXTINP_CTS_NOSENSE_MASK (1 << UART_EXTINP_CTS_NOSENSE_SHIFT) +#define UART_EXTINP_DCD_NOSENSE_SHIFT 18 +#define UART_EXTINP_DCD_NOSENSE_MASK (1 << UART_EXTINP_DCD_NOSENSE_SHIFT) +#define UART_EXTINP_DSR_NOSENSE_SHIFT 19 +#define UART_EXTINP_DSR_NOSENSE_MASK (1 << UART_EXTINP_DSR_NOSENSE_SHIFT) + +/* UART Interrupt register */ +#define UART_IR_REG 0x10 +#define UART_IR_MASK(x) (1 << (x + 16)) +#define UART_IR_STAT(x) (1 << (x)) +#define UART_IR_EXTIP 0 +#define UART_IR_TXUNDER 1 +#define UART_IR_TXOVER 2 +#define UART_IR_TXTRESH 3 +#define UART_IR_TXRDLATCH 4 +#define UART_IR_TXEMPTY 5 +#define UART_IR_RXUNDER 6 +#define UART_IR_RXOVER 7 +#define UART_IR_RXTIMEOUT 8 +#define UART_IR_RXFULL 9 +#define UART_IR_RXTHRESH 10 +#define UART_IR_RXNOTEMPTY 11 +#define UART_IR_RXFRAMEERR 12 +#define UART_IR_RXPARERR 13 +#define UART_IR_RXBRK 14 +#define UART_IR_TXDONE 15 + +/* UART Fifo register */ +#define UART_FIFO_REG 0x14 +#define UART_FIFO_VALID_SHIFT 0 +#define UART_FIFO_VALID_MASK 0xff +#define UART_FIFO_FRAMEERR_SHIFT 8 +#define UART_FIFO_FRAMEERR_MASK (1 << UART_FIFO_FRAMEERR_SHIFT) +#define UART_FIFO_PARERR_SHIFT 9 +#define UART_FIFO_PARERR_MASK (1 << UART_FIFO_PARERR_SHIFT) +#define UART_FIFO_BRKDET_SHIFT 10 +#define UART_FIFO_BRKDET_MASK (1 << UART_FIFO_BRKDET_SHIFT) +#define UART_FIFO_ANYERR_MASK (UART_FIFO_FRAMEERR_MASK | \ + UART_FIFO_PARERR_MASK | \ + UART_FIFO_BRKDET_MASK) + +#endif /* _LINUX_SERIAL_BCM63XX_H */ -- cgit v1.2.3 From 2997609eb4c9e296d9129d45ea1f2ec99cc7c4da Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Thu, 12 Dec 2013 13:46:03 +0100 Subject: bcma: gpio: add own IRQ domain MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Input GPIO changes can generate interrupts, but we need kind of ACK for them by changing IRQ polarity. This is required to stop hardware from keep generating interrupts and generate another one on the next GPIO state change. This code allows using GPIOs with standard interrupts and add for example GPIO buttons support. Signed-off-by: RafaÅ‚ MiÅ‚ecki Acked-by: Hauke Mehrtens Signed-off-by: John Crispin Patchwork: http://patchwork.linux-mips.org/patch/6216/ --- include/linux/bcma/bcma_driver_chipcommon.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bcma/bcma_driver_chipcommon.h b/include/linux/bcma/bcma_driver_chipcommon.h index c49e1a159e6e..63d105cd14a3 100644 --- a/include/linux/bcma/bcma_driver_chipcommon.h +++ b/include/linux/bcma/bcma_driver_chipcommon.h @@ -640,6 +640,7 @@ struct bcma_drv_cc { spinlock_t gpio_lock; #ifdef CONFIG_BCMA_DRIVER_GPIO struct gpio_chip gpio; + struct irq_domain *irq_domain; #endif }; -- cgit v1.2.3 From 6f6b5d1ec56acdeab0503d2b823f6f88a0af493e Mon Sep 17 00:00:00 2001 From: Kent Overstreet Date: Sun, 19 Jan 2014 08:26:37 +0000 Subject: percpu_ida: Make percpu_ida_alloc + callers accept task state bitmask This patch changes percpu_ida_alloc() + callers to accept task state bitmask for prepare_to_wait() for code like target/iscsi that needs it for interruptible sleep, that is provided in a subsequent patch. It now expects TASK_UNINTERRUPTIBLE when the caller is able to sleep waiting for a new tag, or TASK_RUNNING when the caller cannot sleep, and is forced to return a negative value when no tags are available. v2 changes: - Include blk-mq + tcm_fc + vhost/scsi + target/iscsi changes - Drop signal_pending_state() call v3 changes: - Only call prepare_to_wait() + finish_wait() when != TASK_RUNNING (PeterZ) Reported-by: Linus Torvalds Cc: Linus Torvalds Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Jens Axboe Signed-off-by: Kent Overstreet Cc: #3.12+ Signed-off-by: Nicholas Bellinger --- include/linux/percpu_ida.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h index 1900bd0fa639..f5cfdd6a5539 100644 --- a/include/linux/percpu_ida.h +++ b/include/linux/percpu_ida.h @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -61,7 +62,7 @@ struct percpu_ida { /* Max size of percpu freelist, */ #define IDA_DEFAULT_PCPU_SIZE ((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2) -int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp); +int percpu_ida_alloc(struct percpu_ida *pool, int state); void percpu_ida_free(struct percpu_ida *pool, unsigned tag); void percpu_ida_destroy(struct percpu_ida *pool); -- cgit v1.2.3 From 7c1bc0da3206de789a71c4aae8ac44d580bc5578 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Rafa=C5=82=20Mi=C5=82ecki?= Date: Mon, 13 Jan 2014 19:56:08 +0100 Subject: ssb: gpio: add own IRQ domain MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: RafaÅ‚ MiÅ‚ecki Acked-by: Hauke Mehrtens Acked-by: Michael Buesch Signed-off-by: John Crispin Patchwork: http://patchwork.linux-mips.org/patch/6342/ --- include/linux/ssb/ssb.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h index c64999fd1660..07ef9b82b66d 100644 --- a/include/linux/ssb/ssb.h +++ b/include/linux/ssb/ssb.h @@ -486,6 +486,7 @@ struct ssb_bus { #endif /* EMBEDDED */ #ifdef CONFIG_SSB_DRIVER_GPIO struct gpio_chip gpio; + struct irq_domain *irq_domain; #endif /* DRIVER_GPIO */ /* Internal-only stuff follows. Do not touch. */ -- cgit v1.2.3 From fc8b13740b2978b34872650cc8e928392e3758aa Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Tue, 14 Jan 2014 10:25:52 -0600 Subject: kgdb/kdb: Fix no KDB config problem Some code added to the debug_core module had KDB dependencies that it shouldn't have. Move the KDB dependent REASON back to the caller to remove the dependency in the debug core code. Update the call from the UV NMI handler to conform to the new interface. Signed-off-by: Mike Travis Reviewed-by: Hedi Berriche Cc: Russ Anderson Cc: Jason Wessel Cc: Peter Zijlstra Cc: Paul Mackerras Cc: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/20140114162551.318251993@asylum.americas.sgi.com Signed-off-by: Ingo Molnar --- include/linux/kgdb.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h index dfb4f2ffdaa2..6b06d378f3df 100644 --- a/include/linux/kgdb.h +++ b/include/linux/kgdb.h @@ -310,7 +310,8 @@ extern int kgdb_handle_exception(int ex_vector, int signo, int err_code, struct pt_regs *regs); extern int kgdb_nmicallback(int cpu, void *regs); -extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, atomic_t *snd_rdy); +extern int kgdb_nmicallin(int cpu, int trapnr, void *regs, int err_code, + atomic_t *snd_rdy); extern void gdbstub_exit(int status); extern int kgdb_single_step; -- cgit v1.2.3 From ec65993443736a5091b68e80ff1734548944a4b8 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 14:33:16 -0800 Subject: mm, x86: Account for TLB flushes only when debugging Bisection between 3.11 and 3.12 fingered commit 9824cf97 ("mm: vmstats: tlb flush counters") to cause overhead problems. The counters are undeniably useful but how often do we really need to debug TLB flush related issues? It does not justify taking the penalty everywhere so make it a debugging option. Signed-off-by: Mel Gorman Tested-by: Davidlohr Bueso Reviewed-by: Rik van Riel Signed-off-by: Andrew Morton Cc: Hugh Dickins Cc: Alex Shi Cc: Linus Torvalds Cc: Peter Zijlstra Link: http://lkml.kernel.org/n/tip-XzxjntugxuwpxXhcrxqqh53b@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/vm_event_item.h | 4 +++- include/linux/vmstat.h | 8 ++++++++ 2 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index c557c6d096de..3a712e2e7d76 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -71,12 +71,14 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_ZERO_PAGE_ALLOC, THP_ZERO_PAGE_ALLOC_FAILED, #endif +#ifdef CONFIG_DEBUG_TLBFLUSH #ifdef CONFIG_SMP NR_TLB_REMOTE_FLUSH, /* cpu tried to flush others' tlbs */ NR_TLB_REMOTE_FLUSH_RECEIVED,/* cpu received ipi for flush */ -#endif +#endif /* CONFIG_SMP */ NR_TLB_LOCAL_FLUSH_ALL, NR_TLB_LOCAL_FLUSH_ONE, +#endif /* CONFIG_DEBUG_TLBFLUSH */ NR_VM_EVENT_ITEMS }; diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e4b948080d20..80ebba9c2e87 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -83,6 +83,14 @@ static inline void vm_events_fold_cpu(int cpu) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_DEBUG_TLBFLUSH +#define count_vm_tlb_event(x) count_vm_event(x) +#define count_vm_tlb_events(x, y) count_vm_events(x, y) +#else +#define count_vm_tlb_event(x) do {} while (0) +#define count_vm_tlb_events(x, y) do { (void)(y); } while (0) +#endif + #define __count_zone_vm_events(item, zone, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + \ zone_idx(zone), delta) -- cgit v1.2.3 From f7f4f4dd6948e3bca0e04e5217c825052ad88f5a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 10 Dec 2013 16:54:28 -0500 Subject: cramfs: take headers to fs/cramfs Signed-off-by: Al Viro --- include/linux/cramfs_fs.h | 10 ---------- include/linux/cramfs_fs_sb.h | 20 -------------------- 2 files changed, 30 deletions(-) delete mode 100644 include/linux/cramfs_fs.h delete mode 100644 include/linux/cramfs_fs_sb.h (limited to 'include/linux') diff --git a/include/linux/cramfs_fs.h b/include/linux/cramfs_fs.h deleted file mode 100644 index 133789609f23..000000000000 --- a/include/linux/cramfs_fs.h +++ /dev/null @@ -1,10 +0,0 @@ -#ifndef __CRAMFS_H -#define __CRAMFS_H - -#include - -/* Uncompression interfaces to the underlying zlib */ -int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen); -int cramfs_uncompress_init(void); -void cramfs_uncompress_exit(void); -#endif diff --git a/include/linux/cramfs_fs_sb.h b/include/linux/cramfs_fs_sb.h deleted file mode 100644 index 8390693568fd..000000000000 --- a/include/linux/cramfs_fs_sb.h +++ /dev/null @@ -1,20 +0,0 @@ -#ifndef _CRAMFS_FS_SB -#define _CRAMFS_FS_SB - -/* - * cramfs super-block data in memory - */ -struct cramfs_sb_info { - unsigned long magic; - unsigned long size; - unsigned long blocks; - unsigned long files; - unsigned long flags; -}; - -static inline struct cramfs_sb_info *CRAMFS_SB(struct super_block *sb) -{ - return sb->s_fs_info; -} - -#endif -- cgit v1.2.3 From 479e64c21038326f4fe429b4ffb7ea6d3175c2dc Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 22 Nov 2013 01:45:04 -0500 Subject: nls: have register_nls() set ->owner pass owner explicitly to __register_nls(), make register_nls() a macro passing THIS_MODULE as the owner argument to __register_nls(). Signed-off-by: Al Viro --- include/linux/nls.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nls.h b/include/linux/nls.h index 5dc635f8d79e..520681b68208 100644 --- a/include/linux/nls.h +++ b/include/linux/nls.h @@ -44,11 +44,12 @@ enum utf16_endian { }; /* nls_base.c */ -extern int register_nls(struct nls_table *); +extern int __register_nls(struct nls_table *, struct module *); extern int unregister_nls(struct nls_table *); extern struct nls_table *load_nls(char *); extern void unload_nls(struct nls_table *); extern struct nls_table *load_nls_default(void); +#define register_nls(nls) __register_nls((nls), THIS_MODULE) extern int utf8_to_utf32(const u8 *s, int len, unicode_t *pu); extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen); -- cgit v1.2.3 From a8d4b8345e0ee48b732126d980efaf0dc373e2b0 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sat, 11 Jan 2014 19:19:32 +0100 Subject: introduce __fcheck_files() to fix rcu_dereference_check_fdtable(), kill rcu_my_thread_group_empty() rcu_dereference_check_fdtable() looks very wrong, 1. rcu_my_thread_group_empty() was added by 844b9a8707f1 "vfs: fix RCU-lockdep false positive due to /proc" but it doesn't really fix the problem. A CLONE_THREAD (without CLONE_FILES) task can hit the same race with get_files_struct(). And otoh rcu_my_thread_group_empty() can suppress the correct warning if the caller is the CLONE_FILES (without CLONE_THREAD) task. 2. files->count == 1 check is not really right too. Even if this files_struct is not shared it is not safe to access it lockless unless the caller is the owner. Otoh, this check is sub-optimal. files->count == 0 always means it is safe to use it lockless even if files != current->files, but put_files_struct() has to take rcu_read_lock(). See the next patch. This patch removes the buggy checks and turns fcheck_files() into __fcheck_files() which uses rcu_dereference_raw(), the "unshared" callers, fget_light() and fget_raw_light(), can use it to avoid the warning from RCU-lockdep. fcheck_files() is trivially reimplemented as rcu_lockdep_assert() plus __fcheck_files(). Signed-off-by: Oleg Nesterov Signed-off-by: Al Viro --- include/linux/fdtable.h | 35 +++++++++++++++++++++-------------- include/linux/rcupdate.h | 2 -- 2 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index 085197bd8812..70e8e21c0a30 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -59,29 +59,36 @@ struct files_struct { struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; -#define rcu_dereference_check_fdtable(files, fdtfd) \ - (rcu_dereference_check((fdtfd), \ - lockdep_is_held(&(files)->file_lock) || \ - atomic_read(&(files)->count) == 1 || \ - rcu_my_thread_group_empty())) - -#define files_fdtable(files) \ - (rcu_dereference_check_fdtable((files), (files)->fdt)) - struct file_operations; struct vfsmount; struct dentry; extern void __init files_defer_init(void); -static inline struct file * fcheck_files(struct files_struct *files, unsigned int fd) +#define rcu_dereference_check_fdtable(files, fdtfd) \ + rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) + +#define files_fdtable(files) \ + rcu_dereference_check_fdtable((files), (files)->fdt) + +/* + * The caller must ensure that fd table isn't shared or hold rcu or file lock + */ +static inline struct file *__fcheck_files(struct files_struct *files, unsigned int fd) { - struct file * file = NULL; - struct fdtable *fdt = files_fdtable(files); + struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) - file = rcu_dereference_check_fdtable(files, fdt->fd[fd]); - return file; + return rcu_dereference_raw(fdt->fd[fd]); + return NULL; +} + +static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd) +{ + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&files->file_lock), + "suspicious rcu_dereference_check() usage"); + return __fcheck_files(files, fd); } /* diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 39cbb889e20d..a2482cf90b6b 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -448,8 +448,6 @@ static inline int rcu_read_lock_sched_held(void) #ifdef CONFIG_PROVE_RCU -extern int rcu_my_thread_group_empty(void); - /** * rcu_lockdep_assert - emit lockdep splat if specified condition not met * @c: condition to check -- cgit v1.2.3 From 270750dbc18a71b23d660df110e433ff9616a2d4 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 20 Jan 2014 17:34:13 +0000 Subject: hung_task: Display every hung task warning When khungtaskd detects hung tasks, it prints out backtraces from a number of those tasks. Limiting the number of backtraces being printed out can result in the user not seeing the information necessary to debug the issue. The hung_task_warnings sysctl controls this feature. This patch makes it possible for hung_task_warnings to accept a special value to print an unlimited number of backtraces when khungtaskd detects hung tasks. The special value is -1. To use this value it is necessary to change types from ulong to int. Signed-off-by: Aaron Tomlin Reviewed-by: Rik van Riel Acked-by: David Rientjes Cc: oleg@redhat.com Link: http://lkml.kernel.org/r/1390239253-24030-3-git-send-email-atomlin@redhat.com [ Build warning fix. ] Signed-off-by: Ingo Molnar --- include/linux/sched/sysctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 31e0193cb0c5..3a93f842306a 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -5,7 +5,7 @@ extern int sysctl_hung_task_check_count; extern unsigned int sysctl_hung_task_panic; extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_warnings; +extern int sysctl_hung_task_warnings; extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); -- cgit v1.2.3 From 2982baa2ae31eb23ce29b688ab2f77eb019062f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:38 -0800 Subject: fs: add get_acl helper Factor out the code to get an ACL either from the inode or disk from check_acl, so that it can be used elsewhere later on. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Al Viro --- include/linux/posix_acl.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 7931efe71175..a8d9918c0b20 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -175,4 +175,6 @@ static inline void cache_no_acl(struct inode *inode) #endif } +struct posix_acl *get_acl(struct inode *inode, int type); + #endif /* __LINUX_POSIX_ACL_H */ -- cgit v1.2.3 From 893d46e443346370cd4ea81d9d35f72952c62a37 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:39 -0800 Subject: fs: add a set_acl inode operation This will allow moving all the Posix ACL handling into the VFS and clean up tons of cruft in the filesystems. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Al Viro --- include/linux/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 121f11f001c0..09f553c59813 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1580,6 +1580,7 @@ struct inode_operations { struct file *, unsigned open_flag, umode_t create_mode, int *opened); int (*tmpfile) (struct inode *, struct dentry *, umode_t); + int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, -- cgit v1.2.3 From 2aeccbe957d0d2b9fbb2a236e53a955097e2a9ce Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:40 -0800 Subject: fs: add generic xattr_acl handlers With the ->set_acl inode operation we can implement the Posix ACL xattr handlers in generic code instead of duplicating them all over the tree. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Al Viro --- include/linux/posix_acl_xattr.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/posix_acl_xattr.h b/include/linux/posix_acl_xattr.h index ad93ad0f1db0..6f14ee295822 100644 --- a/include/linux/posix_acl_xattr.h +++ b/include/linux/posix_acl_xattr.h @@ -69,4 +69,7 @@ struct posix_acl *posix_acl_from_xattr(struct user_namespace *user_ns, int posix_acl_to_xattr(struct user_namespace *user_ns, const struct posix_acl *acl, void *buffer, size_t size); +extern const struct xattr_handler posix_acl_access_xattr_handler; +extern const struct xattr_handler posix_acl_default_xattr_handler; + #endif /* _POSIX_ACL_XATTR_H */ -- cgit v1.2.3 From 5bf3258fd2acd8515450ab8efcd97c9d3b69f7f9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:41 -0800 Subject: fs: make posix_acl_chmod more useful Rename the current posix_acl_chmod to __posix_acl_chmod and add a fully featured ACL chmod helper that uses the ->set_acl inode operation. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Al Viro --- include/linux/posix_acl.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index a8d9918c0b20..8b64e7899989 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -89,12 +89,14 @@ extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); -extern int posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); +extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL +extern int posix_acl_chmod(struct inode *); + static inline struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { @@ -165,15 +167,22 @@ static inline void forget_all_cached_acls(struct inode *inode) if (old_default != ACL_NOT_CACHED) posix_acl_release(old_default); } -#endif static inline void cache_no_acl(struct inode *inode) { -#ifdef CONFIG_FS_POSIX_ACL inode->i_acl = NULL; inode->i_default_acl = NULL; -#endif } +#else +static inline int posix_acl_chmod(struct inode *inode) +{ + return 0; +} + +static inline void cache_no_acl(struct inode *inode) +{ +} +#endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); -- cgit v1.2.3 From 37bc15392a2363ca822b2c2828e0ccafbea32f75 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:42 -0800 Subject: fs: make posix_acl_create more useful Rename the current posix_acl_created to __posix_acl_create and add a fully featured helper to set up the ACLs on file creation that uses get_acl(). Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Signed-off-by: Al Viro --- include/linux/posix_acl.h | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 8b64e7899989..f7e6f6cb214a 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -88,14 +88,16 @@ extern int posix_acl_valid(const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); -extern int posix_acl_create(struct posix_acl **, gfp_t, umode_t *); +extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL -extern int posix_acl_chmod(struct inode *); +extern int posix_acl_chmod(struct inode *, umode_t); +extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, + struct posix_acl **); static inline struct posix_acl **acl_by_type(struct inode *inode, int type) { @@ -174,7 +176,7 @@ static inline void cache_no_acl(struct inode *inode) inode->i_default_acl = NULL; } #else -static inline int posix_acl_chmod(struct inode *inode) +static inline int posix_acl_chmod(struct inode *inode, umode_t mode) { return 0; } @@ -182,6 +184,13 @@ static inline int posix_acl_chmod(struct inode *inode) static inline void cache_no_acl(struct inode *inode) { } + +static inline int posix_acl_create(struct inode *inode, umode_t *mode, + struct posix_acl **default_acl, struct posix_acl **acl) +{ + *default_acl = *acl = NULL; + return 0; +} #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); -- cgit v1.2.3 From eeb0bed5572b1282009dfc2635604df5a35d1a02 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 9 Jan 2014 20:08:21 +0200 Subject: libceph: add ceph_kv{malloc,free}() and switch to them Encapsulate kmalloc vs vmalloc memory allocation and freeing logic into two helpers, ceph_kvmalloc() and ceph_kvfree(), and switch to them. ceph_kvmalloc() kmalloc()'s a maximum of 8 pages, anything bigger is vmalloc()'ed with __GFP_HIGHMEM set. This changes the existing behaviour: - for buffers (ceph_buffer_new()), from trying to kmalloc() everything and using vmalloc() just as a fallback - for messages (ceph_msg_new()), from going to vmalloc() for anything bigger than a page - for messages (ceph_msg_new()), from disallowing vmalloc() to use high memory Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/buffer.h | 1 - include/linux/ceph/libceph.h | 11 +++++++---- include/linux/ceph/messenger.h | 1 - 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/buffer.h b/include/linux/ceph/buffer.h index 58d19014068f..07ad423cc37f 100644 --- a/include/linux/ceph/buffer.h +++ b/include/linux/ceph/buffer.h @@ -17,7 +17,6 @@ struct ceph_buffer { struct kref kref; struct kvec vec; size_t alloc_len; - bool is_vmalloc; }; extern struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp); diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 7d704db60cbb..2f49aa4c4f7f 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -173,15 +173,18 @@ static inline int calc_pages_for(u64 off, u64 len) (off >> PAGE_CACHE_SHIFT); } +extern struct kmem_cache *ceph_inode_cachep; +extern struct kmem_cache *ceph_cap_cachep; +extern struct kmem_cache *ceph_dentry_cachep; +extern struct kmem_cache *ceph_file_cachep; + /* ceph_common.c */ extern bool libceph_compatible(void *data); extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); -extern struct kmem_cache *ceph_inode_cachep; -extern struct kmem_cache *ceph_cap_cachep; -extern struct kmem_cache *ceph_dentry_cachep; -extern struct kmem_cache *ceph_file_cachep; +extern void *ceph_kvmalloc(size_t size, gfp_t flags); +extern void ceph_kvfree(const void *ptr); extern struct ceph_options *ceph_parse_options(char *options, const char *dev_name, const char *dev_name_end, diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 861138f7c161..20ee8b63a968 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -154,7 +154,6 @@ struct ceph_msg { struct list_head list_head; /* links for connection lists */ struct kref kref; - bool front_is_vmalloc; bool more_to_follow; bool needs_out_seq; int front_alloc_len; -- cgit v1.2.3 From 013cdf1088d7235da9477a2375654921d9b9ba9f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:53 -0800 Subject: nfs: use generic posix ACL infrastructure for v3 Posix ACLs This causes a small behaviour change in that we don't bother to set ACLs on file creation if the mode bit can express the access permissions fully, and thus behaving identical to local filesystems. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/nfs_fs.h | 24 +++++++----------------- include/linux/posix_acl.h | 4 ++++ 2 files changed, 11 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48997374eaf0..2b00625952a7 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -154,10 +154,6 @@ struct nfs_inode { struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; -#ifdef CONFIG_NFS_V3_ACL - struct posix_acl *acl_access; - struct posix_acl *acl_default; -#endif /* * This is the cookie verifier used for NFSv3 readdir @@ -564,23 +560,17 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, * linux/fs/nfs3proc.c */ #ifdef CONFIG_NFS_V3_ACL -extern struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type); -extern int nfs3_proc_setacl(struct inode *inode, int type, - struct posix_acl *acl); -extern int nfs3_proc_set_default_acl(struct inode *dir, struct inode *inode, - umode_t mode); -extern void nfs3_forget_cached_acls(struct inode *inode); +extern struct posix_acl *nfs3_get_acl(struct inode *inode, int type); +extern int nfs3_set_acl(struct inode *inode, struct posix_acl *acl, int type); +extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl); +extern const struct xattr_handler *nfs3_xattr_handlers[]; #else -static inline int nfs3_proc_set_default_acl(struct inode *dir, - struct inode *inode, - umode_t mode) +static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, + struct posix_acl *dfacl) { return 0; } - -static inline void nfs3_forget_cached_acls(struct inode *inode) -{ -} #endif /* CONFIG_NFS_V3_ACL */ /* diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index f7e6f6cb214a..3d14be8e14db 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -191,6 +191,10 @@ static inline int posix_acl_create(struct inode *inode, umode_t *mode, *default_acl = *acl = NULL; return 0; } + +static inline void forget_all_cached_acls(struct inode *inode) +{ +} #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); -- cgit v1.2.3 From feda821e76f3bbbba4bd54d30b4d4005a7848aa5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 20 Dec 2013 05:16:54 -0800 Subject: fs: remove generic_acl And instead convert tmpfs to use the new generic ACL code, with two stub methods provided for in-memory filesystems. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- include/linux/generic_acl.h | 14 -------------- include/linux/posix_acl.h | 9 +++++++++ 2 files changed, 9 insertions(+), 14 deletions(-) delete mode 100644 include/linux/generic_acl.h (limited to 'include/linux') diff --git a/include/linux/generic_acl.h b/include/linux/generic_acl.h deleted file mode 100644 index b6d657544ef1..000000000000 --- a/include/linux/generic_acl.h +++ /dev/null @@ -1,14 +0,0 @@ -#ifndef LINUX_GENERIC_ACL_H -#define LINUX_GENERIC_ACL_H - -#include - -struct inode; - -extern const struct xattr_handler generic_acl_access_handler; -extern const struct xattr_handler generic_acl_default_handler; - -int generic_acl_init(struct inode *, struct inode *); -int generic_acl_chmod(struct inode *); - -#endif /* LINUX_GENERIC_ACL_H */ diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h index 3d14be8e14db..6b12b3d57e90 100644 --- a/include/linux/posix_acl.h +++ b/include/linux/posix_acl.h @@ -99,6 +99,9 @@ extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); +extern int simple_set_acl(struct inode *, struct posix_acl *, int); +extern int simple_acl_create(struct inode *, struct inode *); + static inline struct posix_acl **acl_by_type(struct inode *inode, int type) { switch (type) { @@ -181,6 +184,12 @@ static inline int posix_acl_chmod(struct inode *inode, umode_t mode) return 0; } +#define simple_set_acl NULL + +static inline int simple_acl_create(struct inode *dir, struct inode *inode) +{ + return 0; +} static inline void cache_no_acl(struct inode *inode) { } -- cgit v1.2.3 From 25ee33fb824eb46ae77f6c962007492603d39772 Mon Sep 17 00:00:00 2001 From: Ben Dooks Date: Sun, 26 Jan 2014 16:05:36 +0000 Subject: i2c: update i2c_algorithm documentation Add some kerneldoc style documentaton to the i2c_algorithm structure, and point the master_xfer return codes at the right place in Documentation/i2c/fault_codes Signed-off-by: Ben Dooks Signed-off-by: Wolfram Sang --- include/linux/i2c.h | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c.h b/include/linux/i2c.h index d9c8dbd3373f..deddeb8c337c 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -342,11 +342,25 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info, } #endif /* I2C_BOARDINFO */ -/* +/** + * struct i2c_algorithm - represent I2C transfer method + * @master_xfer: Issue a set of i2c transactions to the given I2C adapter + * defined by the msgs array, with num messages available to transfer via + * the adapter specified by adap. + * @smbus_xfer: Issue smbus transactions to the given I2C adapter. If this + * is not present, then the bus layer will try and convert the SMBus calls + * into I2C transfers instead. + * @functionality: Return the flags that this algorithm/adapter pair supports + * from the I2C_FUNC_* flags. + * * The following structs are for those who like to implement new bus drivers: * i2c_algorithm is the interface to a class of hardware solutions which can * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584 * to name two of the most common. + * + * The return codes from the @master_xfer field should indicate the type of + * error code that occured during the transfer, as documented in the kernel + * Documentation file Documentation/i2c/fault-codes. */ struct i2c_algorithm { /* If an adapter algorithm can't do I2C-level access, set master_xfer -- cgit v1.2.3 From de960aa9ab4decc3304959f69533eef64d05d8e8 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 26 Jan 2014 10:58:16 +0100 Subject: net: add and use skb_gso_transport_seglen() This moves part of Eric Dumazets skb_gso_seglen helper from tbf sched to skbuff core so it may be reused by upcoming ip forwarding path patch. Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 1f689e62e4cb..f589c9af8cbf 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2456,6 +2456,7 @@ void skb_zerocopy(struct sk_buff *to, const struct sk_buff *from, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); void skb_scrub_packet(struct sk_buff *skb, bool xnet); +unsigned int skb_gso_transport_seglen(const struct sk_buff *skb); struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features); struct skb_checksum_ops { -- cgit v1.2.3 From 9d43dc7f403dbe5da25c7eb488a5975b08d95496 Mon Sep 17 00:00:00 2001 From: Sebastian Hesselbarth Date: Sat, 25 Jan 2014 21:48:31 +0100 Subject: clk: si5351: remove variant from platform_data Commit 9807362bfe1748d9bb48eecb9261f1b1aaafea1c "clk: si5351: declare all device IDs for module loading" removed the common i2c_device_id and introduced new ones for each variant of the clock generator. Instead of exploiting that information in the driver, it still depends on platform_data passing the chips .variant. This removes the now redundant .variant from the platform_data and puts it in i2c_device_id's .driver_data instead. Signed-off-by: Sebastian Hesselbarth Signed-off-by: Mike Turquette --- include/linux/platform_data/si5351.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/si5351.h b/include/linux/platform_data/si5351.h index 54334393ab92..a947ab8b441a 100644 --- a/include/linux/platform_data/si5351.h +++ b/include/linux/platform_data/si5351.h @@ -7,20 +7,6 @@ struct clk; -/** - * enum si5351_variant - SiLabs Si5351 chip variant - * @SI5351_VARIANT_A: Si5351A (8 output clocks, XTAL input) - * @SI5351_VARIANT_A3: Si5351A MSOP10 (3 output clocks, XTAL input) - * @SI5351_VARIANT_B: Si5351B (8 output clocks, XTAL/VXCO input) - * @SI5351_VARIANT_C: Si5351C (8 output clocks, XTAL/CLKIN input) - */ -enum si5351_variant { - SI5351_VARIANT_A = 1, - SI5351_VARIANT_A3 = 2, - SI5351_VARIANT_B = 3, - SI5351_VARIANT_C = 4, -}; - /** * enum si5351_pll_src - Si5351 pll clock source * @SI5351_PLL_SRC_DEFAULT: default, do not change eeprom config @@ -115,14 +101,12 @@ struct si5351_clkout_config { /** * struct si5351_platform_data - Platform data for the Si5351 clock driver - * @variant: Si5351 chip variant * @clk_xtal: xtal input clock * @clk_clkin: clkin input clock * @pll_src: array of pll source clock setting * @clkout: array of clkout configuration */ struct si5351_platform_data { - enum si5351_variant variant; struct clk *clk_xtal; struct clk *clk_clkin; enum si5351_pll_src pll_src[2]; -- cgit v1.2.3 From d529ef83c355f97027ff85298a9709fe06216a66 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Mon, 27 Jan 2014 13:46:15 -0500 Subject: NFS: fix the handling of NFS_INO_INVALID_DATA flag in nfs_revalidate_mapping There is a possible race in how the nfs_invalidate_mapping function is handled. Currently, we go and invalidate the pages in the file and then clear NFS_INO_INVALID_DATA. The problem is that it's possible for a stale page to creep into the mapping after the page was invalidated (i.e., via readahead). If another writer comes along and sets the flag after that happens but before invalidate_inode_pages2 returns then we could clear the flag without the cache having been properly invalidated. So, we must clear the flag first and then invalidate the pages. Doing this however, opens another race: It's possible to have two concurrent read() calls that end up in nfs_revalidate_mapping at the same time. The first one clears the NFS_INO_INVALID_DATA flag and then goes to call nfs_invalidate_mapping. Just before calling that though, the other task races in, checks the flag and finds it cleared. At that point, it trusts that the mapping is good and gets the lock on the page, allowing the read() to be satisfied from the cache even though the data is no longer valid. These effects are easily manifested by running diotest3 from the LTP test suite on NFS. That program does a series of DIO writes and buffered reads. The operations are serialized and page-aligned but the existing code fails the test since it occasionally allows a read to come out of the cache incorrectly. While mixing direct and buffered I/O isn't recommended, I believe it's possible to hit this in other ways that just use buffered I/O, though that situation is much harder to reproduce. The problem is that the checking/clearing of that flag and the invalidation of the mapping really need to be atomic. Fix this by serializing concurrent invalidations with a bitlock. At the same time, we also need to allow other places that check NFS_INO_INVALID_DATA to check whether we might be in the middle of invalidating the file, so fix up a couple of places that do that to look for the new NFS_INO_INVALIDATING flag. Doing this requires us to be careful not to set the bitlock unnecessarily, so this code only does that if it believes it will be doing an invalidation. Signed-off-by: Jeff Layton Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48997374eaf0..18fb16f4b939 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -215,6 +215,7 @@ struct nfs_inode { #define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */ #define NFS_INO_STALE (1) /* possible stale inode */ #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ +#define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FLUSHING (4) /* inode is flushing out data */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ -- cgit v1.2.3 From 9df62f054406992ce41ec4558fca6a0fa56fffeb Mon Sep 17 00:00:00 2001 From: Chen Gang Date: Sun, 12 Jan 2014 09:59:13 +0800 Subject: arch: use ASM_NL instead of ';' for assembler new line character in the macro For some assemblers, they use another character as newline in a macro (e.g. arc uses '`'), so for generic assembly code, need use ASM_NL (a macro) instead of ';' for it. Signed-off-by: Chen Gang Acked-by: Vineet Gupta Signed-off-by: Michal Marek --- include/linux/linkage.h | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/linkage.h b/include/linux/linkage.h index d3e8ad23a8e0..a6a42dd02466 100644 --- a/include/linux/linkage.h +++ b/include/linux/linkage.h @@ -6,6 +6,11 @@ #include #include +/* Some toolchains use other characters (e.g. '`') to mark new line in macro */ +#ifndef ASM_NL +#define ASM_NL ; +#endif + #ifdef __cplusplus #define CPP_ASMLINKAGE extern "C" #else @@ -75,21 +80,21 @@ #ifndef ENTRY #define ENTRY(name) \ - .globl name; \ - ALIGN; \ - name: + .globl name ASM_NL \ + ALIGN ASM_NL \ + name: #endif #endif /* LINKER_SCRIPT */ #ifndef WEAK #define WEAK(name) \ - .weak name; \ + .weak name ASM_NL \ name: #endif #ifndef END #define END(name) \ - .size name, .-name + .size name, .-name #endif /* If symbol 'name' is treated as a subroutine (gets called, and returns) @@ -98,8 +103,8 @@ */ #ifndef ENDPROC #define ENDPROC(name) \ - .type name, @function; \ - END(name) + .type name, @function ASM_NL \ + END(name) #endif #endif -- cgit v1.2.3 From 22116525baec1d63f4878eaa92f0b57946a78819 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:18 +0200 Subject: libceph: start using oloc abstraction Instead of relying on pool fields in ceph_file_layout (for mapping) and ceph_pg (for enconding), start using ceph_object_locator (oloc) abstraction. Note that userspace oloc currently consists of pool, key, nspace and hash fields, while this one contains only a pool. This is OK, because at this point we only send (i.e. encode) olocs and never have to receive (i.e. decode) them. This makes keeping a copy of ceph_file_layout in every osd request unnecessary, so ceph_osd_request::r_file_layout field is nuked. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 3 ++- include/linux/ceph/osdmap.h | 3 +-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 4fb6a8938957..5b8555109789 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -159,12 +159,13 @@ struct ceph_osd_request { struct inode *r_inode; /* for use by callbacks */ void *r_priv; /* ditto */ + struct ceph_object_locator r_oloc; + char r_oid[MAX_OBJ_NAME_SIZE]; /* object name */ int r_oid_len; u64 r_snapid; unsigned long r_stamp; /* send OR check time */ - struct ceph_file_layout r_file_layout; struct ceph_snap_context *r_snapc; /* snap context for writes */ }; diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index d05cc4451af6..256134af4ad4 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -40,8 +40,7 @@ struct ceph_pg_pool_info { }; struct ceph_object_locator { - uint64_t pool; - char *key; + s64 pool; }; struct ceph_pg_mapping { -- cgit v1.2.3 From e8221464fc2bc8c9f7b0c2115abbd75ba23f210a Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:18 +0200 Subject: libceph: move ceph_file_layout helpers to ceph_fs.h Move ceph_file_layout helper macros and inline functions to ceph_fs.h. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_fs.h | 23 +++++++++++++++++++++++ include/linux/ceph/osdmap.h | 27 --------------------------- 2 files changed, 23 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 0a37b989b52f..2623cffc73a1 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -53,6 +53,29 @@ struct ceph_file_layout { __le32 fl_pg_pool; /* namespace, crush ruleset, rep level */ } __attribute__ ((packed)); +#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) +#define ceph_file_layout_stripe_count(l) \ + ((__s32)le32_to_cpu((l).fl_stripe_count)) +#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) +#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) +#define ceph_file_layout_object_su(l) \ + ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) +#define ceph_file_layout_pg_pool(l) \ + ((__s32)le32_to_cpu((l).fl_pg_pool)) + +static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_stripe_unit) * + le32_to_cpu(l->fl_stripe_count); +} + +/* "period" == bytes before i start on a new set of objects */ +static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) +{ + return le32_to_cpu(l->fl_object_size) * + le32_to_cpu(l->fl_stripe_count); +} + #define CEPH_MIN_STRIPE_UNIT 65536 int ceph_file_layout_is_valid(const struct ceph_file_layout *layout); diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 256134af4ad4..f2679c384625 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -72,33 +72,6 @@ struct ceph_osdmap { struct crush_map *crush; }; -/* - * file layout helpers - */ -#define ceph_file_layout_su(l) ((__s32)le32_to_cpu((l).fl_stripe_unit)) -#define ceph_file_layout_stripe_count(l) \ - ((__s32)le32_to_cpu((l).fl_stripe_count)) -#define ceph_file_layout_object_size(l) ((__s32)le32_to_cpu((l).fl_object_size)) -#define ceph_file_layout_cas_hash(l) ((__s32)le32_to_cpu((l).fl_cas_hash)) -#define ceph_file_layout_object_su(l) \ - ((__s32)le32_to_cpu((l).fl_object_stripe_unit)) -#define ceph_file_layout_pg_pool(l) \ - ((__s32)le32_to_cpu((l).fl_pg_pool)) - -static inline unsigned ceph_file_layout_stripe_width(struct ceph_file_layout *l) -{ - return le32_to_cpu(l->fl_stripe_unit) * - le32_to_cpu(l->fl_stripe_count); -} - -/* "period" == bytes before i start on a new set of objects */ -static inline unsigned ceph_file_layout_period(struct ceph_file_layout *l) -{ - return le32_to_cpu(l->fl_object_size) * - le32_to_cpu(l->fl_stripe_count); -} - - static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd) { return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP); -- cgit v1.2.3 From 2d0ebc5d591f49131bf8f93b54c5424162c3fb7f Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:18 +0200 Subject: libceph: rename MAX_OBJ_NAME_SIZE to CEPH_MAX_OID_NAME_LEN In preparation for adding oid abstraction, rename MAX_OBJ_NAME_SIZE to CEPH_MAX_OID_NAME_LEN. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 5b8555109789..b42f15848cae 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -16,7 +16,7 @@ * Maximum object name size * (must be at least as big as RBD_MAX_MD_NAME_LEN -- currently 100) */ -#define MAX_OBJ_NAME_SIZE 100 +#define CEPH_MAX_OID_NAME_LEN 100 struct ceph_msg; struct ceph_snap_context; @@ -161,7 +161,7 @@ struct ceph_osd_request { struct ceph_object_locator r_oloc; - char r_oid[MAX_OBJ_NAME_SIZE]; /* object name */ + char r_oid[CEPH_MAX_OID_NAME_LEN]; /* object name */ int r_oid_len; u64 r_snapid; unsigned long r_stamp; /* send OR check time */ -- cgit v1.2.3 From 4295f2217a5aa8ef2738e3a368db3c1ceab41212 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:18 +0200 Subject: libceph: introduce and start using oid abstraction In preparation for tiering support, which would require having two (base and target) object names for each osd request and also copying those names around, introduce struct ceph_object_id (oid) and a couple helpers to facilitate those copies and encapsulate the fact that object name is not necessarily a NUL-terminated string. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 9 +-------- include/linux/ceph/osdmap.h | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index b42f15848cae..8d8bb53994b1 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -12,12 +12,6 @@ #include #include -/* - * Maximum object name size - * (must be at least as big as RBD_MAX_MD_NAME_LEN -- currently 100) - */ -#define CEPH_MAX_OID_NAME_LEN 100 - struct ceph_msg; struct ceph_snap_context; struct ceph_osd_request; @@ -160,9 +154,8 @@ struct ceph_osd_request { void *r_priv; /* ditto */ struct ceph_object_locator r_oloc; + struct ceph_object_id r_oid; - char r_oid[CEPH_MAX_OID_NAME_LEN]; /* object name */ - int r_oid_len; u64 r_snapid; unsigned long r_stamp; /* send OR check time */ diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index f2679c384625..c85f7d43b861 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -43,6 +43,18 @@ struct ceph_object_locator { s64 pool; }; +/* + * Maximum supported by kernel client object name length + * + * (probably outdated: must be >= RBD_MAX_MD_NAME_LEN -- currently 100) + */ +#define CEPH_MAX_OID_NAME_LEN 100 + +struct ceph_object_id { + char name[CEPH_MAX_OID_NAME_LEN]; + int name_len; +}; + struct ceph_pg_mapping { struct rb_node node; struct ceph_pg pgid; @@ -72,6 +84,30 @@ struct ceph_osdmap { struct crush_map *crush; }; +static inline void ceph_oid_set_name(struct ceph_object_id *oid, + const char *name) +{ + int len; + + len = strlen(name); + if (len > sizeof(oid->name)) { + WARN(1, "ceph_oid_set_name '%s' len %d vs %zu, truncating\n", + name, len, sizeof(oid->name)); + len = sizeof(oid->name); + } + + memcpy(oid->name, name, len); + oid->name_len = len; +} + +static inline void ceph_oid_copy(struct ceph_object_id *dest, + struct ceph_object_id *src) +{ + BUG_ON(src->name_len > sizeof(dest->name)); + memcpy(dest->name, src->name, src->name_len); + dest->name_len = src->name_len; +} + static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd) { return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP); -- cgit v1.2.3 From 7c13cb64352230deac24d3cb058387a6c0676f83 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:19 +0200 Subject: libceph: replace ceph_calc_ceph_pg() with ceph_oloc_oid_to_pg() Switch ceph_calc_ceph_pg() to new oloc and oid abstractions and rename it to ceph_oloc_oid_to_pg() to make its purpose more clear. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osdmap.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index c85f7d43b861..ebb8ec285de6 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -163,8 +163,11 @@ extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, u64 *bno, u64 *oxoff, u64 *oxlen); /* calculate mapping of object to a placement group */ -extern int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid, - struct ceph_osdmap *osdmap, uint64_t pool); +extern int ceph_oloc_oid_to_pg(struct ceph_osdmap *osdmap, + struct ceph_object_locator *oloc, + struct ceph_object_id *oid, + struct ceph_pg *pg_out); + extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, struct ceph_pg pgid, int *acting); -- cgit v1.2.3 From 1b3f2ab51095a7aab684bf9f5c14235126188dbc Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:19 +0200 Subject: libceph: CEPH_OSD_FLAG_* enum update Update CEPH_OSD_FLAG_* enum. (We need CEPH_OSD_FLAG_IGNORE_OVERLAY to support tiering). Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/rados.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h index 68c96a508ac2..96292df4041b 100644 --- a/include/linux/ceph/rados.h +++ b/include/linux/ceph/rados.h @@ -344,6 +344,10 @@ enum { CEPH_OSD_FLAG_EXEC_PUBLIC = 0x1000, /* DEPRECATED op may exec (public) */ CEPH_OSD_FLAG_LOCALIZE_READS = 0x2000, /* read from nearby replica, if any */ CEPH_OSD_FLAG_RWORDERED = 0x4000, /* order wrt concurrent reads */ + CEPH_OSD_FLAG_IGNORE_CACHE = 0x8000, /* ignore cache logic */ + CEPH_OSD_FLAG_SKIPRWLOCKS = 0x10000, /* skip rw locks */ + CEPH_OSD_FLAG_IGNORE_OVERLAY = 0x20000, /* ignore pool overlay */ + CEPH_OSD_FLAG_FLUSH = 0x40000, /* this is part of flush */ }; enum { -- cgit v1.2.3 From ce7f6a2790464047199f54b66420243d433142bd Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:19 +0200 Subject: libceph: add ceph_pg_pool_by_id() "Lookup pool info by ID" function is hidden in osdmap.c. Expose it to the rest of libceph. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osdmap.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index ebb8ec285de6..7f894a64c6c7 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -174,6 +174,9 @@ extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap, extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap, struct ceph_pg pgid); +extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, + u64 id); + extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id); extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name); -- cgit v1.2.3 From 17a13e4028e6ad7ded079cf32370c47bd0e0fc07 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:19 +0200 Subject: libceph: follow {read,write}_tier fields on osd request submission Overwrite ceph_osd_request::r_oloc.pool with read_tier for read ops and write_tier for write and read+write ops (aka basic tiering support). {read,write}_tier are part of pg_pool_t since v9. This commit bumps our pg_pool_t decode compat version from v7 to v9, all new fields except for {read,write}_tier are ignored. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osdmap.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index 7f894a64c6c7..49ff69f0746b 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -35,6 +35,8 @@ struct ceph_pg_pool_info { u8 object_hash; u32 pg_num, pgp_num; int pg_num_mask, pgp_num_mask; + s64 read_tier; + s64 write_tier; /* wins for read+write ops */ u64 flags; char *name; }; -- cgit v1.2.3 From 3c972c95c68f455d80ff185aa440857be046bbe0 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:20 +0200 Subject: libceph: rename ceph_osd_request::r_{oloc,oid} to r_base_{oloc,oid} Rename ceph_osd_request::r_{oloc,oid} to r_base_{oloc,oid} before introducing r_target_{oloc,oid} needed for redirects. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 8d8bb53994b1..3170ca6d98b2 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -153,8 +153,8 @@ struct ceph_osd_request { struct inode *r_inode; /* for use by callbacks */ void *r_priv; /* ditto */ - struct ceph_object_locator r_oloc; - struct ceph_object_id r_oid; + struct ceph_object_locator r_base_oloc; + struct ceph_object_id r_base_oid; u64 r_snapid; unsigned long r_stamp; /* send OR check time */ -- cgit v1.2.3 From 205ee1187a671c3b067d7f1e974903b44036f270 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:20 +0200 Subject: libceph: follow redirect replies from osds Follow redirect replies from osds, for details see ceph.git commit fbbe3ad1220799b7bb00ea30fce581c5eadaf034. v1 (current) version of redirect reply consists of oloc and oid, which expands to pool, key, nspace, hash and oid. However, server-side code that would populate anything other than pool doesn't exist yet, and hence this commit adds support for pool redirects only. To make sure that future server-side updates don't break us, we decode all fields and, if any of key, nspace, hash or oid have a non-default value, error out with "corrupt osd_op_reply ..." message. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/osd_client.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 3170ca6d98b2..fd47e872ebcc 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -155,6 +155,8 @@ struct ceph_osd_request { struct ceph_object_locator r_base_oloc; struct ceph_object_id r_base_oid; + struct ceph_object_locator r_target_oloc; + struct ceph_object_id r_target_oid; u64 r_snapid; unsigned long r_stamp; /* send OR check time */ @@ -162,6 +164,10 @@ struct ceph_osd_request { struct ceph_snap_context *r_snapc; /* snap context for writes */ }; +struct ceph_request_redirect { + struct ceph_object_locator oloc; +}; + struct ceph_osd_event { u64 cookie; int one_shot; -- cgit v1.2.3 From 80e163a58c0c69ef1a0ba3500d9932b14d67bf64 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 27 Jan 2014 17:40:20 +0200 Subject: libceph: support CEPH_FEATURE_OSD_CACHEPOOL feature Announce our (limited, see previous commit) support for CACHEPOOL feature. Signed-off-by: Ilya Dryomov Reviewed-by: Sage Weil --- include/linux/ceph/ceph_features.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index d21b34d94436..138448f766b4 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -80,6 +80,7 @@ static inline u64 ceph_sanitize_features(u64 features) CEPH_FEATURE_CRUSH_TUNABLES2 | \ CEPH_FEATURE_REPLY_CREATE_INODE | \ CEPH_FEATURE_OSDHASHPSPOOL | \ + CEPH_FEATURE_OSD_CACHEPOOL | \ CEPH_FEATURE_CRUSH_V2 | \ CEPH_FEATURE_EXPORT_PEER) -- cgit v1.2.3 From d4b4ff8e28b474fac0fbfa9cfc40f88b9e41e380 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 10 Dec 2013 13:10:37 -0700 Subject: NVMe: Schedule reset for failed controllers Schedules a controller reset when it indicates it has a failed status. If the device does not become ready after a reset, the pci device will be scheduled for removal. Signed-off-by: Keith Busch [fixed checkpatch issue] Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index eed81cc56d7e..117d877e8be5 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -95,6 +95,7 @@ struct nvme_dev { u32 max_hw_sectors; u32 stripe_size; u16 oncs; + u8 initialized; }; /* -- cgit v1.2.3 From c30341dc3c436cf43508cd44cdfbb3810c38c195 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 10 Dec 2013 13:10:38 -0700 Subject: NVMe: Abort timed out commands Send nvme abort command to io requests that have timed out on an initialized device. If the command is not returned after another timeout, schedule the controller for reset. Signed-off-by: Keith Busch [fix endianness issues] Signed-off-by: Matthew Wilcox --- include/linux/nvme.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 117d877e8be5..69ae03f6eb15 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -95,6 +95,7 @@ struct nvme_dev { u32 max_hw_sectors; u32 stripe_size; u16 oncs; + u16 abort_limit; u8 initialized; }; -- cgit v1.2.3 From 01a7a063e8cf4bc09af2c02d28c12f3d72bf9649 Mon Sep 17 00:00:00 2001 From: Alexander Shiyan Date: Fri, 6 Dec 2013 22:22:18 -0800 Subject: leds: leds-mc13783: Remove duplicate field in platform data LED platform data are overwhelmed by excessive field "max_cur" which just replicates few bits of "led_control" field. This patch removes this field and adds a definition for the current settings in the header. Signed-off-by: Alexander Shiyan Signed-off-by: Bryan Wu --- include/linux/mfd/mc13xxx.h | 37 ++++++++++++++++++++++++++++--------- 1 file changed, 28 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h index 67c17b5a6f44..ac2230561fc8 100644 --- a/include/linux/mfd/mc13xxx.h +++ b/include/linux/mfd/mc13xxx.h @@ -112,9 +112,6 @@ struct mc13xxx_led_platform_data { int id; const char *name; const char *default_trigger; - -/* Three or two bits current selection depending on the led */ - char max_current; }; #define MAX_LED_CONTROL_REGS 6 @@ -123,7 +120,7 @@ struct mc13xxx_leds_platform_data { struct mc13xxx_led_platform_data *led; int num_leds; -/* LED Control 0 */ +/* MC13783 LED Control 0 */ #define MC13783_LED_C0_ENABLE (1 << 0) #define MC13783_LED_C0_TRIODE_MD (1 << 7) #define MC13783_LED_C0_TRIODE_AD (1 << 8) @@ -131,21 +128,43 @@ struct mc13xxx_leds_platform_data { #define MC13783_LED_C0_BOOST (1 << 10) #define MC13783_LED_C0_ABMODE(x) (((x) & 0x7) << 11) #define MC13783_LED_C0_ABREF(x) (((x) & 0x3) << 14) -/* LED Control 1 */ +/* MC13783 LED Control 1 */ #define MC13783_LED_C1_TC1HALF (1 << 18) #define MC13783_LED_C1_SLEWLIM (1 << 23) -/* LED Control 2 */ +/* MC13783 LED Control 2 */ +#define MC13783_LED_C2_CURRENT_MD(x) (((x) & 0x7) << 0) +#define MC13783_LED_C2_CURRENT_AD(x) (((x) & 0x7) << 3) +#define MC13783_LED_C2_CURRENT_KP(x) (((x) & 0x7) << 6) #define MC13783_LED_C2_PERIOD(x) (((x) & 0x3) << 21) #define MC13783_LED_C2_SLEWLIM (1 << 23) -/* LED Control 3 */ +/* MC13783 LED Control 3 */ +#define MC13783_LED_C3_CURRENT_R1(x) (((x) & 0x3) << 0) +#define MC13783_LED_C3_CURRENT_G1(x) (((x) & 0x3) << 2) +#define MC13783_LED_C3_CURRENT_B1(x) (((x) & 0x3) << 4) #define MC13783_LED_C3_PERIOD(x) (((x) & 0x3) << 21) #define MC13783_LED_C3_TRIODE_TC1 (1 << 23) -/* LED Control 4 */ +/* MC13783 LED Control 4 */ +#define MC13783_LED_C4_CURRENT_R2(x) (((x) & 0x3) << 0) +#define MC13783_LED_C4_CURRENT_G2(x) (((x) & 0x3) << 2) +#define MC13783_LED_C4_CURRENT_B2(x) (((x) & 0x3) << 4) #define MC13783_LED_C4_PERIOD(x) (((x) & 0x3) << 21) #define MC13783_LED_C4_TRIODE_TC2 (1 << 23) -/* LED Control 5 */ +/* MC13783 LED Control 5 */ +#define MC13783_LED_C5_CURRENT_R3(x) (((x) & 0x3) << 0) +#define MC13783_LED_C5_CURRENT_G3(x) (((x) & 0x3) << 2) +#define MC13783_LED_C5_CURRENT_B3(x) (((x) & 0x3) << 4) #define MC13783_LED_C5_PERIOD(x) (((x) & 0x3) << 21) #define MC13783_LED_C5_TRIODE_TC3 (1 << 23) +/* MC13892 LED Control 0 */ +#define MC13892_LED_C0_CURRENT_MD(x) (((x) & 0x7) << 9) +#define MC13892_LED_C0_CURRENT_AD(x) (((x) & 0x7) << 21) +/* MC13892 LED Control 1 */ +#define MC13892_LED_C1_CURRENT_KP(x) (((x) & 0x7) << 9) +/* MC13892 LED Control 2 */ +#define MC13892_LED_C2_CURRENT_R(x) (((x) & 0x7) << 9) +#define MC13892_LED_C2_CURRENT_G(x) (((x) & 0x7) << 21) +/* MC13892 LED Control 3 */ +#define MC13892_LED_C3_CURRENT_B(x) (((x) & 0x7) << 9) u32 led_control[MAX_LED_CONTROL_REGS]; }; -- cgit v1.2.3 From 00d195528547f31ac329aa36dc385b13fdc58f11 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Thu, 2 Jan 2014 01:58:45 -0800 Subject: leds: kirkwood: Cleanup in header files Commit c02cecb92ed4 ("ARM: orion: move platform_data definitions") moved the files to the current location but forgot to remove the pointer to its previous location. Clean it up. While at it also change the header file protection macros appropriately. Signed-off-by: Sachin Kamat Signed-off-by: Bryan Wu --- include/linux/platform_data/leds-kirkwood-netxbig.h | 8 +++----- include/linux/platform_data/leds-kirkwood-ns2.h | 8 +++----- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/platform_data/leds-kirkwood-netxbig.h b/include/linux/platform_data/leds-kirkwood-netxbig.h index 24b536ebdf13..d2be19a51acd 100644 --- a/include/linux/platform_data/leds-kirkwood-netxbig.h +++ b/include/linux/platform_data/leds-kirkwood-netxbig.h @@ -1,6 +1,4 @@ /* - * arch/arm/mach-kirkwood/include/mach/leds-netxbig.h - * * Platform data structure for netxbig LED driver * * This file is licensed under the terms of the GNU General Public @@ -8,8 +6,8 @@ * warranty of any kind, whether express or implied. */ -#ifndef __MACH_LEDS_NETXBIG_H -#define __MACH_LEDS_NETXBIG_H +#ifndef __LEDS_KIRKWOOD_NETXBIG_H +#define __LEDS_KIRKWOOD_NETXBIG_H struct netxbig_gpio_ext { unsigned *addr; @@ -52,4 +50,4 @@ struct netxbig_led_platform_data { int num_leds; }; -#endif /* __MACH_LEDS_NETXBIG_H */ +#endif /* __LEDS_KIRKWOOD_NETXBIG_H */ diff --git a/include/linux/platform_data/leds-kirkwood-ns2.h b/include/linux/platform_data/leds-kirkwood-ns2.h index e21272e5f668..6a9fed57f346 100644 --- a/include/linux/platform_data/leds-kirkwood-ns2.h +++ b/include/linux/platform_data/leds-kirkwood-ns2.h @@ -1,6 +1,4 @@ /* - * arch/arm/mach-kirkwood/include/mach/leds-ns2.h - * * Platform data structure for Network Space v2 LED driver * * This file is licensed under the terms of the GNU General Public @@ -8,8 +6,8 @@ * warranty of any kind, whether express or implied. */ -#ifndef __MACH_LEDS_NS2_H -#define __MACH_LEDS_NS2_H +#ifndef __LEDS_KIRKWOOD_NS2_H +#define __LEDS_KIRKWOOD_NS2_H struct ns2_led { const char *name; @@ -23,4 +21,4 @@ struct ns2_led_platform_data { struct ns2_led *leds; }; -#endif /* __MACH_LEDS_NS2_H */ +#endif /* __LEDS_KIRKWOOD_NS2_H */ -- cgit v1.2.3 From ad6492b80f60a2139fa9bf8fd79b182fe5e3647c Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Mon, 27 Jan 2014 17:06:49 -0800 Subject: memblock, nobootmem: add memblock_virt_alloc_low() The new memblock_virt APIs are used to replaced old bootmem API. We need to allocate page below 4G for swiotlb. That should fix regression on Andrew's system that is using swiotlb. Signed-off-by: Yinghai Lu Cc: Russell King Cc: Konrad Rzeszutek Wilk Acked-by: Santosh Shilimkar Cc: Dave Hansen Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 2fae55def608..b388223bd4a9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -175,6 +175,27 @@ static inline void * __init memblock_virt_alloc_nopanic( NUMA_NO_NODE); } +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + +static inline void * __init memblock_virt_alloc_low( + phys_addr_t size, phys_addr_t align) +{ + return memblock_virt_alloc_try_nid(size, align, + BOOTMEM_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); +} +static inline void * __init memblock_virt_alloc_low_nopanic( + phys_addr_t size, phys_addr_t align) +{ + return memblock_virt_alloc_try_nid_nopanic(size, align, + BOOTMEM_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); +} + static inline void * __init memblock_virt_alloc_from_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) { @@ -238,6 +259,22 @@ static inline void * __init memblock_virt_alloc_nopanic( return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); } +static inline void * __init memblock_virt_alloc_low( + phys_addr_t size, phys_addr_t align) +{ + if (!align) + align = SMP_CACHE_BYTES; + return __alloc_bootmem_low(size, align, BOOTMEM_LOW_LIMIT); +} + +static inline void * __init memblock_virt_alloc_low_nopanic( + phys_addr_t size, phys_addr_t align) +{ + if (!align) + align = SMP_CACHE_BYTES; + return __alloc_bootmem_low_nopanic(size, align, BOOTMEM_LOW_LIMIT); +} + static inline void * __init memblock_virt_alloc_from_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) { -- cgit v1.2.3 From 72a8ff2f9245128c254387c58f948f1f0152ea46 Mon Sep 17 00:00:00 2001 From: Rafael Aquini Date: Mon, 27 Jan 2014 17:07:02 -0800 Subject: ipc: change kern_ipc_perm.deleted type to bool struct kern_ipc_perm.deleted is meant to be used as a boolean toggle, and the changes introduced by this patch are just to make the case explicit. Signed-off-by: Rafael Aquini Reviewed-by: Rik van Riel Cc: Greg Thelen Acked-by: Davidlohr Bueso Cc: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc.h b/include/linux/ipc.h index 8d861b2651f7..9d84942ae2e5 100644 --- a/include/linux/ipc.h +++ b/include/linux/ipc.h @@ -11,7 +11,7 @@ struct kern_ipc_perm { spinlock_t lock; - int deleted; + bool deleted; int id; key_t key; kuid_t uid; -- cgit v1.2.3 From 239521f31d7496a5322ee664ed8bbd1027b98c4b Mon Sep 17 00:00:00 2001 From: Manfred Spraul Date: Mon, 27 Jan 2014 17:07:04 -0800 Subject: ipc: whitespace cleanup The ipc code does not adhere the typical linux coding style. This patch fixes lots of simple whitespace errors. - mostly autogenerated by scripts/checkpatch.pl -f --fix \ --types=pointer_location,spacing,space_before_tab - one manual fixup (keep structure members tab-aligned) - removal of additional space_before_tab that were not found by --fix Tested with some of my msg and sem test apps. Andrew: Could you include it in -mm and move it towards Linus' tree? Signed-off-by: Manfred Spraul Suggested-by: Li Bin Cc: Joe Perches Acked-by: Rafael Aquini Cc: Davidlohr Bueso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/msg.h | 2 +- include/linux/shm.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msg.h b/include/linux/msg.h index e21f9d44307f..f3f302f9c197 100644 --- a/include/linux/msg.h +++ b/include/linux/msg.h @@ -9,7 +9,7 @@ struct msg_msg { struct list_head m_list; long m_type; size_t m_ts; /* message text size */ - struct msg_msgseg* next; + struct msg_msgseg *next; void *security; /* the actual message follows immediately */ }; diff --git a/include/linux/shm.h b/include/linux/shm.h index 429c1995d756..1e2cd2e6b540 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -9,7 +9,7 @@ struct shmid_kernel /* private to the kernel */ { struct kern_ipc_perm shm_perm; - struct file * shm_file; + struct file *shm_file; unsigned long shm_nattch; unsigned long shm_segsz; time_t shm_atim; -- cgit v1.2.3 From daf948c7d1a080041ae19aca07625efec670695a Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Mon, 27 Jan 2014 17:07:09 -0800 Subject: ipc: delete seq_max field in struct ipc_ids This field is only used to reset the ids seq number if it exceeds the smaller of INT_MAX/SEQ_MULTIPLIER and USHRT_MAX, and can therefore be moved out of the structure and into its own macro. Since each ipc_namespace contains a table of 3 pointers to struct ipc_ids we can save space in instruction text: text data bss dec hex filename 56232 2348 24 58604 e4ec ipc/built-in.o 56216 2348 24 58588 e4dc ipc/built-in.o-after Signed-off-by: Davidlohr Bueso Reviewed-by: Jonathan Gonzalez Cc: Aswin Chandramouleeswaran Cc: Rik van Riel Acked-by: Manfred Spraul Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index f6c82de12541..e7831d203737 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -21,7 +21,6 @@ struct user_namespace; struct ipc_ids { int in_use; unsigned short seq; - unsigned short seq_max; struct rw_semaphore rwsem; struct idr ipcs_idr; int next_id; -- cgit v1.2.3 From 53e0ee9fc59cb17fcad57e481b5889c791afe6c3 Mon Sep 17 00:00:00 2001 From: Xiao Guangrong Date: Mon, 27 Jan 2014 17:07:12 -0800 Subject: splice: fix unexpected size truncation @splice_desc.total_len is 32 bit(unsigned int) which is used to store the size passed from userspace which is 64 bit(size_t) so that the size is unexpectedly truncated That means vmsplice can not work if the size passed from userspace is >= 4G, for example, we noticed in vmsplice, splice-reader does not do anything and splice-writer is waiting for available buffer forever if the size is 4G Fix it by extending @splice_desc.total_len to 64 bits as well Signed-off-by: Xiao Guangrong Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/splice.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/splice.h b/include/linux/splice.h index 74575cbf2d6f..0e43906d2fda 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -24,7 +24,8 @@ * Passed to the actors */ struct splice_desc { - unsigned int len, total_len; /* current and remaining length */ + size_t total_len; /* remaining length */ + unsigned int len; /* current length */ unsigned int flags; /* splice flags */ /* * actor() private data -- cgit v1.2.3 From ce85b4f2eab663dfd4ff2cb5b603ba03f595922e Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 27 Jan 2014 17:07:16 -0800 Subject: softirq: use const char * const for softirq_to_name, whitespace neatening Reduce data size a little. Reduce checkpatch noise. $ size kernel/softirq.o* text data bss dec hex filename 11554 6013 4008 21575 5447 kernel/softirq.o.new 11474 6093 4008 21575 5447 kernel/softirq.o.old Signed-off-by: Joe Perches Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/interrupt.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index db43b58a3355..0053adde0ed9 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -360,7 +360,7 @@ enum /* map softirq index to softirq name. update 'softirq_to_name' in * kernel/softirq.c when adding a new softirq. */ -extern char *softirq_to_name[NR_SOFTIRQS]; +extern const char * const softirq_to_name[NR_SOFTIRQS]; /* softirq mask and active fields moved to irq_cpustat_t in * asm/hardirq.h to get better cache usage. KAO -- cgit v1.2.3 From 0d0b7d427987f6e98b6f32e84ee071f36f85c3d4 Mon Sep 17 00:00:00 2001 From: Jose Alonso Date: Tue, 28 Jan 2014 08:09:46 -0700 Subject: blk-mq: for_each_* macro correctness I observed that there are for_each macros that do an extra memory access beyond the defined area. Normally this does not cause problems. But, this can cause exceptions. For example: if the area is allocated at the end of a page and the next page is not accessible. For correctness, I suggest changing the arguments of the 'for loop' like others 'for_each' do in the kernel. Signed-off-by: Jose Alonso Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 851d34b7ac26..161b23105b1e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -158,16 +158,16 @@ static inline struct request *blk_mq_tag_to_rq(struct blk_mq_hw_ctx *hctx, } #define queue_for_each_hw_ctx(q, hctx, i) \ - for ((i) = 0, hctx = (q)->queue_hw_ctx[0]; \ - (i) < (q)->nr_hw_queues; (i)++, hctx = (q)->queue_hw_ctx[i]) + for ((i) = 0; (i) < (q)->nr_hw_queues && \ + ({ hctx = (q)->queue_hw_ctx[i]; 1; }); (i)++) #define queue_for_each_ctx(q, ctx, i) \ - for ((i) = 0, ctx = per_cpu_ptr((q)->queue_ctx, 0); \ - (i) < (q)->nr_queues; (i)++, ctx = per_cpu_ptr(q->queue_ctx, (i))) + for ((i) = 0; (i) < (q)->nr_queues && \ + ({ ctx = per_cpu_ptr((q)->queue_ctx, (i)); 1; }); (i)++) #define hctx_for_each_ctx(hctx, ctx, i) \ - for ((i) = 0, ctx = (hctx)->ctxs[0]; \ - (i) < (hctx)->nr_ctx; (i)++, ctx = (hctx)->ctxs[(i)]) + for ((i) = 0; (i) < (hctx)->nr_ctx && \ + ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) #define blk_ctx_sum(q, sum) \ ({ \ -- cgit v1.2.3 From 4a444b1f06d259ce938a47048840260f71a91c84 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 30 Aug 2013 10:05:22 -0400 Subject: rwsem: add rwsem_is_contended Btrfs needs a simple way to know if it needs to let go of it's read lock on a rwsem. Introduce rwsem_is_contended to check to see if there are any waiters on this rwsem currently. This is just a hueristic, it is meant to be light and not 100% accurate and called by somebody already holding on to the rwsem in either read or write. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason Acked-by: Ingo Molnar --- include/linux/rwsem.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 0616ffe45702..03f3b05e8ec1 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -74,6 +74,17 @@ do { \ __init_rwsem((sem), #sem, &__key); \ } while (0) +/* + * This is the same regardless of which rwsem implementation that is being used. + * It is just a heuristic meant to be called by somebody alreadying holding the + * rwsem to see if somebody from an incompatible type is wanting access to the + * lock. + */ +static inline int rwsem_is_contended(struct rw_semaphore *sem) +{ + return !list_empty(&sem->wait_list); +} + /* * lock for reading */ -- cgit v1.2.3 From 83c0e1b442b488571f4fef4a91c2fe52eed6c705 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 28 Jan 2014 18:53:22 +0100 Subject: fsnotify: Do not return merged event from fsnotify_add_notify_event() The event returned from fsnotify_add_notify_event() cannot ever be used safely as the event may be freed by the time the function returns (after dropping notification_mutex). So change the prototype to just return whether the event was added or merged into some existing event. Reported-and-tested-by: Jiri Kosina Reported-and-tested-by: Dave Jones Signed-off-by: Jan Kara --- include/linux/fsnotify_backend.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 7d8d5e608594..3d286ff49ab0 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -322,10 +322,10 @@ extern int fsnotify_fasync(int fd, struct file *file, int on); extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern struct fsnotify_event *fsnotify_add_notify_event(struct fsnotify_group *group, - struct fsnotify_event *event, - struct fsnotify_event *(*merge)(struct list_head *, - struct fsnotify_event *)); +extern int fsnotify_add_notify_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct list_head *, + struct fsnotify_event *)); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -- cgit v1.2.3 From 7c81c60f3789a082e141d7a013392af5f78db16a Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Wed, 29 Jan 2014 20:40:08 +0100 Subject: Update Jean Delvare's e-mail address Signed-off-by: Jean Delvare --- include/linux/i2c-smbus.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h index 017fb40f702a..8f1b086ca5bc 100644 --- a/include/linux/i2c-smbus.h +++ b/include/linux/i2c-smbus.h @@ -1,7 +1,7 @@ /* * i2c-smbus.h - SMBus extensions to the I2C protocol * - * Copyright (C) 2010 Jean Delvare + * Copyright (C) 2010 Jean Delvare * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by -- cgit v1.2.3 From a1c3bfb2f67ef766de03f1f56bdfff9c8595ab14 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 29 Jan 2014 14:05:41 -0800 Subject: mm/page-writeback.c: do not count anon pages as dirtyable memory The VM is currently heavily tuned to avoid swapping. Whether that is good or bad is a separate discussion, but as long as the VM won't swap to make room for dirty cache, we can not consider anonymous pages when calculating the amount of dirtyable memory, the baseline to which dirty_background_ratio and dirty_ratio are applied. A simple workload that occupies a significant size (40+%, depending on memory layout, storage speeds etc.) of memory with anon/tmpfs pages and uses the remainder for a streaming writer demonstrates this problem. In that case, the actual cache pages are a small fraction of what is considered dirtyable overall, which results in an relatively large portion of the cache pages to be dirtied. As kswapd starts rotating these, random tasks enter direct reclaim and stall on IO. Only consider free pages and file pages dirtyable. Signed-off-by: Johannes Weiner Reported-by: Tejun Heo Tested-by: Tejun Heo Reviewed-by: Rik van Riel Cc: Mel Gorman Cc: Wu Fengguang Reviewed-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmstat.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index e4b948080d20..a67b38415768 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -142,8 +142,6 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone, return x; } -extern unsigned long global_reclaimable_pages(void); - #ifdef CONFIG_NUMA /* * Determine the per node value of a stat item. This function -- cgit v1.2.3 From dfd948e32af2e7b28bcd7a490c0a30d4b8df2a36 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 29 Jan 2014 14:05:44 -0800 Subject: fs/compat: fix parameter handling for compat readv/writev syscalls We got a report that the pwritev syscall does not work correctly in compat mode on s390. It turned out that with commit 72ec35163f9f ("switch compat readv/writev variants to COMPAT_SYSCALL_DEFINE") we lost the zero extension of a couple of syscall parameters because the some parameter types haven't been converted from unsigned long to compat_ulong_t. This is needed for architectures where the ABI requires that the caller of a function performed zero and/or sign extension to 64 bit of all parameters. Signed-off-by: Heiko Carstens Cc: Al Viro Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Hendrik Brueckner Cc: Martin Schwidefsky Cc: [v3.10+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index eb8a49d75ab3..c5642b83e02b 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -327,16 +327,16 @@ asmlinkage long compat_sys_keyctl(u32 option, u32 arg2, u32 arg3, u32 arg4, u32 arg5); asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32); -asmlinkage ssize_t compat_sys_readv(unsigned long fd, - const struct compat_iovec __user *vec, unsigned long vlen); -asmlinkage ssize_t compat_sys_writev(unsigned long fd, - const struct compat_iovec __user *vec, unsigned long vlen); -asmlinkage ssize_t compat_sys_preadv(unsigned long fd, +asmlinkage ssize_t compat_sys_readv(compat_ulong_t fd, + const struct compat_iovec __user *vec, compat_ulong_t vlen); +asmlinkage ssize_t compat_sys_writev(compat_ulong_t fd, + const struct compat_iovec __user *vec, compat_ulong_t vlen); +asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_low, u32 pos_high); -asmlinkage ssize_t compat_sys_pwritev(unsigned long fd, + compat_ulong_t vlen, u32 pos_low, u32 pos_high); +asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct compat_iovec __user *vec, - unsigned long vlen, u32 pos_low, u32 pos_high); + compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage long comat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, -- cgit v1.2.3 From d8d14bd09cddbaf0168d61af638455a26bd027ff Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 29 Jan 2014 14:05:46 -0800 Subject: fs/compat: fix lookup_dcookie() parameter handling Commit d5dc77bfeeab ("consolidate compat lookup_dcookie()") coverted all architectures to the new compat_sys_lookup_dcookie() syscall. The "len" paramater of the new compat syscall must have the type compat_size_t in order to enforce zero extension for architectures where the ABI requires that the caller of a function performed zero and/or sign extension to 64 bit of all parameters. Signed-off-by: Heiko Carstens Cc: Al Viro Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Hendrik Brueckner Cc: Martin Schwidefsky Cc: [v3.10+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index c5642b83e02b..19f6003291de 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -422,7 +422,7 @@ extern long compat_arch_ptrace(struct task_struct *child, compat_long_t request, asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, compat_long_t addr, compat_long_t data); -asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, size_t); +asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t); /* * epoll (fs/eventpoll.c) compat bits follow ... */ -- cgit v1.2.3 From 07bacb3826d613bb651297a201dd2df8dd4fdee5 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Thu, 30 Jan 2014 15:45:44 -0800 Subject: memblock, bootmem: restore goal for alloc_low Now we have memblock_virt_alloc_low to replace original bootmem api in swiotlb. But we should not use BOOTMEM_LOW_LIMIT for arch that does not support CONFIG_NOBOOTMEM, as old api take 0. | #define alloc_bootmem_low(x) \ | __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) |#define alloc_bootmem_low_pages_nopanic(x) \ | __alloc_bootmem_low_nopanic(x, PAGE_SIZE, 0) and we have #define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) for CONFIG_NOBOOTMEM. Restore goal to 0 to fix ia64 crash, that Tony found. Signed-off-by: Yinghai Lu Reported-by: Tony Luck Tested-by: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b388223bd4a9..db51fe4fe317 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -264,7 +264,7 @@ static inline void * __init memblock_virt_alloc_low( { if (!align) align = SMP_CACHE_BYTES; - return __alloc_bootmem_low(size, align, BOOTMEM_LOW_LIMIT); + return __alloc_bootmem_low(size, align, 0); } static inline void * __init memblock_virt_alloc_low_nopanic( @@ -272,7 +272,7 @@ static inline void * __init memblock_virt_alloc_low_nopanic( { if (!align) align = SMP_CACHE_BYTES; - return __alloc_bootmem_low_nopanic(size, align, BOOTMEM_LOW_LIMIT); + return __alloc_bootmem_low_nopanic(size, align, 0); } static inline void * __init memblock_virt_alloc_from_nopanic( -- cgit v1.2.3 From 6897fc22ea01b562b55c6168592bcbd3ee62b006 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 30 Jan 2014 15:45:47 -0800 Subject: kernel: use lockless list for smp_call_function_single Make smp_call_function_single and friends more efficient by using a lockless list. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 5 +---- include/linux/smp.h | 6 +++++- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0375654adb28..8678c4322b44 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -95,10 +95,7 @@ enum rq_cmd_type_bits { * as well! */ struct request { - union { - struct list_head queuelist; - struct llist_node ll_list; - }; + struct list_head queuelist; union { struct call_single_data csd; struct work_struct mq_flush_data; diff --git a/include/linux/smp.h b/include/linux/smp.h index 5da22ee42e16..3834f43f9993 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -11,12 +11,16 @@ #include #include #include +#include extern void cpu_idle(void); typedef void (*smp_call_func_t)(void *info); struct call_single_data { - struct list_head list; + union { + struct list_head list; + struct llist_node llist; + }; smp_call_func_t func; void *info; u16 flags; -- cgit v1.2.3 From bcf1647d0899666f0fb90d176abf63bae22abb7c Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 30 Jan 2014 15:45:50 -0800 Subject: zsmalloc: move it under mm This patch moves zsmalloc under mm directory. Before that, description will explain why we have needed custom allocator. Zsmalloc is a new slab-based memory allocator for storing compressed pages. It is designed for low fragmentation and high allocation success rate on large object, but <= PAGE_SIZE allocations. zsmalloc differs from the kernel slab allocator in two primary ways to achieve these design goals. zsmalloc never requires high order page allocations to back slabs, or "size classes" in zsmalloc terms. Instead it allows multiple single-order pages to be stitched together into a "zspage" which backs the slab. This allows for higher allocation success rate under memory pressure. Also, zsmalloc allows objects to span page boundaries within the zspage. This allows for lower fragmentation than could be had with the kernel slab allocator for objects between PAGE_SIZE/2 and PAGE_SIZE. With the kernel slab allocator, if a page compresses to 60% of it original size, the memory savings gained through compression is lost in fragmentation because another object of the same size can't be stored in the leftover space. This ability to span pages results in zsmalloc allocations not being directly addressable by the user. The user is given an non-dereferencable handle in response to an allocation request. That handle must be mapped, using zs_map_object(), which returns a pointer to the mapped region that can be used. The mapping is necessary since the object data may reside in two different noncontigious pages. The zsmalloc fulfills the allocation needs for zram perfectly [sjenning@linux.vnet.ibm.com: borrow Seth's quote] Signed-off-by: Minchan Kim Acked-by: Nitin Gupta Reviewed-by: Konrad Rzeszutek Wilk Cc: Bob Liu Cc: Greg Kroah-Hartman Cc: Hugh Dickins Cc: Jens Axboe Cc: Luigi Semenzato Cc: Mel Gorman Cc: Pekka Enberg Cc: Rik van Riel Cc: Seth Jennings Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zsmalloc.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 50 insertions(+) create mode 100644 include/linux/zsmalloc.h (limited to 'include/linux') diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h new file mode 100644 index 000000000000..c2eb174b97ee --- /dev/null +++ b/include/linux/zsmalloc.h @@ -0,0 +1,50 @@ +/* + * zsmalloc memory allocator + * + * Copyright (C) 2011 Nitin Gupta + * + * This code is released using a dual license strategy: BSD/GPL + * You can choose the license that better fits your requirements. + * + * Released under the terms of 3-clause BSD License + * Released under the terms of GNU General Public License Version 2.0 + */ + +#ifndef _ZS_MALLOC_H_ +#define _ZS_MALLOC_H_ + +#include + +/* + * zsmalloc mapping modes + * + * NOTE: These only make a difference when a mapped object spans pages. + * They also have no effect when PGTABLE_MAPPING is selected. + */ +enum zs_mapmode { + ZS_MM_RW, /* normal read-write mapping */ + ZS_MM_RO, /* read-only (no copy-out at unmap time) */ + ZS_MM_WO /* write-only (no copy-in at map time) */ + /* + * NOTE: ZS_MM_WO should only be used for initializing new + * (uninitialized) allocations. Partial writes to already + * initialized allocations should use ZS_MM_RW to preserve the + * existing data. + */ +}; + +struct zs_pool; + +struct zs_pool *zs_create_pool(gfp_t flags); +void zs_destroy_pool(struct zs_pool *pool); + +unsigned long zs_malloc(struct zs_pool *pool, size_t size); +void zs_free(struct zs_pool *pool, unsigned long obj); + +void *zs_map_object(struct zs_pool *pool, unsigned long handle, + enum zs_mapmode mm); +void zs_unmap_object(struct zs_pool *pool, unsigned long handle); + +u64 zs_get_total_size_bytes(struct zs_pool *pool); + +#endif -- cgit v1.2.3 From 31fc00bb788ffde7d8d861d8b2bba798ab445992 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 30 Jan 2014 15:45:55 -0800 Subject: zsmalloc: add copyright Add my copyright to the zsmalloc source code which I maintain. Signed-off-by: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/zsmalloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index c2eb174b97ee..e44d634e7fb7 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -2,6 +2,7 @@ * zsmalloc memory allocator * * Copyright (C) 2011 Nitin Gupta + * Copyright (C) 2012, 2013 Minchan Kim * * This code is released using a dual license strategy: BSD/GPL * You can choose the license that better fits your requirements. -- cgit v1.2.3 From 433a91ff5fa19e3eb70b12f7056f234aebd09ac2 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Tue, 28 Jan 2014 14:24:50 -0800 Subject: mm: sl[uo]b: fix misleading comments On x86, SLUB creates and handles <=8192-byte allocations internally. It passes larger ones up to the allocator. Saying "up to order 2" is, at best, ambiguous. Is that order-1? Or (order-2 bytes)? Make it more clear. SLOB commits a similar sin. It *handles* page-size requests, but the comment says that it passes up "all page size and larger requests". SLOB also swaps around the order of the very-similarly-named KMALLOC_SHIFT_HIGH and KMALLOC_SHIFT_MAX #defines. Make it consistent with the order of the other two allocators. Cc: Matt Mackall Cc: Andrew Morton Acked-by: Christoph Lameter Acked-by: David Rientjes Signed-off-by: Dave Hansen Signed-off-by: Pekka Enberg --- include/linux/slab.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 1e2f4fe12773..f76e956b4011 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -205,8 +205,8 @@ struct kmem_cache { #ifdef CONFIG_SLUB /* - * SLUB allocates up to order 2 pages directly and otherwise - * passes the request to the page allocator. + * SLUB directly allocates requests fitting in to an order-1 page + * (PAGE_SIZE*2). Larger requests are passed to the page allocator. */ #define KMALLOC_SHIFT_HIGH (PAGE_SHIFT + 1) #define KMALLOC_SHIFT_MAX (MAX_ORDER + PAGE_SHIFT) @@ -217,12 +217,12 @@ struct kmem_cache { #ifdef CONFIG_SLOB /* - * SLOB passes all page size and larger requests to the page allocator. + * SLOB passes all requests larger than one page to the page allocator. * No kmalloc array is necessary since objects of different sizes can * be allocated from the same page. */ -#define KMALLOC_SHIFT_MAX 30 #define KMALLOC_SHIFT_HIGH PAGE_SHIFT +#define KMALLOC_SHIFT_MAX 30 #ifndef KMALLOC_SHIFT_LOW #define KMALLOC_SHIFT_LOW 3 #endif -- cgit v1.2.3 From e5fbf67dab3341133d4ee3b1c8ce780e087733ba Mon Sep 17 00:00:00 2001 From: Stephan Springl Date: Thu, 30 Jan 2014 17:56:23 +0100 Subject: Typo in compat_sys_lseek() declaration Signed-off-by: Al Viro --- include/linux/compat.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compat.h b/include/linux/compat.h index c5642b83e02b..39f886f84893 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -337,7 +337,7 @@ asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd, asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, const struct compat_iovec __user *vec, compat_ulong_t vlen, u32 pos_low, u32 pos_high); -asmlinkage long comat_sys_lseek(unsigned int, compat_off_t, unsigned int); +asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, const compat_uptr_t __user *envp); -- cgit v1.2.3 From 17ead6c85c3d0ef57a14d1373f1f1cee2ce60ea8 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 1 Feb 2014 14:53:23 -0500 Subject: NFSv4: Fix memory corruption in nfs4_proc_open_confirm nfs41_wake_and_assign_slot() relies on the task->tk_msg.rpc_argp and task->tk_msg.rpc_resp always pointing to the session sequence arguments. nfs4_proc_open_confirm tries to pull a fast one by reusing the open sequence structure, thus causing corruption of the NFSv4 slot table. Cc: stable@vger.kernel.org # 3.12+ Signed-off-by: Trond Myklebust --- include/linux/nfs_xdr.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 3ccfcecf8999..b2fb167b2e6d 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -379,12 +379,14 @@ struct nfs_openres { * Arguments to the open_confirm call. */ struct nfs_open_confirmargs { + struct nfs4_sequence_args seq_args; const struct nfs_fh * fh; nfs4_stateid * stateid; struct nfs_seqid * seqid; }; struct nfs_open_confirmres { + struct nfs4_sequence_res seq_res; nfs4_stateid stateid; struct nfs_seqid * seqid; }; -- cgit v1.2.3 From c4ad8f98bef77c7356aa6a9ad9188a6acc6b849d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 5 Feb 2014 12:54:53 -0800 Subject: execve: use 'struct filename *' for executable name passing This changes 'do_execve()' to get the executable name as a 'struct filename', and to free it when it is done. This is what the normal users want, and it simplifies and streamlines their error handling. The controlled lifetime of the executable name also fixes a use-after-free problem with the trace_sched_process_exec tracepoint: the lifetime of the passed-in string for kernel users was not at all obvious, and the user-mode helper code used UMH_WAIT_EXEC to serialize the pathname allocation lifetime with the execve() having finished, which in turn meant that the trace point that happened after mm_release() of the old process VM ended up using already free'd memory. To solve the kernel string lifetime issue, this simply introduces "getname_kernel()" that works like the normal user-space getname() function, except with the source coming from kernel memory. As Oleg points out, this also means that we could drop the tcomm[] array from 'struct linux_binprm', since the pathname lifetime now covers setup_new_exec(). That would be a separate cleanup. Reported-by: Igor Zhbanov Tested-by: Steven Rostedt Cc: Oleg Nesterov Cc: Al Viro Signed-off-by: Linus Torvalds --- include/linux/binfmts.h | 1 - include/linux/fs.h | 1 + include/linux/sched.h | 3 ++- 3 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index fd8bf3219ef7..b4a745d7d9a9 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -115,7 +115,6 @@ extern int copy_strings_kernel(int argc, const char *const *argv, extern int prepare_bprm_creds(struct linux_binprm *bprm); extern void install_exec_creds(struct linux_binprm *bprm); extern void set_binfmt(struct linux_binfmt *new); -extern void free_bprm(struct linux_binprm *); extern ssize_t read_code(struct file *, unsigned long, loff_t, size_t); #endif /* _LINUX_BINFMTS_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c59813..d79678c188ad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2079,6 +2079,7 @@ extern struct file * dentry_open(const struct path *, int, const struct cred *); extern int filp_close(struct file *, fl_owner_t id); extern struct filename *getname(const char __user *); +extern struct filename *getname_kernel(const char *); enum { FILE_CREATED = 1, diff --git a/include/linux/sched.h b/include/linux/sched.h index 68a0e84463a0..a781dec1cd0b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -128,6 +128,7 @@ struct bio_list; struct fs_struct; struct perf_event_context; struct blk_plug; +struct filename; /* * List of flags we want to share for kernel threads, @@ -2311,7 +2312,7 @@ extern void do_group_exit(int); extern int allow_signal(int); extern int disallow_signal(int); -extern int do_execve(const char *, +extern int do_execve(struct filename *, const char __user * const __user *, const char __user * const __user *); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); -- cgit v1.2.3 From 579f82901f6f41256642936d7e632f3979ad76d4 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 6 Feb 2014 12:04:21 -0800 Subject: swap: add a simple detector for inappropriate swapin readahead This is a patch to improve swap readahead algorithm. It's from Hugh and I slightly changed it. Hugh's original changelog: swapin readahead does a blind readahead, whether or not the swapin is sequential. This may be ok on harddisk, because large reads have relatively small costs, and if the readahead pages are unneeded they can be reclaimed easily - though, what if their allocation forced reclaim of useful pages? But on SSD devices large reads are more expensive than small ones: if the readahead pages are unneeded, reading them in caused significant overhead. This patch adds very simplistic random read detection. Stealing the PageReadahead technique from Konstantin Khlebnikov's patch, avoiding the vma/anon_vma sophistications of Shaohua Li's patch, swapin_nr_pages() simply looks at readahead's current success rate, and narrows or widens its readahead window accordingly. There is little science to its heuristic: it's about as stupid as can be whilst remaining effective. The table below shows elapsed times (in centiseconds) when running a single repetitive swapping load across a 1000MB mapping in 900MB ram with 1GB swap (the harddisk tests had taken painfully too long when I used mem=500M, but SSD shows similar results for that). Vanilla is the 3.6-rc7 kernel on which I started; Shaohua denotes his Sep 3 patch in mmotm and linux-next; HughOld denotes my Oct 1 patch which Shaohua showed to be defective; HughNew this Nov 14 patch, with page_cluster as usual at default of 3 (8-page reads); HughPC4 this same patch with page_cluster 4 (16-page reads); HughPC0 with page_cluster 0 (1-page reads: no readahead). HDD for swapping to harddisk, SSD for swapping to VertexII SSD. Seq for sequential access to the mapping, cycling five times around; Rand for the same number of random touches. Anon for a MAP_PRIVATE anon mapping; Shmem for a MAP_SHARED anon mapping, equivalent to tmpfs. One weakness of Shaohua's vma/anon_vma approach was that it did not optimize Shmem: seen below. Konstantin's approach was perhaps mistuned, 50% slower on Seq: did not compete and is not shown below. HDD Vanilla Shaohua HughOld HughNew HughPC4 HughPC0 Seq Anon 73921 76210 75611 76904 78191 121542 Seq Shmem 73601 73176 73855 72947 74543 118322 Rand Anon 895392 831243 871569 845197 846496 841680 Rand Shmem 1058375 1053486 827935 764955 764376 756489 SSD Vanilla Shaohua HughOld HughNew HughPC4 HughPC0 Seq Anon 24634 24198 24673 25107 21614 70018 Seq Shmem 24959 24932 25052 25703 22030 69678 Rand Anon 43014 26146 28075 25989 26935 25901 Rand Shmem 45349 45215 28249 24268 24138 24332 These tests are, of course, two extremes of a very simple case: under heavier mixed loads I've not yet observed any consistent improvement or degradation, and wider testing would be welcome. Shaohua Li: Test shows Vanilla is slightly better in sequential workload than Hugh's patch. I observed with Hugh's patch sometimes the readahead size is shrinked too fast (from 8 to 1 immediately) in sequential workload if there is no hit. And in such case, continuing doing readahead is good actually. I don't prepare a sophisticated algorithm for the sequential workload because so far we can't guarantee sequential accessed pages are swap out sequentially. So I slightly change Hugh's heuristic - don't shrink readahead size too fast. Here is my test result (unit second, 3 runs average): Vanilla Hugh New Seq 356 370 360 Random 4525 2447 2444 Attached graph is the swapin/swapout throughput I collected with 'vmstat 2'. The first part is running a random workload (till around 1200 of the x-axis) and the second part is running a sequential workload. swapin and swapout throughput are almost identical in steady state in both workloads. These are expected behavior. while in Vanilla, swapin is much bigger than swapout especially in random workload (because wrong readahead). Original patches by: Shaohua Li and Konstantin Khlebnikov. [fengguang.wu@intel.com: swapin_nr_pages() can be static] Signed-off-by: Hugh Dickins Signed-off-by: Shaohua Li Signed-off-by: Fengguang Wu Cc: Rik van Riel Cc: Wu Fengguang Cc: Minchan Kim Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e464b4e987e8..d1fe1a761047 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -228,9 +228,9 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1) TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback) PAGEFLAG(MappedToDisk, mappedtodisk) -/* PG_readahead is only used for file reads; PG_reclaim is only for writes */ +/* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim) TESTCLEARFLAG(Reclaim, reclaim) -PAGEFLAG(Readahead, reclaim) /* Reminder to do async read-ahead */ +PAGEFLAG(Readahead, reclaim) TESTCLEARFLAG(Readahead, reclaim) #ifdef CONFIG_HIGHMEM /* -- cgit v1.2.3 From d311d79de305f1ada47cadd672e6ed1b28a949eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 9 Feb 2014 15:18:09 -0500 Subject: fix O_SYNC|O_APPEND syncing the wrong range on write() It actually goes back to 2004 ([PATCH] Concurrent O_SYNC write support) when sync_page_range() had been introduced; generic_file_write{,v}() correctly synced pos_after_write - written .. pos_after_write - 1 but generic_file_aio_write() synced pos_before_write .. pos_before_write + written - 1 instead. Which is not the same thing with O_APPEND, obviously. A couple of years later correct variant had been killed off when everything switched to use of generic_file_aio_write(). All users of generic_file_aio_write() are affected, and the same bug has been copied into other instances of ->aio_write(). The fix is trivial; the only subtle point is that generic_write_sync() ought to be inlined to avoid calculations useless for the majority of calls. Signed-off-by: Al Viro --- include/linux/fs.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 09f553c59813..75ff961be051 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2273,7 +2273,13 @@ extern int filemap_fdatawrite_range(struct address_space *mapping, extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); extern int vfs_fsync(struct file *file, int datasync); -extern int generic_write_sync(struct file *file, loff_t pos, loff_t count); +static inline int generic_write_sync(struct file *file, loff_t pos, loff_t count) +{ + if (!(file->f_flags & O_DSYNC) && !IS_SYNC(file->f_mapping->host)) + return 0; + return vfs_fsync_range(file, pos, pos + count - 1, + (file->f_flags & __O_SYNC) ? 0 : 1); +} extern void emergency_sync(void); extern void emergency_remount(void); #ifdef CONFIG_BLOCK -- cgit v1.2.3