From d2dcd9083f101584e029cbd4f0e1a4e573170d43 Mon Sep 17 00:00:00 2001 From: Prasad Joshi Date: Fri, 9 Mar 2012 06:27:12 +0530 Subject: [PATCH 001/208] logfs: destroy the reserved inodes while unmounting We were assuming that the evict_inode() would never be called on reserved inodes. However, (after the commit 8e22c1a4e logfs: get rid of magical inodes) while unmounting the file system, in put_super, we call iput() on all of the reserved inodes. The following simple test used to cause a kernel panic on LogFS: 1. Mount a LogFS file system on /mnt 2. Create a file $ touch /mnt/a 3. Try to unmount the FS $ umount /mnt The simple fix would be to drop the assumption and properly destroy the reserved inodes. Signed-off-by: Prasad Joshi --- fs/logfs/inode.c | 16 ++++++++++++++++ fs/logfs/readwrite.c | 1 - fs/logfs/segment.c | 2 +- 3 files changed, 17 insertions(+), 2 deletions(-) diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index a422f42238b2..df093d9e4da1 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -156,10 +156,26 @@ static void __logfs_destroy_inode(struct inode *inode) call_rcu(&inode->i_rcu, logfs_i_callback); } +static void __logfs_destroy_meta_inode(struct inode *inode) +{ + struct logfs_inode *li = logfs_inode(inode); + BUG_ON(li->li_block); + call_rcu(&inode->i_rcu, logfs_i_callback); +} + static void logfs_destroy_inode(struct inode *inode) { struct logfs_inode *li = logfs_inode(inode); + if (inode->i_ino < LOGFS_RESERVED_INOS) { + /* + * The reserved inodes are never destroyed unless we are in + * unmont path. + */ + __logfs_destroy_meta_inode(inode); + return; + } + BUG_ON(list_empty(&li->li_freeing_list)); spin_lock(&logfs_inode_lock); li->li_refcount--; diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index e3ab5e5a904c..c8ea8664699c 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -2189,7 +2189,6 @@ void logfs_evict_inode(struct inode *inode) return; } - BUG_ON(inode->i_ino < LOGFS_RESERVED_INOS); page = inode_to_page(inode); BUG_ON(!page); /* FIXME: Use emergency page */ logfs_put_write_page(page); diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index e28d090c98d6..038da0991794 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -886,7 +886,7 @@ static struct logfs_area *alloc_area(struct super_block *sb) static void map_invalidatepage(struct page *page, unsigned long l) { - BUG(); + return; } static int map_releasepage(struct page *page, gfp_t g) From cd8bfa9c8a13cf3facc5731da17e10188b3795d1 Mon Sep 17 00:00:00 2001 From: Prasad Joshi Date: Mon, 2 Apr 2012 09:23:04 +0530 Subject: [PATCH 002/208] logfs: initialize the number of iovecs in bio This fixes the following crash when a LogFS file system, created on a encrypted LVM volume, was mounted [ 526.548034] BUG: unable to handle kernel NULL pointer dereference at [ 526.550106] IP: [] memcpy+0xb/0x120 [ 526.551008] PGD bd60067 PUD 1778d067 PMD 0 [ 526.551783] Oops: 0000 [#1] SMP Pid: 2043, comm: mount RIP: 0010:[] [] memcpy+0xb/0x120 Call Trace: kcryptd_io_read+0xdb/0x100 crypt_map+0xfd/0x190 __map_bio+0x48/0x150 __split_and_process_bio+0x51b/0x630 dm_request+0x138/0x230 generic_make_request+0xca/0x100 submit_bio+0x87/0x110 sync_request+0xdd/0x120 [logfs] bdev_readpage+0x2e/0x70 [logfs] do_read_cache_page+0x82/0x180 logfs_mount+0x2ad/0x770 [logfs] mount_fs+0x47/0x1c0 vfs_kern_mount+0x72/0x110 do_kern_mount+0x54/0x110 do_mount+0x520/0x7f0 sys_mount+0x90/0xe0 Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42292 Reported-by: Witold Baryluk Signed-off-by: Prasad Joshi --- fs/logfs/dev_bdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index df0de27c2733..ea29df36893d 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -26,6 +26,7 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw) struct completion complete; bio_init(&bio); + bio.bi_max_vecs = 1; bio.bi_io_vec = &bio_vec; bio_vec.bv_page = page; bio_vec.bv_len = PAGE_SIZE; From ddb24bbac3681b87ae0638aacb702d9273e3c025 Mon Sep 17 00:00:00 2001 From: Prasad Joshi Date: Mon, 23 Jul 2012 09:18:14 +0530 Subject: [PATCH 003/208] logfs: create a pagecache page if it is not present While writing the partial journal entries we assumed that the page associated with the journal would always in locatable. This incorrect assumption resulted in the following BUG kernel BUG at /home/benixon/WD_SMR/kernels/linux-3.3.7-logfs/fs/logfs/journal.c:569! EIP is at logfs_write_area+0xb6/0x109 [logfs] EAX: 00000000 EBX: 00000000 ECX: ef6efea4 EDX: 00000000 ESI: 001b9000 EDI: f009e000 EBP: c3c13f14 ESP: c3c13ef0 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 Process sync (pid: 1799, ti=c3c12000 task=f07825b0 task.ti=c3c12000) Stack: 01001000 c3c13f26 781b9000 00000000 f009e000 f7286000 f1f83400 f8445071 f1f83400 c3c13f30 f8445ae9 c3c13f20 0000100a 000ee000 f009e000 00000001 c3c13f5c f8445d17 c05eb0ee 00000000 f1f83400 ef718000 f009e25c ea9c3d80 Call Trace: [] ? account_shadow+0x16d/0x16d [logfs] [] logfs_write_je+0x2a/0x44 [logfs] [] logfs_write_anchor+0x114/0x228 [logfs] [] ? empty+0x5/0x5 [] logfs_sync_fs+0x1e/0x31 [logfs] [] __sync_filesystem+0x5d/0x6f [] sync_one_sb+0x15/0x17 [] iterate_supers+0x59/0x9a [] ? __sync_filesystem+0x6f/0x6f [] sys_sync+0x29/0x4f [] sysenter_do_call+0x12/0x28 EIP: [] logfs_write_area+0xb6/0x109 [logfs] SS:ESP 0068:c3c13ef0 ---[ end trace ef6e9ef52601a945 ]--- The fix is to create the pagecache page if it is not locatable. Reported-and-tested-by: Benixon Dhas Signed-off-by: Prasad Joshi --- fs/logfs/journal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c index 1e1c369df22b..2a09b8d73989 100644 --- a/fs/logfs/journal.c +++ b/fs/logfs/journal.c @@ -565,7 +565,7 @@ static void write_wbuf(struct super_block *sb, struct logfs_area *area, index = ofs >> PAGE_SHIFT; page_ofs = ofs & (PAGE_SIZE - 1); - page = find_lock_page(mapping, index); + page = find_or_create_page(mapping, index, GFP_NOFS); BUG_ON(!page); memcpy(wbuf, page_address(page) + page_ofs, super->s_writesize); unlock_page(page); From 41b93bc1ee7e7276db698dd66afa7b740cda517a Mon Sep 17 00:00:00 2001 From: Prasad Joshi Date: Mon, 23 Jul 2012 09:35:52 +0530 Subject: [PATCH 004/208] logfs: maintain the ordering of meta-inode destruction LogFS does not use a specialized area to maintain the inodes. The inodes information is kept in a specialized file called inode file. Similarly, the segment information is kept in a segment file. Since the segment file also has an inode which is kept in the inode file, the inode for segment file must be evicted before the inode for inode file. The change fixes the following BUG during unmount Pid: 2057, comm: umount Not tainted 3.5.0-rc6+ #25 Bochs Bochs RIP: 0010:[] [] move_page_to_btree+0x32/0x1f0 [logfs] Process umount (pid: 2057, threadinfo ...) Call Trace: [] ? find_get_pages+0x2a/0x180 [] logfs_invalidatepage+0x85/0x90 [logfs] [] truncate_inode_page+0xb1/0xd0 [] truncate_inode_pages_range+0x15f/0x490 [] ? printk+0x78/0x7a [] truncate_inode_pages+0x15/0x20 [] logfs_evict_inode+0x6c/0x190 [logfs] [] ? _raw_spin_unlock+0x2b/0x40 [] evict+0xa7/0x1b0 [] dispose_list+0x3e/0x60 [] evict_inodes+0xf4/0x110 [] generic_shutdown_super+0x53/0xf0 [] logfs_kill_sb+0x52/0xf0 [logfs] [] deactivate_locked_super+0x45/0x80 [] deactivate_super+0x4a/0x70 [] mntput_no_expire+0xde/0x140 [] sys_umount+0x6f/0x3a0 [] system_call_fastpath+0x16/0x1b ---[ end trace 45f7752082cefafd ]--- Signed-off-by: Prasad Joshi --- fs/logfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index df093d9e4da1..6984562738d3 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -389,8 +389,8 @@ static void logfs_put_super(struct super_block *sb) { struct logfs_super *super = logfs_super(sb); /* kill the meta-inodes */ - iput(super->s_master_inode); iput(super->s_segfile_inode); + iput(super->s_master_inode); iput(super->s_mapping_inode); } From 9f0bbd8ca7905fcc0602c038013b095322fec939 Mon Sep 17 00:00:00 2001 From: Prasad Joshi Date: Mon, 23 Jul 2012 10:32:11 +0530 Subject: [PATCH 005/208] logfs: query block device for number of pages to send with bio The block device driver puts a limit on maximum number of pages that can be sent with the bio. Not all block devices can handle BIO_MAX_PAGES number of pages in bio. Specifically the virtio-blk diriver limits it to 126. When the LogFS file system was excersized in KVM, the following bug from do_virtblk_request() was observed static void do_virtblk_request(struct request_queue *q) { .... .... while ((req = blk_peek_request(q)) != NULL) { BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); .... .... } .... } The patch fixes the problem by querring the maximum number of pages in bio allowed from block device driver and then using those many pages during submit_bio. Signed-off-by: Prasad Joshi --- fs/logfs/dev_bdev.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index ea29df36893d..e784a217b500 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -96,12 +96,11 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index, struct address_space *mapping = super->s_mapping_inode->i_mapping; struct bio *bio; struct page *page; - struct request_queue *q = bdev_get_queue(sb->s_bdev); - unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9); + unsigned int max_pages; int i; - if (max_pages > BIO_MAX_PAGES) - max_pages = BIO_MAX_PAGES; + max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev)); + bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); @@ -191,12 +190,11 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index, { struct logfs_super *super = logfs_super(sb); struct bio *bio; - struct request_queue *q = bdev_get_queue(sb->s_bdev); - unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9); + unsigned int max_pages; int i; - if (max_pages > BIO_MAX_PAGES) - max_pages = BIO_MAX_PAGES; + max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev)); + bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); From bba3d8c3b3c0f2123be5bc687d1cddc13437c923 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 23 Jul 2012 12:16:19 +0100 Subject: [PATCH 006/208] [PARISC] Redefine ATOMIC_INIT and ATOMIC64_INIT to drop the casts The following build error occured during a parisc build with swap-over-NFS patches applied. net/core/sock.c:274:36: error: initializer element is not constant net/core/sock.c:274:36: error: (near initialization for 'memalloc_socks') net/core/sock.c:274:36: error: initializer element is not constant Dave Anglin says: > Here is the line in sock.i: > > struct static_key memalloc_socks = ((struct static_key) { .enabled = > ((atomic_t) { (0) }) }); The above line contains two compound literals. It also uses a designated initializer to initialize the field enabled. A compound literal is not a constant expression. The location of the above statement isn't fully clear, but if a compound literal occurs outside the body of a function, the initializer list must consist of constant expressions. Reported-by: Fengguang Wu Signed-off-by: Mel Gorman Cc: Signed-off-by: James Bottomley --- arch/parisc/include/asm/atomic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h index 6c6defc24619..af9cf30ed474 100644 --- a/arch/parisc/include/asm/atomic.h +++ b/arch/parisc/include/asm/atomic.h @@ -141,7 +141,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) #define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0) -#define ATOMIC_INIT(i) ((atomic_t) { (i) }) +#define ATOMIC_INIT(i) { (i) } #define smp_mb__before_atomic_dec() smp_mb() #define smp_mb__after_atomic_dec() smp_mb() @@ -150,7 +150,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u) #ifdef CONFIG_64BIT -#define ATOMIC64_INIT(i) ((atomic64_t) { (i) }) +#define ATOMIC64_INIT(i) { (i) } static __inline__ s64 __atomic64_add_return(s64 i, atomic64_t *v) From 76f16f83ee520d6c10356b0f6ff592441a6f08bd Mon Sep 17 00:00:00 2001 From: Jussi Kivilinna Date: Mon, 30 Jul 2012 15:42:36 +0800 Subject: [PATCH 007/208] crypto: hifn_795x - fix 64bit division and undefined __divdi3 on 32bit archs Commit feb7b7ab928afa97a79a9c424e4e0691f49d63be changed NSEC_PER_SEC to 64-bit constant, which causes "DIV_ROUND_UP(NSEC_PER_SEC, dev->pk_clk_freq)" to generate __divdi3 call on 32-bit archs. Fix this by changing DIV_ROUND_UP to DIV_ROUND_UP_ULL. Signed-off-by: Jussi Kivilinna Acked-by: Randy Dunlap Signed-off-by: Herbert Xu --- drivers/crypto/hifn_795x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c index c9c4befb5a8d..df14358d7fa1 100644 --- a/drivers/crypto/hifn_795x.c +++ b/drivers/crypto/hifn_795x.c @@ -821,8 +821,8 @@ static int hifn_register_rng(struct hifn_device *dev) /* * We must wait at least 256 Pk_clk cycles between two reads of the rng. */ - dev->rng_wait_time = DIV_ROUND_UP(NSEC_PER_SEC, dev->pk_clk_freq) * - 256; + dev->rng_wait_time = DIV_ROUND_UP_ULL(NSEC_PER_SEC, + dev->pk_clk_freq) * 256; dev->rng.name = dev->name; dev->rng.data_present = hifn_rng_data_present, From f6ff53d3611b564661896be23369b54d84941a0e Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 2 Aug 2012 09:48:49 +0200 Subject: [PATCH 008/208] block: reorganize rounding of max_discard_sectors Mostly a preparation for the next patch. In principle this fixes an infinite loop if max_discard_sectors < granularity, but that really shouldn't happen. Signed-off-by: Paolo Bonzini Acked-by: Vivek Goyal Tested-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-lib.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index 2b461b496a78..16b06f62e68c 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -44,6 +44,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); int type = REQ_WRITE | REQ_DISCARD; unsigned int max_discard_sectors; + unsigned int granularity; struct bio_batch bb; struct bio *bio; int ret = 0; @@ -54,18 +55,18 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!blk_queue_discard(q)) return -EOPNOTSUPP; + /* Zero-sector (unknown) and one-sector granularities are the same. */ + granularity = max(q->limits.discard_granularity >> 9, 1U); + /* * Ensure that max_discard_sectors is of the proper * granularity */ max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); + max_discard_sectors = round_down(max_discard_sectors, granularity); if (unlikely(!max_discard_sectors)) { /* Avoid infinite loop below. Being cautious never hurts. */ return -EOPNOTSUPP; - } else if (q->limits.discard_granularity) { - unsigned int disc_sects = q->limits.discard_granularity >> 9; - - max_discard_sectors &= ~(disc_sects - 1); } if (flags & BLKDEV_DISCARD_SECURE) { From c6e666345e1b79c62ba82339cc7d55a89cb73f88 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 2 Aug 2012 09:48:50 +0200 Subject: [PATCH 009/208] block: split discard into aligned requests When a disk has large discard_granularity and small max_discard_sectors, discards are not split with optimal alignment. In the limit case of discard_granularity == max_discard_sectors, no request could be aligned correctly, so in fact you might end up with no discarded logical blocks at all. Another example that helps showing the condition in the patch is with discard_granularity == 64, max_discard_sectors == 128. A request that is submitted for 256 sectors 2..257 will be split in two: 2..129, 130..257. However, only 2 aligned blocks out of 3 are included in the request; 128..191 may be left intact and not discarded. With this patch, the first request will be truncated to ensure good alignment of what's left, and the split will be 2..127, 128..255, 256..257. The patch will also take into account the discard_alignment. At most one extra request will be introduced, because the first request will be reduced by at most granularity-1 sectors, and granularity must be less than max_discard_sectors. Subsequent requests will run on round_down(max_discard_sectors, granularity) sectors, as in the current code. Signed-off-by: Paolo Bonzini Acked-by: Vivek Goyal Tested-by: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-lib.c | 34 ++++++++++++++++++++++++---------- include/linux/blkdev.h | 10 ++++++++++ 2 files changed, 34 insertions(+), 10 deletions(-) diff --git a/block/blk-lib.c b/block/blk-lib.c index 16b06f62e68c..19cc761cacb2 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -44,7 +44,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, struct request_queue *q = bdev_get_queue(bdev); int type = REQ_WRITE | REQ_DISCARD; unsigned int max_discard_sectors; - unsigned int granularity; + unsigned int granularity, alignment, mask; struct bio_batch bb; struct bio *bio; int ret = 0; @@ -57,10 +57,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); + mask = granularity - 1; + alignment = (bdev_discard_alignment(bdev) >> 9) & mask; /* * Ensure that max_discard_sectors is of the proper - * granularity + * granularity, so that requests stay aligned after a split. */ max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); max_discard_sectors = round_down(max_discard_sectors, granularity); @@ -80,25 +82,37 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, bb.wait = &wait; while (nr_sects) { + unsigned int req_sects; + sector_t end_sect; + bio = bio_alloc(gfp_mask, 1); if (!bio) { ret = -ENOMEM; break; } + req_sects = min_t(sector_t, nr_sects, max_discard_sectors); + + /* + * If splitting a request, and the next starting sector would be + * misaligned, stop the discard at the previous aligned sector. + */ + end_sect = sector + req_sects; + if (req_sects < nr_sects && (end_sect & mask) != alignment) { + end_sect = + round_down(end_sect - alignment, granularity) + + alignment; + req_sects = end_sect - sector; + } + bio->bi_sector = sector; bio->bi_end_io = bio_batch_end_io; bio->bi_bdev = bdev; bio->bi_private = &bb; - if (nr_sects > max_discard_sectors) { - bio->bi_size = max_discard_sectors << 9; - nr_sects -= max_discard_sectors; - sector += max_discard_sectors; - } else { - bio->bi_size = nr_sects << 9; - nr_sects = 0; - } + bio->bi_size = req_sects << 9; + nr_sects -= req_sects; + sector = end_sect; atomic_inc(&bb.done); submit_bio(type, bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4e72a9d48232..281516ae8b4e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1139,6 +1139,16 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector & (lim->discard_granularity - 1); } +static inline int bdev_discard_alignment(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (bdev != bdev->bd_contains) + return bdev->bd_part->discard_alignment; + + return q->limits.discard_alignment; +} + static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) { if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1) From 53362a05ae683e12a20d9ffdf58a88094a0bed9d Mon Sep 17 00:00:00 2001 From: Jianpeng Ma Date: Thu, 2 Aug 2012 09:50:39 +0200 Subject: [PATCH 010/208] fs/block-dev.c:fix performance regression in O_DIRECT writes to md block devices For regular file, write operaion used blk_plug function.But for block file,write operation did not use blk_plug. This patch is also for write-cache mode for block-device. Signed-off-by: Jianpeng Ma Reviewed-by: NeilBrown Signed-off-by: Jens Axboe --- fs/block_dev.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/block_dev.c b/fs/block_dev.c index 1e519195d45b..38e721b35d45 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1578,10 +1578,12 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; + struct blk_plug plug; ssize_t ret; BUG_ON(iocb->ki_pos != pos); + blk_start_plug(&plug); ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); if (ret > 0 || ret == -EIOCBQUEUED) { ssize_t err; @@ -1590,6 +1592,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err < 0 && ret > 0) ret = err; } + blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL_GPL(blkdev_aio_write); From 963ab9e5da95c654bb3ab937cc478de4f7088a96 Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 2 Aug 2012 23:42:03 +0200 Subject: [PATCH 011/208] block: Introduce __blk_segment_map_sg() helper Split the mapping code in blk_rq_map_sg() to a helper __blk_segment_map_sg(), so that other mapping function, e.g. blk_bio_map_sg(), can share the code. Cc: Rusty Russell Cc: Christoph Hellwig Cc: Tejun Heo Cc: Shaohua Li Cc: "Michael S. Tsirkin" Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Suggested-by: Jens Axboe Suggested-by: Tejun Heo Signed-off-by: Asias He Signed-off-by: Jens Axboe --- block/blk-merge.c | 80 ++++++++++++++++++++++++++--------------------- 1 file changed, 45 insertions(+), 35 deletions(-) diff --git a/block/blk-merge.c b/block/blk-merge.c index 160035f54882..576b68e79248 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -110,6 +110,49 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, return 0; } +static void +__blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec, + struct scatterlist *sglist, struct bio_vec **bvprv, + struct scatterlist **sg, int *nsegs, int *cluster) +{ + + int nbytes = bvec->bv_len; + + if (*bvprv && *cluster) { + if ((*sg)->length + nbytes > queue_max_segment_size(q)) + goto new_segment; + + if (!BIOVEC_PHYS_MERGEABLE(*bvprv, bvec)) + goto new_segment; + if (!BIOVEC_SEG_BOUNDARY(q, *bvprv, bvec)) + goto new_segment; + + (*sg)->length += nbytes; + } else { +new_segment: + if (!*sg) + *sg = sglist; + else { + /* + * If the driver previously mapped a shorter + * list, we could see a termination bit + * prematurely unless it fully inits the sg + * table on each mapping. We KNOW that there + * must be more entries here or the driver + * would be buggy, so force clear the + * termination bit to avoid doing a full + * sg_init_table() in drivers for each command. + */ + (*sg)->page_link &= ~0x02; + *sg = sg_next(*sg); + } + + sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset); + (*nsegs)++; + } + *bvprv = bvec; +} + /* * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries @@ -131,41 +174,8 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, bvprv = NULL; sg = NULL; rq_for_each_segment(bvec, rq, iter) { - int nbytes = bvec->bv_len; - - if (bvprv && cluster) { - if (sg->length + nbytes > queue_max_segment_size(q)) - goto new_segment; - - if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec)) - goto new_segment; - if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec)) - goto new_segment; - - sg->length += nbytes; - } else { -new_segment: - if (!sg) - sg = sglist; - else { - /* - * If the driver previously mapped a shorter - * list, we could see a termination bit - * prematurely unless it fully inits the sg - * table on each mapping. We KNOW that there - * must be more entries here or the driver - * would be buggy, so force clear the - * termination bit to avoid doing a full - * sg_init_table() in drivers for each command. - */ - sg->page_link &= ~0x02; - sg = sg_next(sg); - } - - sg_set_page(sg, bvec->bv_page, nbytes, bvec->bv_offset); - nsegs++; - } - bvprv = bvec; + __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg, + &nsegs, &cluster); } /* segments in rq */ From 85b9f66a41eb8ee3f1dfc95707412705463cdd97 Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 2 Aug 2012 23:42:04 +0200 Subject: [PATCH 012/208] block: Add blk_bio_map_sg() helper Add a helper to map a bio to a scatterlist, modelled after blk_rq_map_sg. This helper is useful for any driver that wants to create a scatterlist from its ->make_request_fn method. Changes in v2: - Use __blk_segment_map_sg to avoid duplicated code - Add cocbook style function comment Cc: Rusty Russell Cc: Christoph Hellwig Cc: Tejun Heo Cc: Shaohua Li Cc: "Michael S. Tsirkin" Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Signed-off-by: Christoph Hellwig Signed-off-by: Minchan Kim Signed-off-by: Asias He Signed-off-by: Jens Axboe --- block/blk-merge.c | 37 +++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 2 ++ 2 files changed, 39 insertions(+) diff --git a/block/blk-merge.c b/block/blk-merge.c index 576b68e79248..e76279e41162 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -209,6 +209,43 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, } EXPORT_SYMBOL(blk_rq_map_sg); +/** + * blk_bio_map_sg - map a bio to a scatterlist + * @q: request_queue in question + * @bio: bio being mapped + * @sglist: scatterlist being mapped + * + * Note: + * Caller must make sure sg can hold bio->bi_phys_segments entries + * + * Will return the number of sg entries setup + */ +int blk_bio_map_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist) +{ + struct bio_vec *bvec, *bvprv; + struct scatterlist *sg; + int nsegs, cluster; + unsigned long i; + + nsegs = 0; + cluster = blk_queue_cluster(q); + + bvprv = NULL; + sg = NULL; + bio_for_each_segment(bvec, bio, i) { + __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg, + &nsegs, &cluster); + } /* segments in bio */ + + if (sg) + sg_mark_end(sg); + + BUG_ON(bio->bi_phys_segments && nsegs > bio->bi_phys_segments); + return nsegs; +} +EXPORT_SYMBOL(blk_bio_map_sg); + static inline int ll_new_hw_segment(struct request_queue *q, struct request *req, struct bio *bio) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 281516ae8b4e..dc632975d54f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -894,6 +894,8 @@ extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); +extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); From 0676806707281e27b13d44323bed580a8160b7a4 Mon Sep 17 00:00:00 2001 From: Jianpeng Ma Date: Fri, 3 Aug 2012 10:42:00 +0200 Subject: [PATCH 013/208] block: Don't use static to define "void *p" in show_partition_start() I met a odd prblem:read /proc/partitions may return zero. I wrote a file test.c: int main() { char buff[4096]; int ret; int fd; printf("pid=%d\n",getpid()); while (1) { fd = open("/proc/partitions", O_RDONLY); if (fd < 0) { printf("open error %s\n", strerror(errno)); return 0; } ret = read(fd, buff, 4096); if (ret <= 0) printf("ret=%d, %s, %ld\n", ret, strerror(errno), lseek(fd,0,SEEK_CUR)); close(fd); } exit(0); } You can reproduce by: 1:while true;do cat /proc/partitions > /dev/null ;done 2:./test I reviewed the code and found: >> static void *show_partition_start(struct seq_file *seqf, loff_t *pos) >> { >> static void *p; >> >> p = disk_seqf_start(seqf, pos); >> if (!IS_ERR_OR_NULL(p) && !*pos) >> seq_puts(seqf, "major minor #blocks name\n\n"); >> return p; >> } test cat /proc/partitions p = disk_seqf_start()(Not NULL) p = disk_seqf_start()(NULL because pos) if (!IS_ERR_OR_NULL(p) && !*pos) Signed-off-by: Jianpeng Ma Signed-off-by: Jens Axboe --- block/genhd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/genhd.c b/block/genhd.c index cac7366957c3..d839723303c8 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -835,7 +835,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v) static void *show_partition_start(struct seq_file *seqf, loff_t *pos) { - static void *p; + void *p; p = disk_seqf_start(seqf, pos); if (!IS_ERR_OR_NULL(p) && !*pos) From 5b24c421621792fcc588af6f644d6acf2dd798cc Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Thu, 2 Aug 2012 15:33:59 +0200 Subject: [PATCH 014/208] [PARISC] fix personality flag check in copy_thread() Directly comparing task_struct->personality against PER_* is not fully correct, as it doesn't take flags potentially stored in top three bytes into account. Analogically, directly forcefully setting personality to PER_LINUX32 or PER_LINUX discards any flags stored in the top three bytes. Signed-off-by: Jiri Kosina Signed-off-by: James Bottomley --- arch/parisc/kernel/process.c | 2 +- arch/parisc/kernel/sys_parisc.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index d4b94b395c16..2c05a9292a81 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -309,7 +309,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp, cregs->ksp = (unsigned long)stack + (pregs->gr[21] & (THREAD_SIZE - 1)); cregs->gr[30] = usp; - if (p->personality == PER_HPUX) { + if (personality(p->personality) == PER_HPUX) { #ifdef CONFIG_HPUX cregs->kpc = (unsigned long) &hpux_child_return; #else diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index c9b932260f47..7426e40699bd 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -225,12 +225,12 @@ long parisc_personality(unsigned long personality) long err; if (personality(current->personality) == PER_LINUX32 - && personality == PER_LINUX) - personality = PER_LINUX32; + && personality(personality) == PER_LINUX) + personality = (personality & ~PER_MASK) | PER_LINUX32; err = sys_personality(personality); - if (err == PER_LINUX32) - err = PER_LINUX; + if (personality(err) == PER_LINUX32) + err = (err & ~PER_MASK) | PER_LINUX; return err; } From c9f11c30374329a0d2a88cf05281ca49d8eca9ab Mon Sep 17 00:00:00 2001 From: Jia Hongtao Date: Fri, 3 Aug 2012 18:14:09 +0800 Subject: [PATCH 015/208] powerpc/fsl-pci: Only scan PCI bus if configured as a host We change fsl_add_bridge to return -ENODEV if the controller is working in agent mode. Then check the return value of fsl_add_bridge to guarantee that only successfully added host bus will be scanned. Signed-off-by: Jia Hongtao Signed-off-by: Li Yang Signed-off-by: Kumar Gala --- arch/powerpc/sysdev/fsl_pci.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index a7b2a600d0a4..c37f46136321 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -465,7 +465,7 @@ int __init fsl_add_bridge(struct device_node *dev, int is_primary) iounmap(hose->cfg_data); iounmap(hose->cfg_addr); pcibios_free_controller(hose); - return 0; + return -ENODEV; } setup_pci_cmd(hose); @@ -827,6 +827,7 @@ struct device_node *fsl_pci_primary; void __devinit fsl_pci_init(void) { + int ret; struct device_node *node; struct pci_controller *hose; dma_addr_t max = 0xffffffff; @@ -855,10 +856,12 @@ void __devinit fsl_pci_init(void) if (!fsl_pci_primary) fsl_pci_primary = node; - fsl_add_bridge(node, fsl_pci_primary == node); - hose = pci_find_hose_for_OF_device(node); - max = min(max, hose->dma_window_base_cur + - hose->dma_window_size); + ret = fsl_add_bridge(node, fsl_pci_primary == node); + if (ret == 0) { + hose = pci_find_hose_for_OF_device(node); + max = min(max, hose->dma_window_base_cur + + hose->dma_window_size); + } } } From 439793d4b3c99e550daebd868bbd58967c93d0b3 Mon Sep 17 00:00:00 2001 From: Gleb Natapov Date: Wed, 1 Aug 2012 17:01:42 +0300 Subject: [PATCH 016/208] KVM: x86: update KVM_SAVE_MSRS_BEGIN to correct value When MSR_KVM_PV_EOI_EN was added to msrs_to_save array KVM_SAVE_MSRS_BEGIN was not updated accordingly. Signed-off-by: Gleb Natapov Signed-off-by: Marcelo Tosatti Signed-off-by: Avi Kivity --- arch/x86/kvm/x86.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 42bce48f6928..dce75b760312 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -806,7 +806,7 @@ EXPORT_SYMBOL_GPL(kvm_rdpmc); * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 9 +#define KVM_SAVE_MSRS_BEGIN 10 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, From c31cc1b764b6efb713601d351c1a879c042eab34 Mon Sep 17 00:00:00 2001 From: Igor Grinberg Date: Mon, 6 Aug 2012 23:22:15 +0300 Subject: [PATCH 017/208] Revert "ARM: OMAP3530evm: set pendown_state and debounce time for ads7846" 1) The above commit introduced a common ->get_pendown_state() function into the generic code, but that function was board-specific for the OMAP3EVM and thus broke most other boards using this code. 2) The above commit was mis-merged introducing another bug which prevents the ads7846 driver probe function to succeed. The omap_ads7846_init() function frees the pendown GPIO in case there is no ->get_pendown_state() function set by the caller (board specific code), so it can be requested later by the ads7846 driver. The above commit add a common ->get_pendown_state() function without removing the gpio_free() call and thus once the ads7846 driver tries to use the pendown GPIO, it crashes as the pendown GPIO has not been requested. 3) The above commit introduces NO new functionality as get_pendown_state() function is already implemented in a suitable way by the ads7846 driver and the debounce time handling has already been fixed by commit 97ee9f01 (ARM: OMAP: fix the ads7846 init code). This reverts commit 16aced80f6739beb2a6ff7b6f96c83ba80d331e8. Conflicts: arch/arm/mach-omap2/common-board-devices.c Solved by taking the working version prior to the above commit. Cc: Zumeng Chen Cc: Arnd Bergmann Signed-off-by: Igor Grinberg Reviewed-by: Kevin Hilman Tested-by: Kevin Hilman Signed-off-by: Kevin Hilman --- arch/arm/mach-omap2/board-omap3evm.c | 1 + arch/arm/mach-omap2/common-board-devices.c | 11 ----------- arch/arm/mach-omap2/common-board-devices.h | 1 - 3 files changed, 1 insertion(+), 12 deletions(-) diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c index ef230a0eb5eb..0d362e9f9cb9 100644 --- a/arch/arm/mach-omap2/board-omap3evm.c +++ b/arch/arm/mach-omap2/board-omap3evm.c @@ -58,6 +58,7 @@ #include "hsmmc.h" #include "common-board-devices.h" +#define OMAP3_EVM_TS_GPIO 175 #define OMAP3_EVM_EHCI_VBUS 22 #define OMAP3_EVM_EHCI_SELECT 61 diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c index 14734746457c..c1875862679f 100644 --- a/arch/arm/mach-omap2/common-board-devices.c +++ b/arch/arm/mach-omap2/common-board-devices.c @@ -35,16 +35,6 @@ static struct omap2_mcspi_device_config ads7846_mcspi_config = { .turbo_mode = 0, }; -/* - * ADS7846 driver maybe request a gpio according to the value - * of pdata->get_pendown_state, but we have done this. So set - * get_pendown_state to avoid twice gpio requesting. - */ -static int omap3_get_pendown_state(void) -{ - return !gpio_get_value(OMAP3_EVM_TS_GPIO); -} - static struct ads7846_platform_data ads7846_config = { .x_max = 0x0fff, .y_max = 0x0fff, @@ -55,7 +45,6 @@ static struct ads7846_platform_data ads7846_config = { .debounce_rep = 1, .gpio_pendown = -EINVAL, .keep_vref_on = 1, - .get_pendown_state = &omap3_get_pendown_state, }; static struct spi_board_info ads7846_spi_board_info __initdata = { diff --git a/arch/arm/mach-omap2/common-board-devices.h b/arch/arm/mach-omap2/common-board-devices.h index 4c4ef6a6166b..a0b4a42836ab 100644 --- a/arch/arm/mach-omap2/common-board-devices.h +++ b/arch/arm/mach-omap2/common-board-devices.h @@ -4,7 +4,6 @@ #include "twl-common.h" #define NAND_BLOCK_SIZE SZ_128K -#define OMAP3_EVM_TS_GPIO 175 struct mtd_partition; struct ads7846_platform_data; From a71eb61c9d077ec5019b35da6c883d67fc43d002 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Tue, 10 Jul 2012 03:57:32 +0200 Subject: [PATCH 018/208] ARM: OMAP3: igep0020: set GPIO mode for mux mcspi1_cs2 pin According to the IGEPv2 Rev.C data-sheet the LAN9221i pin 14 (IRQ) is connected to the OMAP3730 mcspi1_cs2 pin. Since this omap mux pin acts as an IRQ line, it has to be configured as an input GPIO. IGEPv2 platform code sets the smsc911x_cfg->gpio_irq to GPIO 176 but since the mux pin default mode is MODE7 (safe_mode) the driver fails when trying to register the IRQ with the following error message: [ 1.994598] smsc911x: Driver version 2008-10-21 [ 3.704162] irq 272: nobody cared (try booting with the "irqpoll" option) [ 3.711364] [] (unwind_backtrace+0x0/0xf0) from [] (__report_bad_irq+0x20/0xbc) [ 3.720916] [] (__report_bad_irq+0x20/0xbc) from [] (note_interrupt+0x1d8/0x238) [ 3.730560] [] (note_interrupt+0x1d8/0x238) from [] (handle_irq_event_percpu+0xc0/0x260) [ 3.740936] [] (handle_irq_event_percpu+0xc0/0x260) from [] (handle_irq_event+0x3c/0x5c) [ 3.751312] [] (handle_irq_event+0x3c/0x5c) from [] (handle_level_irq+0xac/0x10c) [ 3.761047] [] (handle_level_irq+0xac/0x10c) from [] (generic_handle_irq+0x30/0x48) [ 3.770935] [] (generic_handle_irq+0x30/0x48) from [] (gpio_irq_handler+0x180/0x1d4) [ 3.780944] [] (gpio_irq_handler+0x180/0x1d4) from [] (generic_handle_irq+0x30/0x48) [ 3.790954] [] (generic_handle_irq+0x30/0x48) from [] (handle_IRQ+0x4c/0xac) [ 3.800231] [] (handle_IRQ+0x4c/0xac) from [] (omap3_intc_handle_irq+0x60/0x74) [ 3.809783] [] (omap3_intc_handle_irq+0x60/0x74) from [] (__irq_svc+0x44/0x60) [ 3.819213] Exception stack(0xee42fde0 to 0xee42fe28) [ 3.824554] fde0: 00000001 00000001 00000000 00000000 60000013 c06cce14 c06cce14 00000110 [ 3.833190] fe00: 00000000 c06ccdf4 60000013 ee41d000 fb058064 ee42fe28 c0089e08 c04976b4 [ 3.841796] fe20: 20000013 ffffffff [ 3.845489] [] (__irq_svc+0x44/0x60) from [] (_raw_spin_unlock_irqrestore+0x34/0x44) [ 3.855499] [] (_raw_spin_unlock_irqrestore+0x34/0x44) from [] (__setup_irq+0x1b8/0x3f0) [ 3.865875] [] (__setup_irq+0x1b8/0x3f0) from [] (request_threaded_irq+0xb8/0x140) [ 3.875701] [] (request_threaded_irq+0xb8/0x140) from [] (smsc911x_drv_probe+0x75c/0x11a4) [ 3.886260] [] (smsc911x_drv_probe+0x75c/0x11a4) from [] (platform_drv_probe+0x18/0x1c) [ 3.906707] [] (driver_probe_device+0x90/0x210) from [] (__driver_attach+0x94/0x98) [ 3.916625] [] (__driver_attach+0x94/0x98) from [] (bus_for_each_dev+0x50/0x7c) [ 3.926177] [] (bus_for_each_dev+0x50/0x7c) from [] (bus_add_driver+0x184/0x248) [ 3.935821] [] (bus_add_driver+0x184/0x248) from [] (driver_register+0x78/0x12c) [ 3.945465] [] (driver_register+0x78/0x12c) from [] (do_one_initcall+0x34/0x178) [ 3.955108] [] (do_one_initcall+0x34/0x178) from [] (kernel_init+0xfc/0x1c0) [ 3.964385] [] (kernel_init+0xfc/0x1c0) from [] (kernel_thread_exit+0x0/0x8) [ 3.973632] handlers: [ 3.976043] [] smsc911x_irqhandler [ 3.980560] Disabling IRQ #272 Signed-off-by: Javier Martinez Canillas Acked-by: Enric Balletbo i Serra Tested-by: Enric Balletbo i Serra Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/board-igep0020.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/mach-omap2/board-igep0020.c b/arch/arm/mach-omap2/board-igep0020.c index 74915295482e..28214483aaba 100644 --- a/arch/arm/mach-omap2/board-igep0020.c +++ b/arch/arm/mach-omap2/board-igep0020.c @@ -554,6 +554,8 @@ static const struct usbhs_omap_board_data igep3_usbhs_bdata __initconst = { #ifdef CONFIG_OMAP_MUX static struct omap_board_mux board_mux[] __initdata = { + /* SMSC9221 LAN Controller ETH IRQ (GPIO_176) */ + OMAP3_MUX(MCSPI1_CS2, OMAP_MUX_MODE4 | OMAP_PIN_INPUT), { .reg_offset = OMAP_MUX_TERMINATOR }, }; #endif From 5f789ebcbc06ff02a53d54f1602e36c9da30dd4c Mon Sep 17 00:00:00 2001 From: Afzal Mohammed Date: Wed, 4 Jul 2012 18:00:37 +0530 Subject: [PATCH 019/208] arm/dts: Fix am33xx wdt node Add am33xx wdt node. Signed-off-by: Afzal Mohammed [tony@atomide.com: I messed up and produced an empty commit db27ac80 with stg apply] Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am33xx.dtsi | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 59509c48d7e5..bd0cff3f808c 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -154,5 +154,10 @@ #size-cells = <0>; ti,hwmods = "i2c3"; }; + + wdt2: wdt@44e35000 { + compatible = "ti,omap3-wdt"; + ti,hwmods = "wd_timer2"; + }; }; }; From acb11fe80a27f4b30fd38be6e6e35a0abc395401 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Fri, 13 Jul 2012 16:15:07 +0530 Subject: [PATCH 020/208] OMAP2+: Fix random config build break with !ARM_CPU_SUSPEND The random config builds with PM and !ARM_CPU_SUSPEND breaks with below error on omap2plus_defconfig. arch/arm/mach-omap2/sleep44xx.S:323: undefined reference to `cpu_resume' arch/arm/mach-omap2/omap-mpuss-lowpower.c:278: undefined reference to `cpu_suspend' This is because recently merged OMAP5 platform shares the common files with OMAP4 but doesn't select ARM_CPU_SUSPEND. Without the ARM_CPU_SUSPEND the sleep code is meaningless. Fix the same by adding ARM_CPU_SUSPEND for OMAP5. The suggestion came from Russell King in an off-list discussion. Cc: Russell King Cc: Kevin Hilman Reported-by: Tony Lindgren Signed-off-by: Santosh Shilimkar Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index dd2db025f778..4a4d058ed146 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -69,6 +69,7 @@ config SOC_OMAP5 select CPU_V7 select ARM_GIC select HAVE_SMP + select ARM_CPU_SUSPEND if PM comment "OMAP Core Type" depends on ARCH_OMAP2 From ae377aaf98630de03e58fffdf3f35dec3d0ca5e0 Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Mon, 30 Jul 2012 18:42:19 +0530 Subject: [PATCH 021/208] arm/dts: Mark vcxio, v2v1 and v1v8 regulators as always on vcxio, v2v1 and v1v8 are expected to be always on, update the dtsi for twl6030 to reflect this. commit '86f5fc' regulator: core: Mark all DT based boards as having full constraints) caused these to be disabled at late boot causing OMAP4 boards (using twl6030) to lockup. Reported-by: Kishon Vijay Abraham I Reported-by: J Keerthy Signed-off-by: Rajendra nayak Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/twl6030.dtsi | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm/boot/dts/twl6030.dtsi b/arch/arm/boot/dts/twl6030.dtsi index 3b2f3510d7eb..d351b27d7213 100644 --- a/arch/arm/boot/dts/twl6030.dtsi +++ b/arch/arm/boot/dts/twl6030.dtsi @@ -66,6 +66,7 @@ vcxio: regulator@8 { compatible = "ti,twl6030-vcxio"; + regulator-always-on; }; vusb: regulator@9 { @@ -74,10 +75,12 @@ v1v8: regulator@10 { compatible = "ti,twl6030-v1v8"; + regulator-always-on; }; v2v1: regulator@11 { compatible = "ti,twl6030-v2v1"; + regulator-always-on; }; clk32kg: regulator@12 { From 128aa925ee7e9aa84943ce64df48192b92a81767 Mon Sep 17 00:00:00 2001 From: Domenico Andreoli Date: Sat, 14 Jul 2012 22:49:54 +0200 Subject: [PATCH 022/208] OMAP: remove unused parameter arch_id from uncompress.h There is not point in having arch_id as parameter of __arch_decomp_setup(), nothing in it uses arch_id. The machine id is already exported (and used) with symbol __machine_arch_type as per mach-types.h. Removing the pointless macro as well. Signed-off-by: Domenico Andreoli Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/include/plat/uncompress.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/arm/plat-omap/include/plat/uncompress.h b/arch/arm/plat-omap/include/plat/uncompress.h index b8d19a136781..7f7b112acccb 100644 --- a/arch/arm/plat-omap/include/plat/uncompress.h +++ b/arch/arm/plat-omap/include/plat/uncompress.h @@ -110,7 +110,7 @@ static inline void flush(void) _DEBUG_LL_ENTRY(mach, AM33XX_UART##p##_BASE, OMAP_PORT_SHIFT, \ AM33XXUART##p) -static inline void __arch_decomp_setup(unsigned long arch_id) +static inline void arch_decomp_setup(void) { int port = 0; @@ -198,8 +198,6 @@ static inline void __arch_decomp_setup(unsigned long arch_id) } while (0); } -#define arch_decomp_setup() __arch_decomp_setup(arch_id) - /* * nothing to do */ From 36b547aa20d1cf0d62bace7b8a9928aa33de36cd Mon Sep 17 00:00:00 2001 From: Michael Jones Date: Thu, 26 Jul 2012 17:44:44 +0200 Subject: [PATCH 023/208] omap2: mux: remove comment for nonexistent member remove comment for nonexistent member Signed-off-by: Michael Jones Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/mux.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/mach-omap2/mux.h b/arch/arm/mach-omap2/mux.h index 471e62a74a16..76f9b3c2f586 100644 --- a/arch/arm/mach-omap2/mux.h +++ b/arch/arm/mach-omap2/mux.h @@ -127,7 +127,6 @@ struct omap_mux_partition { * @gpio: GPIO number * @muxnames: available signal modes for a ball * @balls: available balls on the package - * @partition: mux partition */ struct omap_mux { u16 reg_offset; From 265a2bc84247c9b9e3bb4fe275f16ba99551a7e7 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Mon, 16 Jul 2012 16:56:15 -0700 Subject: [PATCH 024/208] ARM: OMAP3: TWL4030: ensure sys_nirq1 is mux'd and wakeup enabled The SYS_NIRQ1 pin is the interupt line for the PMIC part of the TWL6030 and interrupts from the PMIC are needed as wakeup sources. Ensure this pin is mux'd as input and has wakeup enabled so PMIC interupts (e.g. RTC) can be used as wakeup sources. Tested on 3430/n900, OMAP3530/Overo Fire, 3730/Overo FireSTORM, 3730/Beagle-xM. Signed-off-by: Kevin Hilman --- arch/arm/mach-omap2/twl-common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c index de47f170ba50..db5ff6642375 100644 --- a/arch/arm/mach-omap2/twl-common.c +++ b/arch/arm/mach-omap2/twl-common.c @@ -67,6 +67,7 @@ void __init omap_pmic_init(int bus, u32 clkrate, const char *pmic_type, int pmic_irq, struct twl4030_platform_data *pmic_data) { + omap_mux_init_signal("sys_nirq", OMAP_PIN_INPUT_PULLUP | OMAP_PIN_OFF_WAKEUPENABLE); strncpy(pmic_i2c_board_info.type, pmic_type, sizeof(pmic_i2c_board_info.type)); pmic_i2c_board_info.irq = pmic_irq; From e0e29fd74c3c8bd2ef83bbaa73d528d58a944610 Mon Sep 17 00:00:00 2001 From: Kevin Hilman Date: Tue, 7 Aug 2012 11:28:06 -0700 Subject: [PATCH 025/208] Revert "ARM: OMAP3: PM: call pre/post transition per powerdomain" This reverts commit 58f0829b7186150318c79515f0e0850c5e7a9c89. Converstion to per-pwrdm per/post transition calls was a bit premature. Only tracking MPU, PER & CORE in the idle path means we lose the accounting for all the other powerdomains which may also transition in idle. On OMAP3, due to autodeps, several powerdomains transition along with MPU (e.g. DSS, USBHOST), and the accounting for these was lost with this patch. Since the accounting includes the context loss counters, drivers for devices in those power domains would never notice context lost, so would likely hang after any off-mode transitions. This patch should be revisited when the upcoming clkdm/pwrmdm/voltdm use-counting seires is merged since then we can properly do accounting without relying on a call in the idle path. In addition, the original patch had another bug because the PER powerdomain accounting was not updated until after the GPIO resume hook is called. Since gpio_resume_after_idle() checks the context loss count (which is not yet updated) it would not properly restore context, leaving the GPIO banks in an undefined state. Cc: Jean Pihet Cc: Tero Kristo Cc: Rajendra Nayak Reported-by: Paul Walmsley Signed-off-by: Kevin Hilman --- arch/arm/mach-omap2/pm34xx.c | 21 +++++---------------- 1 file changed, 5 insertions(+), 16 deletions(-) diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c index e4fc88c65dbd..05bd8f02723f 100644 --- a/arch/arm/mach-omap2/pm34xx.c +++ b/arch/arm/mach-omap2/pm34xx.c @@ -272,21 +272,16 @@ void omap_sram_idle(void) per_next_state = pwrdm_read_next_pwrst(per_pwrdm); core_next_state = pwrdm_read_next_pwrst(core_pwrdm); - if (mpu_next_state < PWRDM_POWER_ON) { - pwrdm_pre_transition(mpu_pwrdm); - pwrdm_pre_transition(neon_pwrdm); - } + pwrdm_pre_transition(NULL); /* PER */ if (per_next_state < PWRDM_POWER_ON) { - pwrdm_pre_transition(per_pwrdm); per_going_off = (per_next_state == PWRDM_POWER_OFF) ? 1 : 0; omap2_gpio_prepare_for_idle(per_going_off); } /* CORE */ if (core_next_state < PWRDM_POWER_ON) { - pwrdm_pre_transition(core_pwrdm); if (core_next_state == PWRDM_POWER_OFF) { omap3_core_save_context(); omap3_cm_save_context(); @@ -339,20 +334,14 @@ void omap_sram_idle(void) omap2_prm_clear_mod_reg_bits(OMAP3430_AUTO_OFF_MASK, OMAP3430_GR_MOD, OMAP3_PRM_VOLTCTRL_OFFSET); - pwrdm_post_transition(core_pwrdm); } omap3_intc_resume_idle(); - /* PER */ - if (per_next_state < PWRDM_POWER_ON) { - omap2_gpio_resume_after_idle(); - pwrdm_post_transition(per_pwrdm); - } + pwrdm_post_transition(NULL); - if (mpu_next_state < PWRDM_POWER_ON) { - pwrdm_post_transition(mpu_pwrdm); - pwrdm_post_transition(neon_pwrdm); - } + /* PER */ + if (per_next_state < PWRDM_POWER_ON) + omap2_gpio_resume_after_idle(); } static void omap3_pm_idle(void) From e1267371eacf2cbcf580e41f9e64a986cdaf5c1d Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 7 Aug 2012 19:11:33 +0900 Subject: [PATCH 026/208] ARM: S3C24XX: Add missing DMACH_DT_PROP Commit 2b90807549 (spi: s3c64xx: add device tree support) requires the DMACH_DT_PROP element in the dma_ch enum. It's not used on non-DT platforms but has to be present nevertheless. So mimic the dummy-add of DMACH_DT_PROP on s3c64xx for s3c24xx machines, to correct the build breakage for the s3c24xx variants using the s3c64xx-spi-driver. Signed-off-by: Heiko Stuebner Cc: Stable Signed-off-by: Kukjin Kim --- arch/arm/mach-s3c24xx/include/mach/dma.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-s3c24xx/include/mach/dma.h b/arch/arm/mach-s3c24xx/include/mach/dma.h index 454831b66037..ee99fd56c043 100644 --- a/arch/arm/mach-s3c24xx/include/mach/dma.h +++ b/arch/arm/mach-s3c24xx/include/mach/dma.h @@ -24,7 +24,8 @@ */ enum dma_ch { - DMACH_XD0, + DMACH_DT_PROP = -1, /* not yet supported, do not use */ + DMACH_XD0 = 0, DMACH_XD1, DMACH_SDI, DMACH_SPI0, From b01858c7806e7e6f6121da2e51c9222fc4d21dc6 Mon Sep 17 00:00:00 2001 From: Heiko Stuebner Date: Tue, 7 Aug 2012 19:12:05 +0900 Subject: [PATCH 027/208] ARM: S3C24XX: Fix s3c2410_dma_enqueue parameters Commit d670ac019f60 (ARM: SAMSUNG: DMA Cleanup as per sparse) changed the prototype of the s3c2410_dma_* functions to use the enum dma_ch instead of an generic unsigned int. In the s3c24xx dma.c s3c2410_dma_enqueue seems to have been forgotten, the other functions there were changed correctly. Signed-off-by: Heiko Stuebner Cc: Stable Signed-off-by: Kukjin Kim --- arch/arm/plat-s3c24xx/dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c index 28f898f75380..db98e7021f0d 100644 --- a/arch/arm/plat-s3c24xx/dma.c +++ b/arch/arm/plat-s3c24xx/dma.c @@ -430,7 +430,7 @@ s3c2410_dma_canload(struct s3c2410_dma_chan *chan) * when necessary. */ -int s3c2410_dma_enqueue(unsigned int channel, void *id, +int s3c2410_dma_enqueue(enum dma_ch channel, void *id, dma_addr_t data, int size) { struct s3c2410_dma_chan *chan = s3c_dma_lookup_channel(channel); From c0401241c01705205ed6f2b88460df1133591f58 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Tue, 7 Aug 2012 19:17:14 +0900 Subject: [PATCH 028/208] ARM: Samsung: Make uart_save static in pm.c file Fixes the following sparse warning: arch/arm/plat-samsung/pm.c:77:21: warning: symbol 'uart_save' was not declared. Should it be static? Signed-off-by: Sachin Kamat Signed-off-by: Kukjin Kim --- arch/arm/plat-samsung/pm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/plat-samsung/pm.c b/arch/arm/plat-samsung/pm.c index 64ab65f0fdbc..15070284343e 100644 --- a/arch/arm/plat-samsung/pm.c +++ b/arch/arm/plat-samsung/pm.c @@ -74,7 +74,7 @@ unsigned char pm_uart_udivslot; #ifdef CONFIG_SAMSUNG_PM_DEBUG -struct pm_uart_save uart_save[CONFIG_SERIAL_SAMSUNG_UARTS]; +static struct pm_uart_save uart_save[CONFIG_SERIAL_SAMSUNG_UARTS]; static void s3c_pm_save_uart(unsigned int uart, struct pm_uart_save *save) { From 54f32a35f4d3a653a18a2c8c239f19ae060bd803 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 13 Jul 2012 15:12:03 -0500 Subject: [PATCH 029/208] ARM: OMAP2+: Fix dmtimer set source clock failure Calling the dmtimer function omap_dm_timer_set_source() fails if following a call to pm_runtime_put() to disable the timer. For example the following sequence would fail to set the parent clock ... omap_dm_timer_stop(gptimer); omap_dm_timer_set_source(gptimer, OMAP_TIMER_SRC_32_KHZ); The following error message would be seen ... omap_dm_timer_set_source: failed to set timer_32k_ck as parent The problem is that, by design, pm_runtime_put() simply decrements the usage count and returns before the timer has actually been disabled. Therefore, setting the parent clock failed because the timer was still active when the trying to set the parent clock. Setting a parent clock will fail if the clock you are setting the parent of has a non-zero usage count. To ensure that this does not fail use pm_runtime_put_sync() when disabling the timer. Note that this will not be seen on OMAP1 devices, because these devices do not use the clock framework for dmtimers. Signed-off-by: Jon Hunter Acked-by: Kevin Hilman Cc: stable@vger.kernel.org Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/dmtimer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c index 626ad8cad7a9..7b6689af0cce 100644 --- a/arch/arm/plat-omap/dmtimer.c +++ b/arch/arm/plat-omap/dmtimer.c @@ -258,7 +258,7 @@ EXPORT_SYMBOL_GPL(omap_dm_timer_enable); void omap_dm_timer_disable(struct omap_dm_timer *timer) { - pm_runtime_put(&timer->pdev->dev); + pm_runtime_put_sync(&timer->pdev->dev); } EXPORT_SYMBOL_GPL(omap_dm_timer_disable); From 70d291b215721ce60bde5761e3eaf6a15f7d7671 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Wed, 8 Aug 2012 13:12:19 +0900 Subject: [PATCH 030/208] ARM: SAMSUNG: Set HDMI platform data for Exynos4x12 SoCs Adds support for setting HDMI platform data for Exynos4X12 SoCs. Signed-off-by: Sachin Kamat Signed-off-by: Kukjin Kim --- arch/arm/plat-samsung/devs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 74e31ce35538..3f3c941d9081 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -748,7 +748,8 @@ void __init s5p_i2c_hdmiphy_set_platdata(struct s3c2410_platform_i2c *pd) if (!pd) { pd = &default_i2c_data; - if (soc_is_exynos4210()) + if (soc_is_exynos4210() || + soc_is_exynos4212() || soc_is_exynos4412()) pd->bus_num = 8; else if (soc_is_s5pv210()) pd->bus_num = 3; From ee21ae6809e22676cd014ce02ec3b3387b436aa5 Mon Sep 17 00:00:00 2001 From: Tushar Behera Date: Wed, 8 Aug 2012 13:12:19 +0900 Subject: [PATCH 031/208] ARM: SAMSUNG: Add API to set platform data for s5p-tv driver Commit 350f2f4dad64 ("[media] v4l: s5p-tv: hdmi: add support for platform data") makes the presence of platform data mandatory for s5p-tv driver. Adding an API to plat-samsung for this purpose. Signed-off-by: Tushar Behera Signed-off-by: Sachin Kamat Signed-off-by: Kukjin Kim --- arch/arm/plat-samsung/devs.c | 26 +++++++++++++++++++++++ arch/arm/plat-samsung/include/plat/hdmi.h | 16 ++++++++++++++ 2 files changed, 42 insertions(+) create mode 100644 arch/arm/plat-samsung/include/plat/hdmi.h diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 3f3c941d9081..fc49f3dabd76 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -32,6 +32,8 @@ #include #include +#include + #include #include #include @@ -760,6 +762,30 @@ void __init s5p_i2c_hdmiphy_set_platdata(struct s3c2410_platform_i2c *pd) npd = s3c_set_platdata(pd, sizeof(struct s3c2410_platform_i2c), &s5p_device_i2c_hdmiphy); } + +struct s5p_hdmi_platform_data s5p_hdmi_def_platdata; + +void __init s5p_hdmi_set_platdata(struct i2c_board_info *hdmiphy_info, + struct i2c_board_info *mhl_info, int mhl_bus) +{ + struct s5p_hdmi_platform_data *pd = &s5p_hdmi_def_platdata; + + if (soc_is_exynos4210() || + soc_is_exynos4212() || soc_is_exynos4412()) + pd->hdmiphy_bus = 8; + else if (soc_is_s5pv210()) + pd->hdmiphy_bus = 3; + else + pd->hdmiphy_bus = 0; + + pd->hdmiphy_info = hdmiphy_info; + pd->mhl_info = mhl_info; + pd->mhl_bus = mhl_bus; + + s3c_set_platdata(pd, sizeof(struct s5p_hdmi_platform_data), + &s5p_device_hdmi); +} + #endif /* CONFIG_S5P_DEV_I2C_HDMIPHY */ /* I2S */ diff --git a/arch/arm/plat-samsung/include/plat/hdmi.h b/arch/arm/plat-samsung/include/plat/hdmi.h new file mode 100644 index 000000000000..331d046ac2c5 --- /dev/null +++ b/arch/arm/plat-samsung/include/plat/hdmi.h @@ -0,0 +1,16 @@ +/* + * Copyright (C) 2012 Samsung Electronics Co.Ltd + * + * 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 the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#ifndef __PLAT_SAMSUNG_HDMI_H +#define __PLAT_SAMSUNG_HDMI_H __FILE__ + +extern void s5p_hdmi_set_platdata(struct i2c_board_info *hdmiphy_info, + struct i2c_board_info *mhl_info, int mhl_bus); + +#endif /* __PLAT_SAMSUNG_HDMI_H */ From cceb840904d1c1f7ee453bfa9886117c6931bdbf Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Wed, 8 Aug 2012 13:12:19 +0900 Subject: [PATCH 032/208] ARM: EXYNOS: Set HDMI platform data in SMDKV310 Sets HDMI platform data in SMDKV310 board. Signed-off-by: Sachin Kamat Signed-off-by: Kukjin Kim --- arch/arm/mach-exynos/mach-smdkv310.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm/mach-exynos/mach-smdkv310.c b/arch/arm/mach-exynos/mach-smdkv310.c index 3cfa688d274a..73f2bce097e1 100644 --- a/arch/arm/mach-exynos/mach-smdkv310.c +++ b/arch/arm/mach-exynos/mach-smdkv310.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -354,6 +355,11 @@ static struct platform_pwm_backlight_data smdkv310_bl_data = { .pwm_period_ns = 1000, }; +/* I2C module and id for HDMIPHY */ +static struct i2c_board_info hdmiphy_info = { + I2C_BOARD_INFO("hdmiphy-exynos4210", 0x38), +}; + static void s5p_tv_setup(void) { /* direct HPD to HDMI chip */ @@ -388,6 +394,7 @@ static void __init smdkv310_machine_init(void) s5p_tv_setup(); s5p_i2c_hdmiphy_set_platdata(NULL); + s5p_hdmi_set_platdata(&hdmiphy_info, NULL, 0); samsung_keypad_set_platdata(&smdkv310_keypad_data); From ccc61fd460fc1b20480dbb7e10b2ea82433bfd58 Mon Sep 17 00:00:00 2001 From: Tushar Behera Date: Wed, 8 Aug 2012 13:12:19 +0900 Subject: [PATCH 033/208] ARM: EXYNOS: Set HDMI platform data in Origen board Signed-off-by: Tushar Behera Signed-off-by: Sachin Kamat Signed-off-by: Kukjin Kim --- arch/arm/mach-exynos/mach-origen.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/arm/mach-exynos/mach-origen.c b/arch/arm/mach-exynos/mach-origen.c index 5ca80307d6d7..4e574c24581c 100644 --- a/arch/arm/mach-exynos/mach-origen.c +++ b/arch/arm/mach-exynos/mach-origen.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -734,6 +735,11 @@ static void __init origen_bt_setup(void) s3c_gpio_setpull(EXYNOS4_GPX2(2), S3C_GPIO_PULL_NONE); } +/* I2C module and id for HDMIPHY */ +static struct i2c_board_info hdmiphy_info = { + I2C_BOARD_INFO("hdmiphy-exynos4210", 0x38), +}; + static void s5p_tv_setup(void) { /* Direct HPD to HDMI chip */ @@ -781,6 +787,7 @@ static void __init origen_machine_init(void) s5p_tv_setup(); s5p_i2c_hdmiphy_set_platdata(NULL); + s5p_hdmi_set_platdata(&hdmiphy_info, NULL, 0); #ifdef CONFIG_DRM_EXYNOS s5p_device_fimd0.dev.platform_data = &drm_fimd_pdata; From 6c691b5df1fcd93f2e9f65e1a8a3dd0e6fd158ea Mon Sep 17 00:00:00 2001 From: Jan Luebbe Date: Tue, 7 Aug 2012 18:29:45 +0200 Subject: [PATCH 034/208] omap: Fix multi.h when only ARCH_OMAP3 and SOC_AM33XX are selected When only ARCH_OMAP3 (or -2,-4,...) and SOC_AM33XX are selected, multi.h doesn't set MULTI_OMAP2. In this case, cpu.h will simply define cpu_is_omap24xx() as 1. This causes problems for example for omap_hwmod.c:omap_hwmod_init which checks for cpu_is_omap24xx() first, using the wrong soc_ops for AM33xx. Fix this by defining MULTI_OMAP2 when using SOC_AM33XX together with something else. Signed-off-by: Jan Luebbe Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/include/plat/multi.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/arm/plat-omap/include/plat/multi.h b/arch/arm/plat-omap/include/plat/multi.h index 045e320f1067..324d31b14852 100644 --- a/arch/arm/plat-omap/include/plat/multi.h +++ b/arch/arm/plat-omap/include/plat/multi.h @@ -108,4 +108,13 @@ # endif #endif +#ifdef CONFIG_SOC_AM33XX +# ifdef OMAP_NAME +# undef MULTI_OMAP2 +# define MULTI_OMAP2 +# else +# define OMAP_NAME am33xx +# endif +#endif + #endif /* __PLAT_OMAP_MULTI_H */ From 90f7f9acecc6dde87cf25db1ad7599926d6773f7 Mon Sep 17 00:00:00 2001 From: Vaibhav Hiremath Date: Tue, 7 Aug 2012 19:44:01 +0530 Subject: [PATCH 035/208] ARM: OMAP2+: cpu: Add am33xx device under cpu_class_is_omap2 AM33XX device falls under omap2 class, so make cpu_class_is_omap2() macro true by adding soc_is_am33xx() to existing list of cpu/soc check. This is required to unblock the basic boot support on AM335x platform. Having done that, we still need to sort out properly from common zImage point of view without having to maintain this cpu/soc_is_xxx list. Signed-off-by: Vaibhav Hiremath Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/include/plat/cpu.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/plat-omap/include/plat/cpu.h b/arch/arm/plat-omap/include/plat/cpu.h index 68b180edcfff..bb5d08a70dbc 100644 --- a/arch/arm/plat-omap/include/plat/cpu.h +++ b/arch/arm/plat-omap/include/plat/cpu.h @@ -372,7 +372,8 @@ IS_OMAP_TYPE(3430, 0x3430) #define cpu_class_is_omap1() (cpu_is_omap7xx() || cpu_is_omap15xx() || \ cpu_is_omap16xx()) #define cpu_class_is_omap2() (cpu_is_omap24xx() || cpu_is_omap34xx() || \ - cpu_is_omap44xx() || soc_is_omap54xx()) + cpu_is_omap44xx() || soc_is_omap54xx() || \ + soc_is_am33xx()) /* Various silicon revisions for omap2 */ #define OMAP242X_CLASS 0x24200024 From 389d7b26d9e4f78b17366c23a3aa16b3c5cb3bde Mon Sep 17 00:00:00 2001 From: Alexey Khoroshilov Date: Thu, 9 Aug 2012 15:19:25 +0200 Subject: [PATCH 036/208] bio: Fix potential memory leak in bio_find_or_create_slab() Do not leak memory by updating pointer with potentially NULL realloc return value. Found by Linux Driver Verification project (linuxtesting.org). Signed-off-by: Alexey Khoroshilov Acked-by: Jeff Moyer Signed-off-by: Jens Axboe --- fs/bio.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/fs/bio.c b/fs/bio.c index 73922abba832..fed1f799cb56 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -73,7 +73,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) { unsigned int sz = sizeof(struct bio) + extra_size; struct kmem_cache *slab = NULL; - struct bio_slab *bslab; + struct bio_slab *bslab, *new_bio_slabs; unsigned int i, entry = -1; mutex_lock(&bio_slab_lock); @@ -97,11 +97,12 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) if (bio_slab_nr == bio_slab_max && entry == -1) { bio_slab_max <<= 1; - bio_slabs = krealloc(bio_slabs, - bio_slab_max * sizeof(struct bio_slab), - GFP_KERNEL); - if (!bio_slabs) + new_bio_slabs = krealloc(bio_slabs, + bio_slab_max * sizeof(struct bio_slab), + GFP_KERNEL); + if (!new_bio_slabs) goto out_unlock; + bio_slabs = new_bio_slabs; } if (entry == -1) entry = bio_slab_nr++; From 276f0f5d157bb4a816053f4f3a941dbcd4f76556 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 9 Aug 2012 15:20:23 +0200 Subject: [PATCH 037/208] block: disable discard request merge temporarily The SCSI discard request merge never worked, and looks no solution for in future, let's disable it temporarily. Signed-off-by: Shaohua Li Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dc632975d54f..4a2ab7c85393 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -601,7 +601,7 @@ static inline void blk_clear_rl_full(struct request_list *rl, bool sync) * it already be started by driver. */ #define RQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) + (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA | REQ_DISCARD) #define rq_mergeable(rq) \ (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ (((rq)->cmd_flags & REQ_DISCARD) || \ From 8430f9772f9ac305211f177b0fa56a312175da11 Mon Sep 17 00:00:00 2001 From: Fengguang Wu Date: Thu, 9 Aug 2012 15:23:07 +0200 Subject: [PATCH 038/208] block: remove plugging at buffered write time Buffered write(2) is not directly tied to IO, so it's not suitable to handle plug in generic_file_aio_write(). Note that plugging for O_SYNC writes is also removed. The user may pass arbitrary @size arguments, which may be much larger than the preferable I/O size, or may cross extent/device boundaries. Let the lower layers handle the plugging. The plugging code here actually turns them into no-ops. CC: Li Shaohua Signed-off-by: Wu Fengguang Signed-off-by: Jens Axboe --- mm/filemap.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/mm/filemap.c b/mm/filemap.c index fa5ca304148e..2b0952974cb9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2527,14 +2527,12 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - struct blk_plug plug; ssize_t ret; BUG_ON(iocb->ki_pos != pos); sb_start_write(inode->i_sb); mutex_lock(&inode->i_mutex); - blk_start_plug(&plug); ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); mutex_unlock(&inode->i_mutex); @@ -2545,7 +2543,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err < 0 && ret > 0) ret = err; } - blk_finish_plug(&plug); sb_end_write(inode->i_sb); return ret; } From 647d1e4c5235763b83fbfe74a09d148edc6ca152 Mon Sep 17 00:00:00 2001 From: Fengguang Wu Date: Thu, 9 Aug 2012 15:23:09 +0200 Subject: [PATCH 039/208] block: move down direct IO plugging Move unplugging for direct I/O from around ->direct_IO() down to do_blockdev_direct_IO(). This implicitly adds plugging for direct writes. CC: Li Shaohua Acked-by: Jeff Moyer Signed-off-by: Wu Fengguang Signed-off-by: Jens Axboe --- fs/direct-io.c | 5 +++++ mm/filemap.c | 4 ---- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index 1faf4cb56f39..f86c720dba0e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1062,6 +1062,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, unsigned long user_addr; size_t bytes; struct buffer_head map_bh = { 0, }; + struct blk_plug plug; if (rw & WRITE) rw = WRITE_ODIRECT; @@ -1177,6 +1178,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, PAGE_SIZE - user_addr / PAGE_SIZE); } + blk_start_plug(&plug); + for (seg = 0; seg < nr_segs; seg++) { user_addr = (unsigned long)iov[seg].iov_base; sdio.size += bytes = iov[seg].iov_len; @@ -1235,6 +1238,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, if (sdio.bio) dio_bio_submit(dio, &sdio); + blk_finish_plug(&plug); + /* * It is possible that, we return short IO due to end of file. * In that case, we need to release all the pages we got hold on. diff --git a/mm/filemap.c b/mm/filemap.c index 2b0952974cb9..384344575c37 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1412,12 +1412,8 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); if (!retval) { - struct blk_plug plug; - - blk_start_plug(&plug); retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); - blk_finish_plug(&plug); } if (retval > 0) { *ppos = pos + retval; From 865826644e23c329297459b62ef9cc9904abf61a Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 9 Aug 2012 15:27:28 +0200 Subject: [PATCH 040/208] Documentation: update missing index files in block/00-INDEX Update missing index files in block/00-INDEX. Signed-off-by: Namjae Jeon Signed-off-by: Jens Axboe --- Documentation/block/00-INDEX | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX index d111e3b23db0..d18ecd827c40 100644 --- a/Documentation/block/00-INDEX +++ b/Documentation/block/00-INDEX @@ -3,15 +3,21 @@ biodoc.txt - Notes on the Generic Block Layer Rewrite in Linux 2.5 capability.txt - - Generic Block Device Capability (/sys/block//capability) + - Generic Block Device Capability (/sys/block//capability) +cfq-iosched.txt + - CFQ IO scheduler tunables +data-integrity.txt + - Block data integrity deadline-iosched.txt - Deadline IO scheduler tunables ioprio.txt - Block io priorities (in CFQ scheduler) +queue-sysfs.txt + - Queue's sysfs entries request.txt - The members of struct request (in include/linux/blkdev.h) stat.txt - - Block layer statistics in /sys/block//stat + - Block layer statistics in /sys/block//stat switching-sched.txt - Switching I/O schedulers at runtime writeback_cache_control.txt From 2792d8719393a518a847769d36a080ade4273e6b Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 9 Aug 2012 15:27:29 +0200 Subject: [PATCH 041/208] Documentation: update tunable options in block/cfq-iosched.txt Update tunable options in block/cfq-iosched.txt. Signed-off-by: Namjae Jeon Signed-off-by: Jens Axboe --- Documentation/block/cfq-iosched.txt | 77 +++++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt index 6d670f570451..d89b4fe724d7 100644 --- a/Documentation/block/cfq-iosched.txt +++ b/Documentation/block/cfq-iosched.txt @@ -1,3 +1,14 @@ +CFQ (Complete Fairness Queueing) +=============================== + +The main aim of CFQ scheduler is to provide a fair allocation of the disk +I/O bandwidth for all the processes which requests an I/O operation. + +CFQ maintains the per process queue for the processes which request I/O +operation(syncronous requests). In case of asynchronous requests, all the +requests from all the processes are batched together according to their +process's I/O priority. + CFQ ioscheduler tunables ======================== @@ -25,6 +36,72 @@ there are multiple spindles behind single LUN (Host based hardware RAID controller or for storage arrays), setting slice_idle=0 might end up in better throughput and acceptable latencies. +back_seek_max +------------- +This specifies, given in Kbytes, the maximum "distance" for backward seeking. +The distance is the amount of space from the current head location to the +sectors that are backward in terms of distance. + +This parameter allows the scheduler to anticipate requests in the "backward" +direction and consider them as being the "next" if they are within this +distance from the current head location. + +back_seek_penalty +----------------- +This parameter is used to compute the cost of backward seeking. If the +backward distance of request is just 1/back_seek_penalty from a "front" +request, then the seeking cost of two requests is considered equivalent. + +So scheduler will not bias toward one or the other request (otherwise scheduler +will bias toward front request). Default value of back_seek_penalty is 2. + +fifo_expire_async +----------------- +This parameter is used to set the timeout of asynchronous requests. Default +value of this is 248ms. + +fifo_expire_sync +---------------- +This parameter is used to set the timeout of synchronous requests. Default +value of this is 124ms. In case to favor synchronous requests over asynchronous +one, this value should be decreased relative to fifo_expire_async. + +slice_async +----------- +This parameter is same as of slice_sync but for asynchronous queue. The +default value is 40ms. + +slice_async_rq +-------------- +This parameter is used to limit the dispatching of asynchronous request to +device request queue in queue's slice time. The maximum number of request that +are allowed to be dispatched also depends upon the io priority. Default value +for this is 2. + +slice_sync +---------- +When a queue is selected for execution, the queues IO requests are only +executed for a certain amount of time(time_slice) before switching to another +queue. This parameter is used to calculate the time slice of synchronous +queue. + +time_slice is computed using the below equation:- +time_slice = slice_sync + (slice_sync/5 * (4 - prio)). To increase the +time_slice of synchronous queue, increase the value of slice_sync. Default +value is 100ms. + +quantum +------- +This specifies the number of request dispatched to the device queue. In a +queue's time slice, a request will not be dispatched if the number of request +in the device exceeds this parameter. This parameter is used for synchronous +request. + +In case of storage with several disk, this setting can limit the parallel +processing of request. Therefore, increasing the value can imporve the +performace although this can cause the latency of some I/O to increase due +to more number of requests. + CFQ IOPS Mode for group scheduling =================================== Basic CFQ design is to provide priority based time slices. Higher priority From 4004e90cfa4488cf99798b1138183158b64f4a42 Mon Sep 17 00:00:00 2001 From: Namjae Jeon Date: Thu, 9 Aug 2012 15:28:05 +0200 Subject: [PATCH 042/208] Documentation: update tunable options in block/cfq-iosched.txt Update tunable options in block/cfq-iosched.txt. Signed-off-by: Namjae Jeon Signed-off-by: Jens Axboe --- Documentation/block/queue-sysfs.txt | 64 +++++++++++++++++++++++++++++ 1 file changed, 64 insertions(+) diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index 6518a55273e7..e54ac1d53403 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -9,20 +9,71 @@ These files are the ones found in the /sys/block/xxx/queue/ directory. Files denoted with a RO postfix are readonly and the RW postfix means read-write. +add_random (RW) +---------------- +This file allows to trun off the disk entropy contribution. Default +value of this file is '1'(on). + +discard_granularity (RO) +----------------------- +This shows the size of internal allocation of the device in bytes, if +reported by the device. A value of '0' means device does not support +the discard functionality. + +discard_max_bytes (RO) +---------------------- +Devices that support discard functionality may have internal limits on +the number of bytes that can be trimmed or unmapped in a single operation. +The discard_max_bytes parameter is set by the device driver to the maximum +number of bytes that can be discarded in a single operation. Discard +requests issued to the device must not exceed this limit. A discard_max_bytes +value of 0 means that the device does not support discard functionality. + +discard_zeroes_data (RO) +------------------------ +When read, this file will show if the discarded block are zeroed by the +device or not. If its value is '1' the blocks are zeroed otherwise not. + hw_sector_size (RO) ------------------- This is the hardware sector size of the device, in bytes. +iostats (RW) +------------- +This file is used to control (on/off) the iostats accounting of the +disk. + +logical_block_size (RO) +----------------------- +This is the logcal block size of the device, in bytes. + max_hw_sectors_kb (RO) ---------------------- This is the maximum number of kilobytes supported in a single data transfer. +max_integrity_segments (RO) +--------------------------- +When read, this file shows the max limit of integrity segments as +set by block layer which a hardware controller can handle. + max_sectors_kb (RW) ------------------- This is the maximum number of kilobytes that the block layer will allow for a filesystem request. Must be smaller than or equal to the maximum size allowed by the hardware. +max_segments (RO) +----------------- +Maximum number of segments of the device. + +max_segment_size (RO) +--------------------- +Maximum segment size of the device. + +minimum_io_size (RO) +-------------------- +This is the smallest preferred io size reported by the device. + nomerges (RW) ------------- This enables the user to disable the lookup logic involved with IO @@ -45,11 +96,24 @@ per-block-cgroup request pool. IOW, if there are N block cgroups, each request queue may have upto N request pools, each independently regulated by nr_requests. +optimal_io_size (RO) +-------------------- +This is the optimal io size reported by the device. + +physical_block_size (RO) +------------------------ +This is the physical block size of device, in bytes. + read_ahead_kb (RW) ------------------ Maximum number of kilobytes to read-ahead for filesystems on this block device. +rotational (RW) +--------------- +This file is used to stat if the device is of rotational type or +non-rotational type. + rq_affinity (RW) ---------------- If this option is '1', the block layer will migrate request completions to the From 5b6e3eb576e8ad03264d46982afed77bdc6323a3 Mon Sep 17 00:00:00 2001 From: Santosh Shilimkar Date: Thu, 9 Aug 2012 12:35:48 +0530 Subject: [PATCH 043/208] ARM: OMAP4: sleep: Save the complete used register stack frame OMAP4 sleep entry code even though itself don't use many CPU registers makes call to the v7_flush_dcache_all() which uses them. Since v7_flush_dcache_all() doesn't make use of stack, the caller must take care of the stack frame. Otherwise it will lead to corrupted stack frame. Fix it by saving used registers. Reported-by: Grygorii Strashko Signed-off-by: Santosh Shilimkar Cc: Kevin Hilman Signed-off-by: Kevin Hilman --- arch/arm/mach-omap2/sleep44xx.S | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-omap2/sleep44xx.S b/arch/arm/mach-omap2/sleep44xx.S index 9f6b83d1b193..91e71d8f46f0 100644 --- a/arch/arm/mach-omap2/sleep44xx.S +++ b/arch/arm/mach-omap2/sleep44xx.S @@ -56,9 +56,13 @@ ppa_por_params: * The restore function pointer is stored at CPUx_WAKEUP_NS_PA_ADDR_OFFSET. * It returns to the caller for CPU INACTIVE and ON power states or in case * CPU failed to transition to targeted OFF/DORMANT state. + * + * omap4_finish_suspend() calls v7_flush_dcache_all() which doesn't save + * stack frame and it expects the caller to take care of it. Hence the entire + * stack frame is saved to avoid possible stack corruption. */ ENTRY(omap4_finish_suspend) - stmfd sp!, {lr} + stmfd sp!, {r4-r12, lr} cmp r0, #0x0 beq do_WFI @ No lowpower state, jump to WFI @@ -226,7 +230,7 @@ scu_gp_clear: skip_scu_gp_clear: isb dsb - ldmfd sp!, {pc} + ldmfd sp!, {r4-r12, pc} ENDPROC(omap4_finish_suspend) /* From 1b8652142334a8c0729c5c4536a22cfc6fc49297 Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Thu, 9 Aug 2012 12:38:21 +0530 Subject: [PATCH 044/208] cpufreq: OMAP: Handle missing frequency table on SMP systems On OMAP4, if the first CPU fails to get a valid frequency table (this could happen if the platform does not register any OPP table), the subsequent CPU instances end up dealing with a NULL freq_table and crash. Check for an already existing freq_table, before trying to create one, and increment the freq_table_users only if the table is sucessfully created. Signed-off-by: Rajendra Nayak Signed-off-by: Santosh Shilimkar Cc: Signed-off-by: Kevin Hilman --- drivers/cpufreq/omap-cpufreq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c index 17fa04d08be9..b47034e650a5 100644 --- a/drivers/cpufreq/omap-cpufreq.c +++ b/drivers/cpufreq/omap-cpufreq.c @@ -218,7 +218,7 @@ static int __cpuinit omap_cpu_init(struct cpufreq_policy *policy) policy->cur = policy->min = policy->max = omap_getspeed(policy->cpu); - if (atomic_inc_return(&freq_table_users) == 1) + if (!freq_table) result = opp_init_cpufreq_table(mpu_dev, &freq_table); if (result) { @@ -227,6 +227,8 @@ static int __cpuinit omap_cpu_init(struct cpufreq_policy *policy) goto fail_ck; } + atomic_inc_return(&freq_table_users); + result = cpufreq_frequency_table_cpuinfo(policy, freq_table); if (result) goto fail_table; From 196449de0c886e64b48d01bd7ee153656db92884 Mon Sep 17 00:00:00 2001 From: Rajendra Nayak Date: Thu, 9 Aug 2012 12:38:22 +0530 Subject: [PATCH 045/208] ARM: OMAP4: Register the OPP table only for 4430 device The 4430 OPP table was being registered for all other OMAP4 variants too, like 4460 and 4470 causing issues with cpufreq driver enabled. 4460 and 4470 devices have different OPPs as compared to 4430, and they should be populated seperately. As long as that happens, let the OPP table registeration happen only on 4430 device. Signed-off-by: Rajendra Nayak Acked-by: Santosh Shilimkar Signed-off-by: Kevin Hilman --- arch/arm/mach-omap2/opp4xxx_data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/opp4xxx_data.c b/arch/arm/mach-omap2/opp4xxx_data.c index 2293ba27101b..c95415da23c2 100644 --- a/arch/arm/mach-omap2/opp4xxx_data.c +++ b/arch/arm/mach-omap2/opp4xxx_data.c @@ -94,7 +94,7 @@ int __init omap4_opp_init(void) { int r = -ENODEV; - if (!cpu_is_omap44xx()) + if (!cpu_is_omap443x()) return r; r = omap_init_opp_table(omap44xx_opp_def_list, From 8e90e4cc33ac44fd58635dc1aa94d3fd2145e518 Mon Sep 17 00:00:00 2001 From: Zhao Chenhui Date: Tue, 7 Aug 2012 17:12:47 +0800 Subject: [PATCH 046/208] powerpc/85xx: mpc85xx_defconfig - add VIA PATA support for MPC85xxCDS Signed-off-by: Zhao Chenhui Signed-off-by: Kumar Gala --- arch/powerpc/configs/mpc85xx_defconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index 03ee911c4577..99a4dd3b30cc 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -115,6 +115,7 @@ CONFIG_ATA=y CONFIG_SATA_AHCI=y CONFIG_SATA_FSL=y CONFIG_PATA_ALI=y +CONFIG_PATA_VIA=y CONFIG_NETDEVICES=y CONFIG_DUMMY=y CONFIG_FS_ENET=y From 09a3017a585eb8567a7de15b426bb1dfb548bf0f Mon Sep 17 00:00:00 2001 From: Shengzhou Liu Date: Fri, 10 Aug 2012 18:48:31 +0800 Subject: [PATCH 047/208] powerpc/p4080ds: dts - add usb controller version info and port0 Add the missing usb controller version info and port0, which is required during setup usb phy. Signed-off-by: Shengzhou Liu Signed-off-by: Kumar Gala --- arch/powerpc/boot/dts/fsl/p4080si-post.dtsi | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi index 8d35d2c1f694..4f9c9f682ecf 100644 --- a/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi +++ b/arch/powerpc/boot/dts/fsl/p4080si-post.dtsi @@ -345,6 +345,13 @@ /include/ "qoriq-duart-1.dtsi" /include/ "qoriq-gpio-0.dtsi" /include/ "qoriq-usb2-mph-0.dtsi" + usb@210000 { + compatible = "fsl-usb2-mph-v1.6", "fsl,mpc85xx-usb2-mph", "fsl-usb2-mph"; + port0; + }; /include/ "qoriq-usb2-dr-0.dtsi" + usb@211000 { + compatible = "fsl-usb2-dr-v1.6", "fsl,mpc85xx-usb2-dr", "fsl-usb2-dr"; + }; /include/ "qoriq-sec4.0-0.dtsi" }; From c0db19dabf138741e078f6391fb132821c0d98b5 Mon Sep 17 00:00:00 2001 From: Yuanhan Liu Date: Wed, 8 Aug 2012 17:02:08 +0800 Subject: [PATCH 048/208] ARM: mmp: fix potential NULL dereference Fix the wrong logic: we should use || instead of && Cc: Leo Yan Cc: Eric Miao Signed-off-by: Yuanhan Liu Signed-off-by: Haojian Zhuang --- arch/arm/mach-mmp/sram.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-mmp/sram.c b/arch/arm/mach-mmp/sram.c index 4304f9519372..7e8a5a2e1ec7 100644 --- a/arch/arm/mach-mmp/sram.c +++ b/arch/arm/mach-mmp/sram.c @@ -68,7 +68,7 @@ static int __devinit sram_probe(struct platform_device *pdev) struct resource *res; int ret = 0; - if (!pdata && !pdata->pool_name) + if (!pdata || !pdata->pool_name) return -ENODEV; info = kzalloc(sizeof(*info), GFP_KERNEL); From c5491d1ae1946d394389b83b31b87708e86dc4cf Mon Sep 17 00:00:00 2001 From: Timo Kokkonen Date: Sun, 12 Aug 2012 13:45:34 +0300 Subject: [PATCH 049/208] ARM: OMAP: dmtimers: Fix locking issue in omap_dm_timer_request*() Calling omap_dm_timer_prepare while the spinlock is held is not allowed as sleeping functions are called later on during the preparation (namely within clk_get()). dm_timer_lock is only required for protecting the omap_timer_list. After the timer is marked as reserved, the lock is no longer needed and should be freed. Signed-off-by: Timo Kokkonen Cc: Tarun Kanti DebBarma Signed-off-by: Tony Lindgren --- arch/arm/plat-omap/dmtimer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c index 7b6689af0cce..938b50a33439 100644 --- a/arch/arm/plat-omap/dmtimer.c +++ b/arch/arm/plat-omap/dmtimer.c @@ -189,6 +189,7 @@ struct omap_dm_timer *omap_dm_timer_request(void) timer->reserved = 1; break; } + spin_unlock_irqrestore(&dm_timer_lock, flags); if (timer) { ret = omap_dm_timer_prepare(timer); @@ -197,7 +198,6 @@ struct omap_dm_timer *omap_dm_timer_request(void) timer = NULL; } } - spin_unlock_irqrestore(&dm_timer_lock, flags); if (!timer) pr_debug("%s: timer request failed!\n", __func__); @@ -220,6 +220,7 @@ struct omap_dm_timer *omap_dm_timer_request_specific(int id) break; } } + spin_unlock_irqrestore(&dm_timer_lock, flags); if (timer) { ret = omap_dm_timer_prepare(timer); @@ -228,7 +229,6 @@ struct omap_dm_timer *omap_dm_timer_request_specific(int id) timer = NULL; } } - spin_unlock_irqrestore(&dm_timer_lock, flags); if (!timer) pr_debug("%s: timer%d request failed!\n", __func__, id); From e18287d301bf56dd820137026d51ab38cf6c2e83 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sun, 5 Aug 2012 15:04:42 +0000 Subject: [PATCH 050/208] ARM: mv78xx0: fix win_cfg_base prototype Patch b6d1c33a31 "ARM: Orion: Consolidate the address map setup" tried to merge the address map for the four orion platforms, but apparently got it wrong for mv78xx0. Admittedly I don't understand what this code actually does, but it's clear that the current version is wrong. Without this patch, building mv78xx0_defconfig results in: arch/arm/mach-mv78xx0/addr-map.c:59:2: warning: initialization from incompatible pointer type [enabled by default] arch/arm/mach-mv78xx0/addr-map.c:59:2: warning: (near initialization for 'addr_map_cfg.win_cfg_base') [enabled by default] Signed-off-by: Arnd Bergmann Acked-by: Andrew Lunn Cc: Michael Walle Cc: Nicolas Pitre --- arch/arm/mach-mv78xx0/addr-map.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/mach-mv78xx0/addr-map.c b/arch/arm/mach-mv78xx0/addr-map.c index 62b53d710efd..a9bc84180d21 100644 --- a/arch/arm/mach-mv78xx0/addr-map.c +++ b/arch/arm/mach-mv78xx0/addr-map.c @@ -37,7 +37,7 @@ #define WIN0_OFF(n) (BRIDGE_VIRT_BASE + 0x0000 + ((n) << 4)) #define WIN8_OFF(n) (BRIDGE_VIRT_BASE + 0x0900 + (((n) - 8) << 4)) -static void __init __iomem *win_cfg_base(int win) +static void __init __iomem *win_cfg_base(const struct orion_addr_map_cfg *cfg, int win) { /* * Find the control register base address for this window. From bb2b6d19ec8b593b66402e2895c4314955b19833 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Mon, 23 Jul 2012 16:39:29 +0000 Subject: [PATCH 051/208] udf: fix udf_setsize() for file data in ICB If the new size is larger than the old size and the old file data was stored in the ICB (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) and the new size still fits in the ICB, skip the call to udf_extend_file() as it does not handle this i_alloc_type value (it calls BUG()). Signed-off-by: Ian Abbott Signed-off-by: Jan Kara --- fs/udf/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/udf/inode.c b/fs/udf/inode.c index fafaad795cd6..aa233469b3c1 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1124,14 +1124,17 @@ int udf_setsize(struct inode *inode, loff_t newsize) if (err) return err; down_write(&iinfo->i_data_sem); - } else + } else { iinfo->i_lenAlloc = newsize; + goto set_size; + } } err = udf_extend_file(inode, newsize); if (err) { up_write(&iinfo->i_data_sem); return err; } +set_size: truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); } else { From dc141a402b9dc03a4188cd978a4cf149c397172c Mon Sep 17 00:00:00 2001 From: Ashish Sangwan Date: Sat, 21 Jul 2012 16:35:17 +0530 Subject: [PATCH 052/208] UDF: During mount free lvid_bh before rescanning with different blocksize If s_lvid_bh is not freed and set to NULL before re-scanning partition with default block size, we might end up using wrong lvid in case s_lvid_bh is not updated in udf_load_logicalvolint during rescan. Signed-off-by: Ashish Sangwan Signed-off-by: Namjae Jeon Signed-off-by: Jan Kara --- fs/udf/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/udf/super.c b/fs/udf/super.c index dcbf98722afc..9f55f7981b7d 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -2000,6 +2000,8 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (!silent) pr_notice("Rescanning with blocksize %d\n", UDF_DEFAULT_BLOCKSIZE); + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = NULL; uopt.blocksize = UDF_DEFAULT_BLOCKSIZE; ret = udf_load_vrs(sb, &uopt, silent, &fileset); } From 6ea2eea1fa930b9308a06f77fce65c38931eeb13 Mon Sep 17 00:00:00 2001 From: Jeff Liu Date: Wed, 18 Jul 2012 12:12:41 +0800 Subject: [PATCH 053/208] quota: Move down dqptr_sem read after initializing default warn[] type at __dquot_alloc_space(). sb->s_dqopt->dqptr_sem is used to serialize ops using pointers from inode to dquots. But for __dquot_alloc_space(), it could be safely moved down after the default warn[] array got initialized. Signed-off-by: Jie Liu Signed-off-by: Jan Kara --- fs/quota/dquot.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 36a29b753c79..c495a3055e2a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1589,10 +1589,10 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) goto out; } - down_read(&sb_dqopt(inode->i_sb)->dqptr_sem); for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; + down_read(&sb_dqopt(inode->i_sb)->dqptr_sem); spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!dquots[cnt]) From 48d1788493f874e5d32dccb2911a7bc91c248b4b Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 2 Aug 2012 21:36:04 -0400 Subject: [PATCH 054/208] reiserfs: fix deadlocks with quotas The BKL push-down for reiserfs made lock recursion a special case that needs to be handled explicitly. One of the cases that was unhandled is dropping the quota during inode eviction. Both reiserfs_evict_inode and reiserfs_write_dquot take the write lock, but when the journal lock is taken it only drops one the references. The locking rules are that the journal lock be acquired before the write lock so leaving the reference open leads to a ABBA deadlock. This patch pushes the unlock up before clear_inode and avoids the recursive locking. Another ABBA situation can occur when the write lock is dropped while reading the bitmap buffer while in the quota code. When the lock is reacquired, it will deadlock against dquot->dq_lock and dqopt->dqio_mutex in the dquot_acquire path. It's safe to retain the lock across the read and should be cached under write load. Signed-off-by: Jeff Mahoney Signed-off-by: Jan Kara --- fs/reiserfs/bitmap.c | 2 -- fs/reiserfs/inode.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index 4c0c7d163d15..a98b7740a0fc 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -1334,9 +1334,7 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, else if (bitmap == 0) block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1; - reiserfs_write_unlock(sb); bh = sb_bread(sb, block); - reiserfs_write_lock(sb); if (bh == NULL) reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) " "reading failed", __func__, block); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index a6d4268fb6c1..855da58db145 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -76,10 +76,10 @@ void reiserfs_evict_inode(struct inode *inode) ; } out: + reiserfs_write_unlock_once(inode->i_sb, depth); clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */ dquot_drop(inode); inode->i_blocks = 0; - reiserfs_write_unlock_once(inode->i_sb, depth); return; no_delete: From 2e84f2641ea91a730642ead558a4ee3bd52310c9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Wed, 15 Aug 2012 13:50:27 +0200 Subject: [PATCH 055/208] jbd: don't write superblock when unmounting an ro filesystem This sequence: results in an IO error when unmounting the RO filesystem. The bug was introduced by: commit 9754e39c7bc51328f145e933bfb0df47cd67b6e9 Author: Jan Kara Date: Sat Apr 7 12:33:03 2012 +0200 jbd: Split updating of journal superblock and marking journal empty which lost some of the magic in journal_update_superblock() which used to test for a journal with no outstanding transactions. This is a port of a jbd2 fix by Eric Sandeen. CC: # 3.4.x Signed-off-by: Jan Kara --- fs/jbd/journal.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 09357508ec9a..a2862339323b 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -1113,6 +1113,11 @@ static void mark_journal_empty(journal_t *journal) BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); spin_lock(&journal->j_state_lock); + /* Is it already empty? */ + if (sb->s_start == 0) { + spin_unlock(&journal->j_state_lock); + return; + } jbd_debug(1, "JBD: Marking journal as empty (seq %d)\n", journal->j_tail_sequence); From 68766a2edcd5cd744262a70a2f67a320ac944760 Mon Sep 17 00:00:00 2001 From: Nikola Pajkovsky Date: Wed, 15 Aug 2012 00:38:08 +0200 Subject: [PATCH 056/208] udf: fix retun value on error path in udf_load_logicalvol In case we detect a problem and bail out, we fail to set "ret" to a nonzero value, and udf_load_logicalvol will mistakenly report success. Signed-off-by: Nikola Pajkovsky Signed-off-by: Jan Kara --- fs/udf/super.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/udf/super.c b/fs/udf/super.c index 9f55f7981b7d..18fc038a438d 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1344,6 +1344,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, udf_err(sb, "error loading logical volume descriptor: " "Partition table too long (%u > %lu)\n", table_len, sb->s_blocksize - sizeof(*lvd)); + ret = 1; goto out_bh; } @@ -1388,8 +1389,10 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { if (udf_load_sparable_map(sb, map, - (struct sparablePartitionMap *)gpm) < 0) + (struct sparablePartitionMap *)gpm) < 0) { + ret = 1; goto out_bh; + } } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { From 4e8b14526ca7fb046a81c94002c1c43b6fdf0e9b Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 8 Aug 2012 15:36:20 -0400 Subject: [PATCH 057/208] time: Improve sanity checking of timekeeping inputs Unexpected behavior could occur if the time is set to a value large enough to overflow a 64bit ktime_t (which is something larger then the year 2262). Also unexpected behavior could occur if large negative offsets are injected via adjtimex. So this patch improves the sanity check timekeeping inputs by improving the timespec_valid() check, and then makes better use of timespec_valid() to make sure we don't set the time to an invalid negative value or one that overflows ktime_t. Note: This does not protect from setting the time close to overflowing ktime_t and then letting natural accumulation cause the overflow. Reported-by: CAI Qian Reported-by: Sasha Levin Signed-off-by: John Stultz Cc: Peter Zijlstra Cc: Prarit Bhargava Cc: Zhouping Liu Cc: Ingo Molnar Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1344454580-17031-1-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/ktime.h | 7 ------- include/linux/time.h | 22 ++++++++++++++++++++-- kernel/time/timekeeping.c | 26 ++++++++++++++++++++++++-- 3 files changed, 44 insertions(+), 11 deletions(-) diff --git a/include/linux/ktime.h b/include/linux/ktime.h index 603bec2913b0..06177ba10a16 100644 --- a/include/linux/ktime.h +++ b/include/linux/ktime.h @@ -58,13 +58,6 @@ union ktime { typedef union ktime ktime_t; /* Kill this */ -#define KTIME_MAX ((s64)~((u64)1 << 63)) -#if (BITS_PER_LONG == 64) -# define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) -#else -# define KTIME_SEC_MAX LONG_MAX -#endif - /* * ktime_t definitions when using the 64-bit scalar representation: */ diff --git a/include/linux/time.h b/include/linux/time.h index c81c5e40fcb5..b0bbd8f0130d 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -107,11 +107,29 @@ static inline struct timespec timespec_sub(struct timespec lhs, return ts_delta; } +#define KTIME_MAX ((s64)~((u64)1 << 63)) +#if (BITS_PER_LONG == 64) +# define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +#else +# define KTIME_SEC_MAX LONG_MAX +#endif + /* * Returns true if the timespec is norm, false if denorm: */ -#define timespec_valid(ts) \ - (((ts)->tv_sec >= 0) && (((unsigned long) (ts)->tv_nsec) < NSEC_PER_SEC)) +static inline bool timespec_valid(const struct timespec *ts) +{ + /* Dates before 1970 are bogus */ + if (ts->tv_sec < 0) + return false; + /* Can't have more nanoseconds then a second */ + if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) + return false; + /* Disallow values that could overflow ktime_t */ + if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) + return false; + return true; +} extern void read_persistent_clock(struct timespec *ts); extern void read_boot_clock(struct timespec *ts); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e16af197a2bc..898bef066a44 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -427,7 +427,7 @@ int do_settimeofday(const struct timespec *tv) struct timespec ts_delta, xt; unsigned long flags; - if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) + if (!timespec_valid(tv)) return -EINVAL; write_seqlock_irqsave(&tk->lock, flags); @@ -463,6 +463,8 @@ int timekeeping_inject_offset(struct timespec *ts) { struct timekeeper *tk = &timekeeper; unsigned long flags; + struct timespec tmp; + int ret = 0; if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; @@ -471,10 +473,17 @@ int timekeeping_inject_offset(struct timespec *ts) timekeeping_forward_now(tk); + /* Make sure the proposed value is valid */ + tmp = timespec_add(tk_xtime(tk), *ts); + if (!timespec_valid(&tmp)) { + ret = -EINVAL; + goto error; + } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); +error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, true); write_sequnlock_irqrestore(&tk->lock, flags); @@ -482,7 +491,7 @@ int timekeeping_inject_offset(struct timespec *ts) /* signal hrtimers about time change */ clock_was_set(); - return 0; + return ret; } EXPORT_SYMBOL(timekeeping_inject_offset); @@ -649,7 +658,20 @@ void __init timekeeping_init(void) struct timespec now, boot, tmp; read_persistent_clock(&now); + if (!timespec_valid(&now)) { + pr_warn("WARNING: Persistent clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + now.tv_sec = 0; + now.tv_nsec = 0; + } + read_boot_clock(&boot); + if (!timespec_valid(&boot)) { + pr_warn("WARNING: Boot clock returned invalid value!\n" + " Check your CMOS/BIOS settings.\n"); + boot.tv_sec = 0; + boot.tv_nsec = 0; + } seqlock_init(&tk->lock); From 58569aee5a1a5dcc25c34a0a2ed9a377874e6b05 Mon Sep 17 00:00:00 2001 From: "Arnaud Patard (Rtp)" Date: Thu, 26 Jul 2012 12:15:46 +0200 Subject: [PATCH 058/208] ARM: Orion: Set eth packet size csum offload limit The mv643xx ethernet controller limits the packet size for the TX checksum offloading. This patch sets this limits for Kirkwood and Dove which have smaller limits that the default. As a side note, this patch is an updated version of a patch sent some years ago: http://lists.infradead.org/pipermail/linux-arm-kernel/2010-June/017320.html which seems to have been lost. Signed-off-by: Arnaud Patard Signed-off-by: Jason Cooper Cc: --- arch/arm/mach-dove/common.c | 3 ++- arch/arm/mach-kirkwood/common.c | 4 ++-- arch/arm/mach-mv78xx0/common.c | 6 ++++-- arch/arm/mach-orion5x/common.c | 3 ++- arch/arm/plat-orion/common.c | 8 ++++++-- arch/arm/plat-orion/include/plat/common.h | 6 ++++-- include/linux/mv643xx_eth.h | 2 ++ 7 files changed, 22 insertions(+), 10 deletions(-) diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c index 4db5de54b6a7..6321567d8eaa 100644 --- a/arch/arm/mach-dove/common.c +++ b/arch/arm/mach-dove/common.c @@ -102,7 +102,8 @@ void __init dove_ehci1_init(void) void __init dove_ge00_init(struct mv643xx_eth_platform_data *eth_data) { orion_ge00_init(eth_data, DOVE_GE00_PHYS_BASE, - IRQ_DOVE_GE00_SUM, IRQ_DOVE_GE00_ERR); + IRQ_DOVE_GE00_SUM, IRQ_DOVE_GE00_ERR, + 1600); } /***************************************************************************** diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c index c4b64adcbfce..3226077735b1 100644 --- a/arch/arm/mach-kirkwood/common.c +++ b/arch/arm/mach-kirkwood/common.c @@ -301,7 +301,7 @@ void __init kirkwood_ge00_init(struct mv643xx_eth_platform_data *eth_data) { orion_ge00_init(eth_data, GE00_PHYS_BASE, IRQ_KIRKWOOD_GE00_SUM, - IRQ_KIRKWOOD_GE00_ERR); + IRQ_KIRKWOOD_GE00_ERR, 1600); /* The interface forgets the MAC address assigned by u-boot if the clock is turned off, so claim the clk now. */ clk_prepare_enable(ge0); @@ -315,7 +315,7 @@ void __init kirkwood_ge01_init(struct mv643xx_eth_platform_data *eth_data) { orion_ge01_init(eth_data, GE01_PHYS_BASE, IRQ_KIRKWOOD_GE01_SUM, - IRQ_KIRKWOOD_GE01_ERR); + IRQ_KIRKWOOD_GE01_ERR, 1600); clk_prepare_enable(ge1); } diff --git a/arch/arm/mach-mv78xx0/common.c b/arch/arm/mach-mv78xx0/common.c index b4c53b846c9c..3057f7d4329a 100644 --- a/arch/arm/mach-mv78xx0/common.c +++ b/arch/arm/mach-mv78xx0/common.c @@ -213,7 +213,8 @@ void __init mv78xx0_ge00_init(struct mv643xx_eth_platform_data *eth_data) { orion_ge00_init(eth_data, GE00_PHYS_BASE, IRQ_MV78XX0_GE00_SUM, - IRQ_MV78XX0_GE_ERR); + IRQ_MV78XX0_GE_ERR, + MV643XX_TX_CSUM_DEFAULT_LIMIT); } @@ -224,7 +225,8 @@ void __init mv78xx0_ge01_init(struct mv643xx_eth_platform_data *eth_data) { orion_ge01_init(eth_data, GE01_PHYS_BASE, IRQ_MV78XX0_GE01_SUM, - NO_IRQ); + NO_IRQ, + MV643XX_TX_CSUM_DEFAULT_LIMIT); } diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c index 9148b229d0de..410291c67666 100644 --- a/arch/arm/mach-orion5x/common.c +++ b/arch/arm/mach-orion5x/common.c @@ -109,7 +109,8 @@ void __init orion5x_eth_init(struct mv643xx_eth_platform_data *eth_data) { orion_ge00_init(eth_data, ORION5X_ETH_PHYS_BASE, IRQ_ORION5X_ETH_SUM, - IRQ_ORION5X_ETH_ERR); + IRQ_ORION5X_ETH_ERR, + MV643XX_TX_CSUM_DEFAULT_LIMIT); } diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c index d245a87dc014..b8b747a9d360 100644 --- a/arch/arm/plat-orion/common.c +++ b/arch/arm/plat-orion/common.c @@ -291,10 +291,12 @@ static struct platform_device orion_ge00 = { void __init orion_ge00_init(struct mv643xx_eth_platform_data *eth_data, unsigned long mapbase, unsigned long irq, - unsigned long irq_err) + unsigned long irq_err, + unsigned int tx_csum_limit) { fill_resources(&orion_ge00_shared, orion_ge00_shared_resources, mapbase + 0x2000, SZ_16K - 1, irq_err); + orion_ge00_shared_data.tx_csum_limit = tx_csum_limit; ge_complete(&orion_ge00_shared_data, orion_ge00_resources, irq, &orion_ge00_shared, eth_data, &orion_ge00); @@ -343,10 +345,12 @@ static struct platform_device orion_ge01 = { void __init orion_ge01_init(struct mv643xx_eth_platform_data *eth_data, unsigned long mapbase, unsigned long irq, - unsigned long irq_err) + unsigned long irq_err, + unsigned int tx_csum_limit) { fill_resources(&orion_ge01_shared, orion_ge01_shared_resources, mapbase + 0x2000, SZ_16K - 1, irq_err); + orion_ge01_shared_data.tx_csum_limit = tx_csum_limit; ge_complete(&orion_ge01_shared_data, orion_ge01_resources, irq, &orion_ge01_shared, eth_data, &orion_ge01); diff --git a/arch/arm/plat-orion/include/plat/common.h b/arch/arm/plat-orion/include/plat/common.h index e00fdb213609..ae2377ef63e5 100644 --- a/arch/arm/plat-orion/include/plat/common.h +++ b/arch/arm/plat-orion/include/plat/common.h @@ -39,12 +39,14 @@ void __init orion_rtc_init(unsigned long mapbase, void __init orion_ge00_init(struct mv643xx_eth_platform_data *eth_data, unsigned long mapbase, unsigned long irq, - unsigned long irq_err); + unsigned long irq_err, + unsigned int tx_csum_limit); void __init orion_ge01_init(struct mv643xx_eth_platform_data *eth_data, unsigned long mapbase, unsigned long irq, - unsigned long irq_err); + unsigned long irq_err, + unsigned int tx_csum_limit); void __init orion_ge10_init(struct mv643xx_eth_platform_data *eth_data, unsigned long mapbase, diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 51bf8ada6dc0..49258e0ed1c6 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -15,6 +15,8 @@ #define MV643XX_ETH_SIZE_REG_4 0x2224 #define MV643XX_ETH_BASE_ADDR_ENABLE_REG 0x2290 +#define MV643XX_TX_CSUM_DEFAULT_LIMIT 0 + struct mv643xx_eth_shared_platform_data { struct mbus_dram_target_info *dram; struct platform_device *shared_smi; From 03810a20308af54d01b096bc19a8c145684bd6b2 Mon Sep 17 00:00:00 2001 From: "Arnaud Patard (Rtp)" Date: Sun, 5 Aug 2012 22:35:56 +0200 Subject: [PATCH 059/208] ARM: Kirkwood: Fix iconnect leds While converting, a led has been missed leading to wrong power blue led definition. Add it back and fix the gpio used on the power blue led. Signed-off-by: Arnaud Patard Acked-by: Andrew Lunn Signed-off-by: Jason Cooper --- arch/arm/boot/dts/kirkwood-iconnect.dts | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/kirkwood-iconnect.dts b/arch/arm/boot/dts/kirkwood-iconnect.dts index 52d947045106..f8ca6fa88192 100644 --- a/arch/arm/boot/dts/kirkwood-iconnect.dts +++ b/arch/arm/boot/dts/kirkwood-iconnect.dts @@ -41,9 +41,13 @@ }; power-blue { label = "power:blue"; - gpios = <&gpio1 11 0>; + gpios = <&gpio1 10 0>; linux,default-trigger = "timer"; }; + power-red { + label = "power:red"; + gpios = <&gpio1 11 0>; + }; usb1 { label = "usb1:blue"; gpios = <&gpio1 12 0>; From b74ffd85e32d44e8ed405a2a0a175ef4cd39cf67 Mon Sep 17 00:00:00 2001 From: "Arnaud Patard (Rtp)" Date: Sun, 5 Aug 2012 22:35:57 +0200 Subject: [PATCH 060/208] ARM: Kirkwood: fix Makefile.boot While building the dtbs target, one is getting: make dtbs make[1]: *** No rule to make target `arch/arm/boot/kirkwood-qnap-ts219.dtb', needed by `arch/arm/boot/dtbs'. Stop. make: *** [dtbs] Error 2 The reason is that there's no kirkwood-qnap-ts219.dts file. Update Makefile.boot to reflect the dts files present. Signed-off-by: Arnaud Patard Acked-by: Andrew Lunn Signed-off-by: Jason Cooper --- arch/arm/mach-kirkwood/Makefile.boot | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-kirkwood/Makefile.boot b/arch/arm/mach-kirkwood/Makefile.boot index 2a576abf409b..e2ad35803d27 100644 --- a/arch/arm/mach-kirkwood/Makefile.boot +++ b/arch/arm/mach-kirkwood/Makefile.boot @@ -7,7 +7,8 @@ dtb-$(CONFIG_MACH_DLINK_KIRKWOOD_DT) += kirkwood-dns320.dtb dtb-$(CONFIG_MACH_DLINK_KIRKWOOD_DT) += kirkwood-dns325.dtb dtb-$(CONFIG_MACH_ICONNECT_DT) += kirkwood-iconnect.dtb dtb-$(CONFIG_MACH_IB62X0_DT) += kirkwood-ib62x0.dtb -dtb-$(CONFIG_MACH_TS219_DT) += kirkwood-qnap-ts219.dtb +dtb-$(CONFIG_MACH_TS219_DT) += kirkwood-ts219-6281.dtb +dtb-$(CONFIG_MACH_TS219_DT) += kirkwood-ts219-6282.dtb dtb-$(CONFIG_MACH_GOFLEXNET_DT) += kirkwood-goflexnet.dtb dbt-$(CONFIG_MACH_LSXL_DT) += kirkwood-lschlv2.dtb dbt-$(CONFIG_MACH_LSXL_DT) += kirkwood-lsxhl.dtb From 04f995a544d1289ffb8108849cd71b1325c5af6a Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Mon, 6 Aug 2012 00:03:28 +0000 Subject: [PATCH 061/208] KVM: PPC: Book3S HV: Fix incorrect branch in H_CEDE code In handling the H_CEDE hypercall, if this vcpu has already been prodded (with the H_PROD hypercall, which Linux guests don't in fact use), we branch to a numeric label '1f'. Unfortunately there is another '1:' label before the one that we want to jump to. This fixes the problem by using a textual label, 'kvm_cede_prodded'. It also changes the label for another longish branch from '2:' to 'kvm_cede_exit' to avoid a possible future problem if code modifications add another numeric '2:' label in between. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index 5a84c8d3d040..44b72feaff7d 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1421,13 +1421,13 @@ _GLOBAL(kvmppc_h_cede) sync /* order setting ceded vs. testing prodded */ lbz r5,VCPU_PRODDED(r3) cmpwi r5,0 - bne 1f + bne kvm_cede_prodded li r0,0 /* set trap to 0 to say hcall is handled */ stw r0,VCPU_TRAP(r3) li r0,H_SUCCESS std r0,VCPU_GPR(R3)(r3) BEGIN_FTR_SECTION - b 2f /* just send it up to host on 970 */ + b kvm_cede_exit /* just send it up to host on 970 */ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) /* @@ -1446,7 +1446,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206) or r4,r4,r0 PPC_POPCNTW(R7,R4) cmpw r7,r8 - bge 2f + bge kvm_cede_exit stwcx. r4,0,r6 bne 31b li r0,1 @@ -1555,7 +1555,8 @@ kvm_end_cede: b hcall_real_fallback /* cede when already previously prodded case */ -1: li r0,0 +kvm_cede_prodded: + li r0,0 stb r0,VCPU_PRODDED(r3) sync /* order testing prodded vs. clearing ceded */ stb r0,VCPU_CEDED(r3) @@ -1563,7 +1564,8 @@ kvm_end_cede: blr /* we've ceded but we want to give control to the host */ -2: li r3,H_TOO_HARD +kvm_cede_exit: + li r3,H_TOO_HARD blr secondary_too_late: From 249ba1ee0f8fcb4e40caa5fbea11dafde201cc46 Mon Sep 17 00:00:00 2001 From: Alexander Graf Date: Fri, 3 Aug 2012 13:56:33 +0200 Subject: [PATCH 062/208] KVM: PPC: Add cache flush on page map When we map a page that wasn't icache cleared before, do so when first mapping it in KVM using the same information bits as the Linux mapping logic. That way we are 100% sure that any page we map does not have stale entries in the icache. Signed-off-by: Alexander Graf --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/include/asm/kvm_ppc.h | 12 ++++++++++++ arch/powerpc/kvm/book3s_32_mmu_host.c | 3 +++ arch/powerpc/kvm/book3s_64_mmu_host.c | 2 ++ arch/powerpc/kvm/e500_tlb.c | 3 +++ arch/powerpc/mm/mem.c | 1 + 6 files changed, 22 insertions(+) diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 50ea12fd7bf5..a8bf5c673a3c 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -33,6 +33,7 @@ #include #include #include +#include #define KVM_MAX_VCPUS NR_CPUS #define KVM_MAX_VCORES NR_CPUS diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 0124937a23b9..e006f0bdea95 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -219,4 +219,16 @@ void kvmppc_claim_lpid(long lpid); void kvmppc_free_lpid(long lpid); void kvmppc_init_lpid(unsigned long nr_lpids); +static inline void kvmppc_mmu_flush_icache(pfn_t pfn) +{ + /* Clear i-cache for new pages */ + struct page *page; + page = pfn_to_page(pfn); + if (!test_bit(PG_arch_1, &page->flags)) { + flush_dcache_icache_page(page); + set_bit(PG_arch_1, &page->flags); + } +} + + #endif /* __POWERPC_KVM_PPC_H__ */ diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c index f922c29bb234..837f13e7b6bf 100644 --- a/arch/powerpc/kvm/book3s_32_mmu_host.c +++ b/arch/powerpc/kvm/book3s_32_mmu_host.c @@ -211,6 +211,9 @@ next_pteg: pteg1 |= PP_RWRX; } + if (orig_pte->may_execute) + kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT); + local_irq_disable(); if (pteg[rr]) { diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c index 10fc8ec9d2a8..0688b6b39585 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_host.c +++ b/arch/powerpc/kvm/book3s_64_mmu_host.c @@ -126,6 +126,8 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte) if (!orig_pte->may_execute) rflags |= HPTE_R_N; + else + kvmppc_mmu_flush_icache(hpaddr >> PAGE_SHIFT); hash = hpt_hash(va, PTE_SIZE, MMU_SEGSIZE_256M); diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c index c510fc961302..fb3bb3ad8b3c 100644 --- a/arch/powerpc/kvm/e500_tlb.c +++ b/arch/powerpc/kvm/e500_tlb.c @@ -539,6 +539,9 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe); + + /* Clear i-cache for new pages */ + kvmppc_mmu_flush_icache(pfn); } /* XXX only map the one-one case, for now use TLB0 */ diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index baaafde7d135..fbdad0e3929a 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -469,6 +469,7 @@ void flush_dcache_icache_page(struct page *page) __flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT); #endif } +EXPORT_SYMBOL(flush_dcache_icache_page); void clear_user_page(void *page, unsigned long vaddr, struct page *pg) { From e8143ccb6b501f78bb95d9c5ee100d18423008cf Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Tue, 14 Aug 2012 12:10:09 +0000 Subject: [PATCH 063/208] ppc: e500_tlb memset clears nothing Put the parameters the right way around Addresses https://bugzilla.kernel.org/show_bug.cgi?id=44031 Reported-by: David Binderman Signed-off-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Alexander Graf --- arch/powerpc/kvm/e500_tlb.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c index fb3bb3ad8b3c..a2b66717813d 100644 --- a/arch/powerpc/kvm/e500_tlb.c +++ b/arch/powerpc/kvm/e500_tlb.c @@ -322,11 +322,11 @@ static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) static void clear_tlb1_bitmap(struct kvmppc_vcpu_e500 *vcpu_e500) { if (vcpu_e500->g2h_tlb1_map) - memset(vcpu_e500->g2h_tlb1_map, - sizeof(u64) * vcpu_e500->gtlb_params[1].entries, 0); + memset(vcpu_e500->g2h_tlb1_map, 0, + sizeof(u64) * vcpu_e500->gtlb_params[1].entries); if (vcpu_e500->h2g_tlb1_rmap) - memset(vcpu_e500->h2g_tlb1_rmap, - sizeof(unsigned int) * host_tlb_params[1].entries, 0); + memset(vcpu_e500->h2g_tlb1_rmap, 0, + sizeof(unsigned int) * host_tlb_params[1].entries); } static void clear_tlb_privs(struct kvmppc_vcpu_e500 *vcpu_e500) From 227f052f4711caf432b9a7dbcfe1a2857d3c0def Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Tue, 31 Jul 2012 09:31:11 +0200 Subject: [PATCH 064/208] drbd: fix drbd wire compatibility for empty flushes DRBD has a concept of request epochs or reorder-domains, which are separated on the wire by P_BARRIER packets. Older DRBD is not able to handle zero-sized requests at all, so we need to map empty flushes to these drbd barriers. These are the equivalent of empty flushes, and by default trigger flushes on the receiving side anyways (unless not supported or explicitly disabled), so there is no need to handle this differently in newer drbd either. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_req.c | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 910335c30927..0bb1e41f136f 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -834,7 +834,15 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns req->private_bio = NULL; } if (rw == WRITE) { - remote = 1; + /* Need to replicate writes. Unless it is an empty flush, + * which is better mapped to a DRBD P_BARRIER packet, + * also for drbd wire protocol compatibility reasons. */ + if (unlikely(size == 0)) { + /* The only size==0 bios we expect are empty flushes. */ + D_ASSERT(bio->bi_rw & REQ_FLUSH); + remote = 0; + } else + remote = 1; } else { /* READ || READA */ if (local) { @@ -870,8 +878,11 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, uns * extent. This waits for any resync activity in the corresponding * resync extent to finish, and, if necessary, pulls in the target * extent into the activity log, which involves further disk io because - * of transactional on-disk meta data updates. */ - if (rw == WRITE && local && !test_bit(AL_SUSPENDED, &mdev->flags)) { + * of transactional on-disk meta data updates. + * Empty flushes don't need to go into the activity log, they can only + * flush data for pending writes which are already in there. */ + if (rw == WRITE && local && size + && !test_bit(AL_SUSPENDED, &mdev->flags)) { req->rq_state |= RQ_IN_ACT_LOG; drbd_al_begin_io(mdev, sector); } @@ -994,7 +1005,10 @@ allocate_barrier: if (rw == WRITE && _req_conflicts(req)) goto fail_conflicting; - list_add_tail(&req->tl_requests, &mdev->newest_tle->requests); + /* no point in adding empty flushes to the transfer log, + * they are mapped to drbd barriers already. */ + if (likely(size!=0)) + list_add_tail(&req->tl_requests, &mdev->newest_tle->requests); /* NOTE remote first: to get the concurrent write detection right, * we must register the request before start of local IO. */ @@ -1014,6 +1028,14 @@ allocate_barrier: mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) maybe_pull_ahead(mdev); + /* If this was a flush, queue a drbd barrier/start a new epoch. + * Unless the current epoch was empty anyways, or we are not currently + * replicating, in which case there is no point. */ + if (unlikely(bio->bi_rw & REQ_FLUSH) + && mdev->newest_tle->n_writes + && drbd_should_do_remote(mdev->state)) + queue_barrier(mdev); + spin_unlock_irq(&mdev->req_lock); kfree(b); /* if someone else has beaten us to it... */ From 509fc019e534bdf5f3969d78c53184db4cf7ff48 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Tue, 31 Jul 2012 11:22:58 +0200 Subject: [PATCH 065/208] drbd: Finish requests that completed while IO was frozen Requests of an acked epoch are stored on the barrier_acked_requests list. In case the private bio of such a request completes while IO on the drbd device is suspended [req_mod(completed_ok)] then the request stays there. When thawing IO because the fence_peer handler returned, then we use tl_clear() to apply the connection_lost_while_pending event to all requests on the transfer-log and the barrier_acked_requests list. Up to now the connection_lost_while_pending event was not applied on requests on the barrier_acked_requests list. Fixed that. I.e. now the connection_lost_while_pending and resend events are applied to requests on the barrier_acked_requests list. For that it is necessary that the resend event finishes (local only) READS correctly. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_main.c | 28 ++++++++++++---------------- drivers/block/drbd/drbd_req.c | 6 ++++++ 2 files changed, 18 insertions(+), 16 deletions(-) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 2e0e7fc1dbba..136db95b212d 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -79,6 +79,7 @@ static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused); static void md_sync_timer_fn(unsigned long data); static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused); static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused); +static void _tl_clear(struct drbd_conf *mdev); MODULE_AUTHOR("Philipp Reisner , " "Lars Ellenberg "); @@ -432,19 +433,10 @@ static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what) /* Actions operating on the disk state, also want to work on requests that got barrier acked. */ - switch (what) { - case fail_frozen_disk_io: - case restart_frozen_disk_io: - list_for_each_safe(le, tle, &mdev->barrier_acked_requests) { - req = list_entry(le, struct drbd_request, tl_requests); - _req_mod(req, what); - } - case connection_lost_while_pending: - case resend: - break; - default: - dev_err(DEV, "what = %d in _tl_restart()\n", what); + list_for_each_safe(le, tle, &mdev->barrier_acked_requests) { + req = list_entry(le, struct drbd_request, tl_requests); + _req_mod(req, what); } } @@ -458,12 +450,17 @@ static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what) * receiver thread and the worker thread. */ void tl_clear(struct drbd_conf *mdev) +{ + spin_lock_irq(&mdev->req_lock); + _tl_clear(mdev); + spin_unlock_irq(&mdev->req_lock); +} + +static void _tl_clear(struct drbd_conf *mdev) { struct list_head *le, *tle; struct drbd_request *r; - spin_lock_irq(&mdev->req_lock); - _tl_restart(mdev, connection_lost_while_pending); /* we expect this list to be empty. */ @@ -482,7 +479,6 @@ void tl_clear(struct drbd_conf *mdev) memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *)); - spin_unlock_irq(&mdev->req_lock); } void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what) @@ -1476,12 +1472,12 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, if (ns.susp_fen) { /* case1: The outdate peer handler is successful: */ if (os.pdsk > D_OUTDATED && ns.pdsk <= D_OUTDATED) { - tl_clear(mdev); if (test_bit(NEW_CUR_UUID, &mdev->flags)) { drbd_uuid_new_current(mdev); clear_bit(NEW_CUR_UUID, &mdev->flags); } spin_lock_irq(&mdev->req_lock); + _tl_clear(mdev); _drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL); spin_unlock_irq(&mdev->req_lock); } diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 0bb1e41f136f..01b2ac641c7b 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -695,6 +695,12 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, break; case resend: + /* Simply complete (local only) READs. */ + if (!(req->rq_state & RQ_WRITE) && !req->w.cb) { + _req_may_be_done(req, m); + break; + } + /* If RQ_NET_OK is already set, we got a P_WRITE_ACK or P_RECV_ACK before the connection loss (B&C only); only P_BARRIER_ACK was missing. Trowing them out of the TL here by pretending we got a BARRIER_ACK From d1aa4d04da8de5c89d73859e077d89c4c71d8ed1 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Wed, 8 Aug 2012 21:19:09 +0200 Subject: [PATCH 066/208] drbd: Write all pages of the bitmap after an online resize We need to write the whole bitmap after we moved the meta data due to an online resize operation. With the support for one peta byte devices bitmap IO was optimized to only write out touched pages. This optimization must be turned off when writing the bitmap after an online resize. This issue was introduced with drbd-8.3.10. The impact of this bug is that after an online resize, the next resync could become larger than expected. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_bitmap.c | 15 ++++++++++++++- drivers/block/drbd/drbd_int.h | 1 + drivers/block/drbd/drbd_nl.c | 4 ++-- 3 files changed, 17 insertions(+), 3 deletions(-) diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index ba91b408abad..d84566496746 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -889,6 +889,7 @@ struct bm_aio_ctx { unsigned int done; unsigned flags; #define BM_AIO_COPY_PAGES 1 +#define BM_WRITE_ALL_PAGES 2 int error; struct kref kref; }; @@ -1059,7 +1060,8 @@ static int bm_rw(struct drbd_conf *mdev, int rw, unsigned flags, unsigned lazy_w if (lazy_writeout_upper_idx && i == lazy_writeout_upper_idx) break; if (rw & WRITE) { - if (bm_test_page_unchanged(b->bm_pages[i])) { + if (!(flags & BM_WRITE_ALL_PAGES) && + bm_test_page_unchanged(b->bm_pages[i])) { dynamic_dev_dbg(DEV, "skipped bm write for idx %u\n", i); continue; } @@ -1140,6 +1142,17 @@ int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local) return bm_rw(mdev, WRITE, 0, 0); } +/** + * drbd_bm_write_all() - Write the whole bitmap to its on disk location. + * @mdev: DRBD device. + * + * Will write all pages. + */ +int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local) +{ + return bm_rw(mdev, WRITE, BM_WRITE_ALL_PAGES, 0); +} + /** * drbd_bm_lazy_write_out() - Write bitmap pages 0 to @upper_idx-1, if they have changed. * @mdev: DRBD device. diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index b2ca143d0053..b953cc7c9c00 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1469,6 +1469,7 @@ extern int drbd_bm_e_weight(struct drbd_conf *mdev, unsigned long enr); extern int drbd_bm_write_page(struct drbd_conf *mdev, unsigned int idx) __must_hold(local); extern int drbd_bm_read(struct drbd_conf *mdev) __must_hold(local); extern int drbd_bm_write(struct drbd_conf *mdev) __must_hold(local); +extern int drbd_bm_write_all(struct drbd_conf *mdev) __must_hold(local); extern int drbd_bm_write_copy_pages(struct drbd_conf *mdev) __must_hold(local); extern unsigned long drbd_bm_ALe_set_all(struct drbd_conf *mdev, unsigned long al_enr); diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index fb9dce8daa24..edb490aad8b4 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -674,8 +674,8 @@ enum determine_dev_size drbd_determine_dev_size(struct drbd_conf *mdev, enum dds la_size_changed && md_moved ? "size changed and md moved" : la_size_changed ? "size changed" : "md moved"); /* next line implicitly does drbd_suspend_io()+drbd_resume_io() */ - err = drbd_bitmap_io(mdev, &drbd_bm_write, - "size changed", BM_LOCKED_MASK); + err = drbd_bitmap_io(mdev, md_moved ? &drbd_bm_write_all : &drbd_bm_write, + "size changed", BM_LOCKED_MASK); if (err) { rv = dev_size_error; goto out; From ca08649eb5dd30f11a5a8fe8659b48899b7ea6a1 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 16 Aug 2012 11:31:27 -0400 Subject: [PATCH 067/208] Revert "xen PVonHVM: move shared_info to MMIO before kexec" This reverts commit 00e37bdb0113a98408de42db85be002f21dbffd3. During shutdown of PVHVM guests with more than 2VCPUs on certain machines we can hit the race where the replaced shared_info is not replaced fast enough and the PV time clock retries reading the same area over and over without any any success and is stuck in an infinite loop. Acked-by: Olaf Hering Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/enlighten.c | 118 ++++--------------------------------- arch/x86/xen/suspend.c | 2 +- arch/x86/xen/xen-ops.h | 2 +- drivers/xen/platform-pci.c | 15 ----- include/xen/events.h | 2 - 5 files changed, 13 insertions(+), 126 deletions(-) diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a6f8acbdfc9a..f1814fc2cb77 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include @@ -1472,130 +1471,38 @@ asmlinkage void __init xen_start_kernel(void) #endif } -#ifdef CONFIG_XEN_PVHVM -/* - * The pfn containing the shared_info is located somewhere in RAM. This - * will cause trouble if the current kernel is doing a kexec boot into a - * new kernel. The new kernel (and its startup code) can not know where - * the pfn is, so it can not reserve the page. The hypervisor will - * continue to update the pfn, and as a result memory corruption occours - * in the new kernel. - * - * One way to work around this issue is to allocate a page in the - * xen-platform pci device's BAR memory range. But pci init is done very - * late and the shared_info page is already in use very early to read - * the pvclock. So moving the pfn from RAM to MMIO is racy because some - * code paths on other vcpus could access the pfn during the small - * window when the old pfn is moved to the new pfn. There is even a - * small window were the old pfn is not backed by a mfn, and during that - * time all reads return -1. - * - * Because it is not known upfront where the MMIO region is located it - * can not be used right from the start in xen_hvm_init_shared_info. - * - * To minimise trouble the move of the pfn is done shortly before kexec. - * This does not eliminate the race because all vcpus are still online - * when the syscore_ops will be called. But hopefully there is no work - * pending at this point in time. Also the syscore_op is run last which - * reduces the risk further. - */ - -static struct shared_info *xen_hvm_shared_info; - -static void xen_hvm_connect_shared_info(unsigned long pfn) +void __ref xen_hvm_init_shared_info(void) { + int cpu; struct xen_add_to_physmap xatp; + static struct shared_info *shared_info_page = 0; + if (!shared_info_page) + shared_info_page = (struct shared_info *) + extend_brk(PAGE_SIZE, PAGE_SIZE); xatp.domid = DOMID_SELF; xatp.idx = 0; xatp.space = XENMAPSPACE_shared_info; - xatp.gpfn = pfn; + xatp.gpfn = __pa(shared_info_page) >> PAGE_SHIFT; if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp)) BUG(); -} -static void xen_hvm_set_shared_info(struct shared_info *sip) -{ - int cpu; - - HYPERVISOR_shared_info = sip; + HYPERVISOR_shared_info = (struct shared_info *)shared_info_page; /* xen_vcpu is a pointer to the vcpu_info struct in the shared_info * page, we use it in the event channel upcall and in some pvclock * related functions. We don't need the vcpu_info placement * optimizations because we don't use any pv_mmu or pv_irq op on * HVM. - * When xen_hvm_set_shared_info is run at boot time only vcpu 0 is - * online but xen_hvm_set_shared_info is run at resume time too and + * When xen_hvm_init_shared_info is run at boot time only vcpu 0 is + * online but xen_hvm_init_shared_info is run at resume time too and * in that case multiple vcpus might be online. */ for_each_online_cpu(cpu) { per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu]; } } -/* Reconnect the shared_info pfn to a mfn */ -void xen_hvm_resume_shared_info(void) -{ - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); -} - -#ifdef CONFIG_KEXEC -static struct shared_info *xen_hvm_shared_info_kexec; -static unsigned long xen_hvm_shared_info_pfn_kexec; - -/* Remember a pfn in MMIO space for kexec reboot */ -void __devinit xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn) -{ - xen_hvm_shared_info_kexec = sip; - xen_hvm_shared_info_pfn_kexec = pfn; -} - -static void xen_hvm_syscore_shutdown(void) -{ - struct xen_memory_reservation reservation = { - .domid = DOMID_SELF, - .nr_extents = 1, - }; - unsigned long prev_pfn; - int rc; - - if (!xen_hvm_shared_info_kexec) - return; - - prev_pfn = __pa(xen_hvm_shared_info) >> PAGE_SHIFT; - set_xen_guest_handle(reservation.extent_start, &prev_pfn); - - /* Move pfn to MMIO, disconnects previous pfn from mfn */ - xen_hvm_connect_shared_info(xen_hvm_shared_info_pfn_kexec); - - /* Update pointers, following hypercall is also a memory barrier */ - xen_hvm_set_shared_info(xen_hvm_shared_info_kexec); - - /* Allocate new mfn for previous pfn */ - do { - rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation); - if (rc == 0) - msleep(123); - } while (rc == 0); - - /* Make sure the previous pfn is really connected to a (new) mfn */ - BUG_ON(rc != 1); -} - -static struct syscore_ops xen_hvm_syscore_ops = { - .shutdown = xen_hvm_syscore_shutdown, -}; -#endif - -/* Use a pfn in RAM, may move to MMIO before kexec. */ -static void __init xen_hvm_init_shared_info(void) -{ - /* Remember pointer for resume */ - xen_hvm_shared_info = extend_brk(PAGE_SIZE, PAGE_SIZE); - xen_hvm_connect_shared_info(__pa(xen_hvm_shared_info) >> PAGE_SHIFT); - xen_hvm_set_shared_info(xen_hvm_shared_info); -} - +#ifdef CONFIG_XEN_PVHVM static void __init init_hvm_pv_info(void) { int major, minor; @@ -1646,9 +1553,6 @@ static void __init xen_hvm_guest_init(void) init_hvm_pv_info(); xen_hvm_init_shared_info(); -#ifdef CONFIG_KEXEC - register_syscore_ops(&xen_hvm_syscore_ops); -#endif if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index ae8a00c39de4..45329c8c226e 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -30,7 +30,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_resume_shared_info(); + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1e4329e04e0f..202d4c150154 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -41,7 +41,7 @@ void xen_enable_syscall(void); void xen_vcpu_restore(void); void xen_callback_vector(void); -void xen_hvm_resume_shared_info(void); +void xen_hvm_init_shared_info(void); void xen_unplug_emulated_devices(void); void __init xen_build_dynamic_phys_to_machine(void); diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index d4c50d63acbc..97ca359ae2bd 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -101,19 +101,6 @@ static int platform_pci_resume(struct pci_dev *pdev) return 0; } -static void __devinit prepare_shared_info(void) -{ -#ifdef CONFIG_KEXEC - unsigned long addr; - struct shared_info *hvm_shared_info; - - addr = alloc_xen_mmio(PAGE_SIZE); - hvm_shared_info = ioremap(addr, PAGE_SIZE); - memset(hvm_shared_info, 0, PAGE_SIZE); - xen_hvm_prepare_kexec(hvm_shared_info, addr >> PAGE_SHIFT); -#endif -} - static int __devinit platform_pci_init(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -151,8 +138,6 @@ static int __devinit platform_pci_init(struct pci_dev *pdev, platform_mmio = mmio_addr; platform_mmiolen = mmio_len; - prepare_shared_info(); - if (!xen_have_vector_callback) { ret = xen_allocate_irq(pdev); if (ret) { diff --git a/include/xen/events.h b/include/xen/events.h index 9c641deb65d2..04399b28e821 100644 --- a/include/xen/events.h +++ b/include/xen/events.h @@ -58,8 +58,6 @@ void notify_remote_via_irq(int irq); void xen_irq_resume(void); -void xen_hvm_prepare_kexec(struct shared_info *sip, unsigned long pfn); - /* Clear an irq's pending state, in preparation for polling on it */ void xen_clear_irq_pending(int irq); void xen_set_irq_pending(int irq); From 16339464c5d67d0536837fc5342c9c2432b80ae0 Mon Sep 17 00:00:00 2001 From: Philipp Zabel Date: Wed, 15 Aug 2012 12:00:16 +0200 Subject: [PATCH 068/208] ARM i.MX6q: Add virtual 1/3.5 dividers in the LDB clock path The ldb_di[01]_podf is implemented as a clk-divider that divides by 1 or 2. In reality, the ldb_di[01]_ipu_div dividers divide by either 3.5 or 7. Adding a fixed factor of 1/3.5 fixes their children's clock rates. This should probably be converted to rate table based dividers, once available. Cc: Signed-off-by: Philipp Zabel Signed-off-by: Steffen Trumtrar Signed-off-by: Shawn Guo --- arch/arm/mach-imx/clk-imx6q.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c index ea89520b6e22..4233d9e3531d 100644 --- a/arch/arm/mach-imx/clk-imx6q.c +++ b/arch/arm/mach-imx/clk-imx6q.c @@ -152,7 +152,7 @@ enum mx6q_clks { ssi2, ssi3, uart_ipg, uart_serial, usboh3, usdhc1, usdhc2, usdhc3, usdhc4, vdo_axi, vpu_axi, cko1, pll1_sys, pll2_bus, pll3_usb_otg, pll4_audio, pll5_video, pll6_mlb, pll7_usb_host, pll8_enet, ssi1_ipg, - ssi2_ipg, ssi3_ipg, rom, usbphy1, usbphy2, + ssi2_ipg, ssi3_ipg, rom, usbphy1, usbphy2, ldb_di0_div_3_5, ldb_di1_div_3_5, clk_max }; @@ -288,8 +288,10 @@ int __init mx6q_clocks_init(void) clk[gpu3d_shader] = imx_clk_divider("gpu3d_shader", "gpu3d_shader_sel", base + 0x18, 29, 3); clk[ipu1_podf] = imx_clk_divider("ipu1_podf", "ipu1_sel", base + 0x3c, 11, 3); clk[ipu2_podf] = imx_clk_divider("ipu2_podf", "ipu2_sel", base + 0x3c, 16, 3); - clk[ldb_di0_podf] = imx_clk_divider("ldb_di0_podf", "ldb_di0_sel", base + 0x20, 10, 1); - clk[ldb_di1_podf] = imx_clk_divider("ldb_di1_podf", "ldb_di1_sel", base + 0x20, 11, 1); + clk[ldb_di0_div_3_5] = imx_clk_fixed_factor("ldb_di0_div_3_5", "ldb_di0_sel", 2, 7); + clk[ldb_di0_podf] = imx_clk_divider("ldb_di0_podf", "ldb_di0_div_3_5", base + 0x20, 10, 1); + clk[ldb_di1_div_3_5] = imx_clk_fixed_factor("ldb_di1_div_3_5", "ldb_di1_sel", 2, 7); + clk[ldb_di1_podf] = imx_clk_divider("ldb_di1_podf", "ldb_di1_div_3_5", base + 0x20, 11, 1); clk[ipu1_di0_pre] = imx_clk_divider("ipu1_di0_pre", "ipu1_di0_pre_sel", base + 0x34, 3, 3); clk[ipu1_di1_pre] = imx_clk_divider("ipu1_di1_pre", "ipu1_di1_pre_sel", base + 0x34, 12, 3); clk[ipu2_di0_pre] = imx_clk_divider("ipu2_di0_pre", "ipu2_di0_pre_sel", base + 0x38, 3, 3); From 87161ccdc61862c8b49e75c21209d7f79dc758e9 Mon Sep 17 00:00:00 2001 From: David Daney Date: Fri, 10 Aug 2012 16:00:31 -0700 Subject: [PATCH 069/208] MIPS: Octeon: Fix broken interrupt controller code. Since 3.6.0-rc1, We are getting many messages like: WARNING: at kernel/irq/irqdomain.c:444 irq_domain_associate_many+0x23c/0x260() Modules linked in: Call Trace: [] dump_stack+0x8/0x34 [] warn_slowpath_common+0x78/0xa8 [] irq_domain_associate_many+0x23c/0x260 [] irq_create_mapping+0xd0/0x220 [] irq_create_of_mapping+0x7c/0x158 [] irq_of_parse_and_map+0x28/0x40 . . . Both the CIU and GPIO interrupt domains were somewhat screwed up. For the CIU domain, we need to call irq_domain_associate() for each of the preassigned irq numbers. For the GPIO domain, we were applying the register bit offset in octeon_irq_gpio_xlat, but it should be done in octeon_irq_gpio_map instead. Also: Reserve all 8 'core' irqs for the 'core' irq_chip so that they don't get used by the other domains. Remove unused OCTEON_IRQ_* symbols. Signed-off-by: David Daney Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/4190/ Signed-off-by: Ralf Baechle --- arch/mips/cavium-octeon/octeon-irq.c | 89 +++++++++---------- .../mips/include/asm/mach-cavium-octeon/irq.h | 10 +-- 2 files changed, 44 insertions(+), 55 deletions(-) diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index 7fb1f222b8a5..274cd4fad30c 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -61,6 +61,12 @@ static void octeon_irq_set_ciu_mapping(int irq, int line, int bit, octeon_irq_ciu_to_irq[line][bit] = irq; } +static void octeon_irq_force_ciu_mapping(struct irq_domain *domain, + int irq, int line, int bit) +{ + irq_domain_associate(domain, irq, line << 6 | bit); +} + static int octeon_coreid_for_cpu(int cpu) { #ifdef CONFIG_SMP @@ -183,19 +189,9 @@ static void __init octeon_irq_init_core(void) mutex_init(&cd->core_irq_mutex); irq = OCTEON_IRQ_SW0 + i; - switch (irq) { - case OCTEON_IRQ_TIMER: - case OCTEON_IRQ_SW0: - case OCTEON_IRQ_SW1: - case OCTEON_IRQ_5: - case OCTEON_IRQ_PERF: - irq_set_chip_data(irq, cd); - irq_set_chip_and_handler(irq, &octeon_irq_chip_core, - handle_percpu_irq); - break; - default: - break; - } + irq_set_chip_data(irq, cd); + irq_set_chip_and_handler(irq, &octeon_irq_chip_core, + handle_percpu_irq); } } @@ -890,7 +886,6 @@ static int octeon_irq_gpio_xlat(struct irq_domain *d, unsigned int type; unsigned int pin; unsigned int trigger; - struct octeon_irq_gpio_domain_data *gpiod; if (d->of_node != node) return -EINVAL; @@ -925,8 +920,7 @@ static int octeon_irq_gpio_xlat(struct irq_domain *d, break; } *out_type = type; - gpiod = d->host_data; - *out_hwirq = gpiod->base_hwirq + pin; + *out_hwirq = pin; return 0; } @@ -996,19 +990,21 @@ static int octeon_irq_ciu_map(struct irq_domain *d, static int octeon_irq_gpio_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw) { - unsigned int line = hw >> 6; - unsigned int bit = hw & 63; + struct octeon_irq_gpio_domain_data *gpiod = d->host_data; + unsigned int line, bit; if (!octeon_irq_virq_in_range(virq)) return -EINVAL; + hw += gpiod->base_hwirq; + line = hw >> 6; + bit = hw & 63; if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0) return -EINVAL; octeon_irq_set_ciu_mapping(virq, line, bit, octeon_irq_gpio_chip, octeon_irq_handle_gpio); - return 0; } @@ -1149,6 +1145,7 @@ static void __init octeon_irq_init_ciu(void) struct irq_chip *chip_wd; struct device_node *gpio_node; struct device_node *ciu_node; + struct irq_domain *ciu_domain = NULL; octeon_irq_init_ciu_percpu(); octeon_irq_setup_secondary = octeon_irq_setup_secondary_ciu; @@ -1177,31 +1174,6 @@ static void __init octeon_irq_init_ciu(void) /* Mips internal */ octeon_irq_init_core(); - /* CIU_0 */ - for (i = 0; i < 16; i++) - octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WORKQ0, 0, i + 0, chip, handle_level_irq); - - octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX0, 0, 32, chip_mbox, handle_percpu_irq); - octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX1, 0, 33, chip_mbox, handle_percpu_irq); - - for (i = 0; i < 4; i++) - octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_PCI_INT0, 0, i + 36, chip, handle_level_irq); - for (i = 0; i < 4; i++) - octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_PCI_MSI0, 0, i + 40, chip, handle_level_irq); - - octeon_irq_set_ciu_mapping(OCTEON_IRQ_RML, 0, 46, chip, handle_level_irq); - for (i = 0; i < 4; i++) - octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_TIMER0, 0, i + 52, chip, handle_edge_irq); - - octeon_irq_set_ciu_mapping(OCTEON_IRQ_USB0, 0, 56, chip, handle_level_irq); - octeon_irq_set_ciu_mapping(OCTEON_IRQ_BOOTDMA, 0, 63, chip, handle_level_irq); - - /* CIU_1 */ - for (i = 0; i < 16; i++) - octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WDOG0, 1, i + 0, chip_wd, handle_level_irq); - - octeon_irq_set_ciu_mapping(OCTEON_IRQ_USB1, 1, 17, chip, handle_level_irq); - gpio_node = of_find_compatible_node(NULL, NULL, "cavium,octeon-3860-gpio"); if (gpio_node) { struct octeon_irq_gpio_domain_data *gpiod; @@ -1219,10 +1191,35 @@ static void __init octeon_irq_init_ciu(void) ciu_node = of_find_compatible_node(NULL, NULL, "cavium,octeon-3860-ciu"); if (ciu_node) { - irq_domain_add_tree(ciu_node, &octeon_irq_domain_ciu_ops, NULL); + ciu_domain = irq_domain_add_tree(ciu_node, &octeon_irq_domain_ciu_ops, NULL); of_node_put(ciu_node); } else - pr_warn("Cannot find device node for cavium,octeon-3860-ciu.\n"); + panic("Cannot find device node for cavium,octeon-3860-ciu."); + + /* CIU_0 */ + for (i = 0; i < 16; i++) + octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_WORKQ0, 0, i + 0); + + octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX0, 0, 32, chip_mbox, handle_percpu_irq); + octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX1, 0, 33, chip_mbox, handle_percpu_irq); + + for (i = 0; i < 4; i++) + octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_PCI_INT0, 0, i + 36); + for (i = 0; i < 4; i++) + octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_PCI_MSI0, 0, i + 40); + + octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_RML, 0, 46); + for (i = 0; i < 4; i++) + octeon_irq_force_ciu_mapping(ciu_domain, i + OCTEON_IRQ_TIMER0, 0, i + 52); + + octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB0, 0, 56); + octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_BOOTDMA, 0, 63); + + /* CIU_1 */ + for (i = 0; i < 16; i++) + octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WDOG0, 1, i + 0, chip_wd, handle_level_irq); + + octeon_irq_force_ciu_mapping(ciu_domain, OCTEON_IRQ_USB1, 1, 17); /* Enable the CIU lines */ set_c0_status(STATUSF_IP3 | STATUSF_IP2); diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h index 418992042f6f..c22a3078bf11 100644 --- a/arch/mips/include/asm/mach-cavium-octeon/irq.h +++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h @@ -21,14 +21,10 @@ enum octeon_irq { OCTEON_IRQ_TIMER, /* sources in CIU_INTX_EN0 */ OCTEON_IRQ_WORKQ0, - OCTEON_IRQ_GPIO0 = OCTEON_IRQ_WORKQ0 + 16, - OCTEON_IRQ_WDOG0 = OCTEON_IRQ_GPIO0 + 16, + OCTEON_IRQ_WDOG0 = OCTEON_IRQ_WORKQ0 + 16, OCTEON_IRQ_WDOG15 = OCTEON_IRQ_WDOG0 + 15, OCTEON_IRQ_MBOX0 = OCTEON_IRQ_WDOG0 + 16, OCTEON_IRQ_MBOX1, - OCTEON_IRQ_UART0, - OCTEON_IRQ_UART1, - OCTEON_IRQ_UART2, OCTEON_IRQ_PCI_INT0, OCTEON_IRQ_PCI_INT1, OCTEON_IRQ_PCI_INT2, @@ -38,8 +34,6 @@ enum octeon_irq { OCTEON_IRQ_PCI_MSI2, OCTEON_IRQ_PCI_MSI3, - OCTEON_IRQ_TWSI, - OCTEON_IRQ_TWSI2, OCTEON_IRQ_RML, OCTEON_IRQ_TIMER0, OCTEON_IRQ_TIMER1, @@ -47,8 +41,6 @@ enum octeon_irq { OCTEON_IRQ_TIMER3, OCTEON_IRQ_USB0, OCTEON_IRQ_USB1, - OCTEON_IRQ_MII0, - OCTEON_IRQ_MII1, OCTEON_IRQ_BOOTDMA, #ifndef CONFIG_PCI_MSI OCTEON_IRQ_LAST = 127 From b4da14abf27227fc767ec257f44de70085a0bc68 Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Sat, 4 Aug 2012 18:01:24 +0200 Subject: [PATCH 070/208] MIPS: ath79: Fix number of GPIO lines for AR724[12] The AR724[12] SoCs have more GPIO lines than the AR7240. Signed-off-by: Gabor Juhos Cc: Cc: linux-mips@linux-mips.org Patchwork: https://http://patchwork.linux-mips.org/patch/4167/ Signed-off-by: Ralf Baechle --- arch/mips/ath79/gpio.c | 6 ++++-- arch/mips/include/asm/mach-ath79/ar71xx_regs.h | 3 ++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/mips/ath79/gpio.c b/arch/mips/ath79/gpio.c index 29054f211832..48fe762d2526 100644 --- a/arch/mips/ath79/gpio.c +++ b/arch/mips/ath79/gpio.c @@ -188,8 +188,10 @@ void __init ath79_gpio_init(void) if (soc_is_ar71xx()) ath79_gpio_count = AR71XX_GPIO_COUNT; - else if (soc_is_ar724x()) - ath79_gpio_count = AR724X_GPIO_COUNT; + else if (soc_is_ar7240()) + ath79_gpio_count = AR7240_GPIO_COUNT; + else if (soc_is_ar7241() || soc_is_ar7242()) + ath79_gpio_count = AR7241_GPIO_COUNT; else if (soc_is_ar913x()) ath79_gpio_count = AR913X_GPIO_COUNT; else if (soc_is_ar933x()) diff --git a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h index 1caa78ad06d5..dde504477fac 100644 --- a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h +++ b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h @@ -393,7 +393,8 @@ #define AR71XX_GPIO_REG_FUNC 0x28 #define AR71XX_GPIO_COUNT 16 -#define AR724X_GPIO_COUNT 18 +#define AR7240_GPIO_COUNT 18 +#define AR7241_GPIO_COUNT 20 #define AR913X_GPIO_COUNT 22 #define AR933X_GPIO_COUNT 30 #define AR934X_GPIO_COUNT 23 From 5fb234560eb3033b35812cd0d80613dbf37dca2f Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Sat, 4 Aug 2012 18:01:25 +0200 Subject: [PATCH 071/208] MIPS: ath79: Use correct IRQ number for the OHCI controller on AR7240 The currently assigned IRQ number to the OHCI controller is incorrect for the AR7240 SoC, and that leads to the following error message from the OHCI driver: ohci_hcd: USB 1.1 'Open' Host Controller (OHCI) Driver ath79-ohci ath79-ohci: Atheros built-in OHCI controller ath79-ohci ath79-ohci: new USB bus registered, assigned bus number 1 ath79-ohci ath79-ohci: irq 14, io mem 0x1b000000 hub 1-0:1.0: USB hub found hub 1-0:1.0: 1 port detected usb 1-1: new full-speed USB device number 2 using ath79-ohci ath79-ohci ath79-ohci: Unlink after no-IRQ? Controller is probably using the wrong IRQ. Fix this by using the correct IRQ number. Signed-off-by: Gabor Juhos Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/4168/ Signed-off-by: Ralf Baechle --- arch/mips/ath79/dev-usb.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/ath79/dev-usb.c b/arch/mips/ath79/dev-usb.c index 36e9570e7bc4..b2a2311ec85b 100644 --- a/arch/mips/ath79/dev-usb.c +++ b/arch/mips/ath79/dev-usb.c @@ -145,6 +145,8 @@ static void __init ar7240_usb_setup(void) ath79_ohci_resources[0].start = AR7240_OHCI_BASE; ath79_ohci_resources[0].end = AR7240_OHCI_BASE + AR7240_OHCI_SIZE - 1; + ath79_ohci_resources[1].start = ATH79_CPU_IRQ_USB; + ath79_ohci_resources[1].end = ATH79_CPU_IRQ_USB; platform_device_register(&ath79_ohci_device); } From 946380676396e633878d07ecb23c9144fbb44abc Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Sat, 4 Aug 2012 18:01:26 +0200 Subject: [PATCH 072/208] MIPS: ath79: select HAVE_CLK It is needed in order to get rid of the following errors: arch/mips/ath79/clock.c:353:13: error: redefinition of 'clk_get' include/linux/clk.h:281:27: note: previous definition of 'clk_get' was here arch/mips/ath79/clock.c:377:5: error: redefinition of 'clk_enable' include/linux/clk.h:295:19: note: previous definition of 'clk_enable' was here arch/mips/ath79/clock.c:383:6: error: redefinition of 'clk_disable' include/linux/clk.h:300:20: note: previous definition of 'clk_disable' was here arch/mips/ath79/clock.c:388:15: error: redefinition of 'clk_get_rate' include/linux/clk.h:302:29: note: previous definition of 'clk_get_rate' was here arch/mips/ath79/clock.c:394:6: error: redefinition of 'clk_put' include/linux/clk.h:291:20: note: previous definition of 'clk_put' was here Signed-off-by: Gabor Juhos Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/4170/ Signed-off-by: Ralf Baechle --- arch/mips/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 331d574df99c..faf65286574e 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -89,6 +89,7 @@ config ATH79 select CEVT_R4K select CSRC_R4K select DMA_NONCOHERENT + select HAVE_CLK select IRQ_CPU select MIPS_MACHINE select SYS_HAS_CPU_MIPS32_R2 From 143ec74eb10ac9a8c4357341a03b07ac4f04a761 Mon Sep 17 00:00:00 2001 From: Bruno Randolf Date: Thu, 12 Jul 2012 21:54:05 +0100 Subject: [PATCH 073/208] MIPS: MTX-1: Add udelay to mtx1_pci_idsel Without this udelay(1) PCI idsel does not work correctly on the "singleboard" (T-Mobile Surfbox) for the MiniPCI device. The result is that PCI configuration fails and the MiniPCI card is not detected correctly. Instead of PCI host bridge to bus 0000:00 pci_bus 0000:00: root bus resource [mem 0x40000000-0x4fffffff] pci_bus 0000:00: root bus resource [io 0x1000-0xffff] pci 0000:00:03.0: BAR 0: assigned [mem 0x40000000-0x4000ffff] pci 0000:00:00.0: BAR 0: assigned [mem 0x40010000-0x40010fff] pci 0000:00:00.1: BAR 0: assigned [mem 0x40011000-0x40011fff] We see only the CardBus device: PCI host bridge to bus 0000:00 pci_bus 0000:00: root bus resource [mem 0x40000000-0x4fffffff] pci_bus 0000:00: root bus resource [io 0x1000-0xffff] pci 0000:00:00.0: BAR 0: assigned [mem 0x40000000-0x40000fff] pci 0000:00:00.1: BAR 0: assigned [mem 0x40001000-0x40001fff] Later the device driver shows this error: ath5k 0000:00:03.0: cannot remap PCI memory region ath5k: probe of 0000:00:03.0 failed with error -5 I assume that the logic chip which usually supresses the signal to the CardBus card has some settling time and without the delay it would still let the Cardbus interfere with the response from the MiniPCI card. What I cannot explain is why this behaviour shows up now and not in earlier kernel versions before. Maybe older PCI code was slower? Signed-off-by: Bruno Randolf Cc: linux-mips@linux-mips.org Cc: manuel.lauss@googlemail.com Cc: florian@openwrt.org Patchwork: https://patchwork.linux-mips.org/patch/4087/ Signed-off-by: Ralf Baechle --- arch/mips/alchemy/board-mtx1.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c index 99969484c475..a124c251c0c9 100644 --- a/arch/mips/alchemy/board-mtx1.c +++ b/arch/mips/alchemy/board-mtx1.c @@ -228,6 +228,8 @@ static int mtx1_pci_idsel(unsigned int devsel, int assert) * adapter on the mtx-1 "singleboard" variant. It triggers a custom * logic chip connected to EXT_IO3 (GPIO1) to suppress IDSEL signals. */ + udelay(1); + if (assert && devsel != 0) /* Suppress signal to Cardbus */ alchemy_gpio_set_value(1, 0); /* set EXT_IO3 OFF */ From d3cac35cd0a2a987f7559e1829fb0253cea33872 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 8 Aug 2012 14:57:03 +0200 Subject: [PATCH 074/208] MIPS: Fix memory leak in error path of HI16/LO16 relocation handling. Commit 6f5d2e970452b5c86906adcb8e7ad246f535ba39 (lmo) / 477c4b07406357ad93d0e32788dbf3ee814eadaa (kernel.org) [[MIPS: VPE: Free relocation chain on error.] fixed the same issue in the vpe loader in 2009 but back then the same bug in module.c went unfixed. Signed-off-by: Ralf Baechle Reported-by: Akhilesh Kumar --- arch/mips/kernel/module.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index a5066b1c3de3..e5f2f56524ea 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -146,16 +146,15 @@ static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) { unsigned long insnlo = *location; Elf_Addr val, vallo; + struct mips_hi16 *l, *next; /* Sign extend the addend we extract from the lo insn. */ vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000; if (mips_hi16_list != NULL) { - struct mips_hi16 *l; l = mips_hi16_list; while (l != NULL) { - struct mips_hi16 *next; unsigned long insn; /* @@ -201,6 +200,12 @@ static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) return 0; out_danger: + while (l) { + next = l->next; + kfree(l); + l = next; + } + pr_err("module %s: dangerous R_MIPS_LO16 REL relocation\n", me->name); return -ENOEXEC; From 861667dc82f561e65336ea67f73021b782b4ff74 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Wed, 8 Aug 2012 16:59:43 +0200 Subject: [PATCH 075/208] MIPS: Fix race condition in module relocation code. The relocation code was essentially taken from the 2.4 modutils which perform relocation in userspace. In 2.6 relocation of multiple modules may be performed in parallel by the in-kernel loader so the global variable mips_hi16_list won't fly anymore. Fix race by moving it into mod_arch_specific. [ralf@linux-mips.org: folded in Tony's followup fix. Thanks Tony!] Signed-off-by: Ralf Baechle Signed-off-by: Tony Wu Cc: linux-mips@linux-mips.org Patchwork: http://patchwork.linux-mips.org/patch/4189/ --- arch/mips/include/asm/module.h | 1 + arch/mips/kernel/module.c | 13 ++++++------- 2 files changed, 7 insertions(+), 7 deletions(-) diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h index 7531ecd654d6..dca8bce8c7ab 100644 --- a/arch/mips/include/asm/module.h +++ b/arch/mips/include/asm/module.h @@ -10,6 +10,7 @@ struct mod_arch_specific { struct list_head dbe_list; const struct exception_table_entry *dbe_start; const struct exception_table_entry *dbe_end; + struct mips_hi16 *r_mips_hi16_list; }; typedef uint8_t Elf64_Byte; /* Type for a 8-bit quantity. */ diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index e5f2f56524ea..8e1fb802c3e2 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -39,8 +39,6 @@ struct mips_hi16 { Elf_Addr value; }; -static struct mips_hi16 *mips_hi16_list; - static LIST_HEAD(dbe_list); static DEFINE_SPINLOCK(dbe_lock); @@ -128,8 +126,8 @@ static int apply_r_mips_hi16_rel(struct module *me, u32 *location, Elf_Addr v) n->addr = (Elf_Addr *)location; n->value = v; - n->next = mips_hi16_list; - mips_hi16_list = n; + n->next = me->arch.r_mips_hi16_list; + me->arch.r_mips_hi16_list = n; return 0; } @@ -151,9 +149,9 @@ static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) /* Sign extend the addend we extract from the lo insn. */ vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000; - if (mips_hi16_list != NULL) { + if (me->arch.r_mips_hi16_list != NULL) { - l = mips_hi16_list; + l = me->arch.r_mips_hi16_list; while (l != NULL) { unsigned long insn; @@ -187,7 +185,7 @@ static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) l = next; } - mips_hi16_list = NULL; + me->arch.r_mips_hi16_list = NULL; } /* @@ -278,6 +276,7 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, pr_debug("Applying relocate section %u to %u\n", relsec, sechdrs[relsec].sh_info); + me->arch.r_mips_hi16_list = NULL; for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) { /* This is where to make the change */ location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr From c54de490a2e4e74164f747925ff05c00dfa153cd Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Tue, 14 Aug 2012 00:34:18 +0200 Subject: [PATCH 076/208] MIPS: Module: Deal with malformed HI16/LO16 relocation sequences. In case a series of R_MIPS_HI16 relocations was not followed by an R_MIPS_LO16 relocation we were leaking the hi16 relocation chain. Handle that error and return an error. Signed-off-by: Ralf Baechle --- arch/mips/kernel/module.c | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index 8e1fb802c3e2..4f8c3cba8c0c 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -140,19 +140,30 @@ static int apply_r_mips_hi16_rela(struct module *me, u32 *location, Elf_Addr v) return 0; } +static void free_relocation_chain(struct mips_hi16 *l) +{ + struct mips_hi16 *next; + + while (l) { + next = l->next; + kfree(l); + l = next; + } +} + static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) { unsigned long insnlo = *location; + struct mips_hi16 *l; Elf_Addr val, vallo; - struct mips_hi16 *l, *next; /* Sign extend the addend we extract from the lo insn. */ vallo = ((insnlo & 0xffff) ^ 0x8000) - 0x8000; if (me->arch.r_mips_hi16_list != NULL) { - l = me->arch.r_mips_hi16_list; while (l != NULL) { + struct mips_hi16 *next; unsigned long insn; /* @@ -198,11 +209,8 @@ static int apply_r_mips_lo16_rel(struct module *me, u32 *location, Elf_Addr v) return 0; out_danger: - while (l) { - next = l->next; - kfree(l); - l = next; - } + free_relocation_chain(l); + me->arch.r_mips_hi16_list = NULL; pr_err("module %s: dangerous R_MIPS_LO16 REL relocation\n", me->name); @@ -300,6 +308,19 @@ int apply_relocate(Elf_Shdr *sechdrs, const char *strtab, return res; } + /* + * Normally the hi16 list should be deallocated at this point. A + * malformed binary however could contain a series of R_MIPS_HI16 + * relocations not followed by a R_MIPS_LO16 relocation. In that + * case, free up the list and return an error. + */ + if (me->arch.r_mips_hi16_list) { + free_relocation_chain(me->arch.r_mips_hi16_list); + me->arch.r_mips_hi16_list = NULL; + + return -ENOEXEC; + } + return 0; } From 5a6704454a68ab6e27e4fc5b82818a8c5733bf29 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 18 Jun 2012 12:07:51 +0200 Subject: [PATCH 077/208] MIPS: BCM63xx: Fix SPI message control register handling for BCM6338/6348. BCM6338 and BCM6348 have a message control register width of 8 bits, instead of 16-bits like what the SPI driver assumes right now. Also the SPI message type shift value of 14 is actually 6 for these SoCs. This resulted in transmit FIFO corruption because we were writing 16-bits to an 8-bits wide register, thus spanning on the first byte of the transmit FIFO, which had already been filed in bcm63xx_spi_fill_txrx_fifo(). Fix this by passing the message control register width and message type shift through platform data back to the SPI driver so that it can use it properly. Signed-off-by: Florian Fainelli Cc: linux-mips@linux-mips.org Cc: grant.likely@secretlab.ca Cc: spi-devel-general@lists.sourceforge.net Cc: jonas.gorski@gmail.com Patchwork: https://patchwork.linux-mips.org/patch/3983/ Signed-off-by: Ralf Baechle --- arch/mips/bcm63xx/dev-spi.c | 4 +++ .../asm/mach-bcm63xx/bcm63xx_dev_spi.h | 2 ++ .../include/asm/mach-bcm63xx/bcm63xx_regs.h | 13 +++++++-- drivers/spi/spi-bcm63xx.c | 29 ++++++++++++++++--- 4 files changed, 41 insertions(+), 7 deletions(-) diff --git a/arch/mips/bcm63xx/dev-spi.c b/arch/mips/bcm63xx/dev-spi.c index e39f73048d4f..f1c9c3e2f678 100644 --- a/arch/mips/bcm63xx/dev-spi.c +++ b/arch/mips/bcm63xx/dev-spi.c @@ -106,11 +106,15 @@ int __init bcm63xx_spi_register(void) if (BCMCPU_IS_6338() || BCMCPU_IS_6348()) { spi_resources[0].end += BCM_6338_RSET_SPI_SIZE - 1; spi_pdata.fifo_size = SPI_6338_MSG_DATA_SIZE; + spi_pdata.msg_type_shift = SPI_6338_MSG_TYPE_SHIFT; + spi_pdata.msg_ctl_width = SPI_6338_MSG_CTL_WIDTH; } if (BCMCPU_IS_6358() || BCMCPU_IS_6368()) { spi_resources[0].end += BCM_6358_RSET_SPI_SIZE - 1; spi_pdata.fifo_size = SPI_6358_MSG_DATA_SIZE; + spi_pdata.msg_type_shift = SPI_6358_MSG_TYPE_SHIFT; + spi_pdata.msg_ctl_width = SPI_6358_MSG_CTL_WIDTH; } bcm63xx_spi_regs_init(); diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h index 7d98dbe5d4b5..c9bae1362606 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h @@ -9,6 +9,8 @@ int __init bcm63xx_spi_register(void); struct bcm63xx_spi_pdata { unsigned int fifo_size; + unsigned int msg_type_shift; + unsigned int msg_ctl_width; int bus_num; int num_chipselect; u32 speed_hz; diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h index 4ccc2a748aff..61f2a2a5099d 100644 --- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h +++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h @@ -1054,7 +1054,8 @@ #define SPI_6338_FILL_BYTE 0x07 #define SPI_6338_MSG_TAIL 0x09 #define SPI_6338_RX_TAIL 0x0b -#define SPI_6338_MSG_CTL 0x40 +#define SPI_6338_MSG_CTL 0x40 /* 8-bits register */ +#define SPI_6338_MSG_CTL_WIDTH 8 #define SPI_6338_MSG_DATA 0x41 #define SPI_6338_MSG_DATA_SIZE 0x3f #define SPI_6338_RX_DATA 0x80 @@ -1070,7 +1071,8 @@ #define SPI_6348_FILL_BYTE 0x07 #define SPI_6348_MSG_TAIL 0x09 #define SPI_6348_RX_TAIL 0x0b -#define SPI_6348_MSG_CTL 0x40 +#define SPI_6348_MSG_CTL 0x40 /* 8-bits register */ +#define SPI_6348_MSG_CTL_WIDTH 8 #define SPI_6348_MSG_DATA 0x41 #define SPI_6348_MSG_DATA_SIZE 0x3f #define SPI_6348_RX_DATA 0x80 @@ -1078,6 +1080,7 @@ /* BCM 6358 SPI core */ #define SPI_6358_MSG_CTL 0x00 /* 16-bits register */ +#define SPI_6358_MSG_CTL_WIDTH 16 #define SPI_6358_MSG_DATA 0x02 #define SPI_6358_MSG_DATA_SIZE 0x21e #define SPI_6358_RX_DATA 0x400 @@ -1094,6 +1097,7 @@ /* BCM 6358 SPI core */ #define SPI_6368_MSG_CTL 0x00 /* 16-bits register */ +#define SPI_6368_MSG_CTL_WIDTH 16 #define SPI_6368_MSG_DATA 0x02 #define SPI_6368_MSG_DATA_SIZE 0x21e #define SPI_6368_RX_DATA 0x400 @@ -1115,7 +1119,10 @@ #define SPI_HD_W 0x01 #define SPI_HD_R 0x02 #define SPI_BYTE_CNT_SHIFT 0 -#define SPI_MSG_TYPE_SHIFT 14 +#define SPI_6338_MSG_TYPE_SHIFT 6 +#define SPI_6348_MSG_TYPE_SHIFT 6 +#define SPI_6358_MSG_TYPE_SHIFT 14 +#define SPI_6368_MSG_TYPE_SHIFT 14 /* Command */ #define SPI_CMD_NOOP 0x00 diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c index 6e25ef1bce91..b7d61e7b8737 100644 --- a/drivers/spi/spi-bcm63xx.c +++ b/drivers/spi/spi-bcm63xx.c @@ -47,6 +47,8 @@ struct bcm63xx_spi { /* Platform data */ u32 speed_hz; unsigned fifo_size; + unsigned int msg_type_shift; + unsigned int msg_ctl_width; /* Data buffers */ const unsigned char *tx_ptr; @@ -221,13 +223,20 @@ static unsigned int bcm63xx_txrx_bufs(struct spi_device *spi, msg_ctl = (t->len << SPI_BYTE_CNT_SHIFT); if (t->rx_buf && t->tx_buf) - msg_ctl |= (SPI_FD_RW << SPI_MSG_TYPE_SHIFT); + msg_ctl |= (SPI_FD_RW << bs->msg_type_shift); else if (t->rx_buf) - msg_ctl |= (SPI_HD_R << SPI_MSG_TYPE_SHIFT); + msg_ctl |= (SPI_HD_R << bs->msg_type_shift); else if (t->tx_buf) - msg_ctl |= (SPI_HD_W << SPI_MSG_TYPE_SHIFT); + msg_ctl |= (SPI_HD_W << bs->msg_type_shift); - bcm_spi_writew(bs, msg_ctl, SPI_MSG_CTL); + switch (bs->msg_ctl_width) { + case 8: + bcm_spi_writeb(bs, msg_ctl, SPI_MSG_CTL); + break; + case 16: + bcm_spi_writew(bs, msg_ctl, SPI_MSG_CTL); + break; + } /* Issue the transfer */ cmd = SPI_CMD_START_IMMEDIATE; @@ -406,9 +415,21 @@ static int __devinit bcm63xx_spi_probe(struct platform_device *pdev) master->transfer_one_message = bcm63xx_spi_transfer_one; master->mode_bits = MODEBITS; bs->speed_hz = pdata->speed_hz; + bs->msg_type_shift = pdata->msg_type_shift; + bs->msg_ctl_width = pdata->msg_ctl_width; bs->tx_io = (u8 *)(bs->regs + bcm63xx_spireg(SPI_MSG_DATA)); bs->rx_io = (const u8 *)(bs->regs + bcm63xx_spireg(SPI_RX_DATA)); + switch (bs->msg_ctl_width) { + case 8: + case 16: + break; + default: + dev_err(dev, "unsupported MSG_CTL width: %d\n", + bs->msg_ctl_width); + goto out_clk_disable; + } + /* Initialize hardware */ clk_enable(bs->clk); bcm_spi_writeb(bs, SPI_INTR_CLEAR_ALL, SPI_INT_STATUS); From cf9bfe55f24973a8f40e2c922a7e82cf09e486fd Mon Sep 17 00:00:00 2001 From: Jayachandran C Date: Tue, 14 Aug 2012 18:56:13 +0530 Subject: [PATCH 078/208] MIPS: Synchronize MIPS count one CPU at a time The current implementation of synchronise_count_{master,slave} blocks slave CPUs in early boot until all of them come up. This no longer works because blocking a CPU with interrupts off after notifying the CPU to be online causes problems with the current kernel. Specifically, after the workqueue changes (commit a08489c569dc1 "Pull workqueue changes from Tejun Heo") the CPU_ONLINE notification callback workqueue_cpu_up_callback() will hang on wait_for_completion(&idle_rebind.done), if the slave CPUs are blocked for synchronize_count_slave(). The changes are to update synchronize_count_{master,slave}() to handle one CPU at a time and to call synchronise_count_master() in __cpu_up() so that the CPU_ONLINE notification goes out only after the COP0 COUNT register is synchronized. [ralf@linux-mips.org: This matter only to those few platforms which are using the cp0 counter as their clocksource which are XLP, XLR and MIPS' CMP solution.] Signed-off-by: Jayachandran C Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/4216/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/r4k-timer.h | 8 ++++---- arch/mips/kernel/smp.c | 4 ++-- arch/mips/kernel/sync-r4k.c | 26 +++++++++++--------------- 3 files changed, 17 insertions(+), 21 deletions(-) diff --git a/arch/mips/include/asm/r4k-timer.h b/arch/mips/include/asm/r4k-timer.h index a37d12b3b61c..afe9e0e03fe9 100644 --- a/arch/mips/include/asm/r4k-timer.h +++ b/arch/mips/include/asm/r4k-timer.h @@ -12,16 +12,16 @@ #ifdef CONFIG_SYNC_R4K -extern void synchronise_count_master(void); -extern void synchronise_count_slave(void); +extern void synchronise_count_master(int cpu); +extern void synchronise_count_slave(int cpu); #else -static inline void synchronise_count_master(void) +static inline void synchronise_count_master(int cpu) { } -static inline void synchronise_count_slave(void) +static inline void synchronise_count_slave(int cpu) { } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 31637d8c8738..9005bf9fb859 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -130,7 +130,7 @@ asmlinkage __cpuinit void start_secondary(void) cpu_set(cpu, cpu_callin_map); - synchronise_count_slave(); + synchronise_count_slave(cpu); /* * irq will be enabled in ->smp_finish(), enabling it too early @@ -173,7 +173,6 @@ void smp_send_stop(void) void __init smp_cpus_done(unsigned int max_cpus) { mp_ops->cpus_done(); - synchronise_count_master(); } /* called from main before smp_init() */ @@ -206,6 +205,7 @@ int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle) while (!cpu_isset(cpu, cpu_callin_map)) udelay(100); + synchronise_count_master(cpu); return 0; } diff --git a/arch/mips/kernel/sync-r4k.c b/arch/mips/kernel/sync-r4k.c index 842d55e411fd..7f1eca3858de 100644 --- a/arch/mips/kernel/sync-r4k.c +++ b/arch/mips/kernel/sync-r4k.c @@ -28,12 +28,11 @@ static atomic_t __cpuinitdata count_reference = ATOMIC_INIT(0); #define COUNTON 100 #define NR_LOOPS 5 -void __cpuinit synchronise_count_master(void) +void __cpuinit synchronise_count_master(int cpu) { int i; unsigned long flags; unsigned int initcount; - int nslaves; #ifdef CONFIG_MIPS_MT_SMTC /* @@ -43,8 +42,7 @@ void __cpuinit synchronise_count_master(void) return; #endif - printk(KERN_INFO "Synchronize counters across %u CPUs: ", - num_online_cpus()); + printk(KERN_INFO "Synchronize counters for CPU %u: ", cpu); local_irq_save(flags); @@ -52,7 +50,7 @@ void __cpuinit synchronise_count_master(void) * Notify the slaves that it's time to start */ atomic_set(&count_reference, read_c0_count()); - atomic_set(&count_start_flag, 1); + atomic_set(&count_start_flag, cpu); smp_wmb(); /* Count will be initialised to current timer for all CPU's */ @@ -69,10 +67,9 @@ void __cpuinit synchronise_count_master(void) * two CPUs. */ - nslaves = num_online_cpus()-1; for (i = 0; i < NR_LOOPS; i++) { - /* slaves loop on '!= ncpus' */ - while (atomic_read(&count_count_start) != nslaves) + /* slaves loop on '!= 2' */ + while (atomic_read(&count_count_start) != 1) mb(); atomic_set(&count_count_stop, 0); smp_wmb(); @@ -89,7 +86,7 @@ void __cpuinit synchronise_count_master(void) /* * Wait for all slaves to leave the synchronization point: */ - while (atomic_read(&count_count_stop) != nslaves) + while (atomic_read(&count_count_stop) != 1) mb(); atomic_set(&count_count_start, 0); smp_wmb(); @@ -97,6 +94,7 @@ void __cpuinit synchronise_count_master(void) } /* Arrange for an interrupt in a short while */ write_c0_compare(read_c0_count() + COUNTON); + atomic_set(&count_start_flag, 0); local_irq_restore(flags); @@ -108,11 +106,10 @@ void __cpuinit synchronise_count_master(void) printk("done.\n"); } -void __cpuinit synchronise_count_slave(void) +void __cpuinit synchronise_count_slave(int cpu) { int i; unsigned int initcount; - int ncpus; #ifdef CONFIG_MIPS_MT_SMTC /* @@ -127,16 +124,15 @@ void __cpuinit synchronise_count_slave(void) * so we first wait for the master to say everyone is ready */ - while (!atomic_read(&count_start_flag)) + while (atomic_read(&count_start_flag) != cpu) mb(); /* Count will be initialised to next expire for all CPU's */ initcount = atomic_read(&count_reference); - ncpus = num_online_cpus(); for (i = 0; i < NR_LOOPS; i++) { atomic_inc(&count_count_start); - while (atomic_read(&count_count_start) != ncpus) + while (atomic_read(&count_count_start) != 2) mb(); /* @@ -146,7 +142,7 @@ void __cpuinit synchronise_count_slave(void) write_c0_count(initcount); atomic_inc(&count_count_stop); - while (atomic_read(&count_count_stop) != ncpus) + while (atomic_read(&count_count_stop) != 2) mb(); } /* Arrange for an interrupt in a short while */ From 00dc5ce2a653a332190aa29b2e1f3bceaa7d5b8d Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Tue, 14 Aug 2012 21:12:21 +0200 Subject: [PATCH 079/208] MIPS: ath79: don't hardcode the unavailability of the DSP ASE The ath79 platform code allows to run a single kernel image on various SoCs which are based on the 24Kc and 74Kc cores. The current code explicitely disables the DSP ASE, but that is available in the 74Kc core. Remove the override in order to let the kernel to detect the availability of the DSP ASE at runtime. Signed-off-by: Gabor Juhos Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/4222/ Signed-off-by: Ralf Baechle --- arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h index 4476fa03bf36..6ddae926bf79 100644 --- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h +++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h @@ -42,7 +42,6 @@ #define cpu_has_mips64r1 0 #define cpu_has_mips64r2 0 -#define cpu_has_dsp 0 #define cpu_has_mipsmt 0 #define cpu_has_64bits 0 From 16cc2cf642eb73978a3ebde66dc94d24d46b4798 Mon Sep 17 00:00:00 2001 From: Ralf Baechle Date: Fri, 17 Aug 2012 10:45:27 +0200 Subject: [PATCH 080/208] MIPS: Malta: Delete duplicate PCI fixup. 2ec8663f9c03a96f2c328c7c483603c31d62ad37 (lmo) rsp. 497e5ff03f58583ada469db8a1aa34eced9dd63e (kernel.org) [MIPS: Malta: Move PIIX4 PCI fixup to where it belongs.] attempted to move this PCI fixup but really only added it at it's new location without deleting the old instance. Signed-off-by: Ralf Baechle --- arch/mips/mti-malta/malta-pci.c | 13 ------------- 1 file changed, 13 deletions(-) diff --git a/arch/mips/mti-malta/malta-pci.c b/arch/mips/mti-malta/malta-pci.c index 284dea54faf5..2147cb34e705 100644 --- a/arch/mips/mti-malta/malta-pci.c +++ b/arch/mips/mti-malta/malta-pci.c @@ -252,16 +252,3 @@ void __init mips_pcibios_init(void) register_pci_controller(controller); } - -/* Enable PCI 2.1 compatibility in PIIX4 */ -static void __devinit quirk_dlcsetup(struct pci_dev *dev) -{ - u8 odlc, ndlc; - (void) pci_read_config_byte(dev, 0x82, &odlc); - /* Enable passive releases and delayed transaction */ - ndlc = odlc | 7; - (void) pci_write_config_byte(dev, 0x82, ndlc); -} - -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0, - quirk_dlcsetup); From 97f50c6c415d84c612094d9514a3df3d70ab30e3 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 9 Aug 2012 16:47:27 +0100 Subject: [PATCH 081/208] ARM: ux500: Fix merge error, no matching driver name for 'snd_soc_u8500' The platform attempts to register platform device 'snd_soc_u8500' which doesn't actually exist. Here we change the reference to the correct one 'snd_soc_mop500'. Signed-off-by: Lee Jones Signed-off-by: Linus Walleij --- arch/arm/mach-ux500/board-mop500-msp.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm/mach-ux500/board-mop500-msp.c b/arch/arm/mach-ux500/board-mop500-msp.c index 996048038743..df15646036aa 100644 --- a/arch/arm/mach-ux500/board-mop500-msp.c +++ b/arch/arm/mach-ux500/board-mop500-msp.c @@ -191,9 +191,9 @@ static struct platform_device *db8500_add_msp_i2s(struct device *parent, return pdev; } -/* Platform device for ASoC U8500 machine */ -static struct platform_device snd_soc_u8500 = { - .name = "snd-soc-u8500", +/* Platform device for ASoC MOP500 machine */ +static struct platform_device snd_soc_mop500 = { + .name = "snd-soc-mop500", .id = 0, .dev = { .platform_data = NULL, @@ -227,8 +227,8 @@ int mop500_msp_init(struct device *parent) { struct platform_device *msp1; - pr_info("%s: Register platform-device 'snd-soc-u8500'.\n", __func__); - platform_device_register(&snd_soc_u8500); + pr_info("%s: Register platform-device 'snd-soc-mop500'.\n", __func__); + platform_device_register(&snd_soc_mop500); pr_info("Initialize MSP I2S-devices.\n"); db8500_add_msp_i2s(parent, 0, U8500_MSP0_BASE, IRQ_DB8500_MSP0, From 46a8b9837da20206c6daca11949485fab7b6e875 Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Thu, 9 Aug 2012 16:47:28 +0100 Subject: [PATCH 082/208] ARM: ux500: Ensure probing of Audio devices when Device Tree is enabled Previous attempts to add platform probing of the Audio related devices only call from non-DT initialisation functions. This patch extends that functionality to the Device Tree related ones too. Signed-off-by: Lee Jones Signed-off-by: Linus Walleij --- arch/arm/mach-ux500/board-mop500.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c index 8674a890fd1c..a534d8880de1 100644 --- a/arch/arm/mach-ux500/board-mop500.c +++ b/arch/arm/mach-ux500/board-mop500.c @@ -797,6 +797,7 @@ static void __init u8500_init_machine(void) ARRAY_SIZE(mop500_platform_devs)); mop500_sdi_init(parent); + mop500_msp_init(parent); i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices); i2c_register_board_info(0, mop500_i2c0_devices, i2c0_devs); i2c_register_board_info(2, mop500_i2c2_devices, @@ -804,6 +805,8 @@ static void __init u8500_init_machine(void) mop500_uib_init(); + } else if (of_machine_is_compatible("calaosystems,snowball-a9500")) { + mop500_msp_init(parent); } else if (of_machine_is_compatible("st-ericsson,hrefv60+")) { /* * The HREFv60 board removed a GPIO expander and routed @@ -815,6 +818,7 @@ static void __init u8500_init_machine(void) ARRAY_SIZE(mop500_platform_devs)); hrefv60_sdi_init(parent); + mop500_msp_init(parent); i2c0_devs = ARRAY_SIZE(mop500_i2c0_devices); i2c0_devs -= NUM_PRE_V60_I2C0_DEVICES; From 250a41e0ecc433cdd553a364d0fc74c766425209 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 17 Aug 2012 09:27:35 -0400 Subject: [PATCH 083/208] xen/p2m: Reuse existing P2M leafs if they are filled with 1:1 PFNs or INVALID. If P2M leaf is completly packed with INVALID_P2M_ENTRY or with 1:1 PFNs (so IDENTITY_FRAME type PFNs), we can swap the P2M leaf with either a p2m_missing or p2m_identity respectively. The old page (which was created via extend_brk or was grafted on from the mfn_list) can be re-used for setting new PFNs. This also means we can remove git commit: 5bc6f9888db5739abfa0cae279b4b442e4db8049 xen/p2m: Reserve 8MB of _brk space for P2M leafs when populating back which tried to fix this. and make the amount that is required to be reserved much smaller. CC: stable@vger.kernel.org # for 3.5 only. Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/p2m.c | 95 ++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 92 insertions(+), 3 deletions(-) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b2e91d40a4cb..d4b255463253 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -196,9 +196,11 @@ RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); /* When we populate back during bootup, the amount of pages can vary. The * max we have is seen is 395979, but that does not mean it can't be more. - * But some machines can have 3GB I/O holes even. So lets reserve enough - * for 4GB of I/O and E820 holes. */ -RESERVE_BRK(p2m_populated, PMD_SIZE * 4); + * Some machines can have 3GB I/O holes even. With early_can_reuse_p2m_middle + * it can re-use Xen provided mfn_list array, so we only need to allocate at + * most three P2M top nodes. */ +RESERVE_BRK(p2m_populated, PAGE_SIZE * 3); + static inline unsigned p2m_top_index(unsigned long pfn) { BUG_ON(pfn >= MAX_P2M_PFN); @@ -575,12 +577,99 @@ static bool __init early_alloc_p2m(unsigned long pfn) } return true; } + +/* + * Skim over the P2M tree looking at pages that are either filled with + * INVALID_P2M_ENTRY or with 1:1 PFNs. If found, re-use that page and + * replace the P2M leaf with a p2m_missing or p2m_identity. + * Stick the old page in the new P2M tree location. + */ +bool __init early_can_reuse_p2m_middle(unsigned long set_pfn, unsigned long set_mfn) +{ + unsigned topidx; + unsigned mididx; + unsigned ident_pfns; + unsigned inv_pfns; + unsigned long *p2m; + unsigned long *mid_mfn_p; + unsigned idx; + unsigned long pfn; + + /* We only look when this entails a P2M middle layer */ + if (p2m_index(set_pfn)) + return false; + + for (pfn = 0; pfn <= MAX_DOMAIN_PAGES; pfn += P2M_PER_PAGE) { + topidx = p2m_top_index(pfn); + + if (!p2m_top[topidx]) + continue; + + if (p2m_top[topidx] == p2m_mid_missing) + continue; + + mididx = p2m_mid_index(pfn); + p2m = p2m_top[topidx][mididx]; + if (!p2m) + continue; + + if ((p2m == p2m_missing) || (p2m == p2m_identity)) + continue; + + if ((unsigned long)p2m == INVALID_P2M_ENTRY) + continue; + + ident_pfns = 0; + inv_pfns = 0; + for (idx = 0; idx < P2M_PER_PAGE; idx++) { + /* IDENTITY_PFNs are 1:1 */ + if (p2m[idx] == IDENTITY_FRAME(pfn + idx)) + ident_pfns++; + else if (p2m[idx] == INVALID_P2M_ENTRY) + inv_pfns++; + else + break; + } + if ((ident_pfns == P2M_PER_PAGE) || (inv_pfns == P2M_PER_PAGE)) + goto found; + } + return false; +found: + /* Found one, replace old with p2m_identity or p2m_missing */ + p2m_top[topidx][mididx] = (ident_pfns ? p2m_identity : p2m_missing); + /* And the other for save/restore.. */ + mid_mfn_p = p2m_top_mfn_p[topidx]; + /* NOTE: Even if it is a p2m_identity it should still be point to + * a page filled with INVALID_P2M_ENTRY entries. */ + mid_mfn_p[mididx] = virt_to_mfn(p2m_missing); + + /* Reset where we want to stick the old page in. */ + topidx = p2m_top_index(set_pfn); + mididx = p2m_mid_index(set_pfn); + + /* This shouldn't happen */ + if (WARN_ON(p2m_top[topidx] == p2m_mid_missing)) + early_alloc_p2m(set_pfn); + + if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing)) + return false; + + p2m_init(p2m); + p2m_top[topidx][mididx] = p2m; + mid_mfn_p = p2m_top_mfn_p[topidx]; + mid_mfn_p[mididx] = virt_to_mfn(p2m); + + return true; +} bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { if (!early_alloc_p2m(pfn)) return false; + if (early_can_reuse_p2m_middle(pfn, mfn)) + return __set_phys_to_machine(pfn, mfn); + if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/)) return false; From 127c6e731106a2071ee4a6c5a34c471cd3e719f0 Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Tue, 7 Aug 2012 09:59:40 +0800 Subject: [PATCH 084/208] booke/wdt: some ioctls do not return values properly Fix some booke wdt ioctls return value error. Signed-off-by: Tiejun Chen Acked-by: Timur Tabi Signed-off-by: Kumar Gala --- drivers/watchdog/booke_wdt.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/drivers/watchdog/booke_wdt.c b/drivers/watchdog/booke_wdt.c index 3fe82d0e8caa..5b06d31ab6a9 100644 --- a/drivers/watchdog/booke_wdt.c +++ b/drivers/watchdog/booke_wdt.c @@ -166,18 +166,17 @@ static long booke_wdt_ioctl(struct file *file, switch (cmd) { case WDIOC_GETSUPPORT: - if (copy_to_user((void *)arg, &ident, sizeof(ident))) - return -EFAULT; + return copy_to_user(p, &ident, sizeof(ident)) ? -EFAULT : 0; case WDIOC_GETSTATUS: return put_user(0, p); case WDIOC_GETBOOTSTATUS: /* XXX: something is clearing TSR */ tmp = mfspr(SPRN_TSR) & TSR_WRS(3); /* returns CARDRESET if last reset was caused by the WDT */ - return (tmp ? WDIOF_CARDRESET : 0); + return put_user((tmp ? WDIOF_CARDRESET : 0), p); case WDIOC_SETOPTIONS: if (get_user(tmp, p)) - return -EINVAL; + return -EFAULT; if (tmp == WDIOS_ENABLECARD) { booke_wdt_ping(); break; From bbb4ab43f82adf02c8b4d0d7e7b7e79d24204b05 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 17 Aug 2012 09:51:50 -0500 Subject: [PATCH 085/208] ahci: un-staticize ahci_dev_classify Make ahci_dev_classify available to the ahci platform driver for custom hard reset function. Signed-off-by: Rob Herring Signed-off-by: Jeff Garzik --- drivers/ata/ahci.h | 1 + drivers/ata/libahci.c | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index c2594ddf25b0..57eb1c212a4c 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -320,6 +320,7 @@ extern struct device_attribute *ahci_sdev_attrs[]; extern struct ata_port_operations ahci_ops; extern struct ata_port_operations ahci_pmp_retry_srst_ops; +unsigned int ahci_dev_classify(struct ata_port *ap); void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag, u32 opts); void ahci_save_initial_config(struct device *dev, diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index f9eaa82311a9..555c07afa05b 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1139,7 +1139,7 @@ static void ahci_dev_config(struct ata_device *dev) } } -static unsigned int ahci_dev_classify(struct ata_port *ap) +unsigned int ahci_dev_classify(struct ata_port *ap) { void __iomem *port_mmio = ahci_port_base(ap); struct ata_taskfile tf; @@ -1153,6 +1153,7 @@ static unsigned int ahci_dev_classify(struct ata_port *ap) return ata_dev_classify(&tf); } +EXPORT_SYMBOL_GPL(ahci_dev_classify); void ahci_fill_cmd_slot(struct ahci_port_priv *pp, unsigned int tag, u32 opts) From 1117c811a64d948c9f88ee80a0c7f35e9fea1d69 Mon Sep 17 00:00:00 2001 From: Arnd Hannemann Date: Fri, 17 Aug 2012 10:11:15 +0200 Subject: [PATCH 086/208] pata_atiixp: override cable detection on MSI E350DM-E33 The mainboard MSI E350DM-E33 is advertised with 6 SATA ports. As it turns out, two of them seem to be driven by on-board SATA<->PATA converters. If a disk drive is connected to one of them kernel uses UDMA/33 mode due to cable detection: [ 34.550823] scsi4 : pata_atiixp [ 34.555517] scsi5 : pata_atiixp [ 34.555942] ata5: PATA max UDMA/100 cmd 0x1f0 ctl 0x3f6 bmdma 0xf100 irq 14 [ 34.555948] ata6: PATA max UDMA/100 cmd 0x170 ctl 0x376 bmdma 0xf108 irq 15 ... [ 35.040799] ata5.00: ATA-8: WDC WD20EADS-00R6B0, 01.00A01, max UDMA/133 [ 35.040806] ata5.00: 3907029168 sectors, multi 16: LBA48 NCQ (depth 0/32) [ 35.040817] ata5.00: limited to UDMA/33 due to 40-wire cable [ 35.049166] ata5.00: configured for UDMA/33 [ 35.049402] scsi 4:0:0:0: Direct-Access ATA WDC WD20EADS-00R 01.0 PQ: 0 ANSI: 5 This patch forces "short cable" mode on this board, as it seems clear that the on-board SATA<->PATA "cable" is short. With this patch the disk is configured for UDMA/100: [ 5.976756] ata5.00: ATA-8: WDC WD20EADS-00R6B0, 01.00A01, max UDMA/133 [ 5.996434] ata5.00: 3907029168 sectors, multi 16: LBA48 NCQ (depth 0/32) [ 6.024787] ata5.00: configured for UDMA/100 Testing revealed no transfer issues. Signed-off-by: Arnd Hannemann Signed-off-by: Jeff Garzik --- drivers/ata/pata_atiixp.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c index 361c75cea57b..24e51056ac26 100644 --- a/drivers/ata/pata_atiixp.c +++ b/drivers/ata/pata_atiixp.c @@ -20,6 +20,7 @@ #include #include #include +#include #define DRV_NAME "pata_atiixp" #define DRV_VERSION "0.4.6" @@ -33,11 +34,26 @@ enum { ATIIXP_IDE_UDMA_MODE = 0x56 }; +static const struct dmi_system_id attixp_cable_override_dmi_table[] = { + { + /* Board has onboard PATA<->SATA converters */ + .ident = "MSI E350DM-E33", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "MSI"), + DMI_MATCH(DMI_BOARD_NAME, "E350DM-E33(MS-7720)"), + }, + }, + { } +}; + static int atiixp_cable_detect(struct ata_port *ap) { struct pci_dev *pdev = to_pci_dev(ap->host->dev); u8 udma; + if (dmi_check_system(attixp_cable_override_dmi_table)) + return ATA_CBL_PATA40_SHORT; + /* Hack from drivers/ide/pci. Really we want to know how to do the raw detection not play follow the bios mode guess */ pci_read_config_byte(pdev, ATIIXP_IDE_UDMA_MODE + ap->port_no, &udma); From 77b12bc9cf7b10c7c1a04ca45272fbb4287902d0 Mon Sep 17 00:00:00 2001 From: James Ralston Date: Thu, 9 Aug 2012 09:02:31 -0700 Subject: [PATCH 087/208] ahci: Add Device IDs for Intel Lynx Point-LP PCH This patch adds the AHCI-mode SATA Device IDs for the Intel Lynx Point-LP PCH Signed-off-by: James Ralston Signed-off-by: Jeff Garzik --- drivers/ata/ahci.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 062e6a1a248f..50d5dea0ff59 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -256,6 +256,14 @@ static const struct pci_device_id ahci_pci_tbl[] = { { PCI_VDEVICE(INTEL, 0x8c07), board_ahci }, /* Lynx Point RAID */ { PCI_VDEVICE(INTEL, 0x8c0e), board_ahci }, /* Lynx Point RAID */ { PCI_VDEVICE(INTEL, 0x8c0f), board_ahci }, /* Lynx Point RAID */ + { PCI_VDEVICE(INTEL, 0x9c02), board_ahci }, /* Lynx Point-LP AHCI */ + { PCI_VDEVICE(INTEL, 0x9c03), board_ahci }, /* Lynx Point-LP AHCI */ + { PCI_VDEVICE(INTEL, 0x9c04), board_ahci }, /* Lynx Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9c05), board_ahci }, /* Lynx Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9c06), board_ahci }, /* Lynx Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9c07), board_ahci }, /* Lynx Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9c0e), board_ahci }, /* Lynx Point-LP RAID */ + { PCI_VDEVICE(INTEL, 0x9c0f), board_ahci }, /* Lynx Point-LP RAID */ /* JMicron 360/1/3/5/6, match class to avoid IDE function */ { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, From 389cd784969e9148fedcde0608f15bd74d6b769e Mon Sep 17 00:00:00 2001 From: James Ralston Date: Thu, 9 Aug 2012 09:34:20 -0700 Subject: [PATCH 088/208] ata_piix: Add Device IDs for Intel Lynx Point-LP PCH This patch adds the IDE-mode SATA Device IDs for the Intel Lynx Point-LP PCH Signed-off-by: James Ralston Signed-off-by: Jeff Garzik --- drivers/ata/ata_piix.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 3c809bfbccf5..ef773e12af79 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -329,6 +329,14 @@ static const struct pci_device_id piix_pci_tbl[] = { { 0x8086, 0x8c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, /* SATA Controller IDE (Lynx Point) */ { 0x8086, 0x8c09, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + /* SATA Controller IDE (Lynx Point-LP) */ + { 0x8086, 0x9c00, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, + /* SATA Controller IDE (Lynx Point-LP) */ + { 0x8086, 0x9c01, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_sata_snb }, + /* SATA Controller IDE (Lynx Point-LP) */ + { 0x8086, 0x9c08, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, + /* SATA Controller IDE (Lynx Point-LP) */ + { 0x8086, 0x9c09, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, /* SATA Controller IDE (DH89xxCC) */ { 0x8086, 0x2326, PCI_ANY_ID, PCI_ANY_ID, 0, 0, ich8_2port_sata }, { } /* terminate list */ From 834009170986f295c5eca37c76c59f1b28670d69 Mon Sep 17 00:00:00 2001 From: Aaron Lu Date: Wed, 15 Aug 2012 17:08:12 +0800 Subject: [PATCH 089/208] [libata] acpi: call ata_acpi_gtm during ata port init time Commit 30dcf76acc695cbd2fa919e294670fe9552e16e7 mistakenly dropped the code to get an initial gtm for the IDE channel. This caused the following problem for Sergei: http://marc.info/?l=linux-kernel&m=134484963618457&w=2 Fix this by adding the call back in ata_acpi_bind_host, and due to this, the ata_ap_acpi_handle is modified accordingly. Tested-by: Sergei Trofimovich Signed-off-by: Aaron Lu Signed-off-by: Jeff Garzik --- drivers/ata/libata-acpi.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 902b5a457170..fd9ecf74e631 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -60,17 +60,7 @@ acpi_handle ata_ap_acpi_handle(struct ata_port *ap) if (ap->flags & ATA_FLAG_ACPI_SATA) return NULL; - /* - * If acpi bind operation has already happened, we can get the handle - * for the port by checking the corresponding scsi_host device's - * firmware node, otherwise we will need to find out the handle from - * its parent's acpi node. - */ - if (ap->scsi_host) - return DEVICE_ACPI_HANDLE(&ap->scsi_host->shost_gendev); - else - return acpi_get_child(DEVICE_ACPI_HANDLE(ap->host->dev), - ap->port_no); + return acpi_get_child(DEVICE_ACPI_HANDLE(ap->host->dev), ap->port_no); } EXPORT_SYMBOL(ata_ap_acpi_handle); @@ -1101,6 +1091,9 @@ static int ata_acpi_bind_host(struct ata_port *ap, acpi_handle *handle) if (!*handle) return -ENODEV; + if (ata_acpi_gtm(ap, &ap->__acpi_init_gtm) == 0) + ap->pflags |= ATA_PFLAG_INIT_GTM_VALID; + return 0; } From ebd600281566ab40fb2e3004af7eacb3375626d1 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Sun, 12 Aug 2012 23:43:42 +0200 Subject: [PATCH 090/208] [libata] Kconfig: Elaborate that SFF is meant for legacy and PATA stuff MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Building Linux for an ASUS Eee PC 701 4G with ata2.00: CFA: SILICONMOTION SM223AC, , max UDMA/66 ata2.00: 7815024 sectors, multi 0: LBA ata2.00: configured for UDMA/66 scsi 1:0:0:0: Direct-Access ATA SILICONMOTION SM n/a PQ: 0 ANSI: 5 sd 1:0:0:0: [sda] 7815024 512-byte logical blocks: (4.00 GB/3.72 GiB) sd 1:0:0:0: [sda] Write Protect is off sd 1:0:0:0: [sda] Mode Sense: 00 3a 00 00 sd 1:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't support DPO or FUA sda: sda1 sd 1:0:0:0: [sda] Attached SCSI disk sd 1:0:0:0: Attached scsi generic sg0 type 0 I followed the advice to not use the deprecated old PATA subsystem ATA/ATAPI/MFM/RLL support (DEPRECATED) ---> and use the ATA subsystem instead. Serial ATA and Parallel ATA drivers ---> Unfortunately I needed several tries to find out, that I needed the SFF menu I had not selected before because I had never heard that term before. I think it would have helped me, to have PATA or legacy IDE in that item’s name. Signed-off-by: Paul Menzel Signed-off-by: Jeff Garzik --- drivers/ata/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 2be8ef1d3093..27cecd313e75 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -115,7 +115,7 @@ config SATA_SIL24 If unsure, say N. config ATA_SFF - bool "ATA SFF support" + bool "ATA SFF support (for legacy IDE and PATA)" default y help This option adds support for ATA controllers with SFF From 04d0f1b84927169cdaa4e3a24da768a9fd9aca6f Mon Sep 17 00:00:00 2001 From: Jeff Garzik Date: Fri, 17 Aug 2012 13:36:59 -0400 Subject: [PATCH 091/208] [libata] new quirk, lift bridge limits for Buffalo DriveStation Quattro Michael Eitelwein writes: I have an external SATA drive that was slowed down by bridge limits. I found a solution in a thread on this list posted in 2008: It introduces whitelist entries in libata-core.c for devices with well working bridges (e.g. email on Fri, 31 Oct 2008 01:45:27 -0400). I added my device to this whitelist in a custom built kernel and it works fine for weeks now. How can I have this device added on the whitelist within the official kernel? Is this whitelist mechanism still supported or is there a smarter way to achieve whitelisting? I added the following whitelist entry for my Buffalo DriveStation Quattro "BUFFALO HD-QSU2/R5": /* Devices that do not need bridging limits applied */ { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK, }, Reported-by: Michael Eitelwein Signed-off-by: Jeff Garzik --- drivers/ata/libata-core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index fadd5866d40f..5eee1c1537d2 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4128,6 +4128,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Devices that do not need bridging limits applied */ { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, + { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK, }, /* Devices which aren't very happy with higher link speeds */ { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, }, From 60916a9382e88fbf5e54fd36a3e658efd7ab7bed Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 16 Aug 2012 18:14:14 +0100 Subject: [PATCH 092/208] tracing/syscalls: Fix perf syscall tracing when syscall_nr == -1 syscall_get_nr can return -1 in the case that the task is not executing a system call. This patch fixes perf_syscall_{enter,exit} to check that the syscall number is valid before using it as an index into a bitmap. Link: http://lkml.kernel.org/r/1345137254-7377-1-git-send-email-will.deacon@arm.com Cc: Jason Baron Cc: Wade Farnsworth Cc: Frederic Weisbecker Signed-off-by: Will Deacon Signed-off-by: Steven Rostedt --- kernel/trace/trace_syscalls.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 60e4d7875672..6b245f64c8dd 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -506,6 +506,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) int size; syscall_nr = syscall_get_nr(current, regs); + if (syscall_nr < 0) + return; if (!test_bit(syscall_nr, enabled_perf_enter_syscalls)) return; @@ -580,6 +582,8 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) int size; syscall_nr = syscall_get_nr(current, regs); + if (syscall_nr < 0) + return; if (!test_bit(syscall_nr, enabled_perf_exit_syscalls)) return; From ce026cb9cbf1d529652394ea91fb8a459072be91 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Fri, 13 Jul 2012 18:04:23 -0500 Subject: [PATCH 093/208] crypto: caam - fix possible deadlock condition commit "crypto: caam - use non-irq versions of spinlocks for job rings" made two bad assumptions: (a) The caam_jr_enqueue lock isn't used in softirq context. Not true: jr_enqueue can be interrupted by an incoming net interrupt and the received packet may be sent for encryption, via caam_jr_enqueue in softirq context, thereby inducing a deadlock. This is evidenced when running netperf over an IPSec tunnel between two P4080's, with spinlock debugging turned on: [ 892.092569] BUG: spinlock lockup on CPU#7, netperf/10634, e8bf5f70 [ 892.098747] Call Trace: [ 892.101197] [eff9fc10] [c00084c0] show_stack+0x48/0x15c (unreliable) [ 892.107563] [eff9fc50] [c0239c2c] do_raw_spin_lock+0x16c/0x174 [ 892.113399] [eff9fc80] [c0596494] _raw_spin_lock+0x3c/0x50 [ 892.118889] [eff9fc90] [c0445e74] caam_jr_enqueue+0xf8/0x250 [ 892.124550] [eff9fcd0] [c044a644] aead_decrypt+0x6c/0xc8 [ 892.129625] BUG: spinlock lockup on CPU#5, swapper/5/0, e8bf5f70 [ 892.129629] Call Trace: [ 892.129637] [effa7c10] [c00084c0] show_stack+0x48/0x15c (unreliable) [ 892.129645] [effa7c50] [c0239c2c] do_raw_spin_lock+0x16c/0x174 [ 892.129652] [effa7c80] [c0596494] _raw_spin_lock+0x3c/0x50 [ 892.129660] [effa7c90] [c0445e74] caam_jr_enqueue+0xf8/0x250 [ 892.129666] [effa7cd0] [c044a644] aead_decrypt+0x6c/0xc8 [ 892.129674] [effa7d00] [c0509724] esp_input+0x178/0x334 [ 892.129681] [effa7d50] [c0519778] xfrm_input+0x77c/0x818 [ 892.129688] [effa7da0] [c050e344] xfrm4_rcv_encap+0x20/0x30 [ 892.129697] [effa7db0] [c04b90c8] ip_local_deliver+0x190/0x408 [ 892.129703] [effa7de0] [c04b966c] ip_rcv+0x32c/0x898 [ 892.129709] [effa7e10] [c048b998] __netif_receive_skb+0x27c/0x4e8 [ 892.129715] [effa7e80] [c048d744] netif_receive_skb+0x4c/0x13c [ 892.129726] [effa7eb0] [c03c28ac] _dpa_rx+0x1a8/0x354 [ 892.129732] [effa7ef0] [c03c2ac4] ingress_rx_default_dqrr+0x6c/0x108 [ 892.129742] [effa7f10] [c0467ae0] qman_poll_dqrr+0x170/0x1d4 [ 892.129748] [effa7f40] [c03c153c] dpaa_eth_poll+0x20/0x94 [ 892.129754] [effa7f60] [c048dbd0] net_rx_action+0x13c/0x1f4 [ 892.129763] [effa7fa0] [c003d1b8] __do_softirq+0x108/0x1b0 [ 892.129769] [effa7ff0] [c000df58] call_do_softirq+0x14/0x24 [ 892.129775] [ebacfe70] [c0004868] do_softirq+0xd8/0x104 [ 892.129780] [ebacfe90] [c003d5a4] irq_exit+0xb8/0xd8 [ 892.129786] [ebacfea0] [c0004498] do_IRQ+0xa4/0x1b0 [ 892.129792] [ebacfed0] [c000fad8] ret_from_except+0x0/0x18 [ 892.129798] [ebacff90] [c0009010] cpu_idle+0x94/0xf0 [ 892.129804] [ebacffb0] [c059ff88] start_secondary+0x42c/0x430 [ 892.129809] [ebacfff0] [c0001e28] __secondary_start+0x30/0x84 [ 892.281474] [ 892.282959] [eff9fd00] [c0509724] esp_input+0x178/0x334 [ 892.288186] [eff9fd50] [c0519778] xfrm_input+0x77c/0x818 [ 892.293499] [eff9fda0] [c050e344] xfrm4_rcv_encap+0x20/0x30 [ 892.299074] [eff9fdb0] [c04b90c8] ip_local_deliver+0x190/0x408 [ 892.304907] [eff9fde0] [c04b966c] ip_rcv+0x32c/0x898 [ 892.309872] [eff9fe10] [c048b998] __netif_receive_skb+0x27c/0x4e8 [ 892.315966] [eff9fe80] [c048d744] netif_receive_skb+0x4c/0x13c [ 892.321803] [eff9feb0] [c03c28ac] _dpa_rx+0x1a8/0x354 [ 892.326855] [eff9fef0] [c03c2ac4] ingress_rx_default_dqrr+0x6c/0x108 [ 892.333212] [eff9ff10] [c0467ae0] qman_poll_dqrr+0x170/0x1d4 [ 892.338872] [eff9ff40] [c03c153c] dpaa_eth_poll+0x20/0x94 [ 892.344271] [eff9ff60] [c048dbd0] net_rx_action+0x13c/0x1f4 [ 892.349846] [eff9ffa0] [c003d1b8] __do_softirq+0x108/0x1b0 [ 892.355338] [eff9fff0] [c000df58] call_do_softirq+0x14/0x24 [ 892.360910] [e7169950] [c0004868] do_softirq+0xd8/0x104 [ 892.366135] [e7169970] [c003d5a4] irq_exit+0xb8/0xd8 [ 892.371101] [e7169980] [c0004498] do_IRQ+0xa4/0x1b0 [ 892.375979] [e71699b0] [c000fad8] ret_from_except+0x0/0x18 [ 892.381466] [e7169a70] [c0445e74] caam_jr_enqueue+0xf8/0x250 [ 892.387127] [e7169ab0] [c044ad4c] aead_givencrypt+0x6ac/0xa70 [ 892.392873] [e7169b20] [c050a0b8] esp_output+0x2b4/0x570 [ 892.398186] [e7169b80] [c0519b9c] xfrm_output_resume+0x248/0x7c0 [ 892.404194] [e7169bb0] [c050e89c] xfrm4_output_finish+0x18/0x28 [ 892.410113] [e7169bc0] [c050e8f4] xfrm4_output+0x48/0x98 [ 892.415427] [e7169bd0] [c04beac0] ip_local_out+0x48/0x98 [ 892.420740] [e7169be0] [c04bec7c] ip_queue_xmit+0x16c/0x490 [ 892.426314] [e7169c10] [c04d6128] tcp_transmit_skb+0x35c/0x9a4 [ 892.432147] [e7169c70] [c04d6f98] tcp_write_xmit+0x200/0xa04 [ 892.437808] [e7169cc0] [c04c8ccc] tcp_sendmsg+0x994/0xcec [ 892.443213] [e7169d40] [c04eebfc] inet_sendmsg+0xd0/0x164 [ 892.448617] [e7169d70] [c04792f8] sock_sendmsg+0x8c/0xbc [ 892.453931] [e7169e40] [c047aecc] sys_sendto+0xc0/0xfc [ 892.459069] [e7169f10] [c047b934] sys_socketcall+0x110/0x25c [ 892.464729] [e7169f40] [c000f480] ret_from_syscall+0x0/0x3c (b) since the caam_jr_dequeue lock is only used in bh context, then semantically it should use _bh spin_lock types. spin_lock_bh semantics are to disable back-halves, and used when a lock is shared between softirq (bh) context and process and/or h/w IRQ context. Since the lock is only used within softirq context, and this tasklet is atomic, there is no need to do the additional work to disable back halves. This patch adds back-half disabling protection to caam_jr_enqueue spin_locks to fix (a), and drops it from caam_jr_dequeue to fix (b). Signed-off-by: Kim Phillips Signed-off-by: Herbert Xu --- drivers/crypto/caam/jr.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index 53c8c51d5881..93d14070141a 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -63,7 +63,7 @@ static void caam_jr_dequeue(unsigned long devarg) head = ACCESS_ONCE(jrp->head); - spin_lock_bh(&jrp->outlock); + spin_lock(&jrp->outlock); sw_idx = tail = jrp->tail; hw_idx = jrp->out_ring_read_index; @@ -115,7 +115,7 @@ static void caam_jr_dequeue(unsigned long devarg) jrp->tail = tail; } - spin_unlock_bh(&jrp->outlock); + spin_unlock(&jrp->outlock); /* Finally, execute user's callback */ usercall(dev, userdesc, userstatus, userarg); @@ -236,14 +236,14 @@ int caam_jr_enqueue(struct device *dev, u32 *desc, return -EIO; } - spin_lock(&jrp->inplock); + spin_lock_bh(&jrp->inplock); head = jrp->head; tail = ACCESS_ONCE(jrp->tail); if (!rd_reg32(&jrp->rregs->inpring_avail) || CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) { - spin_unlock(&jrp->inplock); + spin_unlock_bh(&jrp->inplock); dma_unmap_single(dev, desc_dma, desc_size, DMA_TO_DEVICE); return -EBUSY; } @@ -265,7 +265,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc, wr_reg32(&jrp->rregs->inpring_jobadd, 1); - spin_unlock(&jrp->inplock); + spin_unlock_bh(&jrp->inplock); return 0; } From 39307655a1effa8d913bba054c0e985bfaca808c Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 16 Aug 2012 17:01:21 -0400 Subject: [PATCH 094/208] nfsd4: fix security flavor of NFSv4.0 callback Commit d5497fc693a446ce9100fcf4117c3f795ddfd0d2 "nfsd4: move rq_flavor into svc_cred" forgot to remove cl_flavor from the client, leaving two places (cl_flavor and cl_cred.cr_flavor) for the flavor to be stored. After that patch, the latter was the one that was updated, but the former was the one that the callback used. Symptoms were a long delay on utime(). This is because the utime() generated a setattr which recalled a delegation, but the cb_recall was ignored by the client because it had the wrong security flavor. Cc: stable@vger.kernel.org Tested-by: Jamie Heilman Reported-by: Jamie Heilman Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs4callback.c | 4 ++-- fs/nfsd/state.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index cbaf4f8bb7b7..4c7bd35b1876 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -651,12 +651,12 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && - (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) + (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) return -EINVAL; args.client_name = clp->cl_cred.cr_principal; args.prognumber = conn->cb_prog, args.protocol = XPRT_TRANSPORT_TCP; - args.authflavor = clp->cl_flavor; + args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { if (!conn->cb_xprt) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e6173147f982..22bd0a66c356 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -231,7 +231,6 @@ struct nfs4_client { nfs4_verifier cl_verifier; /* generated by client */ time_t cl_time; /* time of last lease renewal */ struct sockaddr_storage cl_addr; /* client ipaddress */ - u32 cl_flavor; /* setclientid pseudoflavor */ struct svc_cred cl_cred; /* setclientid principal */ clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ From be1e44441a560c43c136a562d49a1c9623c91197 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 9 Aug 2012 18:12:28 -0400 Subject: [PATCH 095/208] svcrpc: fix BUG() in svc_tcp_clear_pages Examination of svc_tcp_clear_pages shows that it assumes sk_tcplen is consistent with sk_pages[] (in particular, sk_pages[n] can't be NULL if sk_tcplen would lead us to expect n pages of data). svc_tcp_restore_pages zeroes out sk_pages[] while leaving sk_tcplen. This is OK, since both functions are serialized by XPT_BUSY. However, that means the inconsistency must be repaired before dropping XPT_BUSY. Therefore we should be ensuring that svc_tcp_save_pages repairs the problem before exiting svc_tcp_recv_record on error. Symptoms were a BUG() in svc_tcp_clear_pages. Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- net/sunrpc/svcsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 18bc130255a7..998aa8c1807c 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1129,9 +1129,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) if (len >= 0) svsk->sk_tcplen += len; if (len != want) { + svc_tcp_save_pages(svsk, rqstp); if (len < 0 && len != -EAGAIN) goto err_other; - svc_tcp_save_pages(svsk, rqstp); dprintk("svc: incomplete TCP record (%d of %d)\n", svsk->sk_tcplen, svsk->sk_reclen); goto err_noclose; From f06f00a24d76e168ecb38d352126fd203937b601 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Mon, 20 Aug 2012 16:04:40 -0400 Subject: [PATCH 096/208] svcrpc: sends on closed socket should stop immediately svc_tcp_sendto sets XPT_CLOSE if we fail to transmit the entire reply. However, the XPT_CLOSE won't be acted on immediately. Meanwhile other threads could send further replies before the socket is really shut down. This can manifest as data corruption: for example, if a truncated read reply is followed by another rpc reply, that second reply will look to the client like further read data. Symptoms were data corruption preceded by svc_tcp_sendto logging something like kernel: rpc-srv/tcp: nfsd: sent only 963696 when sending 1048708 bytes - shutting down socket Cc: stable@vger.kernel.org Reported-by: Malahal Naineni Tested-by: Malahal Naineni Signed-off-by: J. Bruce Fields --- net/sunrpc/svc_xprt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 88f2bf671960..0d693a89434f 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -794,7 +794,8 @@ int svc_send(struct svc_rqst *rqstp) /* Grab mutex to serialize outgoing data. */ mutex_lock(&xprt->xpt_mutex); - if (test_bit(XPT_DEAD, &xprt->xpt_flags)) + if (test_bit(XPT_DEAD, &xprt->xpt_flags) + || test_bit(XPT_CLOSE, &xprt->xpt_flags)) len = -ENOTCONN; else len = xprt->xpt_ops->xpo_sendto(rqstp); From d10f27a750312ed5638c876e4bd6aa83664cccd8 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Fri, 17 Aug 2012 17:31:53 -0400 Subject: [PATCH 097/208] svcrpc: fix svc_xprt_enqueue/svc_recv busy-looping The rpc server tries to ensure that there will be room to send a reply before it receives a request. It does this by tracking, in xpt_reserved, an upper bound on the total size of the replies that is has already committed to for the socket. Currently it is adding in the estimate for a new reply *before* it checks whether there is space available. If it finds that there is not space, it then subtracts the estimate back out. This may lead the subsequent svc_xprt_enqueue to decide that there is space after all. The results is a svc_recv() that will repeatedly return -EAGAIN, causing server threads to loop without doing any actual work. Cc: stable@vger.kernel.org Reported-by: Michael Tokarev Tested-by: Michael Tokarev Signed-off-by: J. Bruce Fields --- net/sunrpc/svc_xprt.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 0d693a89434f..bac973a31367 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -316,7 +316,6 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt) */ void svc_xprt_enqueue(struct svc_xprt *xprt) { - struct svc_serv *serv = xprt->xpt_server; struct svc_pool *pool; struct svc_rqst *rqstp; int cpu; @@ -362,8 +361,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt) rqstp, rqstp->rq_xprt); rqstp->rq_xprt = xprt; svc_xprt_get(xprt); - rqstp->rq_reserved = serv->sv_max_mesg; - atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); pool->sp_stats.threads_woken++; wake_up(&rqstp->rq_wait); } else { @@ -640,8 +637,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) if (xprt) { rqstp->rq_xprt = xprt; svc_xprt_get(xprt); - rqstp->rq_reserved = serv->sv_max_mesg; - atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); /* As there is a shortage of threads and this request * had to be queued, don't allow the thread to wait so @@ -738,6 +733,8 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) else len = xprt->xpt_ops->xpo_recvfrom(rqstp); dprintk("svc: got len=%d\n", len); + rqstp->rq_reserved = serv->sv_max_mesg; + atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved); } svc_xprt_received(xprt); From c7a3a88c938fbe3d70c2278e082b80eb830d1c58 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Sun, 19 Aug 2012 19:10:42 +0200 Subject: [PATCH 098/208] uprobes: Fix mmap_region()'s mm->mm_rb corruption if uprobe_mmap() fails This patch fixes: https://bugzilla.redhat.com/show_bug.cgi?id=843640 If mmap_region()->uprobe_mmap() fails, unmap_and_free_vma path does unmap_region() but does not remove the soon-to-be-freed vma from rb tree. Actually there are more problems but this is how William noticed this bug. Perhaps we could do do_munmap() + return in this case, but in fact it is simply wrong to abort if uprobe_mmap() fails. Until at least we move the !UPROBE_COPY_INSN code from install_breakpoint() to uprobe_register(). For example, uprobe_mmap()->install_breakpoint() can fail if the probed insn is not supported (remember, uprobe_register() succeeds if nobody mmaps inode/offset), mmap() should not fail in this case. dup_mmap()->uprobe_mmap() is wrong too by the same reason, fork() can race with uprobe_register() and fail for no reason if it wins the race and does install_breakpoint() first. And, if nothing else, both mmap_region() and dup_mmap() return success if uprobe_mmap() fails. Change them to ignore the error code from uprobe_mmap(). Reported-and-tested-by: William Cohen Signed-off-by: Oleg Nesterov Acked-by: Srikar Dronamraju Cc: # v3.5 Cc: Anton Arapov Cc: William Cohen Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20120819171042.GB26957@redhat.com Signed-off-by: Ingo Molnar --- kernel/fork.c | 4 ++-- mm/mmap.c | 5 ++--- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 3bd2280d79f6..2c8857e12855 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -455,8 +455,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; - if (file && uprobe_mmap(tmp)) - goto out; + if (file) + uprobe_mmap(tmp); } /* a new mm has just been created */ arch_dup_mmap(oldmm, mm); diff --git a/mm/mmap.c b/mm/mmap.c index e3e86914f11a..52e08fc9186d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1356,9 +1356,8 @@ out: } else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK)) make_pages_present(addr, addr + len); - if (file && uprobe_mmap(vma)) - /* matching probes but cannot insert */ - goto unmap_and_free_vma; + if (file) + uprobe_mmap(vma); return addr; From 73e8712aa02d924844fbd5bd84a2445a1c3f68d7 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 20 Aug 2012 14:10:00 +0300 Subject: [PATCH 099/208] UBIFS: remove stale commentary Signed-off-by: Artem Bityutskiy --- fs/ubifs/super.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index c3fa6c5327a3..71a197f0f93d 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -1157,9 +1157,6 @@ static int check_free_space(struct ubifs_info *c) * * This function mounts UBIFS file system. Returns zero in case of success and * a negative error code in case of failure. - * - * Note, the function does not de-allocate resources it it fails half way - * through, and the caller has to do this instead. */ static int mount_ubifs(struct ubifs_info *c) { From 11e3be0be2a1314e0861304857e7efcaed5d3e54 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Mon, 20 Aug 2012 15:16:24 +0300 Subject: [PATCH 100/208] UBIFS: fix crash on error path This patch fixes a regression introduced by "4994297 UBIFS: make ubifs_lpt_init clean-up in case of failure" which I've hit while running the 'integck -p' test. When remount the file-system from R/O mode to R/W mode and 'lpt_init_wr()' fails, we free _all_ LPT resources by calling 'ubifs_lpt_free(c, 0)', even those needed for R/O mode. This leads to subsequent crashes, e.g., if we try to unmount the file-system. Cc: stable@vger.kernel.org [v3.5+] Signed-off-by: Artem Bityutskiy --- fs/ubifs/lpt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index ce33b2beb151..8640920766ed 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -1749,7 +1749,10 @@ int ubifs_lpt_init(struct ubifs_info *c, int rd, int wr) return 0; out_err: - ubifs_lpt_free(c, 0); + if (wr) + ubifs_lpt_free(c, 1); + if (rd) + ubifs_lpt_free(c, 0); return err; } From c212f4020de7b5d35a71327d1483120a698d60a0 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 21 Aug 2012 13:45:35 +0300 Subject: [PATCH 101/208] UBIFS: fix replay regression MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit "d51f17e UBIFS: simplify reply code a bit" introduces a bug with the following symptoms: UBIFS error (pid 1): replay_log_leb: first CS node at LEB 3:0 has wrong commit number 0 expected 1 The issue is that we start replaying the log from UBIFS_LOG_LNUM instead of c->lhead_lnum. This patch fixes that. Reported-by: Uwe Kleine-König Signed-off-by: Artem Bityutskiy --- fs/ubifs/replay.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index eba46d4a7619..94d78fc5d4e0 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -1026,7 +1026,6 @@ int ubifs_replay_journal(struct ubifs_info *c) c->replaying = 1; lnum = c->ltail_lnum = c->lhead_lnum; - lnum = UBIFS_LOG_LNUM; do { err = replay_log_leb(c, lnum, 0, c->sbuf); if (err == 1) @@ -1035,7 +1034,7 @@ int ubifs_replay_journal(struct ubifs_info *c) if (err) goto out; lnum = ubifs_next_log_lnum(c, lnum); - } while (lnum != UBIFS_LOG_LNUM); + } while (lnum != c->ltail_lnum); err = replay_buds(c); if (err) From cbe05685c1859e655c663b6ff2d0f71093ee834d Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Sun, 12 Aug 2012 12:01:34 +0200 Subject: [PATCH 102/208] s390: Always use "long" for ssize_t to match size_t On s390x-linux-gcc, __SIZE_TYPE__ expands to "long unsigned int" for both 32-bit s390 and 64-bit s390x, as gcc-4.6.3-nolibc/s390x-linux/lib/gcc/s390x-linux/4.6.3/plugin/include/config/s390/linux.h has #define SIZE_TYPE (TARGET_64BIT ? "long unsigned int" : "long unsigned int") To match this, __kernel_size_t is always set to "long unsigned int". But while __kernel_ssize_t is "long" on 64-bit s390x, it is "int" on 32-bit s390, causing compiler warnings like: fs/quota/quota_tree.c:372:4: warning: format '%zd' expects argument of type 'signed size_t', but argument 4 has type 'ssize_t' [-Wformat] To fix this, __kernel_ssize_t should be "long", irrespective of word size. Signed-off-by: Geert Uytterhoeven Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/posix_types.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/s390/include/asm/posix_types.h b/arch/s390/include/asm/posix_types.h index 7bcc14e395f0..bf2a2ad2f800 100644 --- a/arch/s390/include/asm/posix_types.h +++ b/arch/s390/include/asm/posix_types.h @@ -13,6 +13,7 @@ */ typedef unsigned long __kernel_size_t; +typedef long __kernel_ssize_t; #define __kernel_size_t __kernel_size_t typedef unsigned short __kernel_old_dev_t; @@ -25,7 +26,6 @@ typedef unsigned short __kernel_mode_t; typedef unsigned short __kernel_ipc_pid_t; typedef unsigned short __kernel_uid_t; typedef unsigned short __kernel_gid_t; -typedef int __kernel_ssize_t; typedef int __kernel_ptrdiff_t; #else /* __s390x__ */ @@ -35,7 +35,6 @@ typedef unsigned int __kernel_mode_t; typedef int __kernel_ipc_pid_t; typedef unsigned int __kernel_uid_t; typedef unsigned int __kernel_gid_t; -typedef long __kernel_ssize_t; typedef long __kernel_ptrdiff_t; typedef unsigned long __kernel_sigset_t; /* at least 32 bits */ From 3ab484b8622b7b890ca8d2ab5ee034c217ee4eeb Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Tue, 14 Aug 2012 14:17:30 -0300 Subject: [PATCH 103/208] perf tools: Add missing files to build the python binding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Changeset 0f6a3015: "perf tools: Support user regs and stack in sample parsing" uses hweight_long in evsel.c, so we need to drag util/hweight.c to the python binding. Ditto for ee8dd3c: "perf tools: Change strlist to use the new rblist" where we need to add util/rblist.c. Now twatch.py works again: # export PYTHONPATH=~acme/git/build/perf/python/ # ~acme/git/linux/tools/perf/python/twatch.py cpu: 4, pid: 23639, tid: 23639 { type: fork, pid: 30659, ppid: 23639, tid: 30659, ptid: 23639, time: 36287872076780} cpu: 5, pid: 30659, tid: 30659 { type: comm, pid: 30659, tid: 30659, comm: ls } cpu: 5, pid: 30659, tid: 30659 { type: exit, pid: 30659, ppid: 30659, tid: 30659, ptid: 30659, time: 36287873681539} cpu: 4, pid: 23639, tid: 23639 { type: fork, pid: 30660, ppid: 23639, tid: 30660, ptid: 23639, time: 36291720420480} cpu: 5, pid: 30659, tid: 30659 { type: exit, pid: 30659, ppid: 30659, tid: 30659, ptid: 30659, time: 36287873685714} cpu: 5, pid: 30660, tid: 30660 { type: comm, pid: 30660, tid: 30660, comm: git } ^C KeyboardInterrupt Reported-by: Jérôme Carretero Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Mike Galbraith Cc: Namhyung Kim Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-gmq82zp5blin9aml9g5tzokr@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/python-ext-sources | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 2884e67ee625..213362850abd 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,10 +10,12 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c +util/hweight.c util/thread_map.c util/util.c util/xyarray.c util/cgroup.c util/debugfs.c +util/rblist.c util/strlist.c ../../lib/rbtree.c From 9974e43d900af7979e0a571b8e0c9674c7399b79 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Tue, 21 Aug 2012 17:20:30 +0200 Subject: [PATCH 104/208] ide: fix generic_ide_suspend/resume Oops This patch fixes a regresion introduced by commit 0998d063 (device-core: Ensure drvdata = NULL when no driver is bound). Suspend oopses in generic_ide_suspend() because dev_get_drvdata() returns NULL (dev->p->driver_data == NULL) and this function is not prepared for this. Fix is based on Alan Stern's suggestion. Signed-off-by: Miklos Szeredi Acked-by: Rafael J. Wysocki Signed-off-by: David S. Miller --- drivers/ide/ide-pm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index 92406097efeb..8d1e32d7cd97 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -4,7 +4,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) { - ide_drive_t *drive = dev_get_drvdata(dev); + ide_drive_t *drive = to_ide_device(dev); ide_drive_t *pair = ide_get_pair_dev(drive); ide_hwif_t *hwif = drive->hwif; struct request *rq; @@ -40,7 +40,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg) int generic_ide_resume(struct device *dev) { - ide_drive_t *drive = dev_get_drvdata(dev); + ide_drive_t *drive = to_ide_device(dev); ide_drive_t *pair = ide_get_pair_dev(drive); ide_hwif_t *hwif = drive->hwif; struct request *rq; From 83be4ffa1acbcd529b771f4d2e639b15e2b7957e Mon Sep 17 00:00:00 2001 From: Richard Weinberger Date: Tue, 14 Aug 2012 14:47:37 -0700 Subject: [PATCH 105/208] x86/spinlocks: Fix comment in spinlock.h This comment is no longer true. We support up to 2^16 CPUs because __ticket_t is an u16 if NR_CPUS is larger than 256. Signed-off-by: Richard Weinberger Signed-off-by: Andrew Morton Signed-off-by: Ingo Molnar --- arch/x86/include/asm/spinlock.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index b315a33867f2..33692eaabab5 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -12,8 +12,7 @@ * Simple spin lock operations. There are two variants, one clears IRQ's * on the local processor, one does not. * - * These are fair FIFO ticket locks, which are currently limited to 256 - * CPUs. + * These are fair FIFO ticket locks, which support up to 2^16 CPUs. * * (the type definitions are in asm/spinlock_types.h) */ From 2530cd4f448935c74eeb49f29559589928e4b2f0 Mon Sep 17 00:00:00 2001 From: "Liu, Chuansheng" Date: Tue, 14 Aug 2012 06:55:01 +0000 Subject: [PATCH 106/208] x86/fixup_irq: Use cpu_online_mask instead of cpu_all_mask When one CPU is going down and this CPU is the last one in irq affinity, current code is setting cpu_all_mask as the new affinity for that irq. But for some systems (such as in Medfield Android mobile) the firmware sends the interrupt to each CPU in the irq affinity mask, averaged, and cpu_all_mask includes all potential CPUs, i.e. offline ones as well. So replace cpu_all_mask with cpu_online_mask. Signed-off-by: liu chuansheng Acked-by: Yanmin Zhang Acked-by: Thomas Gleixner Link: http://lkml.kernel.org/r/27240C0AC20F114CBF8149A2696CBE4A137286@SHSMSX101.ccr.corp.intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 7ad683d78645..d44f7829968e 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -270,7 +270,7 @@ void fixup_irqs(void) if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { break_affinity = 1; - affinity = cpu_all_mask; + affinity = cpu_online_mask; } chip = irq_data_get_irq_chip(data); From 784ffcbb96c3a97b4c64fd48b1dfe12ef3fcbcda Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 21 Aug 2012 20:30:46 -0400 Subject: [PATCH 107/208] time: Ensure we normalize the timekeeper in tk_xtime_add Andreas noticed problems with resume on specific hardware after commit 1e75fa8b (time: Condense timekeeper.xtime into xtime_sec) combined with commit b44d50dca (time: Fix casting issue in tk_set_xtime and tk_xtime_add) After some digging I realized we aren't normalizing the timekeeper after the add. Add the missing normalize call. Reported-by: Andreas Schwab Tested-by: Andreas Schwab Signed-off-by: John Stultz Cc: Prarit Bhargava Cc: Ingo Molnar Link: http://lkml.kernel.org/r/1345595449-34965-2-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 898bef066a44..258164ae45cc 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -115,6 +115,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec *ts) { tk->xtime_sec += ts->tv_sec; tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift; + tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm) From 85dc8f05c93c8105987de9d7e7cebf15a72ff4ec Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Tue, 21 Aug 2012 20:30:47 -0400 Subject: [PATCH 108/208] time: Fix casting issue in timekeeping_forward_now arch_gettimeoffset returns a u32 value which when shifted by tk->shift can overflow. This issue was introduced with 1e75fa8be (time: Condense timekeeper.xtime into xtime_sec) Cast it to u64 first. Signed-off-by: Andreas Schwab Signed-off-by: John Stultz Cc: Prarit Bhargava Cc: Ingo Molnar Link: http://lkml.kernel.org/r/1345595449-34965-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 258164ae45cc..1dbf80ec7696 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -277,7 +277,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk->xtime_nsec += cycle_delta * tk->mult; /* If arch requires, add in gettimeoffset() */ - tk->xtime_nsec += arch_gettimeoffset() << tk->shift; + tk->xtime_nsec += (u64)arch_gettimeoffset() << tk->shift; tk_normalize_xtime(tk); From 6ea565a9be32a3c8d1092017686f183b6d8c4514 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 21 Aug 2012 20:30:48 -0400 Subject: [PATCH 109/208] time: Avoid potential shift overflow with large shift values Andreas Schwab noticed that the 1 << tk->shift could overflow if the shift value was greater than 30, since 1 would be a 32bit long on 32bit architectures. This issue was introduced by 1e75fa8be (time: Condense timekeeper.xtime into xtime_sec) Use 1ULL instead to ensure we don't overflow on the shift. Reported-by: Andreas Schwab Signed-off-by: John Stultz Cc: Prarit Bhargava Cc: Ingo Molnar Link: http://lkml.kernel.org/r/1345595449-34965-4-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1dbf80ec7696..a5a9389c4c30 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1184,9 +1184,9 @@ static void update_wall_time(void) * the vsyscall implementations are converted to use xtime_nsec * (shifted nanoseconds), this can be killed. */ - remainder = tk->xtime_nsec & ((1 << tk->shift) - 1); + remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); tk->xtime_nsec -= remainder; - tk->xtime_nsec += 1 << tk->shift; + tk->xtime_nsec += 1ULL << tk->shift; tk->ntp_error += remainder << tk->ntp_error_shift; /* From bf2ac312195155511a0f79325515cbb61929898a Mon Sep 17 00:00:00 2001 From: John Stultz Date: Tue, 21 Aug 2012 20:30:49 -0400 Subject: [PATCH 110/208] time: Avoid making adjustments if we haven't accumulated anything If update_wall_time() is called and the current offset isn't large enough to accumulate, avoid re-calling timekeeping_adjust which may change the clock freq and can cause 1ns inconsistencies with CLOCK_REALTIME_COARSE/CLOCK_MONOTONIC_COARSE. Signed-off-by: John Stultz Cc: Prarit Bhargava Cc: Ingo Molnar Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1345595449-34965-5-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- kernel/time/timekeeping.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index a5a9389c4c30..0c1485e42be6 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1152,6 +1152,10 @@ static void update_wall_time(void) offset = (clock->read(clock) - clock->cycle_last) & clock->mask; #endif + /* Check if there's really nothing to do */ + if (offset < tk->cycle_interval) + goto out; + /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, From 65b455b123c7e2b835a0b7148f9bae584f95000e Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Tue, 21 Aug 2012 21:50:58 +0300 Subject: [PATCH 111/208] UBIFS: fix complaints about too small debug buffer size When debugging is enabled, we use a temporary on-stack buffer for formatting the key strings like "(11368871, direntry, 0xcd0750)". The buffer size is 32 bytes and sometimes it is not enough to fit the key string - e.g., when inode numbers are high. This is not fatal, but the key strings are incomplete and UBIFS complains like this: UBIFS assert failed in dbg_snprintf_key at 137 (pid 1) This is a regression caused by "515315a UBIFS: fix key printing". Fix the issue by increasing the buffer to 48 bytes. Reported-by: Michael Hench Signed-off-by: Artem Bityutskiy Tested-by: Michael Hench Cc: stable@vger.kernel.org [v3.3+] --- fs/ubifs/debug.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 8b8cc4e945f4..760de723dadb 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -167,7 +167,7 @@ struct ubifs_global_debug_info { #define ubifs_dbg_msg(type, fmt, ...) \ pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__) -#define DBG_KEY_BUF_LEN 32 +#define DBG_KEY_BUF_LEN 48 #define ubifs_dbg_msg_key(type, key, fmt, ...) do { \ char __tmp_key_buf[DBG_KEY_BUF_LEN]; \ pr_debug("UBIFS DBG " type ": " fmt "%s\n", ##__VA_ARGS__, \ From cb09cad44f07044d9810f18f6f9a6a6f3771f979 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Wed, 22 Aug 2012 13:03:48 +0300 Subject: [PATCH 112/208] x86/alternatives: Fix p6 nops on non-modular kernels Probably a leftover from the early days of self-patching, p6nops are marked __initconst_or_module, which causes them to be discarded in a non-modular kernel. If something later triggers patching, it will overwrite kernel code with garbage. Reported-by: Tomas Racek Signed-off-by: Avi Kivity Cc: Michael Tokarev Cc: Borislav Petkov Cc: Marcelo Tosatti Cc: qemu-devel@nongnu.org Cc: Anthony Liguori Cc: H. Peter Anvin Cc: Alan Cox Cc: Alan Cox Link: http://lkml.kernel.org/r/5034AE84.90708@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/alternative.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index afb7ff79a29f..ced4534baed5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -165,7 +165,7 @@ static const unsigned char * const k7_nops[ASM_NOP_MAX+2] = #endif #ifdef P6_NOP1 -static const unsigned char __initconst_or_module p6nops[] = +static const unsigned char p6nops[] = { P6_NOP1, P6_NOP2, From 35f2d16bb9ace0fb2671b8232839944ad9057c6f Mon Sep 17 00:00:00 2001 From: Takuya Yoshikawa Date: Mon, 20 Aug 2012 18:35:39 +0900 Subject: [PATCH 113/208] KVM: MMU: Fix mmu_shrink() so that it can free mmu pages as intended Although the possible race described in commit 85b7059169e128c57a3a8a3e588fb89cb2031da1 KVM: MMU: fix shrinking page from the empty mmu was correct, the real cause of that issue was a more trivial bug of mmu_shrink() introduced by commit 1952639665e92481c34c34c3e2a71bf3e66ba362 KVM: MMU: do not iterate over all VMs in mmu_shrink() Here is the bug: if (kvm->arch.n_used_mmu_pages > 0) { if (!nr_to_scan--) break; continue; } We skip VMs whose n_used_mmu_pages is not zero and try to shrink others: in other words we try to shrink empty ones by mistake. This patch reverses the logic so that mmu_shrink() can free pages from the first VM whose n_used_mmu_pages is not zero. Note that we also add comments explaining the role of nr_to_scan which is not practically important now, hoping this will be improved in the future. Signed-off-by: Takuya Yoshikawa Cc: Gleb Natapov Signed-off-by: Avi Kivity --- arch/x86/kvm/mmu.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 01ca00423938..7fbd0d273ea8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -4112,17 +4112,22 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) int idx; LIST_HEAD(invalid_list); + /* + * Never scan more than sc->nr_to_scan VM instances. + * Will not hit this condition practically since we do not try + * to shrink more than one VM and it is very unlikely to see + * !n_used_mmu_pages so many times. + */ + if (!nr_to_scan--) + break; /* * n_used_mmu_pages is accessed without holding kvm->mmu_lock * here. We may skip a VM instance errorneosly, but we do not * want to shrink a VM that only started to populate its MMU * anyway. */ - if (kvm->arch.n_used_mmu_pages > 0) { - if (!nr_to_scan--) - break; + if (!kvm->arch.n_used_mmu_pages) continue; - } idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); From 69f9025894c391fec2f7c7ea9150203418454915 Mon Sep 17 00:00:00 2001 From: Artem Bityutskiy Date: Wed, 22 Aug 2012 16:47:28 +0300 Subject: [PATCH 114/208] UBIFS: fix error messages spelling Corruptio -> corruption. Signed-off-by: Artem Bityutskiy --- fs/ubifs/recovery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index c30d976b4be8..edeec499c048 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -788,7 +788,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, corrupted_rescan: /* Re-scan the corrupted data with verbose messages */ - ubifs_err("corruptio %d", ret); + ubifs_err("corruption %d", ret); ubifs_scan_a_node(c, buf, len, lnum, offs, 1); corrupted: ubifs_scanned_corruption(c, lnum, offs, buf); From 53c84983549230495156d7da666cd1acdb9c9015 Mon Sep 17 00:00:00 2001 From: Simon Farnsworth Date: Wed, 22 Aug 2012 11:17:17 +0100 Subject: [PATCH 115/208] HID: Remove QUANTA from special drivers list This QUANTA device is driven by the generic hid-multitouch.ko driver, and therefore shouldn't be in the special drivers list. This has been an oversight in 4fa3a58 ("HID: hid-multitouch: Switch to device groups"). Signed-off-by: Simon Farnsworth Signed-off-by: Jiri Kosina --- drivers/hid/hid-core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 500844f04f93..78f0ee74b853 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1624,7 +1624,6 @@ static const struct hid_device_id hid_have_special_driver[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ORTEK, USB_DEVICE_ID_ORTEK_WKB2000) }, { HID_USB_DEVICE(USB_VENDOR_ID_PETALYNX, USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE) }, { HID_USB_DEVICE(USB_VENDOR_ID_PRIMAX, USB_DEVICE_ID_PRIMAX_KEYBOARD) }, - { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_PIXART_IMAGING_INC_OPTICAL_TOUCH_SCREEN) }, { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_KONE) }, { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ARVO) }, { HID_USB_DEVICE(USB_VENDOR_ID_ROCCAT, USB_DEVICE_ID_ROCCAT_ISKU) }, From 5ad105e569c45dcfad50d724c61d5061248be755 Mon Sep 17 00:00:00 2001 From: Avi Kivity Date: Sun, 19 Aug 2012 14:34:31 +0300 Subject: [PATCH 116/208] KVM: x86 emulator: use stack size attribute to mask rsp in stack ops The sub-register used to access the stack (sp, esp, or rsp) is not determined by the address size attribute like other memory references, but by the stack segment's B bit (if not in x86_64 mode). Fix by using the existing stack_mask() to figure out the correct mask. This long-existing bug was exposed by a combination of a27685c33acccce (emulate invalid guest state by default), which causes many more instructions to be emulated, and a seabios change (possibly a bug) which causes the high 16 bits of esp to become polluted across calls to real mode software interrupts. Signed-off-by: Avi Kivity Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/emulate.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 97d9a9914ba8..a3b57a27be88 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -475,13 +475,26 @@ register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg) return address_mask(ctxt, reg); } +static void masked_increment(ulong *reg, ulong mask, int inc) +{ + assign_masked(reg, *reg + inc, mask); +} + static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc) { + ulong mask; + if (ctxt->ad_bytes == sizeof(unsigned long)) - *reg += inc; + mask = ~0UL; else - *reg = (*reg & ~ad_mask(ctxt)) | ((*reg + inc) & ad_mask(ctxt)); + mask = ad_mask(ctxt); + masked_increment(reg, mask, inc); +} + +static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) +{ + masked_increment(&ctxt->regs[VCPU_REGS_RSP], stack_mask(ctxt), inc); } static inline void jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -1522,8 +1535,8 @@ static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], -bytes); - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + rsp_increment(ctxt, -bytes); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; return segmented_write(ctxt, addr, data, bytes); @@ -1542,13 +1555,13 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt, int rc; struct segmented_address addr; - addr.ea = register_address(ctxt, ctxt->regs[VCPU_REGS_RSP]); + addr.ea = ctxt->regs[VCPU_REGS_RSP] & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; rc = segmented_read(ctxt, addr, dest, len); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], len); + rsp_increment(ctxt, len); return rc; } @@ -1688,8 +1701,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], - ctxt->op_bytes); + rsp_increment(ctxt, ctxt->op_bytes); --reg; } @@ -2825,7 +2837,7 @@ static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) rc = emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; - register_address_increment(ctxt, &ctxt->regs[VCPU_REGS_RSP], ctxt->src.val); + rsp_increment(ctxt, ctxt->src.val); return X86EMUL_CONTINUE; } From 36bf50d7697be18c6bfd0401e037df10bff1e573 Mon Sep 17 00:00:00 2001 From: Andreas Herrmann Date: Tue, 31 Jul 2012 15:41:45 +0200 Subject: [PATCH 117/208] x86, microcode, AMD: Fix broken ucode patch size check This issue was recently observed on an AMD C-50 CPU where a patch of maximum size was applied. Commit be62adb49294 ("x86, microcode, AMD: Simplify ucode verification") added current_size in get_matching_microcode(). This is calculated as size of the ucode patch + 8 (ie. size of the header). Later this is compared against the maximum possible ucode patch size for a CPU family. And of course this fails if the patch has already maximum size. Cc: [3.3+] Signed-off-by: Andreas Herrmann Signed-off-by: Borislav Petkov Link: http://lkml.kernel.org/r/1344361461-10076-1-git-send-email-bp@amd64.org Signed-off-by: H. Peter Anvin --- arch/x86/kernel/microcode_amd.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 8a2ce8fd41c0..82746f942cd8 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -143,11 +143,12 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr, unsigned int *current_size) { struct microcode_header_amd *mc_hdr; - unsigned int actual_size; + unsigned int actual_size, patch_size; u16 equiv_cpu_id; /* size of the current patch we're staring at */ - *current_size = *(u32 *)(ucode_ptr + 4) + SECTION_HDR_SIZE; + patch_size = *(u32 *)(ucode_ptr + 4); + *current_size = patch_size + SECTION_HDR_SIZE; equiv_cpu_id = find_equiv_id(); if (!equiv_cpu_id) @@ -174,7 +175,7 @@ static int get_matching_microcode(int cpu, const u8 *ucode_ptr, /* * now that the header looks sane, verify its size */ - actual_size = verify_ucode_size(cpu, *current_size, leftover_size); + actual_size = verify_ucode_size(cpu, patch_size, leftover_size); if (!actual_size) return 0; From 43ca6cb28c871f2fbad10117b0648e5ae3b0f638 Mon Sep 17 00:00:00 2001 From: Luca Tettamanti Date: Tue, 21 Aug 2012 17:36:28 +0200 Subject: [PATCH 118/208] hwmon: (asus_atk0110) Add quirk for Asus M5A78L MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The old interface is bugged and reads the wrong sensor when retrieving the reading for the chassis fan (it reads the CPU sensor); the new interface works fine. Reported-by: Göran Uddeborg Cc: stable@vger.kernel.org Tested-by: Göran Uddeborg Signed-off-by: Luca Tettamanti Signed-off-by: Guenter Roeck --- drivers/hwmon/asus_atk0110.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/hwmon/asus_atk0110.c b/drivers/hwmon/asus_atk0110.c index 351d1f4593e7..4ee578948723 100644 --- a/drivers/hwmon/asus_atk0110.c +++ b/drivers/hwmon/asus_atk0110.c @@ -34,6 +34,12 @@ static const struct dmi_system_id __initconst atk_force_new_if[] = { .matches = { DMI_MATCH(DMI_BOARD_NAME, "SABERTOOTH X58") } + }, { + /* Old interface reads the same sensor for fan0 and fan1 */ + .ident = "Asus M5A78L", + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "M5A78L") + } }, { } }; From b70ad586162609141f0aa9eb34790f31a8954f89 Mon Sep 17 00:00:00 2001 From: "Xu, Anhua" Date: Mon, 13 Aug 2012 03:08:33 +0000 Subject: [PATCH 119/208] drm/i915: fix wrong order of parameters in port checking functions Wrong order of parameters passed-in when calling hdmi/adpa /lvds_pipe_enabled(), 2nd and 3rd parameters are reversed. This bug was indroduced by commit 1519b9956eb4b4180fa3f47c73341463cdcfaa37 Author: Keith Packard Date: Sat Aug 6 10:35:34 2011 -0700 drm/i915: Fix PCH port pipe select in CPT disable paths The reachable tag for this commit is v3.1-rc1-3-g1519b99 Signed-off-by: Anhua Xu Reviewed-by: Chris Wilson Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=44876 Tested-by: Daniel Schroeder Cc: stable@vger.kernel.org Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_display.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index a69a3d0d3acf..2dfa6cf4886b 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1384,7 +1384,7 @@ static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) { u32 val = I915_READ(reg); - WARN(hdmi_pipe_enabled(dev_priv, val, pipe), + WARN(hdmi_pipe_enabled(dev_priv, pipe, val), "PCH HDMI (0x%08x) enabled on transcoder %c, should be disabled\n", reg, pipe_name(pipe)); @@ -1404,13 +1404,13 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv, reg = PCH_ADPA; val = I915_READ(reg); - WARN(adpa_pipe_enabled(dev_priv, val, pipe), + WARN(adpa_pipe_enabled(dev_priv, pipe, val), "PCH VGA enabled on transcoder %c, should be disabled\n", pipe_name(pipe)); reg = PCH_LVDS; val = I915_READ(reg); - WARN(lvds_pipe_enabled(dev_priv, val, pipe), + WARN(lvds_pipe_enabled(dev_priv, pipe, val), "PCH LVDS enabled on transcoder %c, should be disabled\n", pipe_name(pipe)); @@ -1872,7 +1872,7 @@ static void disable_pch_hdmi(struct drm_i915_private *dev_priv, enum pipe pipe, int reg) { u32 val = I915_READ(reg); - if (hdmi_pipe_enabled(dev_priv, val, pipe)) { + if (hdmi_pipe_enabled(dev_priv, pipe, val)) { DRM_DEBUG_KMS("Disabling pch HDMI %x on pipe %d\n", reg, pipe); I915_WRITE(reg, val & ~PORT_ENABLE); @@ -1894,12 +1894,12 @@ static void intel_disable_pch_ports(struct drm_i915_private *dev_priv, reg = PCH_ADPA; val = I915_READ(reg); - if (adpa_pipe_enabled(dev_priv, val, pipe)) + if (adpa_pipe_enabled(dev_priv, pipe, val)) I915_WRITE(reg, val & ~ADPA_DAC_ENABLE); reg = PCH_LVDS; val = I915_READ(reg); - if (lvds_pipe_enabled(dev_priv, val, pipe)) { + if (lvds_pipe_enabled(dev_priv, pipe, val)) { DRM_DEBUG_KMS("disable lvds on pipe %d val 0x%08x\n", pipe, val); I915_WRITE(reg, val & ~LVDS_PORT_EN); POSTING_READ(reg); From 5ee369138d28c17305e1cdc662a62a2fc83d80d7 Mon Sep 17 00:00:00 2001 From: Vijay Purushothaman Date: Thu, 23 Aug 2012 12:08:57 +0530 Subject: [PATCH 120/208] drm/i915: fix color order for BGR formats on IVB MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is already fixed for ILK and SNB in the below commit but somehow IVB is missed. commit ab2f9df10dd955f1fc0a8650e377588c98f1c029 Author: Jesse Barnes Date: Mon Feb 27 12:40:10 2012 -0800 drm/i915: fix color order for BGR formats on SNB Had the wrong bits and field definitions. Signed-off-by: Vijay Purushothaman Reviewed-by: Antti Koskipää Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/intel_sprite.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index cc8df4de2d92..7644f31a3778 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -60,11 +60,11 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb, switch (fb->pixel_format) { case DRM_FORMAT_XBGR8888: - sprctl |= SPRITE_FORMAT_RGBX888; + sprctl |= SPRITE_FORMAT_RGBX888 | SPRITE_RGB_ORDER_RGBX; pixel_size = 4; break; case DRM_FORMAT_XRGB8888: - sprctl |= SPRITE_FORMAT_RGBX888 | SPRITE_RGB_ORDER_RGBX; + sprctl |= SPRITE_FORMAT_RGBX888; pixel_size = 4; break; case DRM_FORMAT_YUYV: From 676ce6d5ca3098339c028d44fe0427d1566a4d2d Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 23 Aug 2012 12:17:36 +0200 Subject: [PATCH 121/208] block: replace __getblk_slow misfix by grow_dev_page fix Commit 91f68c89d8f3 ("block: fix infinite loop in __getblk_slow") is not good: a successful call to grow_buffers() cannot guarantee that the page won't be reclaimed before the immediate next call to __find_get_block(), which is why there was always a loop there. Yesterday I got "EXT4-fs error (device loop0): __ext4_get_inode_loc:3595: inode #19278: block 664: comm cc1: unable to read itable block" on console, which pointed to this commit. I've been trying to bisect for weeks, why kbuild-on-ext4-on-loop-on-tmpfs sometimes fails from a missing header file, under memory pressure on ppc G5. I've never seen this on x86, and I've never seen it on 3.5-rc7 itself, despite that commit being in there: bisection pointed to an irrelevant pinctrl merge, but hard to tell when failure takes between 18 minutes and 38 hours (but so far it's happened quicker on 3.6-rc2). (I've since found such __ext4_get_inode_loc errors in /var/log/messages from previous weeks: why the message never appeared on console until yesterday morning is a mystery for another day.) Revert 91f68c89d8f3, restoring __getblk_slow() to how it was (plus a checkpatch nitfix). Simplify the interface between grow_buffers() and grow_dev_page(), and avoid the infinite loop beyond end of device by instead checking init_page_buffers()'s end_block there (I presume that's more efficient than a repeated call to blkdev_max_block()), returning -ENXIO to __getblk_slow() in that case. And remove akpm's ten-year-old "__getblk() cannot fail ... weird" comment, but that is worrying: are all users of __getblk() really now prepared for a NULL bh beyond end of device, or will some oops?? Signed-off-by: Hugh Dickins Cc: stable@vger.kernel.org # 3.0 3.2 3.4 3.5 Signed-off-by: Jens Axboe --- fs/buffer.c | 66 ++++++++++++++++++++++++----------------------------- 1 file changed, 30 insertions(+), 36 deletions(-) diff --git a/fs/buffer.c b/fs/buffer.c index 9f6d2e41281d..58e2e7b77372 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -914,7 +914,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head) /* * Initialise the state of a blockdev page's buffers. */ -static void +static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { @@ -936,33 +936,41 @@ init_page_buffers(struct page *page, struct block_device *bdev, block++; bh = bh->b_this_page; } while (bh != head); + + /* + * Caller needs to validate requested block against end of device. + */ + return end_block; } /* * Create the page-cache page that contains the requested block. * - * This is user purely for blockdev mappings. + * This is used purely for blockdev mappings. */ -static struct page * +static int grow_dev_page(struct block_device *bdev, sector_t block, - pgoff_t index, int size) + pgoff_t index, int size, int sizebits) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; + sector_t end_block; + int ret = 0; /* Will call free_more_memory() */ page = find_or_create_page(inode->i_mapping, index, (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); if (!page) - return NULL; + return ret; BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { - init_page_buffers(page, bdev, block, size); - return page; + end_block = init_page_buffers(page, bdev, + index << sizebits, size); + goto done; } if (!try_to_free_buffers(page)) goto failed; @@ -982,14 +990,14 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - init_page_buffers(page, bdev, block, size); + end_block = init_page_buffers(page, bdev, index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); - return page; - +done: + ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); page_cache_release(page); - return NULL; + return ret; } /* @@ -999,7 +1007,6 @@ failed: static int grow_buffers(struct block_device *bdev, sector_t block, int size) { - struct page *page; pgoff_t index; int sizebits; @@ -1023,22 +1030,14 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) bdevname(bdev, b)); return -EIO; } - block = index << sizebits; + /* Create a page with the proper size buffers.. */ - page = grow_dev_page(bdev, block, index, size); - if (!page) - return 0; - unlock_page(page); - page_cache_release(page); - return 1; + return grow_dev_page(bdev, block, index, size, sizebits); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { - int ret; - struct buffer_head *bh; - /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { @@ -1051,21 +1050,20 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) return NULL; } -retry: - bh = __find_get_block(bdev, block, size); - if (bh) - return bh; + for (;;) { + struct buffer_head *bh; + int ret; - ret = grow_buffers(bdev, block, size); - if (ret == 0) { - free_more_memory(); - goto retry; - } else if (ret > 0) { bh = __find_get_block(bdev, block, size); if (bh) return bh; + + ret = grow_buffers(bdev, block, size); + if (ret < 0) + return NULL; + if (ret == 0) + free_more_memory(); } - return NULL; } /* @@ -1321,10 +1319,6 @@ EXPORT_SYMBOL(__find_get_block); * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * - * __getblk() cannot fail - it just keeps trying. If you pass it an - * illegal block number, __getblk() will happily return a buffer_head - * which represents the non-existent block. Very weird. - * * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers() * attempt is failing. FIXME, perhaps? */ From c944b0b9354ea06ffb0c8a7178949f1185f9f499 Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Sat, 18 Aug 2012 14:27:32 +0800 Subject: [PATCH 122/208] ARM: imx6: spin the cpu until hardware takes it down Though commit 602bf40 (ARM: imx6: exit coherency when shutting down a cpu) improves the stability of imx6q cpu hotplug a lot, there are still hangs seen with a more stressful hotplug testing. It's expected that once imx_enable_cpu(cpu, false) is called, the cpu will be taken down by hardware immediately, and the code after that will not get any chance to execute. However, this is not always the case from the testing. The cpu could possibly be alive for a few cycles before hardware actually takes it down. So rather than letting cpu execute some code that could cause a hang in these cycles, let's make the cpu spin there and wait for hardware to take it down. Cc: Signed-off-by: Shawn Guo --- arch/arm/mach-imx/hotplug.c | 23 +++-------------------- 1 file changed, 3 insertions(+), 20 deletions(-) diff --git a/arch/arm/mach-imx/hotplug.c b/arch/arm/mach-imx/hotplug.c index 20ed2d56c1af..f8f7437c83b8 100644 --- a/arch/arm/mach-imx/hotplug.c +++ b/arch/arm/mach-imx/hotplug.c @@ -42,22 +42,6 @@ static inline void cpu_enter_lowpower(void) : "cc"); } -static inline void cpu_leave_lowpower(void) -{ - unsigned int v; - - asm volatile( - "mrc p15, 0, %0, c1, c0, 0\n" - " orr %0, %0, %1\n" - " mcr p15, 0, %0, c1, c0, 0\n" - " mrc p15, 0, %0, c1, c0, 1\n" - " orr %0, %0, %2\n" - " mcr p15, 0, %0, c1, c0, 1\n" - : "=&r" (v) - : "Ir" (CR_C), "Ir" (0x40) - : "cc"); -} - /* * platform-specific code to shutdown a CPU * @@ -67,11 +51,10 @@ void platform_cpu_die(unsigned int cpu) { cpu_enter_lowpower(); imx_enable_cpu(cpu, false); - cpu_do_idle(); - cpu_leave_lowpower(); - /* We should never return from idle */ - panic("cpu %d unexpectedly exit from shutdown\n", cpu); + /* spin here until hardware takes it down */ + while (1) + ; } int platform_cpu_disable(unsigned int cpu) From a46d2619d7180bda12bad2bf15bbd0731dfc2dcf Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Wed, 22 Aug 2012 21:46:39 +0800 Subject: [PATCH 123/208] ARM: dts: imx51-babbage: fix esdhc cd/wp properties The binding doc and dts use properties "fsl,{cd,wp}-internal" while esdhc driver uses "fsl,{cd,wp}-controller". Fix binding doc and dts to get them match driver code. Reported-by: Chris Ball Signed-off-by: Shawn Guo Cc: Acked-by: Chris Ball --- Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt | 8 ++++---- arch/arm/boot/dts/imx51-babbage.dts | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt index 70cd49b1caa8..1dd622546d06 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt @@ -10,8 +10,8 @@ Required properties: - compatible : Should be "fsl,-esdhc" Optional properties: -- fsl,cd-internal : Indicate to use controller internal card detection -- fsl,wp-internal : Indicate to use controller internal write protection +- fsl,cd-controller : Indicate to use controller internal card detection +- fsl,wp-controller : Indicate to use controller internal write protection Examples: @@ -19,8 +19,8 @@ esdhc@70004000 { compatible = "fsl,imx51-esdhc"; reg = <0x70004000 0x4000>; interrupts = <1>; - fsl,cd-internal; - fsl,wp-internal; + fsl,cd-controller; + fsl,wp-controller; }; esdhc@70008000 { diff --git a/arch/arm/boot/dts/imx51-babbage.dts b/arch/arm/boot/dts/imx51-babbage.dts index cd86177a3ea2..59d9789e5508 100644 --- a/arch/arm/boot/dts/imx51-babbage.dts +++ b/arch/arm/boot/dts/imx51-babbage.dts @@ -25,8 +25,8 @@ aips@70000000 { /* aips-1 */ spba@70000000 { esdhc@70004000 { /* ESDHC1 */ - fsl,cd-internal; - fsl,wp-internal; + fsl,cd-controller; + fsl,wp-controller; status = "okay"; }; From a1dca315ce3f78347bca8ce8befe3cc71ae63b7e Mon Sep 17 00:00:00 2001 From: Gabor Juhos Date: Thu, 23 Aug 2012 15:35:26 +0200 Subject: [PATCH 124/208] MIPS: pci-ar724x: avoid data bus error due to a missing PCIe module If the controller has no PCIe module attached, accessing of the device configuration space causes a data bus error. Avoid this by checking the status of the PCIe link in advance, and indicate an error if the link is down. Signed-off-by: Gabor Juhos Cc: stable@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/4293/ Signed-off-by: Ralf Baechle --- arch/mips/pci/pci-ar724x.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c index 414a7459858d..86d77a666458 100644 --- a/arch/mips/pci/pci-ar724x.c +++ b/arch/mips/pci/pci-ar724x.c @@ -23,9 +23,12 @@ #define AR724X_PCI_MEM_BASE 0x10000000 #define AR724X_PCI_MEM_SIZE 0x08000000 +#define AR724X_PCI_REG_RESET 0x18 #define AR724X_PCI_REG_INT_STATUS 0x4c #define AR724X_PCI_REG_INT_MASK 0x50 +#define AR724X_PCI_RESET_LINK_UP BIT(0) + #define AR724X_PCI_INT_DEV0 BIT(14) #define AR724X_PCI_IRQ_COUNT 1 @@ -38,6 +41,15 @@ static void __iomem *ar724x_pci_ctrl_base; static u32 ar724x_pci_bar0_value; static bool ar724x_pci_bar0_is_cached; +static bool ar724x_pci_link_up; + +static inline bool ar724x_pci_check_link(void) +{ + u32 reset; + + reset = __raw_readl(ar724x_pci_ctrl_base + AR724X_PCI_REG_RESET); + return reset & AR724X_PCI_RESET_LINK_UP; +} static int ar724x_pci_read(struct pci_bus *bus, unsigned int devfn, int where, int size, uint32_t *value) @@ -46,6 +58,9 @@ static int ar724x_pci_read(struct pci_bus *bus, unsigned int devfn, int where, void __iomem *base; u32 data; + if (!ar724x_pci_link_up) + return PCIBIOS_DEVICE_NOT_FOUND; + if (devfn) return PCIBIOS_DEVICE_NOT_FOUND; @@ -96,6 +111,9 @@ static int ar724x_pci_write(struct pci_bus *bus, unsigned int devfn, int where, u32 data; int s; + if (!ar724x_pci_link_up) + return PCIBIOS_DEVICE_NOT_FOUND; + if (devfn) return PCIBIOS_DEVICE_NOT_FOUND; @@ -280,6 +298,10 @@ int __init ar724x_pcibios_init(int irq) if (ar724x_pci_ctrl_base == NULL) goto err_unmap_devcfg; + ar724x_pci_link_up = ar724x_pci_check_link(); + if (!ar724x_pci_link_up) + pr_warn("ar724x: PCIe link is down\n"); + ar724x_pci_irq_init(irq); register_pci_controller(&ar724x_pci_controller); From c96aae1f7f393387d160211f60398d58463a7e65 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 17 Aug 2012 16:43:28 -0400 Subject: [PATCH 125/208] xen/setup: Fix one-off error when adding for-balloon PFNs to the P2M. When we are finished with return PFNs to the hypervisor, then populate it back, and also mark the E820 MMIO and E820 gaps as IDENTITY_FRAMEs, we then call P2M to set areas that can be used for ballooning. We were off by one, and ended up over-writting a P2M entry that most likely was an IDENTITY_FRAME. For example: 1-1 mapping on 40000->40200 1-1 mapping on bc558->bc5ac 1-1 mapping on bc5b4->bc8c5 1-1 mapping on bc8c6->bcb7c 1-1 mapping on bcd00->100000 Released 614 pages of unused memory Set 277889 page(s) to 1-1 mapping Populating 40200-40466 pfn range: 614 pages added => here we set from 40466 up to bc559 P2M tree to be INVALID_P2M_ENTRY. We should have done it up to bc558. The end result is that if anybody is trying to construct a PTE for PFN bc558 they end up with ~PAGE_PRESENT. CC: stable@vger.kernel.org Reported-by-and-Tested-by: Andre Przywara Signed-off-by: Konrad Rzeszutek Wilk --- arch/x86/xen/setup.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index ead85576d54a..d11ca11d14fc 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -78,9 +78,16 @@ static void __init xen_add_extra_mem(u64 start, u64 size) memblock_reserve(start, size); xen_max_p2m_pfn = PFN_DOWN(start + size); + for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) { + unsigned long mfn = pfn_to_mfn(pfn); + + if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) + continue; + WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", + pfn, mfn); - for (pfn = PFN_DOWN(start); pfn <= xen_max_p2m_pfn; pfn++) __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); + } } static unsigned long __init xen_do_chunk(unsigned long start, From c7a9b09b1a4a1fbccb2ec409daec95f9068d77c0 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 15 Aug 2012 20:51:54 +0000 Subject: [PATCH 126/208] ARM: omap: allow building omap44xx without SMP The new omap4 cpuidle implementation currently requires ARCH_NEEDS_CPU_IDLE_COUPLED, which only works on SMP. This patch makes it possible to build a non-SMP kernel for that platform. This is not normally desired for end-users but can be useful for testing. Without this patch, building rand-0y2jSKT results in: drivers/cpuidle/coupled.c: In function 'cpuidle_coupled_poke': drivers/cpuidle/coupled.c:317:3: error: implicit declaration of function '__smp_call_function_single' [-Werror=implicit-function-declaration] It's not clear if this patch is the best solution for the problem at hand. I have made sure that we can now build the kernel in all configurations, but that does not mean it will actually work on an OMAP44xx. Signed-off-by: Arnd Bergmann Acked-by: Santosh Shilimkar Tested-by: Santosh Shilimkar Cc: Kevin Hilman Cc: Tony Lindgren --- arch/arm/mach-omap2/Kconfig | 2 +- arch/arm/mach-omap2/cpuidle44xx.c | 3 ++- include/linux/cpuidle.h | 4 ++++ 3 files changed, 7 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index dd2db025f778..66a8be331caf 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -62,7 +62,7 @@ config ARCH_OMAP4 select PM_OPP if PM select USB_ARCH_HAS_EHCI if USB_SUPPORT select ARM_CPU_SUSPEND if PM - select ARCH_NEEDS_CPU_IDLE_COUPLED + select ARCH_NEEDS_CPU_IDLE_COUPLED if SMP config SOC_OMAP5 bool "TI OMAP5" diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index ee05e193fc61..288bee6cbb76 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -238,8 +238,9 @@ int __init omap4_idle_init(void) for_each_cpu(cpu_id, cpu_online_mask) { dev = &per_cpu(omap4_idle_dev, cpu_id); dev->cpu = cpu_id; +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED dev->coupled_cpus = *cpu_online_mask; - +#endif cpuidle_register_driver(&omap4_idle_driver); if (cpuidle_register_device(dev)) { diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 040b13b5c14a..279b1eaa8b73 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -194,6 +194,10 @@ static inline int cpuidle_play_dead(void) {return -ENODEV; } #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a); +#else +static inline void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a) +{ +} #endif /****************************** From a28eecef8ac2671dce7d892165bf374eeaa04e15 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 15 Aug 2012 21:56:39 +0000 Subject: [PATCH 127/208] ARM: imx: build pm-imx5 code only when PM is enabled This moves the imx5 pm code out of the list of unconditionally compiled files for imx5, mirroring what we already do for imx6 and how it was done before the code was move from mach-mx5 to mach-imx in v3.3. Without this patch, building with CONFIG_PM disabled results in: arch/arm/mach-imx/pm-imx5.c:202:116: error: redefinition of 'imx51_pm_init' arch/arm/mach-imx/include/mach-imx/common.h:154:91: note: previous definition of 'imx51_pm_init' was here arch/arm/mach-imx/pm-imx5.c:209:116: error: redefinition of 'imx53_pm_init' arch/arm/mach-imx/include/mach-imx/common.h:155:91: note: previous definition of 'imx53_pm_init' was here Signed-off-by: Arnd Bergmann Acked-by: Shawn Guo Cc: Sascha Hauer Cc: stable@vger.kernel.org --- arch/arm/mach-imx/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index 07f7c226e4cf..e08adb7b8dd5 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -9,7 +9,8 @@ obj-$(CONFIG_SOC_IMX27) += clk-imx27.o mm-imx27.o ehci-imx27.o obj-$(CONFIG_SOC_IMX31) += mm-imx3.o cpu-imx31.o clk-imx31.o iomux-imx31.o ehci-imx31.o pm-imx3.o obj-$(CONFIG_SOC_IMX35) += mm-imx3.o cpu-imx35.o clk-imx35.o ehci-imx35.o pm-imx3.o -obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o pm-imx5.o cpu_op-mx51.o +imx5-pm-$(CONFIG_PM) += pm-imx5.o +obj-$(CONFIG_SOC_IMX5) += cpu-imx5.o mm-imx5.o clk-imx51-imx53.o ehci-imx5.o $(imx5-pm-y) cpu_op-mx51.o obj-$(CONFIG_COMMON_CLK) += clk-pllv1.o clk-pllv2.o clk-pllv3.o clk-gate2.o \ clk-pfd.o clk-busy.o From 9f9ba0fdecff64ffc6986645216ffc3a8b664f08 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 16 Aug 2012 07:42:50 +0000 Subject: [PATCH 128/208] ARM: imx: fix ksz9021rn_phy_fixup The ksz9021rn_phy_fixup and mx6q_sabrelite functions try to set up an ethernet phy if they can. They do check whether phylib is enabled, but unfortunately the functions can only be called from platform code if phylib is builtin, not if it is a module Without this patch, building with a modular phylib results in: arch/arm/mach-imx/mach-imx6q.c: In function 'imx6q_sabrelite_init': arch/arm/mach-imx/mach-imx6q.c:120:5: error: 'ksz9021rn_phy_fixup' undeclared (first use in this function) arch/arm/mach-imx/mach-imx6q.c:120:5: note: each undeclared identifier is reported only once for each function it appears in The bug was originally reported by Artem Bityutskiy but only partially fixed in ef441806 "ARM: imx6q: register phy fixup only when CONFIG_PHYLIB is enabled". Signed-off-by: Arnd Bergmann Acked-by: Shawn Guo Cc: Artem Bityutskiy Cc: Sascha Hauer --- arch/arm/mach-imx/mach-imx6q.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 5ec0608f2a76..045b3f6a387d 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -71,7 +71,7 @@ soft: /* For imx6q sabrelite board: set KSZ9021RN RGMII pad skew */ static int ksz9021rn_phy_fixup(struct phy_device *phydev) { - if (IS_ENABLED(CONFIG_PHYLIB)) { + if (IS_BUILTIN(CONFIG_PHYLIB)) { /* min rx data delay */ phy_write(phydev, 0x0b, 0x8105); phy_write(phydev, 0x0c, 0x0000); @@ -112,7 +112,7 @@ put_clk: static void __init imx6q_sabrelite_init(void) { - if (IS_ENABLED(CONFIG_PHYLIB)) + if (IS_BUILTIN(CONFIG_PHYLIB)) phy_register_fixup_for_uid(PHY_ID_KSZ9021, MICREL_PHY_ID_MASK, ksz9021rn_phy_fixup); imx6q_sabrelite_cko1_setup(); From f637c4c9405e21f44cf0045eaf77eddd3a79ca5a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 16 Aug 2012 10:40:40 +0000 Subject: [PATCH 129/208] ARM: imx: select CPU_FREQ_TABLE when needed The i.MX cpufreq implementation uses the CPU_FREQ_TABLE helpers, so it needs to select that code to be built. This problem has apparently existed since the i.MX cpufreq code was first merged in v2.6.37. Building IMX without CPU_FREQ_TABLE results in: arch/arm/plat-mxc/built-in.o: In function `mxc_cpufreq_exit': arch/arm/plat-mxc/cpufreq.c:173: undefined reference to `cpufreq_frequency_table_put_attr' arch/arm/plat-mxc/built-in.o: In function `mxc_set_target': arch/arm/plat-mxc/cpufreq.c:84: undefined reference to `cpufreq_frequency_table_target' arch/arm/plat-mxc/built-in.o: In function `mxc_verify_speed': arch/arm/plat-mxc/cpufreq.c:65: undefined reference to `cpufreq_frequency_table_verify' arch/arm/plat-mxc/built-in.o: In function `mxc_cpufreq_init': arch/arm/plat-mxc/cpufreq.c:154: undefined reference to `cpufreq_frequency_table_cpuinfo' arch/arm/plat-mxc/cpufreq.c:162: undefined reference to `cpufreq_frequency_table_get_attr' Signed-off-by: Arnd Bergmann Acked-by: Shawn Guo Cc: Sascha Hauer Cc: Yong Shen Cc: stable@vger.kernel.org --- arch/arm/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index e91c7cdc6fe5..84b5a0cb7a5c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2150,6 +2150,7 @@ source "drivers/cpufreq/Kconfig" config CPU_FREQ_IMX tristate "CPUfreq driver for i.MX CPUs" depends on ARCH_MXC && CPU_FREQ + select CPU_FREQ_TABLE help This enables the CPUfreq driver for i.MX CPUs. From 1fc593feaf8e440511f381f4cdff483b55bbf546 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 17 Aug 2012 00:16:08 +0000 Subject: [PATCH 130/208] ARM: imx: build i.MX6 functions only when needed The head-v7.S contains a call to the generic cpu_suspend function, which is only available when selected by the i.MX6 code. As pointed out by Shawn Guo, i.MX5 does not actually use any functions defined in head-v7.S. It is also needed only for the i.MX6 power management code and for the SMP code, so we can restrict building this file to situations in which at least one of those two is present. Finally, other platforms with a similar file call it headsmp.S, so we can rename it to the same for consistency. Without this patch, building imx5 standalone results in: arch/arm/mach-imx/built-in.o: In function `v7_cpu_resume': arch/arm/mach-imx/head-v7.S:104: undefined reference to `cpu_resume' Signed-off-by: Arnd Bergmann Acked-by: Shawn Guo Cc: Eric Miao Cc: stable@vger.kernel.org --- arch/arm/mach-imx/Makefile | 7 +++---- arch/arm/mach-imx/{head-v7.S => headsmp.S} | 0 2 files changed, 3 insertions(+), 4 deletions(-) rename arch/arm/mach-imx/{head-v7.S => headsmp.S} (100%) diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index e08adb7b8dd5..d004d37ad9d8 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -71,14 +71,13 @@ obj-$(CONFIG_DEBUG_LL) += lluart.o obj-$(CONFIG_HAVE_IMX_GPC) += gpc.o obj-$(CONFIG_HAVE_IMX_MMDC) += mmdc.o obj-$(CONFIG_HAVE_IMX_SRC) += src.o -obj-$(CONFIG_CPU_V7) += head-v7.o -AFLAGS_head-v7.o :=-Wa,-march=armv7-a -obj-$(CONFIG_SMP) += platsmp.o +AFLAGS_headsmp.o :=-Wa,-march=armv7-a +obj-$(CONFIG_SMP) += headsmp.o platsmp.o obj-$(CONFIG_HOTPLUG_CPU) += hotplug.o obj-$(CONFIG_SOC_IMX6Q) += clk-imx6q.o mach-imx6q.o ifeq ($(CONFIG_PM),y) -obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o +obj-$(CONFIG_SOC_IMX6Q) += pm-imx6q.o headsmp.o endif # i.MX5 based machines diff --git a/arch/arm/mach-imx/head-v7.S b/arch/arm/mach-imx/headsmp.S similarity index 100% rename from arch/arm/mach-imx/head-v7.S rename to arch/arm/mach-imx/headsmp.S From db43b184685632b7c23ccd47ec08b61010d55798 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 15 Aug 2012 20:34:48 +0000 Subject: [PATCH 131/208] ARM: ux500: don't select LEDS_GPIO for snowball Using 'select' in Kconfig is hard, a platform cannot just enable a driver without also making sure that its subsystem is there. Also, there is no actual code dependency between the platform and the gpio leds driver. Without this patch, building without LEDS_CLASS esults in: drivers/built-in.o: In function `create_gpio_led.part.2': governor_userspace.c:(.devinit.text+0x5a58): undefined reference to `led_classdev_register' drivers/built-in.o: In function `gpio_led_remove': governor_userspace.c:(.devexit.text+0x6b8): undefined reference to `led_classdev_unregister' This reverts 8733f53c6 "ARM: ux500: Kconfig: Compile in leds-gpio support for Snowball" that introduced the regression and did not provide a helpful explanation. In order to leave the GPIO LED code still present in normal builds, this also enables the symbol in u8500_defconfig, in addition to the other LED drivers that are already selected there. Signed-off-by: Arnd Bergmann Cc: Linus Walleij Cc: Lee Jones --- arch/arm/configs/u8500_defconfig | 1 + arch/arm/mach-ux500/Kconfig | 1 - 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig index 2d4f661d1cf6..da6845493caa 100644 --- a/arch/arm/configs/u8500_defconfig +++ b/arch/arm/configs/u8500_defconfig @@ -86,6 +86,7 @@ CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y CONFIG_LEDS_LM3530=y CONFIG_LEDS_LP5521=y +CONFIG_LEDS_GPIO=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_AB8500=y CONFIG_RTC_DRV_PL031=y diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig index c013bbf79cac..53d3d46dec12 100644 --- a/arch/arm/mach-ux500/Kconfig +++ b/arch/arm/mach-ux500/Kconfig @@ -41,7 +41,6 @@ config MACH_HREFV60 config MACH_SNOWBALL bool "U8500 Snowball platform" select MACH_MOP500 - select LEDS_GPIO help Include support for the snowball development platform. From 823f74733d8f89eaabfb25f93680fb7e05861348 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 22 Aug 2012 13:43:24 -0500 Subject: [PATCH 132/208] powerpc/fsl: update defconfigs run make savedefconfig on fsl defconfigs. Signed-off-by: Kim Phillips Signed-off-by: Kumar Gala --- arch/powerpc/configs/85xx/p1023rds_defconfig | 30 ++++++------------- arch/powerpc/configs/corenet32_smp_defconfig | 30 ++++++------------- arch/powerpc/configs/mpc83xx_defconfig | 17 +++-------- arch/powerpc/configs/mpc85xx_defconfig | 31 +++++--------------- arch/powerpc/configs/mpc85xx_smp_defconfig | 31 +++++--------------- 5 files changed, 36 insertions(+), 103 deletions(-) diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig index f4337bacd0e7..a79b0a9316a5 100644 --- a/arch/powerpc/configs/85xx/p1023rds_defconfig +++ b/arch/powerpc/configs/85xx/p1023rds_defconfig @@ -6,28 +6,27 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_AUDIT=y -CONFIG_SPARSE_IRQ=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_KALLSYMS_ALL=y -CONFIG_KALLSYMS_EXTRA_PASS=y CONFIG_EMBEDDED=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y CONFIG_P1023_RDS=y CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_CPM2=y -CONFIG_GPIO_MPC8XXX=y CONFIG_HIGHMEM=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y @@ -67,7 +66,6 @@ CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_MISC_DEVICES=y CONFIG_EEPROM_LEGACY=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y @@ -80,15 +78,14 @@ CONFIG_SATA_FSL=y CONFIG_SATA_SIL24=y CONFIG_NETDEVICES=y CONFIG_DUMMY=y +CONFIG_FS_ENET=y +CONFIG_FSL_PQ_MDIO=y +CONFIG_E1000E=y CONFIG_MARVELL_PHY=y CONFIG_DAVICOM_PHY=y CONFIG_CICADA_PHY=y CONFIG_VITESSE_PHY=y CONFIG_FIXED_PHY=y -CONFIG_NET_ETHERNET=y -CONFIG_FS_ENET=y -CONFIG_E1000E=y -CONFIG_FSL_PQ_MDIO=y CONFIG_INPUT_FF_MEMLESS=m # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set @@ -98,16 +95,15 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 CONFIG_SERIAL_8250_RUNTIME_UARTS=2 -CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y CONFIG_SERIAL_QE=m -CONFIG_HW_RANDOM=y CONFIG_NVRAM=y CONFIG_I2C=y CONFIG_I2C_CPM=m CONFIG_I2C_MPC=y +CONFIG_GPIO_MPC8XXX=y # CONFIG_HWMON is not set CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_SOUND=y @@ -123,7 +119,6 @@ CONFIG_DMADEVICES=y CONFIG_FSL_DMA=y # CONFIG_NET_DMA is not set CONFIG_STAGING=y -# CONFIG_STAGING_EXCLUDE_BUILD is not set CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set @@ -150,22 +145,15 @@ CONFIG_QNX4FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y CONFIG_CRC_T10DIF=y CONFIG_FRAME_WARN=8092 CONFIG_DEBUG_FS=y -CONFIG_DEBUG_KERNEL=y CONFIG_DETECT_HUNG_TASK=y # CONFIG_DEBUG_BUGVERBOSE is not set CONFIG_DEBUG_INFO=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y -CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig index cbb98c1234fd..f085699dab7c 100644 --- a/arch/powerpc/configs/corenet32_smp_defconfig +++ b/arch/powerpc/configs/corenet32_smp_defconfig @@ -6,8 +6,8 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_AUDIT=y -CONFIG_SPARSE_IRQ=y -CONFIG_RCU_TRACE=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -21,23 +21,22 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y CONFIG_P2041_RDB=y CONFIG_P3041_DS=y CONFIG_P4080_DS=y CONFIG_P5020_DS=y CONFIG_HIGHMEM=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_BINFMT_MISC=m CONFIG_KEXEC=y CONFIG_IRQ_ALL_CPUS=y CONFIG_FORCE_MAX_ZONEORDER=13 -CONFIG_FSL_LBC=y CONFIG_PCI=y CONFIG_PCIEPORTBUS=y -CONFIG_PCI_MSI=y # CONFIG_PCIEASPM is not set +CONFIG_PCI_MSI=y CONFIG_RAPIDIO=y CONFIG_FSL_RIO=y CONFIG_NET=y @@ -77,17 +76,14 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_PHYSMAP_OF=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_ECC=y -CONFIG_MTD_NAND_IDS=y -CONFIG_MTD_NAND_FSL_IFC=y -CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_M25P80=y +CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_FSL_ELBC=y +CONFIG_MTD_NAND_FSL_IFC=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_MISC_DEVICES=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -115,11 +111,9 @@ CONFIG_SERIO_LIBPS2=y CONFIG_PPC_EPAPR_HV_BYTECHAN=y CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y -CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y -CONFIG_HW_RANDOM=y CONFIG_NVRAM=y CONFIG_I2C=y CONFIG_I2C_CHARDEV=y @@ -132,7 +126,6 @@ CONFIG_SPI_FSL_ESPI=y CONFIG_VIDEO_OUTPUT_CONTROL=y CONFIG_USB_HID=m CONFIG_USB=y -CONFIG_USB_DEVICEFS=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_FSL=y @@ -142,8 +135,6 @@ CONFIG_USB_OHCI_HCD_PPC_OF_LE=y CONFIG_USB_STORAGE=y CONFIG_MMC=y CONFIG_MMC_SDHCI=y -CONFIG_MMC_SDHCI_OF=y -CONFIG_MMC_SDHCI_OF_ESDHC=y CONFIG_EDAC=y CONFIG_EDAC_MM_EDAC=y CONFIG_EDAC_MPC85XX=y @@ -170,19 +161,16 @@ CONFIG_HUGETLBFS=y CONFIG_JFFS2_FS=y CONFIG_CRAMFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NFSD=m -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=m CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_SHIRQ=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y -CONFIG_SYSCTL_SYSCALL_CHECK=y +CONFIG_RCU_TRACE=y CONFIG_CRYPTO_NULL=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_MD4=y diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index 5aac9a8bc53b..e116dc9e8a2e 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -2,12 +2,12 @@ CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y -# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set CONFIG_EXPERT=y CONFIG_SLAB=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y # CONFIG_PPC_CHRP is not set # CONFIG_PPC_PMAC is not set CONFIG_PPC_83xx=y @@ -25,7 +25,6 @@ CONFIG_ASP834x=y CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_MATH_EMULATION=y -CONFIG_SPARSE_IRQ=y CONFIG_PCI=y CONFIG_NET=y CONFIG_PACKET=y @@ -44,8 +43,6 @@ CONFIG_INET_ESP=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" # CONFIG_FW_LOADER is not set CONFIG_MTD=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_OF_PARTS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y @@ -64,15 +61,14 @@ CONFIG_ATA=y CONFIG_SATA_FSL=y CONFIG_SATA_SIL=y CONFIG_NETDEVICES=y +CONFIG_MII=y +CONFIG_UCC_GETH=y +CONFIG_GIANFAR=y CONFIG_MARVELL_PHY=y CONFIG_DAVICOM_PHY=y CONFIG_VITESSE_PHY=y CONFIG_ICPLUS_PHY=y CONFIG_FIXED_PHY=y -CONFIG_NET_ETHERNET=y -CONFIG_MII=y -CONFIG_GIANFAR=y -CONFIG_UCC_GETH=y CONFIG_INPUT_FF_MEMLESS=m # CONFIG_INPUT_MOUSEDEV is not set # CONFIG_INPUT_KEYBOARD is not set @@ -112,17 +108,12 @@ CONFIG_RTC_DRV_DS1374=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y # CONFIG_EXT3_DEFAULTS_TO_ORDERED is not set -CONFIG_INOTIFY=y CONFIG_PROC_KCORE=y CONFIG_TMPFS=y CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y -CONFIG_PARTITION_ADVANCED=y CONFIG_CRC_T10DIF=y -# CONFIG_RCU_CPU_STALL_DETECTOR is not set -CONFIG_SYSCTL_SYSCALL_CHECK=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_SHA256=y diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index 99a4dd3b30cc..a036a622be5a 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -5,7 +5,9 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_AUDIT=y -CONFIG_SPARSE_IRQ=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -17,6 +19,8 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y CONFIG_MPC8540_ADS=y CONFIG_MPC8560_ADS=y CONFIG_MPC85xx_CDS=y @@ -40,8 +44,6 @@ CONFIG_SBC8548=y CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_HIGHMEM=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y CONFIG_FORCE_MAX_ZONEORDER=12 @@ -78,32 +80,20 @@ CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y CONFIG_FTL=y -CONFIG_MTD_GEN_PROBE=y -CONFIG_MTD_MAP_BANK_WIDTH_1=y -CONFIG_MTD_MAP_BANK_WIDTH_2=y -CONFIG_MTD_MAP_BANK_WIDTH_4=y -CONFIG_MTD_CFI_I1=y -CONFIG_MTD_CFI_I2=y +CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_CFI_UTIL=y CONFIG_MTD_PHYSMAP_OF=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_OF_PARTS=y +CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_NAND_FSL_IFC=y -CONFIG_MTD_NAND_IDS=y -CONFIG_MTD_NAND_ECC=y -CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_MISC_DEVICES=y CONFIG_EEPROM_LEGACY=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y @@ -135,7 +125,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 CONFIG_SERIAL_8250_RUNTIME_UARTS=2 -CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y @@ -184,7 +173,6 @@ CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y CONFIG_USB=y -CONFIG_USB_DEVICEFS=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_FSL=y @@ -230,18 +218,13 @@ CONFIG_QNX4FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y CONFIG_CRC_T10DIF=y CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y -CONFIG_SYSCTL_SYSCALL_CHECK=y -CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index fdfa84dc908f..4ba5255232bc 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -7,7 +7,9 @@ CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_AUDIT=y -CONFIG_SPARSE_IRQ=y +CONFIG_IRQ_DOMAIN_DEBUG=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 @@ -19,6 +21,8 @@ CONFIG_MODULE_UNLOAD=y CONFIG_MODULE_FORCE_UNLOAD=y CONFIG_MODVERSIONS=y # CONFIG_BLK_DEV_BSG is not set +CONFIG_PARTITION_ADVANCED=y +CONFIG_MAC_PARTITION=y CONFIG_MPC8540_ADS=y CONFIG_MPC8560_ADS=y CONFIG_MPC85xx_CDS=y @@ -42,8 +46,6 @@ CONFIG_SBC8548=y CONFIG_QUICC_ENGINE=y CONFIG_QE_GPIO=y CONFIG_HIGHMEM=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_BINFMT_MISC=m CONFIG_MATH_EMULATION=y CONFIG_IRQ_ALL_CPUS=y @@ -81,32 +83,20 @@ CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y CONFIG_MTD_BLOCK=y -CONFIG_MTD_CFI=y CONFIG_FTL=y -CONFIG_MTD_GEN_PROBE=y -CONFIG_MTD_MAP_BANK_WIDTH_1=y -CONFIG_MTD_MAP_BANK_WIDTH_2=y -CONFIG_MTD_MAP_BANK_WIDTH_4=y -CONFIG_MTD_CFI_I1=y -CONFIG_MTD_CFI_I2=y +CONFIG_MTD_CFI=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_CFI_AMDSTD=y -CONFIG_MTD_CFI_UTIL=y CONFIG_MTD_PHYSMAP_OF=y -CONFIG_MTD_PARTITIONS=y -CONFIG_MTD_OF_PARTS=y +CONFIG_MTD_M25P80=y CONFIG_MTD_NAND=y CONFIG_MTD_NAND_FSL_ELBC=y CONFIG_MTD_NAND_FSL_IFC=y -CONFIG_MTD_NAND_IDS=y -CONFIG_MTD_NAND_ECC=y -CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_SIZE=131072 -CONFIG_MISC_DEVICES=y CONFIG_EEPROM_LEGACY=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y @@ -137,7 +127,6 @@ CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=2 CONFIG_SERIAL_8250_RUNTIME_UARTS=2 -CONFIG_SERIAL_8250_EXTENDED=y CONFIG_SERIAL_8250_MANY_PORTS=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_SERIAL_8250_RSA=y @@ -186,7 +175,6 @@ CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y CONFIG_USB=y -CONFIG_USB_DEVICEFS=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_FSL=y @@ -232,18 +220,13 @@ CONFIG_QNX4FS_FS=m CONFIG_SYSV_FS=m CONFIG_UFS_FS=m CONFIG_NFS_FS=y -CONFIG_NFS_V3=y CONFIG_NFS_V4=y CONFIG_ROOT_NFS=y CONFIG_NFSD=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y CONFIG_CRC_T10DIF=y CONFIG_DEBUG_FS=y CONFIG_DETECT_HUNG_TASK=y CONFIG_DEBUG_INFO=y -CONFIG_SYSCTL_SYSCALL_CHECK=y -CONFIG_IRQ_DOMAIN_DEBUG=y CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_SHA256=y CONFIG_CRYPTO_SHA512=y From 1267643dc311e860e728dbd09a97c2e0a773bfdb Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 22 Aug 2012 13:43:30 -0500 Subject: [PATCH 133/208] powerpc/fsl: fix "Failed to mount /dev: No such device" errors Yocto (Built by Poky 7.0) 1.2 root filesystems fail to boot, at least over nfs, with: Failed to mount /dev: No such device Configuring DEVTMPFS fixes it. Signed-off-by: Kim Phillips Signed-off-by: Kumar Gala --- arch/powerpc/configs/85xx/p1023rds_defconfig | 1 + arch/powerpc/configs/corenet32_smp_defconfig | 1 + arch/powerpc/configs/corenet64_smp_defconfig | 1 + arch/powerpc/configs/mpc83xx_defconfig | 1 + arch/powerpc/configs/mpc85xx_defconfig | 1 + arch/powerpc/configs/mpc85xx_smp_defconfig | 1 + 6 files changed, 6 insertions(+) diff --git a/arch/powerpc/configs/85xx/p1023rds_defconfig b/arch/powerpc/configs/85xx/p1023rds_defconfig index a79b0a9316a5..26e541c4662b 100644 --- a/arch/powerpc/configs/85xx/p1023rds_defconfig +++ b/arch/powerpc/configs/85xx/p1023rds_defconfig @@ -62,6 +62,7 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y diff --git a/arch/powerpc/configs/corenet32_smp_defconfig b/arch/powerpc/configs/corenet32_smp_defconfig index f085699dab7c..8b3d57c1ebe8 100644 --- a/arch/powerpc/configs/corenet32_smp_defconfig +++ b/arch/powerpc/configs/corenet32_smp_defconfig @@ -69,6 +69,7 @@ CONFIG_INET_IPCOMP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y diff --git a/arch/powerpc/configs/corenet64_smp_defconfig b/arch/powerpc/configs/corenet64_smp_defconfig index dd89de8b0b7f..0516e22ca3de 100644 --- a/arch/powerpc/configs/corenet64_smp_defconfig +++ b/arch/powerpc/configs/corenet64_smp_defconfig @@ -56,6 +56,7 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig index e116dc9e8a2e..9352e4430c3b 100644 --- a/arch/powerpc/configs/mpc83xx_defconfig +++ b/arch/powerpc/configs/mpc83xx_defconfig @@ -41,6 +41,7 @@ CONFIG_INET_ESP=y # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y # CONFIG_FW_LOADER is not set CONFIG_MTD=y CONFIG_MTD_CHAR=y diff --git a/arch/powerpc/configs/mpc85xx_defconfig b/arch/powerpc/configs/mpc85xx_defconfig index a036a622be5a..8b5bda27d248 100644 --- a/arch/powerpc/configs/mpc85xx_defconfig +++ b/arch/powerpc/configs/mpc85xx_defconfig @@ -76,6 +76,7 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y diff --git a/arch/powerpc/configs/mpc85xx_smp_defconfig b/arch/powerpc/configs/mpc85xx_smp_defconfig index 4ba5255232bc..b0974e7e98ae 100644 --- a/arch/powerpc/configs/mpc85xx_smp_defconfig +++ b/arch/powerpc/configs/mpc85xx_smp_defconfig @@ -79,6 +79,7 @@ CONFIG_INET_ESP=y CONFIG_IPV6=y CONFIG_IP_SCTP=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_DEVTMPFS=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_CHAR=y From 0b9e3f6d84ce619f697bb622d9165cccaa93d67c Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Tue, 31 Jul 2012 14:55:51 +1000 Subject: [PATCH 134/208] xfs: fix uninitialised variable in xfs_rtbuf_get() Results in this assert failure in generic/090: XFS: Assertion failed: *nmap >= 1, file: fs/xfs/xfs_bmap.c, line: 4363 ..... Call Trace: [] xfs_bmapi_read+0x6b/0x370 [] xfs_rtbuf_get+0x42/0x130 [] xfs_rtget_summary+0x89/0x120 [] xfs_rtallocate_extent_size+0xce/0x340 [] xfs_rtallocate_extent+0x240/0x290 [] xfs_bmap_rtalloc+0x1ba/0x340 [] xfs_bmap_alloc+0x35/0x40 [] xfs_bmapi_allocate+0xf1/0x350 [] xfs_bmapi_write+0x66e/0xa60 [] xfs_iomap_write_direct+0x22a/0x3f0 [] __xfs_get_blocks+0x38b/0x5d0 [] xfs_get_blocks_direct+0x14/0x20 [] do_blockdev_direct_IO+0xf71/0x1eb0 [] __blockdev_direct_IO+0x55/0x60 [] xfs_vm_direct_IO+0x11a/0x1e0 [] generic_file_direct_write+0xd7/0x1b0 [] xfs_file_dio_aio_write+0x13c/0x320 [] xfs_file_aio_write+0x1c2/0x1d0 [] do_sync_write+0xa7/0xe0 [] vfs_write+0xa8/0x160 [] sys_pwrite64+0x92/0xb0 [] system_call_fastpath+0x16/0x1b Signed-off-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_rtalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 92d4331cd4f1..ca28a4ba4b54 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -857,7 +857,7 @@ xfs_rtbuf_get( xfs_buf_t *bp; /* block buffer, result */ xfs_inode_t *ip; /* bitmap or summary inode */ xfs_bmbt_irec_t map; - int nmap; + int nmap = 1; int error; /* error value */ ip = issum ? mp->m_rsumip : mp->m_rbmip; From 761290309939743ddf97e2bd94c6da18c6436b79 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 7 Aug 2012 02:02:02 -0400 Subject: [PATCH 135/208] xfs: unlock the AGI buffer when looping in xfs_dialloc Also update some commens in the area to make the code easier to read. Signed-off-by: Christoph Hellwig Reviewed-by: Mark Tinguely Reviewed-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_ialloc.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 21e37b55f7e5..5aceb3f8ecd6 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -962,23 +962,22 @@ xfs_dialloc( if (!pag->pagi_freecount && !okalloc) goto nextag; + /* + * Then read in the AGI buffer and recheck with the AGI buffer + * lock held. + */ error = xfs_ialloc_read_agi(mp, tp, agno, &agbp); if (error) goto out_error; - /* - * Once the AGI has been read in we have to recheck - * pagi_freecount with the AGI buffer lock held. - */ if (pag->pagi_freecount) { xfs_perag_put(pag); goto out_alloc; } - if (!okalloc) { - xfs_trans_brelse(tp, agbp); - goto nextag; - } + if (!okalloc) + goto nextag_relse_buffer; + error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced); if (error) { @@ -1007,6 +1006,8 @@ xfs_dialloc( return 0; } +nextag_relse_buffer: + xfs_trans_brelse(tp, agbp); nextag: xfs_perag_put(pag); if (++agno == mp->m_sb.sb_agcount) From a672e1be30d5bc848cd0067c55ed29b2015b7c17 Mon Sep 17 00:00:00 2001 From: Tomas Racek Date: Tue, 14 Aug 2012 10:35:04 +0200 Subject: [PATCH 136/208] xfs: check for possible overflow in xfs_ioc_trim If range.start or range.minlen is bigger than filesystem size, return invalid value error. This fixes possible overflow in BTOBB macro when passed value was nearly ULLONG_MAX. Signed-off-by: Tomas Racek Reviewed-by: Dave Chinner Signed-off-by: Ben Myers --- fs/xfs/xfs_discard.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index f9c3fe304a17..69cf4fcde03e 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -179,12 +179,14 @@ xfs_ioc_trim( * used by the fstrim application. In the end it really doesn't * matter as trimming blocks is an advisory interface. */ + if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) || + range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp))) + return -XFS_ERROR(EINVAL); + start = BTOBB(range.start); end = start + BTOBBT(range.len) - 1; minlen = BTOBB(max_t(u64, granularity, range.minlen)); - if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks) - return -XFS_ERROR(EINVAL); if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1) end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1; From 22f5d115a2b087c977128f84ee557ad71530330e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Tue, 14 Aug 2012 10:53:38 +0000 Subject: [PATCH 137/208] drm: Initialize object type when using DRM_MODE() macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit DRM_MODE() macro doesn't initialize the type of the base drm object. When a copy is made of the mode, the object type is overwritten with zero, and the the object can no longer be found by drm_mode_object_find() due to the type check failing. Signed-off-by: Ville Syrjälä Signed-off-by: Dave Airlie --- include/drm/drm_crtc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index ced362533e3c..bfacf0d5a225 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -118,7 +118,8 @@ enum drm_mode_status { .hdisplay = (hd), .hsync_start = (hss), .hsync_end = (hse), \ .htotal = (ht), .hskew = (hsk), .vdisplay = (vd), \ .vsync_start = (vss), .vsync_end = (vse), .vtotal = (vt), \ - .vscan = (vs), .flags = (f), .vrefresh = 0 + .vscan = (vs), .flags = (f), .vrefresh = 0, \ + .base.type = DRM_MODE_OBJECT_MODE #define CRTC_INTERLACE_HALVE_V 0x1 /* halve V values for interlacing */ From 7c4eaca4162d0b5ad4fb39f974d7ffd71b9daa09 Mon Sep 17 00:00:00 2001 From: Jakob Bornecrantz Date: Thu, 16 Aug 2012 08:29:03 +0000 Subject: [PATCH 138/208] drm: Check for invalid cursor flags Signed-off-by: Jakob Bornecrantz Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_crtc.c | 2 +- include/drm/drm_mode.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index 08a7aa722d6b..6fbfc244748f 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -1981,7 +1981,7 @@ int drm_mode_cursor_ioctl(struct drm_device *dev, if (!drm_core_check_feature(dev, DRIVER_MODESET)) return -EINVAL; - if (!req->flags) + if (!req->flags || (~DRM_MODE_CURSOR_FLAGS & req->flags)) return -EINVAL; mutex_lock(&dev->mode_config.mutex); diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h index 5581980b14f6..3d6301b6ec16 100644 --- a/include/drm/drm_mode.h +++ b/include/drm/drm_mode.h @@ -359,8 +359,9 @@ struct drm_mode_mode_cmd { struct drm_mode_modeinfo mode; }; -#define DRM_MODE_CURSOR_BO (1<<0) -#define DRM_MODE_CURSOR_MOVE (1<<1) +#define DRM_MODE_CURSOR_BO 0x01 +#define DRM_MODE_CURSOR_MOVE 0x02 +#define DRM_MODE_CURSOR_FLAGS 0x03 /* * depending on the value in flags different members are used. From 9a0f938bde74bf9e50bd75c8de9e38c1787398cd Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 24 Aug 2012 09:12:22 +0100 Subject: [PATCH 139/208] drm/i915: Use the correct size of the GTT for placing the per-process entries The current layout is to place the per-process tables at the end of the GTT. However, this is currently using a hardcoded maximum size for the GTT and not taking in account limitations imposed by the BIOS. Use the value for the total number of entries allocated in the table as provided by the configuration registers. Reported-by: Matthew Garrett Signed-off-by: Chris Wilson Cc: Daniel Vetter Cc: Ben Widawsky Cc: Matthew Garret Signed-off-by: Daniel Vetter --- drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index d9a5372ec56f..60815b861ec2 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -72,7 +72,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_device *dev) /* ppgtt PDEs reside in the global gtt pagetable, which has 512*1024 * entries. For aliasing ppgtt support we just steal them at the end for * now. */ - first_pd_entry_in_global_pt = 512*1024 - I915_PPGTT_PD_ENTRIES; + first_pd_entry_in_global_pt = dev_priv->mm.gtt->gtt_total_entries - I915_PPGTT_PD_ENTRIES; ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL); if (!ppgtt) From ca5dd3954a62dc14c2afff1c34b3b5d8dc74f777 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 23 Aug 2012 22:09:12 +0000 Subject: [PATCH 140/208] powerpc: Fix xmon dl command for new printk implementation Since the printk internals were reworked the xmon 'dl' command which dumps the content of __log_buf has stopped working. It is now a structured buffer, so just dumping it doesn't really work. Use the helpers added for kgdb to print out the content. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/xmon/xmon.c | 36 ++++++++++-------------------------- 1 file changed, 10 insertions(+), 26 deletions(-) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index eab3492a45c5..013f28668781 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -2148,40 +2149,23 @@ print_address(unsigned long addr) void dump_log_buf(void) { - const unsigned long size = 128; - unsigned long end, addr; - unsigned char buf[size + 1]; - - addr = 0; - buf[size] = '\0'; + struct kmsg_dumper dumper = { .active = 1 }; + unsigned char buf[128]; + size_t len; if (setjmp(bus_error_jmp) != 0) { - printf("Unable to lookup symbol __log_buf!\n"); + printf("Error dumping printk buffer!\n"); return; } catch_memory_errors = 1; sync(); - addr = kallsyms_lookup_name("__log_buf"); - if (! addr) - printf("Symbol __log_buf not found!\n"); - else { - end = addr + (1 << CONFIG_LOG_BUF_SHIFT); - while (addr < end) { - if (! mread(addr, buf, size)) { - printf("Can't read memory at address 0x%lx\n", addr); - break; - } - - printf("%s", buf); - - if (strlen(buf) < size) - break; - - addr += size; - } - } + kmsg_dump_rewind_nolock(&dumper); + while (kmsg_dump_get_line_nolock(&dumper, false, buf, sizeof(buf), &len)) { + buf[len] = '\0'; + printf("%s", buf); + } sync(); /* wait a little while to see if we get a machine check */ From e3bc8049e524f13e09a58f5bad70b6738494277a Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Thu, 23 Aug 2012 22:09:13 +0000 Subject: [PATCH 141/208] powerpc: Fixup whitespace in xmon There are a few whitespace goolies in xmon.c, some of them appear to be my fault. Fix them all in one go. Signed-off-by: Michael Ellerman Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/xmon/xmon.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 013f28668781..9b49c65ee7a4 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -895,13 +895,13 @@ cmds(struct pt_regs *excp) #endif default: printf("Unrecognized command: "); - do { + do { if (' ' < cmd && cmd <= '~') putchar(cmd); else printf("\\x%x", cmd); cmd = inchar(); - } while (cmd != '\n'); + } while (cmd != '\n'); printf(" (type ? for help)\n"); break; } @@ -1098,7 +1098,7 @@ static long check_bp_loc(unsigned long addr) return 1; } -static char *breakpoint_help_string = +static char *breakpoint_help_string = "Breakpoint command usage:\n" "b show breakpoints\n" "b [cnt] set breakpoint at given instr addr\n" @@ -1194,7 +1194,7 @@ bpt_cmds(void) default: termch = cmd; - cmd = skipbl(); + cmd = skipbl(); if (cmd == '?') { printf(breakpoint_help_string); break; @@ -1360,7 +1360,7 @@ static void xmon_show_stack(unsigned long sp, unsigned long lr, sp + REGS_OFFSET); break; } - printf("--- Exception: %lx %s at ", regs.trap, + printf("--- Exception: %lx %s at ", regs.trap, getvecname(TRAP(®s))); pc = regs.nip; lr = regs.link; @@ -1624,14 +1624,14 @@ static void super_regs(void) cmd = skipbl(); if (cmd == '\n') { - unsigned long sp, toc; + unsigned long sp, toc; asm("mr %0,1" : "=r" (sp) :); asm("mr %0,2" : "=r" (toc) :); printf("msr = "REG" sprg0= "REG"\n", mfmsr(), mfspr(SPRN_SPRG0)); printf("pvr = "REG" sprg1= "REG"\n", - mfspr(SPRN_PVR), mfspr(SPRN_SPRG1)); + mfspr(SPRN_PVR), mfspr(SPRN_SPRG1)); printf("dec = "REG" sprg2= "REG"\n", mfspr(SPRN_DEC), mfspr(SPRN_SPRG2)); printf("sp = "REG" sprg3= "REG"\n", sp, mfspr(SPRN_SPRG3)); @@ -1784,7 +1784,7 @@ byterev(unsigned char *val, int size) static int brev; static int mnoread; -static char *memex_help_string = +static char *memex_help_string = "Memory examine command usage:\n" "m [addr] [flags] examine/change memory\n" " addr is optional. will start where left off.\n" @@ -1799,7 +1799,7 @@ static char *memex_help_string = "NOTE: flags are saved as defaults\n" ""; -static char *memex_subcmd_help_string = +static char *memex_subcmd_help_string = "Memory examine subcommands:\n" " hexval write this val to current location\n" " 'string' write chars from string to this location\n" @@ -2065,7 +2065,7 @@ prdump(unsigned long adrs, long ndump) nr = mread(adrs, temp, r); adrs += nr; for (m = 0; m < r; ++m) { - if ((m & (sizeof(long) - 1)) == 0 && m > 0) + if ((m & (sizeof(long) - 1)) == 0 && m > 0) putchar(' '); if (m < nr) printf("%.2x", temp[m]); @@ -2073,7 +2073,7 @@ prdump(unsigned long adrs, long ndump) printf("%s", fault_chars[fault_type]); } for (; m < 16; ++m) { - if ((m & (sizeof(long) - 1)) == 0) + if ((m & (sizeof(long) - 1)) == 0) putchar(' '); printf(" "); } @@ -2153,13 +2153,13 @@ dump_log_buf(void) unsigned char buf[128]; size_t len; - if (setjmp(bus_error_jmp) != 0) { + if (setjmp(bus_error_jmp) != 0) { printf("Error dumping printk buffer!\n"); - return; - } + return; + } - catch_memory_errors = 1; - sync(); + catch_memory_errors = 1; + sync(); kmsg_dump_rewind_nolock(&dumper); while (kmsg_dump_get_line_nolock(&dumper, false, buf, sizeof(buf), &len)) { @@ -2167,10 +2167,10 @@ dump_log_buf(void) printf("%s", buf); } - sync(); - /* wait a little while to see if we get a machine check */ - __delay(200); - catch_memory_errors = 0; + sync(); + /* wait a little while to see if we get a machine check */ + __delay(200); + catch_memory_errors = 0; } /* From 6d9c00c67b4768105e8ae3d213484095c744eea8 Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Wed, 22 Aug 2012 20:30:43 +0000 Subject: [PATCH 142/208] powerpc: Fix null pointer deref in perf hardware breakpoints Currently if you are doing a global perf recording with hardware breakpoints (ie perf record -e mem:0xdeadbeef -a), you can oops with: Faulting instruction address: 0xc000000000738890 cpu 0xc: Vector: 300 (Data Access) at [c0000003f76af8d0] pc: c000000000738890: .hw_breakpoint_handler+0xa0/0x1e0 lr: c000000000738830: .hw_breakpoint_handler+0x40/0x1e0 sp: c0000003f76afb50 msr: 8000000000001032 dar: 6f0 dsisr: 42000000 current = 0xc0000003f765ac00 paca = 0xc00000000f262a00 softe: 0 irq_happened: 0x01 pid = 6810, comm = loop-read enter ? for help [c0000003f76afbe0] c00000000073cd04 .notifier_call_chain.isra.0+0x84/0xe0 [c0000003f76afc80] c00000000073cdbc .notify_die+0x3c/0x60 [c0000003f76afd20] c0000000000139f0 .do_dabr+0x40/0xf0 [c0000003f76afe30] c000000000005a9c handle_dabr_fault+0x14/0x48 --- Exception: 300 (Data Access) at 0000000010000480 SP (ff8679e0) is in userspace This is because we don't check to see if the break point is associated with task before we deference the task_struct pointer. This changes the update to use current. Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/hw_breakpoint.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c index f3a82dde61db..956a4c496de9 100644 --- a/arch/powerpc/kernel/hw_breakpoint.c +++ b/arch/powerpc/kernel/hw_breakpoint.c @@ -253,7 +253,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args) /* Do not emulate user-space instructions, instead single-step them */ if (user_mode(regs)) { - bp->ctx->task->thread.last_hit_ubp = bp; + current->thread.last_hit_ubp = bp; regs->msr |= MSR_SE; goto out; } From 46c5c59e6902855b61a31be1b8e26bfffcae1e07 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Wed, 22 Aug 2012 15:35:47 +0000 Subject: [PATCH 143/208] powerpc/mpic_msgr: Add missing includes Add several #includes that mpic_msgr relies on being pulled implicitly, which only happens on certain configs. Signed-off-by: Scott Wood Cc: Meador Inge Cc: Jia Hongtao Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/mpic_msgr.h | 1 + arch/powerpc/sysdev/mpic_msgr.c | 3 +++ 2 files changed, 4 insertions(+) diff --git a/arch/powerpc/include/asm/mpic_msgr.h b/arch/powerpc/include/asm/mpic_msgr.h index 326d33ca55cd..d4f471fb1031 100644 --- a/arch/powerpc/include/asm/mpic_msgr.h +++ b/arch/powerpc/include/asm/mpic_msgr.h @@ -14,6 +14,7 @@ #include #include #include +#include struct mpic_msgr { u32 __iomem *base; diff --git a/arch/powerpc/sysdev/mpic_msgr.c b/arch/powerpc/sysdev/mpic_msgr.c index 483d8fa72e8b..e961f8c4a8f0 100644 --- a/arch/powerpc/sysdev/mpic_msgr.c +++ b/arch/powerpc/sysdev/mpic_msgr.c @@ -14,6 +14,9 @@ #include #include #include +#include +#include +#include #include #include #include From 572b411cb4f1b208bb8ea278752f956b3554371e Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Wed, 22 Aug 2012 16:10:18 +0000 Subject: [PATCH 144/208] powerpc/kgdb: Do not set kgdb_single_step on ppc The kgdb_single_step flag has the possibility to indefinitely hang the system on an SMP system. The x86 arch have the same problem, and that problem was fixed by commit 8097551d9ab9b9e3630(kgdb,x86: do not set kgdb_single_step on x86). This patch does the same behaviors as x86's patch. Signed-off-by: Dongdong Deng Signed-off-by: Jason Wessel Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/kgdb.c | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 782bd0a3c2f0..bbabc5abb1c4 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -410,7 +410,6 @@ int kgdb_arch_handle_exception(int vector, int signo, int err_code, #else linux_regs->msr |= MSR_SE; #endif - kgdb_single_step = 1; atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id()); } From 949616cf2d3095d1bb6b3d155c1cc963abd98b5c Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Wed, 22 Aug 2012 16:10:19 +0000 Subject: [PATCH 145/208] powerpc/kgdb: Bail out of KGDB when we've been triggered We need to skip a breakpoint exception when it occurs after a breakpoint has already been removed. Signed-off-by: Tiejun Chen Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/kgdb.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index bbabc5abb1c4..05adb69febf4 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -101,6 +101,21 @@ static int computeSignal(unsigned int tt) return SIGHUP; /* default for things we don't know about */ } +/** + * + * kgdb_skipexception - Bail out of KGDB when we've been triggered. + * @exception: Exception vector number + * @regs: Current &struct pt_regs. + * + * On some architectures we need to skip a breakpoint exception when + * it occurs after a breakpoint has been removed. + * + */ +int kgdb_skipexception(int exception, struct pt_regs *regs) +{ + return kgdb_isremovedbreak(regs->nip); +} + static int kgdb_call_nmi_hook(struct pt_regs *regs) { kgdb_nmicallback(raw_smp_processor_id(), regs); From 5f630401f9e98bd062733b5bbef096dbf2158066 Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Wed, 22 Aug 2012 16:10:20 +0000 Subject: [PATCH 146/208] powerpc/kgdb: Restore current_thread_info properly For powerpc BooKE and e200, singlestep is handled on the critical/dbg exception stack. This causes current_thread_info() to fail for kgdb internal, so previously We work around this issue by copying the thread_info from the kernel stack before calling kgdb_handle_exception, and copying it back afterwards. But actually we don't do this properly. We should backup current_thread_info then restore that when exit. Signed-off-by: Tiejun Chen Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/kgdb.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/kgdb.c b/arch/powerpc/kernel/kgdb.c index 05adb69febf4..c470a40b29f5 100644 --- a/arch/powerpc/kernel/kgdb.c +++ b/arch/powerpc/kernel/kgdb.c @@ -25,6 +25,7 @@ #include #include #include +#include /* * This table contains the mapping between PowerPC hardware trap types, and @@ -153,6 +154,8 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs) static int kgdb_singlestep(struct pt_regs *regs) { struct thread_info *thread_info, *exception_thread_info; + struct thread_info *backup_current_thread_info = \ + (struct thread_info *)kmalloc(sizeof(struct thread_info), GFP_KERNEL); if (user_mode(regs)) return 0; @@ -170,13 +173,17 @@ static int kgdb_singlestep(struct pt_regs *regs) thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1)); exception_thread_info = current_thread_info(); - if (thread_info != exception_thread_info) + if (thread_info != exception_thread_info) { + /* Save the original current_thread_info. */ + memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info); memcpy(exception_thread_info, thread_info, sizeof *thread_info); + } kgdb_handle_exception(0, SIGTRAP, 0, regs); if (thread_info != exception_thread_info) - memcpy(thread_info, exception_thread_info, sizeof *thread_info); + /* Restore current_thread_info lastly. */ + memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info); return 1; } From f0f0c9ac2051e5da4afa1f3f908ace197a4de80e Mon Sep 17 00:00:00 2001 From: Michael Neuling Date: Tue, 21 Aug 2012 21:22:22 +0000 Subject: [PATCH 147/208] powerpc: Remove unnecessary ifdefs Signed-off-by: Michael Neuling Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/cputable.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 50d82c8a037f..b3c083de17ad 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -553,9 +553,7 @@ static inline int cpu_has_feature(unsigned long feature) & feature); } -#ifdef CONFIG_HAVE_HW_BREAKPOINT #define HBP_NUM 1 -#endif /* CONFIG_HAVE_HW_BREAKPOINT */ #endif /* !__ASSEMBLY__ */ From 4c374af5fdee4bc6b4f5ea96c1a0f0ad7d3566be Mon Sep 17 00:00:00 2001 From: Aaro Koskinen Date: Sat, 18 Aug 2012 07:34:15 +0000 Subject: [PATCH 148/208] powerpc/dma-iommu: Fix IOMMU window check Checking for device mask to cover the whole IOMMU table is too strict. IOMMU allocators should handle mask constraint properly for each allocation. The patch enables to use old AirPort Extreme cards on PowerMacs with more than 1GB of memory; without the patch the driver init fails with: b43-pci-bridge 0001:01:01.0: Warning: IOMMU window too big for device mask b43-pci-bridge 0001:01:01.0: mask: 0x3fffffff, table end: 0x80000000 b43-phy0 ERROR: The machine/kernel does not support the required 30-bit DMA mask Signed-off-by: Aaro Koskinen Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/dma-iommu.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c index 2d7bb8ced136..e4897523de41 100644 --- a/arch/powerpc/kernel/dma-iommu.c +++ b/arch/powerpc/kernel/dma-iommu.c @@ -83,11 +83,10 @@ static int dma_iommu_dma_supported(struct device *dev, u64 mask) return 0; } - if ((tbl->it_offset + tbl->it_size) > (mask >> IOMMU_PAGE_SHIFT)) { - dev_info(dev, "Warning: IOMMU window too big for device mask\n"); - dev_info(dev, "mask: 0x%08llx, table end: 0x%08lx\n", - mask, (tbl->it_offset + tbl->it_size) << - IOMMU_PAGE_SHIFT); + if (tbl->it_offset > (mask >> IOMMU_PAGE_SHIFT)) { + dev_info(dev, "Warning: IOMMU offset too big for device mask\n"); + dev_info(dev, "mask: 0x%08llx, table offset: 0x%08lx\n", + mask, tbl->it_offset << IOMMU_PAGE_SHIFT); return 0; } else return 1; From 7256a5d2da56f2ea8ad49e8dbe9e2984f0899b42 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 13 Aug 2012 03:18:28 +0000 Subject: [PATCH 149/208] powerpc: Fix personality handling in ppc64_personality() Directly comparing current->personality against PER_LINUX32 doesn't work in cases when any of the personality flags stored in the top three bytes are used. Directly forcefully setting personality to PER_LINUX32 or PER_LINUX discards any flags stored in the top three bytes Use personality() macro to compare only PER_MASK bytes and make sure that we are setting only the bits that should be set, instead of overwriting the whole value. Signed-off-by: Jiri Kosina Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/kernel/syscalls.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c index f2496f2faecc..4e3cc47f26b9 100644 --- a/arch/powerpc/kernel/syscalls.c +++ b/arch/powerpc/kernel/syscalls.c @@ -107,11 +107,11 @@ long ppc64_personality(unsigned long personality) long ret; if (personality(current->personality) == PER_LINUX32 - && personality == PER_LINUX) - personality = PER_LINUX32; + && personality(personality) == PER_LINUX) + personality = (personality & ~PER_MASK) | PER_LINUX32; ret = sys_personality(personality); - if (ret == PER_LINUX32) - ret = PER_LINUX; + if (personality(ret) == PER_LINUX32) + ret = (ret & ~PER_MASK) | PER_LINUX; return ret; } #endif From dad477ccd65f05bf3b5a874e0118bf4156a1fcbb Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 7 Aug 2012 17:50:46 +0000 Subject: [PATCH 150/208] powerpc: POWER7 copy_to_user/copy_from_user patch applied twice "powerpc: Use enhanced touch instructions in POWER7 copy_to_user/copy_from_user" was applied twice. Remove one. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/lib/copyuser_power7.S | 31 ------------------------------ 1 file changed, 31 deletions(-) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index f9ede7c6606e..4a4a46fbad0e 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -316,37 +316,6 @@ err1; stb r0,0(r3) lis r8,0x8000 /* GO=1 */ clrldi r8,r8,32 -.machine push -.machine "power4" - dcbt r0,r6,0b01000 - dcbt r0,r7,0b01010 - dcbtst r0,r9,0b01000 - dcbtst r0,r10,0b01010 - eieio - dcbt r0,r8,0b01010 /* GO */ -.machine pop - - /* - * We prefetch both the source and destination using enhanced touch - * instructions. We use a stream ID of 0 for the load side and - * 1 for the store side. - */ - clrrdi r6,r4,7 - clrrdi r9,r3,7 - ori r9,r9,1 /* stream=1 */ - - srdi r7,r5,7 /* length in cachelines, capped at 0x3FF */ - cmpldi cr1,r7,0x3FF - ble cr1,1f - li r7,0x3FF -1: lis r0,0x0E00 /* depth=7 */ - sldi r7,r7,7 - or r7,r7,r0 - ori r10,r7,1 /* stream=1 */ - - lis r8,0x8000 /* GO=1 */ - clrldi r8,r8,32 - .machine push .machine "power4" dcbt r0,r6,0b01000 From 2fae7cdb60240e2e2d9b378afbf6d9fcce8a3890 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Tue, 7 Aug 2012 17:51:41 +0000 Subject: [PATCH 151/208] powerpc: Fix VMX in interrupt check in POWER7 copy loops The enhanced prefetch hint patches corrupt the condition register that was used to check if we are in interrupt. Fix this by using cr1. Signed-off-by: Anton Blanchard Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/lib/copyuser_power7.S | 4 ++-- arch/powerpc/lib/memcpy_power7.S | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S index 4a4a46fbad0e..0d24ff15f5f6 100644 --- a/arch/powerpc/lib/copyuser_power7.S +++ b/arch/powerpc/lib/copyuser_power7.S @@ -288,7 +288,7 @@ err1; stb r0,0(r3) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) bl .enter_vmx_usercopy - cmpwi r3,0 + cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STACKFRAMESIZE+48(r1) ld r4,STACKFRAMESIZE+56(r1) @@ -326,7 +326,7 @@ err1; stb r0,0(r3) dcbt r0,r8,0b01010 /* GO */ .machine pop - beq .Lunwind_stack_nonvmx_copy + beq cr1,.Lunwind_stack_nonvmx_copy /* * If source and destination are not relatively aligned we use a diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S index 0efdc51bc716..7ba6c96de778 100644 --- a/arch/powerpc/lib/memcpy_power7.S +++ b/arch/powerpc/lib/memcpy_power7.S @@ -222,7 +222,7 @@ _GLOBAL(memcpy_power7) std r0,16(r1) stdu r1,-STACKFRAMESIZE(r1) bl .enter_vmx_copy - cmpwi r3,0 + cmpwi cr1,r3,0 ld r0,STACKFRAMESIZE+16(r1) ld r3,STACKFRAMESIZE+48(r1) ld r4,STACKFRAMESIZE+56(r1) @@ -260,7 +260,7 @@ _GLOBAL(memcpy_power7) dcbt r0,r8,0b01010 /* GO */ .machine pop - beq .Lunwind_stack_nonvmx_copy + beq cr1,.Lunwind_stack_nonvmx_copy /* * If source and destination are not relatively aligned we use a From 813312110bede27bffd082c25cd31730bd567beb Mon Sep 17 00:00:00 2001 From: Sukadev Bhattiprolu Date: Tue, 7 Aug 2012 15:07:19 +0000 Subject: [PATCH 152/208] powerpc/perf: Use pmc_overflow() to detect rolled back events For certain speculative events on Power7, 'perf stat' reports far higher event count than 'perf record' for the same event. As described in following commit, a performance monitor exception is raised even when the the performance events are rolled back. commit 0837e3242c73566fc1c0196b4ec61779c25ffc93 Author: Anton Blanchard Date: Wed Mar 9 14:38:42 2011 +1100 perf_event_interrupt() records an event only when an overflow occurs. But this check for overflow is a simple 'if (val < 0)'. Because the events are rolled back, this check for overflow fails and the event is not recorded. perf_event_interrupt() later uses pmc_overflow() to detect the overflow and resets the counters and the events are lost completely. To properly detect the overflow of rolled back events, use pmc_overflow() even when recording events. To reproduce: $ cat strcpy.c #include #include main() { char buf[256]; alarm(5); while(1) strcpy(buf, "string1"); } $ perf record -e r20014 ./strcpy $ perf report -n > report.1 $ perf stat -e r20014 > report.2 # Compare report.1 and report.2 Reported-by: Maynard Johnson Signed-off-by: Sukadev Bhattiprolu Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/perf/core-book3s.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c index 77b49ddda9d3..7cd2dbd6e4c4 100644 --- a/arch/powerpc/perf/core-book3s.c +++ b/arch/powerpc/perf/core-book3s.c @@ -1431,7 +1431,7 @@ static void perf_event_interrupt(struct pt_regs *regs) if (!event->hw.idx || is_limited_pmc(event->hw.idx)) continue; val = read_pmc(event->hw.idx); - if ((int)val < 0) { + if (pmc_overflow(val)) { /* event has overflowed */ found = 1; record_and_restart(event, val, regs); From 2c39bf49fd05305bea6d70670855047b2191d3f5 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Fri, 24 Aug 2012 20:55:55 +1000 Subject: [PATCH 153/208] Revert "powerpc: Update g5_defconfig" This reverts commit b1acf1bb544cf28c1f4be0a45620fa899c74b7e9. Something went horribly wrong when I did savedefconfig, not sure what, but what's in there is busted so let's revert it. Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/configs/g5_defconfig | 103 +++++++++++++++++++++--------- 1 file changed, 73 insertions(+), 30 deletions(-) diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig index 15130066e5e2..07b7f2af2dca 100644 --- a/arch/powerpc/configs/g5_defconfig +++ b/arch/powerpc/configs/g5_defconfig @@ -1,8 +1,10 @@ +CONFIG_PPC64=y +CONFIG_ALTIVEC=y +CONFIG_SMP=y +CONFIG_NR_CPUS=4 CONFIG_EXPERIMENTAL=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y -CONFIG_NO_HZ=y -CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_BLK_DEV_INITRD=y @@ -13,15 +15,16 @@ CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_MODVERSIONS=y CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_PARTITION_ADVANCED=y -CONFIG_MAC_PARTITION=y -CONFIG_SMP=y -CONFIG_NR_CPUS=4 -CONFIG_KEXEC=y -# CONFIG_RELOCATABLE is not set +# CONFIG_PPC_PSERIES is not set CONFIG_CPU_FREQ=y CONFIG_CPU_FREQ_GOV_POWERSAVE=y CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_PMAC64=y +CONFIG_NO_HZ=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_KEXEC=y +CONFIG_IRQ_ALL_CPUS=y +# CONFIG_MIGRATION is not set CONFIG_PCI_MSI=y CONFIG_NET=y CONFIG_PACKET=y @@ -49,6 +52,7 @@ CONFIG_NF_CT_NETLINK=m CONFIG_NF_CONNTRACK_IPV4=m CONFIG_IP_NF_QUEUE=m CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" +CONFIG_PROC_DEVICETREE=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y @@ -56,6 +60,8 @@ CONFIG_BLK_DEV_RAM_SIZE=65536 CONFIG_CDROM_PKTCDVD=m CONFIG_IDE=y CONFIG_BLK_DEV_IDECD=y +CONFIG_BLK_DEV_IDE_PMAC=y +CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -79,24 +85,33 @@ CONFIG_DM_CRYPT=m CONFIG_DM_SNAPSHOT=m CONFIG_DM_MIRROR=m CONFIG_DM_ZERO=m -CONFIG_MACINTOSH_DRIVERS=y +CONFIG_IEEE1394=y +CONFIG_IEEE1394_OHCI1394=y +CONFIG_IEEE1394_SBP2=m +CONFIG_IEEE1394_ETH1394=m +CONFIG_IEEE1394_RAWIO=y +CONFIG_IEEE1394_VIDEO1394=m +CONFIG_IEEE1394_DV1394=m +CONFIG_ADB_PMU=y +CONFIG_PMAC_SMU=y CONFIG_MAC_EMUMOUSEBTN=y +CONFIG_THERM_PM72=y +CONFIG_WINDFARM=y +CONFIG_WINDFARM_PM81=y +CONFIG_WINDFARM_PM91=y +CONFIG_WINDFARM_PM112=y +CONFIG_WINDFARM_PM121=y CONFIG_NETDEVICES=y -CONFIG_BONDING=m CONFIG_DUMMY=m -CONFIG_MII=y +CONFIG_BONDING=m CONFIG_TUN=m +CONFIG_NET_ETHERNET=y +CONFIG_MII=y +CONFIG_SUNGEM=y CONFIG_ACENIC=m CONFIG_ACENIC_OMIT_TIGON_I=y -CONFIG_TIGON3=y CONFIG_E1000=y -CONFIG_SUNGEM=y -CONFIG_PPP=m -CONFIG_PPP_BSDCOMP=m -CONFIG_PPP_DEFLATE=m -CONFIG_PPPOE=m -CONFIG_PPP_ASYNC=m -CONFIG_PPP_SYNC_TTY=m +CONFIG_TIGON3=y CONFIG_USB_CATC=m CONFIG_USB_KAWETH=m CONFIG_USB_PEGASUS=m @@ -106,24 +121,36 @@ CONFIG_USB_USBNET=m # CONFIG_USB_NET_NET1080 is not set # CONFIG_USB_NET_CDC_SUBSET is not set # CONFIG_USB_NET_ZAURUS is not set +CONFIG_PPP=m +CONFIG_PPP_ASYNC=m +CONFIG_PPP_SYNC_TTY=m +CONFIG_PPP_DEFLATE=m +CONFIG_PPP_BSDCOMP=m +CONFIG_PPPOE=m # CONFIG_INPUT_MOUSEDEV_PSAUX is not set CONFIG_INPUT_JOYDEV=m CONFIG_INPUT_EVDEV=y +# CONFIG_KEYBOARD_ATKBD is not set # CONFIG_MOUSE_PS2 is not set +# CONFIG_SERIO_I8042 is not set # CONFIG_SERIO_SERPORT is not set -CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_HW_RANDOM is not set CONFIG_GEN_RTC=y CONFIG_RAW_DRIVER=y CONFIG_I2C_CHARDEV=y # CONFIG_HWMON is not set -CONFIG_AGP=y -CONFIG_DRM=y -CONFIG_DRM_NOUVEAU=y +CONFIG_AGP=m +CONFIG_AGP_UNINORTH=m CONFIG_VIDEO_OUTPUT_CONTROL=m +CONFIG_FB=y CONFIG_FIRMWARE_EDID=y CONFIG_FB_TILEBLITTING=y +CONFIG_FB_OF=y +CONFIG_FB_NVIDIA=y +CONFIG_FB_NVIDIA_I2C=y CONFIG_FB_RADEON=y +# CONFIG_VGA_CONSOLE is not set +CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y CONFIG_SOUND=m CONFIG_SND=m @@ -131,7 +158,15 @@ CONFIG_SND_SEQUENCER=m CONFIG_SND_MIXER_OSS=m CONFIG_SND_PCM_OSS=m CONFIG_SND_SEQUENCER_OSS=y +CONFIG_SND_POWERMAC=m +CONFIG_SND_AOA=m +CONFIG_SND_AOA_FABRIC_LAYOUT=m +CONFIG_SND_AOA_ONYX=m +CONFIG_SND_AOA_TAS=m +CONFIG_SND_AOA_TOONIE=m CONFIG_SND_USB_AUDIO=m +CONFIG_HID_PID=y +CONFIG_USB_HIDDEV=y CONFIG_HID_GYRATION=y CONFIG_LOGITECH_FF=y CONFIG_HID_PANTHERLORD=y @@ -139,12 +174,13 @@ CONFIG_HID_PETALYNX=y CONFIG_HID_SAMSUNG=y CONFIG_HID_SONY=y CONFIG_HID_SUNPLUS=y -CONFIG_HID_PID=y -CONFIG_USB_HIDDEV=y CONFIG_USB=y +CONFIG_USB_DEVICEFS=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y +# CONFIG_USB_EHCI_HCD_PPC_OF is not set CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PPC_OF_BE=y CONFIG_USB_ACM=m CONFIG_USB_PRINTER=y CONFIG_USB_STORAGE=y @@ -208,6 +244,8 @@ CONFIG_REISERFS_FS_POSIX_ACL=y CONFIG_REISERFS_FS_SECURITY=y CONFIG_XFS_FS=m CONFIG_XFS_POSIX_ACL=y +CONFIG_INOTIFY=y +CONFIG_AUTOFS_FS=m CONFIG_ISO9660_FS=y CONFIG_JOLIET=y CONFIG_ZISOFS=y @@ -221,12 +259,14 @@ CONFIG_HFS_FS=m CONFIG_HFSPLUS_FS=m CONFIG_CRAMFS=y CONFIG_NFS_FS=y +CONFIG_NFS_V3=y CONFIG_NFS_V3_ACL=y CONFIG_NFS_V4=y CONFIG_NFSD=y CONFIG_NFSD_V3_ACL=y CONFIG_NFSD_V4=y CONFIG_CIFS=m +CONFIG_PARTITION_ADVANCED=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_CODEPAGE_1250=y CONFIG_NLS_CODEPAGE_1251=y @@ -234,23 +274,29 @@ CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_ISO8859_15=y CONFIG_NLS_UTF8=y +CONFIG_CRC_T10DIF=y +CONFIG_LIBCRC32C=m CONFIG_MAGIC_SYSRQ=y -# CONFIG_UNUSED_SYMBOLS is not set CONFIG_DEBUG_FS=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_MUTEXES=y +# CONFIG_RCU_CPU_STALL_DETECTOR is not set CONFIG_LATENCYTOP=y -CONFIG_STRICT_DEVMEM=y +CONFIG_SYSCTL_SYSCALL_CHECK=y +CONFIG_BOOTX_TEXT=y CONFIG_CRYPTO_NULL=m CONFIG_CRYPTO_TEST=m +CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y +CONFIG_CRYPTO_MD4=m CONFIG_CRYPTO_MICHAEL_MIC=m CONFIG_CRYPTO_SHA256=m CONFIG_CRYPTO_SHA512=m CONFIG_CRYPTO_WP512=m CONFIG_CRYPTO_AES=m CONFIG_CRYPTO_ANUBIS=m +CONFIG_CRYPTO_ARC4=m CONFIG_CRYPTO_BLOWFISH=m CONFIG_CRYPTO_CAST5=m CONFIG_CRYPTO_CAST6=m @@ -260,6 +306,3 @@ CONFIG_CRYPTO_TEA=m CONFIG_CRYPTO_TWOFISH=m # CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set -# CONFIG_VIRTUALIZATION is not set -CONFIG_CRC_T10DIF=y -CONFIG_LIBCRC32C=m From a51d4ed01e5bb39d2cf36a12f9976ab08872c192 Mon Sep 17 00:00:00 2001 From: Calvin Walton Date: Fri, 24 Aug 2012 07:56:31 -0400 Subject: [PATCH 154/208] i915: Quirk no_lvds on Gigabyte GA-D525TUD ITX motherboard This board is incorrectly detected as having an LVDS connector, resulting in the VGA output (the only available output on the board) showing the console only in the top-left 1024x768 pixels, and an extra LVDS connector appearing in X. It's a desktop Mini-ITX board using an Atom D525 CPU with an NM10 chipset. I've had this board for about a year, but this is the first time I noticed the issue because I've been running it headless for most of its life. Signed-off-by: Calvin Walton --- drivers/gpu/drm/i915/intel_lvds.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index e05c0d3e3440..e9a6f6aaed85 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -780,6 +780,14 @@ static const struct dmi_system_id intel_no_lvds[] = { DMI_MATCH(DMI_BOARD_NAME, "ZBOXSD-ID12/ID13"), }, }, + { + .callback = intel_no_lvds_dmi_callback, + .ident = "Gigabyte GA-D525TUD", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Gigabyte Technology Co., Ltd."), + DMI_MATCH(DMI_BOARD_NAME, "D525TUD"), + }, + }, { } /* terminating entry */ }; From d17d794c63e2dc0a5b1ffc8367c9475880427fc7 Mon Sep 17 00:00:00 2001 From: Prarit Bhargava Date: Thu, 23 Aug 2012 15:11:52 -0400 Subject: [PATCH 155/208] libata: Add a space to " 2GB ATA Flash Disk" DMA blacklist entry commit d70e551c8e1ecb6f20422f8db6bfe6a0049edcb8, Add " 2GB ATA Flash Disk"/"ADMA428M" to DMA blacklist, should have added a space before 2GB. Signed-off-by: Prarit Bhargava Signed-off-by: Jeff Garzik --- drivers/ata/libata-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 5eee1c1537d2..8e1039c8e159 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4062,7 +4062,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "_NEC DV5800A", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SN-124", "N001", ATA_HORKAGE_NODMA }, { "Seagate STT20000A", NULL, ATA_HORKAGE_NODMA }, - { "2GB ATA Flash Disk", "ADMA428M", ATA_HORKAGE_NODMA }, + { " 2GB ATA Flash Disk", "ADMA428M", ATA_HORKAGE_NODMA }, /* Odd clown on sil3726/4726 PMPs */ { "Config Disk", NULL, ATA_HORKAGE_DISABLE }, From 760a9a30adc558a75916a13902f38c6792fa8c4b Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 22 Aug 2012 14:34:11 +0100 Subject: [PATCH 156/208] kvm: Fix nonsense handling of compat ioctl KVM_SET_SIGNAL_MASK passed a NULL argument leaves the on stack signal sets uninitialized. It then passes them through to kvm_vcpu_ioctl_set_sigmask. We should be passing a NULL in this case not translated garbage. Signed-off-by: Alan Cox Signed-off-by: Marcelo Tosatti --- virt/kvm/kvm_main.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 246852397e30..d617f69131d7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1976,9 +1976,10 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, if (copy_from_user(&csigset, sigmask_arg->sigset, sizeof csigset)) goto out; - } - sigset_from_compat(&sigset, &csigset); - r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); + sigset_from_compat(&sigset, &csigset); + r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); + } else + r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL); break; } default: From 1d92128fe9e30c2340283361957a840f108e4abf Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Sun, 26 Aug 2012 18:00:29 +0300 Subject: [PATCH 157/208] KVM: x86: fix KVM_GET_MSR for PV EOI KVM_GET_MSR was missing support for PV EOI, which is needed for migration. Signed-off-by: Michael S. Tsirkin Signed-off-by: Marcelo Tosatti --- arch/x86/kvm/x86.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index dce75b760312..148ed666e311 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2000,6 +2000,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_KVM_STEAL_TIME: data = vcpu->arch.st.msr_val; break; + case MSR_KVM_PV_EOI_EN: + data = vcpu->arch.pv_eoi.msr_val; + break; case MSR_IA32_P5_MC_ADDR: case MSR_IA32_P5_MC_TYPE: case MSR_IA32_MCG_CAP: From 6b79d14e7a9f5d31b78bcd01a122f0c692e94a19 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Aug 2012 10:59:42 +0200 Subject: [PATCH 158/208] s390/dasd: fix ioctl return value For unimplemented ioctls the dasd driver should return -ENOTTY. Reported-by: Wanlong Gao Acked-by: Stefan Weinhuber Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- drivers/s390/block/dasd_eckd.c | 2 +- drivers/s390/block/dasd_ioctl.c | 7 ++----- 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 40a826a7295f..2fb2b9ea97ec 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -3804,7 +3804,7 @@ dasd_eckd_ioctl(struct dasd_block *block, unsigned int cmd, void __user *argp) case BIODASDSYMMIO: return dasd_symm_io(device, argp); default: - return -ENOIOCTLCMD; + return -ENOTTY; } } diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index cceae70279f6..654c6921a6d4 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -498,12 +498,9 @@ int dasd_ioctl(struct block_device *bdev, fmode_t mode, break; default: /* if the discipline has an ioctl method try it. */ - if (base->discipline->ioctl) { + rc = -ENOTTY; + if (base->discipline->ioctl) rc = base->discipline->ioctl(block, cmd, argp); - if (rc == -ENOIOCTLCMD) - rc = -EINVAL; - } else - rc = -EINVAL; } dasd_put_device(base); return rc; From 29a877fa1f402ce2c1a0c52957c4e29b9bb34216 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 27 Aug 2012 15:18:45 +0200 Subject: [PATCH 159/208] s390/smp: add missing smp_store_status() for !SMP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fix this compile error: arch/s390/kernel/machine_kexec.c: In function ‘setup_regs’: arch/s390/kernel/machine_kexec.c:63:3: error: implicit declaration of function ‘smp_store_status’ [-Werror=implicit-function-declaration] Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/smp.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h index a0a8340daafa..ce26ac3cb162 100644 --- a/arch/s390/include/asm/smp.h +++ b/arch/s390/include/asm/smp.h @@ -44,6 +44,7 @@ static inline void smp_call_online_cpu(void (*func)(void *), void *data) } static inline int smp_find_processor_id(int address) { return 0; } +static inline int smp_store_status(int cpu) { return 0; } static inline int smp_vcpu_scheduled(int cpu) { return 1; } static inline void smp_yield_cpu(int cpu) { } static inline void smp_yield(void) { } From aa2ffd06168e25689e0eb9662bf4595ba2bbac14 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Thu, 26 Jul 2012 03:40:35 -0600 Subject: [PATCH 160/208] Btrfs: fix a misplaced address operator in a condition This should obviously not be "if (&flag)" but "if (flag)". Signed-off-by: Stefan Behrens --- fs/btrfs/locking.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index a44eff074805..2a1762c66041 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -67,7 +67,7 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) { if (eb->lock_nested) { read_lock(&eb->lock); - if (&eb->lock_nested && current->pid == eb->lock_owner) { + if (eb->lock_nested && current->pid == eb->lock_owner) { read_unlock(&eb->lock); return; } From 5986802c2fcc754040bb7ed95f30bb16c4a843b7 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 30 Jul 2012 02:16:10 -0600 Subject: [PATCH 161/208] Btrfs: fix some error codes in btrfs_qgroup_inherit() These are returning zero when it should be returning a negative error code. Signed-off-by: Dan Carpenter --- fs/btrfs/qgroup.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index bc424ae5a81a..229ef8927e6b 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1369,8 +1369,10 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, if (srcid) { srcgroup = find_qgroup_rb(fs_info, srcid); - if (!srcgroup) + if (!srcgroup) { + ret = -EINVAL; goto unlock; + } dstgroup->rfer = srcgroup->rfer - level_size; dstgroup->rfer_cmpr = srcgroup->rfer_cmpr - level_size; srcgroup->excl = level_size; @@ -1379,8 +1381,10 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, qgroup_dirty(fs_info, srcgroup); } - if (!inherit) + if (!inherit) { + ret = -EINVAL; goto unlock; + } i_qgroups = (u64 *)(inherit + 1); for (i = 0; i < inherit->num_qgroups; ++i) { From 57a5a882031dba5cb7bc7ebc955b897498365fe2 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 30 Jul 2012 02:15:43 -0600 Subject: [PATCH 162/208] Btrfs: checking for NULL instead of IS_ERR add_qgroup_rb() never returns NULL, only error pointers. Signed-off-by: Dan Carpenter --- fs/btrfs/qgroup.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 229ef8927e6b..38b42e7bc91d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1364,8 +1364,10 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, spin_lock(&fs_info->qgroup_lock); dstgroup = add_qgroup_rb(fs_info, objectid); - if (!dstgroup) + if (IS_ERR(dstgroup)) { + ret = PTR_ERR(dstgroup); goto unlock; + } if (srcid) { srcgroup = find_qgroup_rb(fs_info, srcid); From 55e591ffde38e0088b022129e035e18a8d04c7e6 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 30 Jul 2012 02:15:15 -0600 Subject: [PATCH 163/208] Btrfs: unlock on error in btrfs_delalloc_reserve_metadata() We should release this mutex before returning the error code. Signed-off-by: Dan Carpenter --- fs/btrfs/extent-tree.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4e1b153b7c47..45c69c4184c9 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4571,8 +4571,10 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) if (root->fs_info->quota_enabled) { ret = btrfs_qgroup_reserve(root, num_bytes + nr_extents * root->leafsize); - if (ret) + if (ret) { + mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); return ret; + } } ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush); From dadd1105ca9a1e506c678e8e410e9623efdda821 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Mon, 30 Jul 2012 02:10:44 -0600 Subject: [PATCH 164/208] Btrfs: fix some endian bugs handling the root times "trans->transid" is cpu endian but we want to store the data as little endian. "item->ctime.nsec" is only 32 bits, not 64. Signed-off-by: Dan Carpenter --- fs/btrfs/ioctl.c | 2 +- fs/btrfs/root-tree.c | 4 ++-- fs/btrfs/transaction.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 43f0012016e3..a1fbca0a1003 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -424,7 +424,7 @@ static noinline int create_subvol(struct btrfs_root *root, uuid_le_gen(&new_uuid); memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE); root_item.otime.sec = cpu_to_le64(cur_time.tv_sec); - root_item.otime.nsec = cpu_to_le64(cur_time.tv_nsec); + root_item.otime.nsec = cpu_to_le32(cur_time.tv_nsec); root_item.ctime = root_item.otime; btrfs_set_root_ctransid(&root_item, trans->transid); btrfs_set_root_otransid(&root_item, trans->transid); diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 6bb465cca20f..10d8e4d88071 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -544,8 +544,8 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans, struct timespec ct = CURRENT_TIME; spin_lock(&root->root_times_lock); - item->ctransid = trans->transid; + item->ctransid = cpu_to_le64(trans->transid); item->ctime.sec = cpu_to_le64(ct.tv_sec); - item->ctime.nsec = cpu_to_le64(ct.tv_nsec); + item->ctime.nsec = cpu_to_le32(ct.tv_nsec); spin_unlock(&root->root_times_lock); } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 7ac7cdcc294e..7208ada41e0e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1061,7 +1061,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, memcpy(new_root_item->parent_uuid, root->root_item.uuid, BTRFS_UUID_SIZE); new_root_item->otime.sec = cpu_to_le64(cur_time.tv_sec); - new_root_item->otime.nsec = cpu_to_le64(cur_time.tv_nsec); + new_root_item->otime.nsec = cpu_to_le32(cur_time.tv_nsec); btrfs_set_root_otransid(new_root_item, trans->transid); memset(&new_root_item->stime, 0, sizeof(new_root_item->stime)); memset(&new_root_item->rtime, 0, sizeof(new_root_item->rtime)); From eb838e73dc2121d2bae47d5678952cd7d48793b5 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 31 Jul 2012 16:28:48 -0400 Subject: [PATCH 165/208] Btrfs: lock extents as we map them in DIO A deadlock in xfstests 113 was uncovered by commit d187663ef24cd3d033f0cbf2867e70b36a3a90b8 This is because we would not return EIOCBQUEUED for short AIO reads, instead we'd wait for the DIO to complete and then return the amount of data we transferred, which would allow our stuff to unlock the remaning amount. But with this change this no longer happens, so if we have a short AIO read (for example if we try to read past EOF), we could leave the section from EOF to the end of where we tried to read locked. Fixing this is tricky since there is no clear way to know exactly how much data DIO truly submitted for IO, so to make this less hard on ourselves and less combersome we need to lock the extents as we try to map them, and then we unlock any areas we didn't actually map. This makes us completely safe from deadlocks and reliance on a particular behavior of the DIO code. This also lays the groundwork for allowing us to use the normal csum storage method for reads which means we can remove an allocation. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/inode.c | 256 +++++++++++++++++++++++------------------------ 1 file changed, 127 insertions(+), 129 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dac1fc21d809..09182449cbdf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5773,18 +5773,109 @@ out: return ret; } +static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, + struct extent_state **cached_state, int writing) +{ + struct btrfs_ordered_extent *ordered; + int ret = 0; + + while (1) { + lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, + 0, cached_state); + /* + * We're concerned with the entire range that we're going to be + * doing DIO to, so we need to make sure theres no ordered + * extents in this range. + */ + ordered = btrfs_lookup_ordered_range(inode, lockstart, + lockend - lockstart + 1); + + /* + * We need to make sure there are no buffered pages in this + * range either, we could have raced between the invalidate in + * generic_file_direct_write and locking the extent. The + * invalidate needs to happen so that reads after a write do not + * get stale data. + */ + if (!ordered && (!writing || + !test_range_bit(&BTRFS_I(inode)->io_tree, + lockstart, lockend, EXTENT_UPTODATE, 0, + *cached_state))) + break; + + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, + cached_state, GFP_NOFS); + + if (ordered) { + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } else { + /* Screw you mmap */ + ret = filemap_write_and_wait_range(inode->i_mapping, + lockstart, + lockend); + if (ret) + break; + + /* + * If we found a page that couldn't be invalidated just + * fall back to buffered. + */ + ret = invalidate_inode_pages2_range(inode->i_mapping, + lockstart >> PAGE_CACHE_SHIFT, + lockend >> PAGE_CACHE_SHIFT); + if (ret) + break; + } + + cond_resched(); + } + + return ret; +} + static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; + struct extent_state *cached_state = NULL; u64 start = iblock << inode->i_blkbits; + u64 lockstart, lockend; u64 len = bh_result->b_size; struct btrfs_trans_handle *trans; + int unlock_bits = EXTENT_LOCKED; + int ret; + + lockstart = start; + lockend = start + len - 1; + if (create) { + ret = btrfs_delalloc_reserve_space(inode, len); + if (ret) + return ret; + unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY; + } + + /* + * If this errors out it's because we couldn't invalidate pagecache for + * this range and we need to fallback to buffered. + */ + if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create)) + return -ENOTBLK; + + if (create) { + ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockend, EXTENT_DELALLOC, NULL, + &cached_state, GFP_NOFS); + if (ret) + goto unlock_err; + } em = btrfs_get_extent(inode, NULL, 0, start, len, 0); - if (IS_ERR(em)) - return PTR_ERR(em); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto unlock_err; + } /* * Ok for INLINE and COMPRESSED extents we need to fallback on buffered @@ -5803,17 +5894,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) || em->block_start == EXTENT_MAP_INLINE) { free_extent_map(em); - return -ENOTBLK; + ret = -ENOTBLK; + goto unlock_err; } /* Just a good old fashioned hole, return */ if (!create && (em->block_start == EXTENT_MAP_HOLE || test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { free_extent_map(em); - /* DIO will do one hole at a time, so just unlock a sector */ - unlock_extent(&BTRFS_I(inode)->io_tree, start, - start + root->sectorsize - 1); - return 0; + ret = 0; + goto unlock_err; } /* @@ -5826,8 +5916,9 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * */ if (!create) { - len = em->len - (start - em->start); - goto map; + len = min(len, em->len - (start - em->start)); + lockstart = start + len; + goto unlock; } if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) || @@ -5859,7 +5950,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, btrfs_end_transaction(trans, root); if (ret) { free_extent_map(em); - return ret; + goto unlock_err; } goto unlock; } @@ -5872,14 +5963,12 @@ must_cow: */ len = bh_result->b_size; em = btrfs_new_extent_direct(inode, em, start, len); - if (IS_ERR(em)) - return PTR_ERR(em); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto unlock_err; + } len = min(len, em->len - (start - em->start)); unlock: - clear_extent_bit(&BTRFS_I(inode)->io_tree, start, start + len - 1, - EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DIRTY, 1, - 0, NULL, GFP_NOFS); -map: bh_result->b_blocknr = (em->block_start + (start - em->start)) >> inode->i_blkbits; bh_result->b_size = len; @@ -5897,9 +5986,28 @@ map: i_size_write(inode, start + len); } + /* + * In the case of write we need to clear and unlock the entire range, + * in the case of read we need to unlock only the end area that we + * aren't using if there is any left over space. + */ + if (lockstart < lockend) + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, + unlock_bits, 1, 0, &cached_state, GFP_NOFS); + else + free_extent_state(cached_state); + free_extent_map(em); return 0; + +unlock_err: + if (create) + unlock_bits |= EXTENT_DO_ACCOUNTING; + + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, + unlock_bits, 1, 0, &cached_state, GFP_NOFS); + return ret; } struct btrfs_dio_private { @@ -6340,132 +6448,22 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io out: return retval; } + static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, unsigned long nr_segs) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - struct btrfs_ordered_extent *ordered; - struct extent_state *cached_state = NULL; - u64 lockstart, lockend; - ssize_t ret; - int writing = rw & WRITE; - int write_bits = 0; - size_t count = iov_length(iov, nr_segs); if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov, - offset, nr_segs)) { + offset, nr_segs)) return 0; - } - lockstart = offset; - lockend = offset + count - 1; - - if (writing) { - ret = btrfs_delalloc_reserve_space(inode, count); - if (ret) - goto out; - } - - while (1) { - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, - 0, &cached_state); - /* - * We're concerned with the entire range that we're going to be - * doing DIO to, so we need to make sure theres no ordered - * extents in this range. - */ - ordered = btrfs_lookup_ordered_range(inode, lockstart, - lockend - lockstart + 1); - - /* - * We need to make sure there are no buffered pages in this - * range either, we could have raced between the invalidate in - * generic_file_direct_write and locking the extent. The - * invalidate needs to happen so that reads after a write do not - * get stale data. - */ - if (!ordered && (!writing || - !test_range_bit(&BTRFS_I(inode)->io_tree, - lockstart, lockend, EXTENT_UPTODATE, 0, - cached_state))) - break; - - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state, GFP_NOFS); - - if (ordered) { - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); - } else { - /* Screw you mmap */ - ret = filemap_write_and_wait_range(file->f_mapping, - lockstart, - lockend); - if (ret) - goto out; - - /* - * If we found a page that couldn't be invalidated just - * fall back to buffered. - */ - ret = invalidate_inode_pages2_range(file->f_mapping, - lockstart >> PAGE_CACHE_SHIFT, - lockend >> PAGE_CACHE_SHIFT); - if (ret) { - if (ret == -EBUSY) - ret = 0; - goto out; - } - } - - cond_resched(); - } - - /* - * we don't use btrfs_set_extent_delalloc because we don't want - * the dirty or uptodate bits - */ - if (writing) { - write_bits = EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING; - ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, - EXTENT_DELALLOC, NULL, &cached_state, - GFP_NOFS); - if (ret) { - clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, - lockend, EXTENT_LOCKED | write_bits, - 1, 0, &cached_state, GFP_NOFS); - goto out; - } - } - - free_extent_state(cached_state); - cached_state = NULL; - - ret = __blockdev_direct_IO(rw, iocb, inode, + return __blockdev_direct_IO(rw, iocb, inode, BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, iov, offset, nr_segs, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, 0); - - if (ret < 0 && ret != -EIOCBQUEUED) { - clear_extent_bit(&BTRFS_I(inode)->io_tree, offset, - offset + iov_length(iov, nr_segs) - 1, - EXTENT_LOCKED | write_bits, 1, 0, - &cached_state, GFP_NOFS); - } else if (ret >= 0 && ret < iov_length(iov, nr_segs)) { - /* - * We're falling back to buffered, unlock the section we didn't - * do IO on. - */ - clear_extent_bit(&BTRFS_I(inode)->io_tree, offset + ret, - offset + iov_length(iov, nr_segs) - 1, - EXTENT_LOCKED | write_bits, 1, 0, - &cached_state, GFP_NOFS); - } -out: - free_extent_state(cached_state); - return ret; } static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, From 3627bf4503b504077332c13496cb1bd54713bcbb Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Wed, 1 Aug 2012 04:28:01 -0600 Subject: [PATCH 166/208] Btrfs: fix that error value is changed by mistake In iterate_inodes_from_logical() the error result from extent_from_logical() is patched by mistake. Typically ENOENT is patched to EINVAL because (-ENOENT & BTRFS_EXTENT_FLAG_TREE_BLOCK) evaluates to true. Signed-off-by: Stefan Behrens --- fs/btrfs/backref.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index a256f3b2a845..ff6475f409d6 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1438,10 +1438,10 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info, ret = extent_from_logical(fs_info, logical, path, &found_key); btrfs_release_path(path); - if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) - ret = -EINVAL; if (ret < 0) return ret; + if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) + return -EINVAL; extent_item_pos = logical - found_key.objectid; ret = iterate_extent_inodes(fs_info, found_key.objectid, From aa9ddcd4b5557102fa25695c11904f249b4dec49 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 2 Aug 2012 10:22:20 -0400 Subject: [PATCH 167/208] Btrfs: do not use missing devices when showing devname If you do the following mkfs.btrfs /dev/sdb /dev/sdc rmmod btrfs dd if=/dev/zero of=/dev/sdb bs=1M count=1 mount -o degraded /dev/sdc /mnt/btrfs-test the box will panic trying to deref the name for the missing dev since it is the lower numbered devid. So fix show_devname to not use missing devices. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/super.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 75ee2c7791f0..2e06f124f284 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1505,6 +1505,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) while (cur_devices) { head = &cur_devices->devices; list_for_each_entry(dev, head, dev_list) { + if (dev->missing) + continue; if (!first_dev || dev->devid < first_dev->devid) first_dev = dev; } From 99f5944b8477914406173b47b4f261356286730b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 2 Aug 2012 10:23:59 -0400 Subject: [PATCH 168/208] Btrfs: do not strdup non existent strings When we close devices we add back empty devices for some reason that escapes me. In the case of a missing dev we don't allocate an rcu_string for it's name, so check to see if the device has a name and if it doesn't don't bother strdup()'ing it. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/volumes.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b8708f994e67..3b394503bd4e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -569,9 +569,11 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) memcpy(new_device, device, sizeof(*new_device)); /* Safe because we are under uuid_mutex */ - name = rcu_string_strdup(device->name->str, GFP_NOFS); - BUG_ON(device->name && !name); /* -ENOMEM */ - rcu_assign_pointer(new_device->name, name); + if (device->name) { + name = rcu_string_strdup(device->name->str, GFP_NOFS); + BUG_ON(device->name && !name); /* -ENOMEM */ + rcu_assign_pointer(new_device->name, name); + } new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; From c329861da40623cd838b8c9ee31a850242fd88cf Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 3 Aug 2012 16:49:19 -0400 Subject: [PATCH 169/208] Btrfs: don't allocate a seperate csums array for direct reads We've been allocating a big array for csums instead of storing them in the io_tree like we do for buffered reads because previously we were locking the entire range, so we didn't have an extent state for each sector of the range. But now that we do the range locking as we map the buffers we can limit the mapping lenght to sectorsize and use the private part of the io_tree for our csums. This allows us to avoid an extra memory allocation for direct reads which could incur latency. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/ctree.h | 2 +- fs/btrfs/file-item.c | 4 ++-- fs/btrfs/inode.c | 45 ++++++++++++++++---------------------------- 3 files changed, 19 insertions(+), 32 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index adb1cd7ceb9b..348196350bf0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3192,7 +3192,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, struct bio *bio, u32 *dst); int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode, - struct bio *bio, u64 logical_offset, u32 *dst); + struct bio *bio, u64 logical_offset); int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 objectid, u64 pos, diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index b45b9de0c21d..857d93cd01dc 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -272,9 +272,9 @@ int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, } int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode, - struct bio *bio, u64 offset, u32 *dst) + struct bio *bio, u64 offset) { - return __btrfs_lookup_bio_sums(root, inode, bio, offset, dst, 1); + return __btrfs_lookup_bio_sums(root, inode, bio, offset, NULL, 1); } int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 09182449cbdf..2d65c52b0944 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5847,15 +5847,18 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, int unlock_bits = EXTENT_LOCKED; int ret; - lockstart = start; - lockend = start + len - 1; if (create) { ret = btrfs_delalloc_reserve_space(inode, len); if (ret) return ret; unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY; + } else { + len = min_t(u64, len, root->sectorsize); } + lockstart = start; + lockend = start + len - 1; + /* * If this errors out it's because we couldn't invalidate pagecache for * this range and we need to fallback to buffered. @@ -6015,7 +6018,6 @@ struct btrfs_dio_private { u64 logical_offset; u64 disk_bytenr; u64 bytes; - u32 *csums; void *private; /* number of bios pending for this dio */ @@ -6035,7 +6037,6 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct inode *inode = dip->inode; struct btrfs_root *root = BTRFS_I(inode)->root; u64 start; - u32 *private = dip->csums; start = dip->logical_offset; do { @@ -6043,8 +6044,12 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct page *page = bvec->bv_page; char *kaddr; u32 csum = ~(u32)0; + u64 private = ~(u32)0; unsigned long flags; + if (get_state_private(&BTRFS_I(inode)->io_tree, + start, &private)) + goto failed; local_irq_save(flags); kaddr = kmap_atomic(page); csum = btrfs_csum_data(root, kaddr + bvec->bv_offset, @@ -6054,18 +6059,18 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) local_irq_restore(flags); flush_dcache_page(bvec->bv_page); - if (csum != *private) { + if (csum != private) { +failed: printk(KERN_ERR "btrfs csum failed ino %llu off" " %llu csum %u private %u\n", (unsigned long long)btrfs_ino(inode), (unsigned long long)start, - csum, *private); + csum, (unsigned)private); err = -EIO; } } start += bvec->bv_len; - private++; bvec++; } while (bvec <= bvec_end); @@ -6073,7 +6078,6 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) dip->logical_offset + dip->bytes - 1); bio->bi_private = dip->private; - kfree(dip->csums); kfree(dip); /* If we had a csum failure make sure to clear the uptodate flag */ @@ -6179,7 +6183,7 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, int rw, u64 file_offset, int skip_sum, - u32 *csums, int async_submit) + int async_submit) { int write = rw & REQ_WRITE; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -6212,8 +6216,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, if (ret) goto err; } else if (!skip_sum) { - ret = btrfs_lookup_bio_sums_dio(root, inode, bio, - file_offset, csums); + ret = btrfs_lookup_bio_sums_dio(root, inode, bio, file_offset); if (ret) goto err; } @@ -6239,10 +6242,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, u64 submit_len = 0; u64 map_length; int nr_pages = 0; - u32 *csums = dip->csums; int ret = 0; int async_submit = 0; - int write = rw & REQ_WRITE; map_length = orig_bio->bi_size; ret = btrfs_map_block(map_tree, READ, start_sector << 9, @@ -6278,16 +6279,13 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, atomic_inc(&dip->pending_bios); ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, - csums, async_submit); + async_submit); if (ret) { bio_put(bio); atomic_dec(&dip->pending_bios); goto out_err; } - /* Write's use the ordered csums */ - if (!write && !skip_sum) - csums = csums + nr_pages; start_sector += submit_len >> 9; file_offset += submit_len; @@ -6317,7 +6315,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, submit: ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, - csums, async_submit); + async_submit); if (!ret) return 0; @@ -6353,17 +6351,6 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, ret = -ENOMEM; goto free_ordered; } - dip->csums = NULL; - - /* Write's use the ordered csum stuff, so we don't need dip->csums */ - if (!write && !skip_sum) { - dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS); - if (!dip->csums) { - kfree(dip); - ret = -ENOMEM; - goto free_ordered; - } - } dip->private = bio->bi_private; dip->inode = inode; From 6209526531e70c080f79318ab8f50e26846c40a8 Mon Sep 17 00:00:00 2001 From: Fengguang Wu Date: Sat, 4 Aug 2012 01:45:02 -0600 Subject: [PATCH 170/208] btrfs: fix second lock in btrfs_delete_delayed_items() Fix a real bug caught by coccinelle. fs/btrfs/delayed-inode.c:1013:1-11: second lock on line 1013 Signed-off-by: Fengguang Wu --- fs/btrfs/delayed-inode.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 335605c8ceab..00deed4ef3ed 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1028,9 +1028,10 @@ do_again: btrfs_release_delayed_item(prev); ret = 0; btrfs_release_path(path); - if (curr) + if (curr) { + mutex_unlock(&node->mutex); goto do_again; - else + } else goto delete_fail; } From 1fa11e265fa2562fb713171b6a58e72bb7afd276 Mon Sep 17 00:00:00 2001 From: Arne Jansen Date: Mon, 6 Aug 2012 14:18:51 -0600 Subject: [PATCH 171/208] Btrfs: fix deadlock in wait_for_more_refs Commit a168650c introduced a waiting mechanism to prevent busy waiting in btrfs_run_delayed_refs. This can deadlock with btrfs_run_ordered_operations, where a tree_mod_seq is held while waiting for the io to complete, while the end_io calls btrfs_run_delayed_refs. This whole mechanism is unnecessary. If not enough runnable refs are available to satisfy count, just return as count is more like a guideline than a strict requirement. In case we have to run all refs, commit transaction makes sure that no other threads are working in the transaction anymore, so we just assert here that no refs are blocked. Signed-off-by: Arne Jansen Signed-off-by: Chris Mason --- fs/btrfs/ctree.c | 6 ---- fs/btrfs/ctree.h | 1 - fs/btrfs/delayed-ref.c | 8 ----- fs/btrfs/disk-io.c | 2 -- fs/btrfs/extent-tree.c | 77 ++++++++++++------------------------------ 5 files changed, 21 insertions(+), 73 deletions(-) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 9d7621f271ff..08e0b11ba0a1 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -420,12 +420,6 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, } spin_unlock(&fs_info->tree_mod_seq_lock); - /* - * we removed the lowest blocker from the blocker list, so there may be - * more processible delayed refs. - */ - wake_up(&fs_info->tree_mod_seq_wait); - /* * anything that's lower than the lowest existing (read: blocked) * sequence number can be removed from the tree. diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 348196350bf0..c38734a07a65 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1252,7 +1252,6 @@ struct btrfs_fs_info { atomic_t tree_mod_seq; struct list_head tree_mod_seq_list; struct seq_list tree_mod_seq_elem; - wait_queue_head_t tree_mod_seq_wait; /* this protects tree_mod_log */ rwlock_t tree_mod_log_lock; diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index da7419ed01bb..7561431af50d 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -662,9 +662,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr, num_bytes, parent, ref_root, level, action, for_cow); - if (!need_ref_seq(for_cow, ref_root) && - waitqueue_active(&fs_info->tree_mod_seq_wait)) - wake_up(&fs_info->tree_mod_seq_wait); spin_unlock(&delayed_refs->lock); if (need_ref_seq(for_cow, ref_root)) btrfs_qgroup_record_ref(trans, &ref->node, extent_op); @@ -713,9 +710,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, add_delayed_data_ref(fs_info, trans, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, action, for_cow); - if (!need_ref_seq(for_cow, ref_root) && - waitqueue_active(&fs_info->tree_mod_seq_wait)) - wake_up(&fs_info->tree_mod_seq_wait); spin_unlock(&delayed_refs->lock); if (need_ref_seq(for_cow, ref_root)) btrfs_qgroup_record_ref(trans, &ref->node, extent_op); @@ -744,8 +738,6 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, num_bytes, BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data); - if (waitqueue_active(&fs_info->tree_mod_seq_wait)) - wake_up(&fs_info->tree_mod_seq_wait); spin_unlock(&delayed_refs->lock); return 0; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 502b20c56e84..a7ad8fc8dc53 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2035,8 +2035,6 @@ int open_ctree(struct super_block *sb, fs_info->free_chunk_space = 0; fs_info->tree_mod_log = RB_ROOT; - init_waitqueue_head(&fs_info->tree_mod_seq_wait); - /* readahead state */ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); spin_lock_init(&fs_info->reada_lock); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 45c69c4184c9..d3df65f83b5c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2318,12 +2318,6 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, ref->in_tree = 0; rb_erase(&ref->rb_node, &delayed_refs->root); delayed_refs->num_entries--; - /* - * we modified num_entries, but as we're currently running - * delayed refs, skip - * wake_up(&delayed_refs->seq_wait); - * here. - */ spin_unlock(&delayed_refs->lock); ret = run_one_delayed_ref(trans, root, ref, extent_op, @@ -2350,22 +2344,6 @@ next: return count; } -static void wait_for_more_refs(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - unsigned long num_refs, - struct list_head *first_seq) -{ - spin_unlock(&delayed_refs->lock); - pr_debug("waiting for more refs (num %ld, first %p)\n", - num_refs, first_seq); - wait_event(fs_info->tree_mod_seq_wait, - num_refs != delayed_refs->num_entries || - fs_info->tree_mod_seq_list.next != first_seq); - pr_debug("done waiting for more refs (num %ld, first %p)\n", - delayed_refs->num_entries, fs_info->tree_mod_seq_list.next); - spin_lock(&delayed_refs->lock); -} - #ifdef SCRAMBLE_DELAYED_REFS /* * Normally delayed refs get processed in ascending bytenr order. This @@ -2460,13 +2438,11 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; struct list_head cluster; - struct list_head *first_seq = NULL; int ret; u64 delayed_start; int run_all = count == (unsigned long)-1; int run_most = 0; - unsigned long num_refs = 0; - int consider_waiting; + int loops; /* We'll clean this up in btrfs_cleanup_transaction */ if (trans->aborted) @@ -2484,7 +2460,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; INIT_LIST_HEAD(&cluster); again: - consider_waiting = 0; + loops = 0; spin_lock(&delayed_refs->lock); #ifdef SCRAMBLE_DELAYED_REFS @@ -2512,31 +2488,6 @@ again: if (ret) break; - if (delayed_start >= delayed_refs->run_delayed_start) { - if (consider_waiting == 0) { - /* - * btrfs_find_ref_cluster looped. let's do one - * more cycle. if we don't run any delayed ref - * during that cycle (because we can't because - * all of them are blocked) and if the number of - * refs doesn't change, we avoid busy waiting. - */ - consider_waiting = 1; - num_refs = delayed_refs->num_entries; - first_seq = root->fs_info->tree_mod_seq_list.next; - } else { - wait_for_more_refs(root->fs_info, delayed_refs, - num_refs, first_seq); - /* - * after waiting, things have changed. we - * dropped the lock and someone else might have - * run some refs, built new clusters and so on. - * therefore, we restart staleness detection. - */ - consider_waiting = 0; - } - } - ret = run_clustered_refs(trans, root, &cluster); if (ret < 0) { spin_unlock(&delayed_refs->lock); @@ -2549,9 +2500,26 @@ again: if (count == 0) break; - if (ret || delayed_refs->run_delayed_start == 0) { + if (delayed_start >= delayed_refs->run_delayed_start) { + if (loops == 0) { + /* + * btrfs_find_ref_cluster looped. let's do one + * more cycle. if we don't run any delayed ref + * during that cycle (because we can't because + * all of them are blocked), bail out. + */ + loops = 1; + } else { + /* + * no runnable refs left, stop trying + */ + BUG_ON(run_all); + break; + } + } + if (ret) { /* refs were run, let's reset staleness detection */ - consider_waiting = 0; + loops = 0; } } @@ -5296,9 +5264,6 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, rb_erase(&head->node.rb_node, &delayed_refs->root); delayed_refs->num_entries--; - smp_mb(); - if (waitqueue_active(&root->fs_info->tree_mod_seq_wait)) - wake_up(&root->fs_info->tree_mod_seq_wait); /* * we don't take a ref on the node because we're removing it from the From 66657b318e0e443ada229fccd40c8be86cfebdbf Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 1 Aug 2012 15:36:24 -0400 Subject: [PATCH 172/208] Btrfs: barrier before waitqueue_active We need a barrir before calling waitqueue_active otherwise we will miss wakeups. So in places that do atomic_dec(); then atomic_read() use atomic_dec_return() which imply a memory barrier (see memory-barriers.txt) and then add an explicit memory barrier everywhere else that need them. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/compression.c | 1 + fs/btrfs/delayed-inode.c | 7 +++---- fs/btrfs/disk-io.c | 7 ++++--- fs/btrfs/inode.c | 4 +--- fs/btrfs/volumes.c | 3 +-- 5 files changed, 10 insertions(+), 12 deletions(-) diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 86eff48dab78..43d1c5a3a030 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -818,6 +818,7 @@ static void free_workspace(int type, struct list_head *workspace) btrfs_compress_op[idx]->free_workspace(workspace); atomic_dec(alloc_workspace); wake: + smp_mb(); if (waitqueue_active(workspace_wait)) wake_up(workspace_wait); } diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 00deed4ef3ed..07d5eeb1e6f1 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -512,8 +512,8 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) rb_erase(&delayed_item->rb_node, root); delayed_item->delayed_node->count--; - atomic_dec(&delayed_root->items); - if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND && + if (atomic_dec_return(&delayed_root->items) < + BTRFS_DELAYED_BACKGROUND && waitqueue_active(&delayed_root->wait)) wake_up(&delayed_root->wait); } @@ -1056,8 +1056,7 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node) delayed_node->count--; delayed_root = delayed_node->root->fs_info->delayed_root; - atomic_dec(&delayed_root->items); - if (atomic_read(&delayed_root->items) < + if (atomic_dec_return(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND && waitqueue_active(&delayed_root->wait)) wake_up(&delayed_root->wait); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a7ad8fc8dc53..dd86a5d88428 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -754,9 +754,7 @@ static void run_one_async_done(struct btrfs_work *work) limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; - atomic_dec(&fs_info->nr_async_submits); - - if (atomic_read(&fs_info->nr_async_submits) < limit && + if (atomic_dec_return(&fs_info->nr_async_submits) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); @@ -3783,14 +3781,17 @@ int btrfs_cleanup_transaction(struct btrfs_root *root) /* FIXME: cleanup wait for commit */ t->in_commit = 1; t->blocked = 1; + smp_mb(); if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) wake_up(&root->fs_info->transaction_blocked_wait); t->blocked = 0; + smp_mb(); if (waitqueue_active(&root->fs_info->transaction_wait)) wake_up(&root->fs_info->transaction_wait); t->commit_done = 1; + smp_mb(); if (waitqueue_active(&t->commit_wait)) wake_up(&t->commit_wait); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2d65c52b0944..97baf00b40d1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1007,9 +1007,7 @@ static noinline void async_cow_submit(struct btrfs_work *work) nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >> PAGE_CACHE_SHIFT; - atomic_sub(nr_pages, &root->fs_info->async_delalloc_pages); - - if (atomic_read(&root->fs_info->async_delalloc_pages) < + if (atomic_sub_return(nr_pages, &root->fs_info->async_delalloc_pages) < 5 * 1024 * 1024 && waitqueue_active(&root->fs_info->async_submit_wait)) wake_up(&root->fs_info->async_submit_wait); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3b394503bd4e..0b1e69d380dd 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -227,9 +227,8 @@ loop_lock: cur = pending; pending = pending->bi_next; cur->bi_next = NULL; - atomic_dec(&fs_info->nr_async_bios); - if (atomic_read(&fs_info->nr_async_bios) < limit && + if (atomic_dec_return(&fs_info->nr_async_bios) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); From 6fc823b10f333313deb0b5d9069cbfd3a3f99f3a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 6 Aug 2012 13:46:38 -0600 Subject: [PATCH 173/208] Btrfs: increase the size of the free space cache Arne was complaining about the space cache having mismatching generation numbers when debugging a deadlock. This is because we can run out of space in our preallocated range for our space cache if you have a pretty fragmented amount of space in your pinned space. So just increase the amount of space we preallocate for space cache so we can be sure to have enough space. This will only really affect data ranges since their the only chunks that end up larger than 256MB. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d3df65f83b5c..1bb408f737fb 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2975,17 +2975,16 @@ again: } spin_unlock(&block_group->lock); - num_pages = (int)div64_u64(block_group->key.offset, 1024 * 1024 * 1024); + /* + * Try to preallocate enough space based on how big the block group is. + * Keep in mind this has to include any pinned space which could end up + * taking up quite a bit since it's not folded into the other space + * cache. + */ + num_pages = (int)div64_u64(block_group->key.offset, 256 * 1024 * 1024); if (!num_pages) num_pages = 1; - /* - * Just to make absolutely sure we have enough space, we're going to - * preallocate 12 pages worth of space for each block group. In - * practice we ought to use at most 8, but we need extra space so we can - * add our header and have a terminator between the extents and the - * bitmaps. - */ num_pages *= 16; num_pages *= PAGE_CACHE_SIZE; From b12a3b1ea209d9dec02731fba58c3dbe7d31cfd8 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Tue, 7 Aug 2012 15:34:49 -0400 Subject: [PATCH 174/208] Btrfs: don't run __tree_mod_log_free_eb on leaves When we split a leaf, we may end up inserting a new root on top of that leaf. The reflog code was incorrectly assuming the old root was always a node. This makes sure we skip over leaves. Signed-off-by: Chris Mason --- fs/btrfs/ctree.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 08e0b11ba0a1..6d183f60d63a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -625,6 +625,9 @@ __tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) u32 nritems; int ret; + if (btrfs_header_level(eb) == 0) + return; + nritems = btrfs_header_nritems(eb); for (i = nritems - 1; i >= 0; i--) { ret = tree_mod_log_insert_key_locked(fs_info, eb, i, From 22cd2e7de7b0bd68fb668d23e1564707ca689510 Mon Sep 17 00:00:00 2001 From: Arne Jansen Date: Thu, 9 Aug 2012 00:16:53 -0600 Subject: [PATCH 175/208] Btrfs: fix race in run_clustered_refs With commit commit d1270cd91f308c9d22b2804720c36ccd32dbc35e Author: Arne Jansen Date: Tue Sep 13 15:16:43 2011 +0200 Btrfs: put back delayed refs that are too new I added a window where the delayed_ref's head->ref_mod code can diverge from the sum of the remaining refs, because we release the head->mutex in the middle. This leads to btrfs_lookup_extent_info returning wrong numbers. This patch fixes this by adjusting the head's ref_mod with each delayed ref we run. Signed-off-by: Arne Jansen Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1bb408f737fb..f16411d3c252 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2318,6 +2318,23 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, ref->in_tree = 0; rb_erase(&ref->rb_node, &delayed_refs->root); delayed_refs->num_entries--; + if (locked_ref) { + /* + * when we play the delayed ref, also correct the + * ref_mod on head + */ + switch (ref->action) { + case BTRFS_ADD_DELAYED_REF: + case BTRFS_ADD_DELAYED_EXTENT: + locked_ref->node.ref_mod -= ref->ref_mod; + break; + case BTRFS_DROP_DELAYED_REF: + locked_ref->node.ref_mod += ref->ref_mod; + break; + default: + WARN_ON(1); + } + } spin_unlock(&delayed_refs->lock); ret = run_one_delayed_ref(trans, root, ref, extent_op, From c0f62dedd04ae0f3b8a18079db5a015af24e416f Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Wed, 8 Aug 2012 21:39:36 -0600 Subject: [PATCH 176/208] Btrfs: fix wrong mtime and ctime when creating snapshots When we created a new snapshot, the mtime and ctime of its parent directory were not updated. Fix it. Signed-off-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/transaction.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 7208ada41e0e..3ee8d58e97ad 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1026,6 +1026,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->i_size + dentry->d_name.len * 2); + parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, parent_root, parent_inode); if (ret) goto abort_trans_dput; From 5a24e84c55f57cc49bd1cab531b6ef28b6b7bdaa Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 8 Aug 2012 10:12:59 -0600 Subject: [PATCH 177/208] Btrfs: fix enospc problems when deleting a subvol Subvol delete is a special kind of awful where we use the global reserve to cover the ENOSPC requirements. The problem is once we're done removing everything we do a btrfs_update_inode(), which by default will try to do the delayed update stuff which will use it's own reserve. There will be no space in this reserve and we'll return ENOSPC. So instead use btrfs_update_inode_fallback() which will just fallback to updating the inode item in the case of enospc. This is fine because the global reserve covers the space requirements for this. With this patch I can now delete a subvol on a problem image Dave Sterba sent me. Thanks, Reported-by: David Sterba Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 97baf00b40d1..0808f483dafa 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3171,7 +3171,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, btrfs_i_size_write(dir, dir->i_size - name_len * 2); inode_inc_iversion(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME; - ret = btrfs_update_inode(trans, root, dir); + ret = btrfs_update_inode_fallback(trans, root, dir); if (ret) btrfs_abort_transaction(trans, root, ret); out: From ae1e206b806ccc490dadff59af8a7a2477b32884 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 7 Aug 2012 16:00:32 -0400 Subject: [PATCH 178/208] Btrfs: allow delayed refs to be merged Daniel Blueman reported a bug with fio+balance on a ramdisk setup. Basically what happens is the balance relocates a tree block which will drop the implicit refs for all of its children and adds a full backref. Once the block is relocated we have to add the implicit refs back, so when we cow the block again we add the implicit refs for its children back. The problem comes when the original drop ref doesn't get run before we add the implicit refs back. The delayed ref stuff will specifically prefer ADD operations over DROP to keep us from freeing up an extent that will have references to it, so we try to add the implicit ref before it is actually removed and we panic. This worked fine before because the add would have just canceled the drop out and we would have been fine. But the backref walking work needs to be able to freeze the delayed ref stuff in time so we have this ever increasing sequence number that gets attached to all new delayed ref updates which makes us not merge refs and we run into this issue. So to fix this we need to merge delayed refs. So everytime we run a clustered ref we need to try and merge all of its delayed refs. The backref walking stuff locks the delayed ref head before processing, so if we have it locked we are safe to merge any refs inside of the sequence number. If there is no sequence number we can merge all refs. Doing this not only fixes our bug but keeps the delayed ref code from adding and removing useless refs and batching together multiple refs into one search instead of one search per delayed ref, which will really help our commit times. I ran this with Daniels test and 276 and I haven't seen any problems. Thanks, Reported-by: Daniel J Blueman Signed-off-by: Josef Bacik --- fs/btrfs/delayed-ref.c | 155 ++++++++++++++++++++++++++++++++++------- fs/btrfs/delayed-ref.h | 4 ++ fs/btrfs/extent-tree.c | 10 +++ 3 files changed, 142 insertions(+), 27 deletions(-) diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 7561431af50d..ae9411773397 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -38,17 +38,14 @@ static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref2, struct btrfs_delayed_tree_ref *ref1) { - if (ref1->node.type == BTRFS_TREE_BLOCK_REF_KEY) { - if (ref1->root < ref2->root) - return -1; - if (ref1->root > ref2->root) - return 1; - } else { - if (ref1->parent < ref2->parent) - return -1; - if (ref1->parent > ref2->parent) - return 1; - } + if (ref1->root < ref2->root) + return -1; + if (ref1->root > ref2->root) + return 1; + if (ref1->parent < ref2->parent) + return -1; + if (ref1->parent > ref2->parent) + return 1; return 0; } @@ -85,7 +82,8 @@ static int comp_data_refs(struct btrfs_delayed_data_ref *ref2, * type of the delayed backrefs and content of delayed backrefs. */ static int comp_entry(struct btrfs_delayed_ref_node *ref2, - struct btrfs_delayed_ref_node *ref1) + struct btrfs_delayed_ref_node *ref1, + bool compare_seq) { if (ref1->bytenr < ref2->bytenr) return -1; @@ -102,10 +100,12 @@ static int comp_entry(struct btrfs_delayed_ref_node *ref2, if (ref1->type > ref2->type) return 1; /* merging of sequenced refs is not allowed */ - if (ref1->seq < ref2->seq) - return -1; - if (ref1->seq > ref2->seq) - return 1; + if (compare_seq) { + if (ref1->seq < ref2->seq) + return -1; + if (ref1->seq > ref2->seq) + return 1; + } if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY || ref1->type == BTRFS_SHARED_BLOCK_REF_KEY) { return comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref2), @@ -139,7 +139,7 @@ static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root, entry = rb_entry(parent_node, struct btrfs_delayed_ref_node, rb_node); - cmp = comp_entry(entry, ins); + cmp = comp_entry(entry, ins, 1); if (cmp < 0) p = &(*p)->rb_left; else if (cmp > 0) @@ -233,6 +233,114 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, return 0; } +static void inline drop_delayed_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_node *ref) +{ + rb_erase(&ref->rb_node, &delayed_refs->root); + ref->in_tree = 0; + btrfs_put_delayed_ref(ref); + delayed_refs->num_entries--; + if (trans->delayed_ref_updates) + trans->delayed_ref_updates--; +} + +static int merge_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_node *ref, u64 seq) +{ + struct rb_node *node; + int merged = 0; + int mod = 0; + int done = 0; + + node = rb_prev(&ref->rb_node); + while (node) { + struct btrfs_delayed_ref_node *next; + + next = rb_entry(node, struct btrfs_delayed_ref_node, rb_node); + node = rb_prev(node); + if (next->bytenr != ref->bytenr) + break; + if (seq && next->seq >= seq) + break; + if (comp_entry(ref, next, 0)) + continue; + + if (ref->action == next->action) { + mod = next->ref_mod; + } else { + if (ref->ref_mod < next->ref_mod) { + struct btrfs_delayed_ref_node *tmp; + + tmp = ref; + ref = next; + next = tmp; + done = 1; + } + mod = -next->ref_mod; + } + + merged++; + drop_delayed_ref(trans, delayed_refs, next); + ref->ref_mod += mod; + if (ref->ref_mod == 0) { + drop_delayed_ref(trans, delayed_refs, ref); + break; + } else { + /* + * You can't have multiples of the same ref on a tree + * block. + */ + WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY || + ref->type == BTRFS_SHARED_BLOCK_REF_KEY); + } + + if (done) + break; + node = rb_prev(&ref->rb_node); + } + + return merged; +} + +void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head) +{ + struct rb_node *node; + u64 seq = 0; + + spin_lock(&fs_info->tree_mod_seq_lock); + if (!list_empty(&fs_info->tree_mod_seq_list)) { + struct seq_list *elem; + + elem = list_first_entry(&fs_info->tree_mod_seq_list, + struct seq_list, list); + seq = elem->seq; + } + spin_unlock(&fs_info->tree_mod_seq_lock); + + node = rb_prev(&head->node.rb_node); + while (node) { + struct btrfs_delayed_ref_node *ref; + + ref = rb_entry(node, struct btrfs_delayed_ref_node, + rb_node); + if (ref->bytenr != head->node.bytenr) + break; + + /* We can't merge refs that are outside of our seq count */ + if (seq && ref->seq >= seq) + break; + if (merge_ref(trans, delayed_refs, ref, seq)) + node = rb_prev(&head->node.rb_node); + else + node = rb_prev(node); + } +} + int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, u64 seq) @@ -336,18 +444,11 @@ update_existing_ref(struct btrfs_trans_handle *trans, * every changing the extent allocation tree. */ existing->ref_mod--; - if (existing->ref_mod == 0) { - rb_erase(&existing->rb_node, - &delayed_refs->root); - existing->in_tree = 0; - btrfs_put_delayed_ref(existing); - delayed_refs->num_entries--; - if (trans->delayed_ref_updates) - trans->delayed_ref_updates--; - } else { + if (existing->ref_mod == 0) + drop_delayed_ref(trans, delayed_refs, existing); + else WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY || existing->type == BTRFS_SHARED_BLOCK_REF_KEY); - } } else { WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY || existing->type == BTRFS_SHARED_BLOCK_REF_KEY); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 0d7c90c366b6..ab5300595847 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -167,6 +167,10 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); +void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head); struct btrfs_delayed_ref_head * btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f16411d3c252..ba58024d40d3 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2251,6 +2251,16 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, } } + /* + * We need to try and merge add/drops of the same ref since we + * can run into issues with relocate dropping the implicit ref + * and then it being added back again before the drop can + * finish. If we merged anything we need to re-loop so we can + * get a good ref. + */ + btrfs_merge_delayed_refs(trans, fs_info, delayed_refs, + locked_ref); + /* * locked_ref is the head node, so we have to go one * node back for any delayed ref updates From 68ce9682a4bb95d6be5529cb57214bf2a1b7d20e Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Wed, 1 Aug 2012 05:45:52 -0600 Subject: [PATCH 179/208] Btrfs: remove superblock writing after fatal error With commit acce952b0, btrfs was changed to flag the filesystem with BTRFS_SUPER_FLAG_ERROR and switch to read-only mode after a fatal error happened like a write I/O errors of all mirrors. In such situations, on unmount, the superblock is written in btrfs_error_commit_super(). This is done with the intention to be able to evaluate the error flag on the next mount. A warning is printed in this case during the next mount and the log tree is ignored. The issue is that it is possible that the superblock points to a root that was not written (due to write I/O errors). The result is that the filesystem cannot be mounted. btrfsck also does not start and all the other btrfs-progs tools fail to start as well. However, mount -o recovery is working well and does the right things to recover the filesystem (i.e., don't use the log root, clear the free space cache and use the next mountable root that is stored in the root backup array). This patch removes the writing of the superblock when BTRFS_SUPER_FLAG_ERROR is set, and removes the handling of the error flag in the mount function. These lines can be used to reproduce the issue (using /dev/sdm): SCRATCH_DEV=/dev/sdm SCRATCH_MNT=/mnt echo 0 25165824 linear $SCRATCH_DEV 0 | dmsetup create foo ls -alLF /dev/mapper/foo mkfs.btrfs /dev/mapper/foo mount /dev/mapper/foo $SCRATCH_MNT echo bar > $SCRATCH_MNT/foo sync echo 0 25165824 error | dmsetup reload foo dmsetup resume foo ls -alF $SCRATCH_MNT touch $SCRATCH_MNT/1 ls -alF $SCRATCH_MNT sleep 35 echo 0 25165824 linear $SCRATCH_DEV 0 | dmsetup reload foo dmsetup resume foo sleep 1 umount $SCRATCH_MNT btrfsck /dev/mapper/foo dmsetup remove foo Signed-off-by: Stefan Behrens Signed-off-by: Jan Schmidt --- fs/btrfs/disk-io.c | 36 ++++-------------------------------- fs/btrfs/disk-io.h | 2 +- 2 files changed, 5 insertions(+), 33 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index dd86a5d88428..3c4c4397f470 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2527,8 +2527,7 @@ retry_root_backup: goto fail_trans_kthread; /* do not make disk changes in broken FS */ - if (btrfs_super_log_root(disk_super) != 0 && - !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) { + if (btrfs_super_log_root(disk_super) != 0) { u64 bytenr = btrfs_super_log_root(disk_super); if (fs_devices->rw_devices == 0) { @@ -3188,30 +3187,14 @@ int close_ctree(struct btrfs_root *root) /* clear out the rbtree of defraggable inodes */ btrfs_run_defrag_inodes(fs_info); - /* - * Here come 2 situations when btrfs is broken to flip readonly: - * - * 1. when btrfs flips readonly somewhere else before - * btrfs_commit_super, sb->s_flags has MS_RDONLY flag, - * and btrfs will skip to write sb directly to keep - * ERROR state on disk. - * - * 2. when btrfs flips readonly just in btrfs_commit_super, - * and in such case, btrfs cannot write sb via btrfs_commit_super, - * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag, - * btrfs will cleanup all FS resources first and write sb then. - */ if (!(fs_info->sb->s_flags & MS_RDONLY)) { ret = btrfs_commit_super(root); if (ret) printk(KERN_ERR "btrfs: commit super ret %d\n", ret); } - if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { - ret = btrfs_error_commit_super(root); - if (ret) - printk(KERN_ERR "btrfs: commit super ret %d\n", ret); - } + if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) + btrfs_error_commit_super(root); btrfs_put_block_group_cache(fs_info); @@ -3433,18 +3416,11 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, if (read_only) return 0; - if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { - printk(KERN_WARNING "warning: mount fs with errors, " - "running btrfsck is recommended\n"); - } - return 0; } -int btrfs_error_commit_super(struct btrfs_root *root) +void btrfs_error_commit_super(struct btrfs_root *root) { - int ret; - mutex_lock(&root->fs_info->cleaner_mutex); btrfs_run_delayed_iputs(root); mutex_unlock(&root->fs_info->cleaner_mutex); @@ -3454,10 +3430,6 @@ int btrfs_error_commit_super(struct btrfs_root *root) /* cleanup FS via transaction */ btrfs_cleanup_transaction(root); - - ret = write_ctree_super(NULL, root, 0); - - return ret; } static void btrfs_destroy_ordered_operations(struct btrfs_root *root) diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 95e147eea239..c5b00a735fef 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -54,7 +54,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); int btrfs_commit_super(struct btrfs_root *root); -int btrfs_error_commit_super(struct btrfs_root *root); +void btrfs_error_commit_super(struct btrfs_root *root); struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize); struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, From 5ee0844d6427e7338e0aba748f62b62d07ea2ed0 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Mon, 27 Aug 2012 08:30:03 -0600 Subject: [PATCH 180/208] Btrfs: revert checksum error statistic which can cause a BUG() Commit 442a4f6308e694e0fa6025708bd5e4e424bbf51c added btrfs device statistic counters for detected IO and checksum errors to Linux 3.5. The statistic part that counts checksum errors in end_bio_extent_readpage() can cause a BUG() in a subfunction: "kernel BUG at fs/btrfs/volumes.c:3762!" That part is reverted with the current patch. However, the counting of checksum errors in the scrub context remains active, and the counting of detected IO errors (read, write or flush errors) in all contexts remains active. Cc: stable # 3.5 Signed-off-by: Stefan Behrens Signed-off-by: Chris Mason --- fs/btrfs/extent_io.c | 17 ++--------------- fs/btrfs/volumes.c | 22 ---------------------- fs/btrfs/volumes.h | 2 -- 3 files changed, 2 insertions(+), 39 deletions(-) diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 3e7c9ed6505b..49085f2336d2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2329,23 +2329,10 @@ static void end_bio_extent_readpage(struct bio *bio, int err) if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { ret = tree->ops->readpage_end_io_hook(page, start, end, state, mirror); - if (ret) { - /* no IO indicated but software detected errors - * in the block, either checksum errors or - * issues with the contents */ - struct btrfs_root *root = - BTRFS_I(page->mapping->host)->root; - struct btrfs_device *device; - + if (ret) uptodate = 0; - device = btrfs_find_device_for_logical( - root, start, mirror); - if (device) - btrfs_dev_stat_inc_and_print(device, - BTRFS_DEV_STAT_CORRUPTION_ERRS); - } else { + else clean_io_failure(start, page); - } } if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0b1e69d380dd..3f4e70e171ed 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4610,28 +4610,6 @@ int btrfs_read_sys_array(struct btrfs_root *root) return ret; } -struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, - u64 logical, int mirror_num) -{ - struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree; - int ret; - u64 map_length = 0; - struct btrfs_bio *bbio = NULL; - struct btrfs_device *device; - - BUG_ON(mirror_num == 0); - ret = btrfs_map_block(map_tree, WRITE, logical, &map_length, &bbio, - mirror_num); - if (ret) { - BUG_ON(bbio != NULL); - return NULL; - } - BUG_ON(mirror_num != bbio->mirror_num); - device = bbio->stripes[mirror_num - 1].dev; - kfree(bbio); - return device; -} - int btrfs_read_chunk_tree(struct btrfs_root *root) { struct btrfs_path *path; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 5479325987b3..53c06af92e8d 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -289,8 +289,6 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *max_avail); -struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, - u64 logical, int mirror_num); void btrfs_dev_stat_print_on_error(struct btrfs_device *device); void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index); int btrfs_get_dev_stats(struct btrfs_root *root, From bd7de2c9a449e26a5493d918618eb20ae60d56bd Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 24 Aug 2012 12:53:03 -0600 Subject: [PATCH 181/208] Btrfs: fix deadlock with freeze and sync V2 We can deadlock with freeze right now because we unconditionally start a transaction in our ->sync_fs() call. To fix this just check and see if we have a running transaction to commit. This saves us from the deadlock because at this point we'll have the umount sem for the sb so we're safe from freezes coming in after we've done our check. With this patch the freeze xfstests no longer deadlocks. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/super.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 2e06f124f284..073c2368f459 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -813,7 +813,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait) struct btrfs_trans_handle *trans; struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root = fs_info->tree_root; - int ret; trace_btrfs_sync_fs(wait); @@ -824,11 +823,17 @@ int btrfs_sync_fs(struct super_block *sb, int wait) btrfs_wait_ordered_extents(root, 0, 0); - trans = btrfs_start_transaction(root, 0); + spin_lock(&fs_info->trans_lock); + if (!fs_info->running_transaction) { + spin_unlock(&fs_info->trans_lock); + return 0; + } + spin_unlock(&fs_info->trans_lock); + + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - return ret; + return btrfs_commit_transaction(trans, root); } static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) From 24c03fa5cf3d02c327cf9f2fc39f72664b1bd7e1 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Wed, 22 Aug 2012 20:10:38 -0600 Subject: [PATCH 182/208] Btrfs: fix a dio write regression This bug is introduced by commit 3b8bde746f6f9bd36a9f05f5f3b6e334318176a9 (Btrfs: lock extents as we map them in DIO). In dio write, we should unlock the section which we didn't do IO on in case that we fall back to buffered write. But we need to not only unlock the section but also cleanup reserved space for the section. This bug was found while running xfstests 133, with this 133 no longer complains. Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0808f483dafa..38cda78de5e4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5992,11 +5992,27 @@ unlock: * in the case of read we need to unlock only the end area that we * aren't using if there is any left over space. */ - if (lockstart < lockend) - clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, - unlock_bits, 1, 0, &cached_state, GFP_NOFS); - else + if (lockstart < lockend) { + if (create && len < lockend - lockstart) { + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockstart + len - 1, unlock_bits, 1, 0, + &cached_state, GFP_NOFS); + /* + * Beside unlock, we also need to cleanup reserved space + * for the left range by attaching EXTENT_DO_ACCOUNTING. + */ + clear_extent_bit(&BTRFS_I(inode)->io_tree, + lockstart + len, lockend, + unlock_bits | EXTENT_DO_ACCOUNTING, + 1, 0, NULL, GFP_NOFS); + } else { + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockend, unlock_bits, 1, 0, + &cached_state, GFP_NOFS); + } + } else { free_extent_state(cached_state); + } free_extent_map(em); From d280e5be940931c84bb2e9831ead9d02bc785484 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Tue, 21 Aug 2012 21:13:25 -0600 Subject: [PATCH 183/208] Btrfs: fix ordered extent leak when failing to start a transaction We cannot just return error before freeing ordered extent and releasing reserved space when we fail to start a transacion. Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 38cda78de5e4..6ba80b902877 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1882,8 +1882,11 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) trans = btrfs_join_transaction_nolock(root); else trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + trans = NULL; + goto out; + } trans->block_rsv = &root->fs_info->delalloc_block_rsv; ret = btrfs_update_inode_fallback(trans, root, inode); if (ret) /* -ENOMEM or corruption */ From 256dd1bb3750ac5ad49b40887c1691788dc44b33 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Fri, 10 Aug 2012 08:58:21 -0600 Subject: [PATCH 184/208] Btrfs: fix that repair code is spuriously executed for transid failures If verify_parent_transid() fails for all mirrors, the current code calls repair_io_failure() anyway which means: - that the disk block is rewritten without repairing anything and - that a kernel log message is printed which misleadingly claims that a read error was corrected. This is an example: parent transid verify failed on 615015833600 wanted 110423 found 110424 parent transid verify failed on 615015833600 wanted 110423 found 110424 btrfs read error corrected: ino 1 off 615015833600 (dev /dev/...) It is wrong to ignore the results from verify_parent_transid() and to call repair_eb_io_failure() when the verification of the transids failed. This commit fixes the issue. Signed-off-by: Stefan Behrens Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 3c4c4397f470..29c69e60d3b0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -377,9 +377,13 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, ret = read_extent_buffer_pages(io_tree, eb, start, WAIT_COMPLETE, btree_get_extent, mirror_num); - if (!ret && !verify_parent_transid(io_tree, eb, + if (!ret) { + if (!verify_parent_transid(io_tree, eb, parent_transid, 0)) - break; + break; + else + ret = -EIO; + } /* * This buffer's crc is fine, but its contents are corrupted, so From 14f0458a41e033dee31ba605137419385c03fc78 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Mon, 27 Aug 2012 16:22:49 +1000 Subject: [PATCH 185/208] drm/nvc0/copy: check PUNITS to determine which copy engines are disabled On some Fermi chipsets (NVCE particularly) PCOPY1 doesn't exist. And if what I've seen on Kepler is true of Fermi too, chipsets of the same type can have different PCOPY units available. This should fix a v3.5 regression reported by a number of people effecting suspend/resume on NVC8/NVCE chipsets. Cc: stable@vger.kernel.org [3.5] Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_state.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c index 1866dbb49979..c61014442aa9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_state.c +++ b/drivers/gpu/drm/nouveau/nouveau_state.c @@ -736,9 +736,11 @@ nouveau_card_init(struct drm_device *dev) } break; case NV_C0: - nvc0_copy_create(dev, 1); + if (!(nv_rd32(dev, 0x022500) & 0x00000200)) + nvc0_copy_create(dev, 1); case NV_D0: - nvc0_copy_create(dev, 0); + if (!(nv_rd32(dev, 0x022500) & 0x00000100)) + nvc0_copy_create(dev, 0); break; default: break; From 4b1c2f41c2dda158bb7a3dded70775a76b581995 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 23 Jul 2012 10:46:11 -0700 Subject: [PATCH 186/208] watchdog: fix watchdog-test.c build warning Fix compiler warning by making the function static: Documentation/watchdog/src/watchdog-test.c:34:6: warning: no previous prototype for 'term' Signed-off-by: Randy Dunlap Signed-off-by: Wim Van Sebroeck --- Documentation/watchdog/src/watchdog-test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/watchdog/src/watchdog-test.c b/Documentation/watchdog/src/watchdog-test.c index 73ff5cc93e05..3da822967ee0 100644 --- a/Documentation/watchdog/src/watchdog-test.c +++ b/Documentation/watchdog/src/watchdog-test.c @@ -31,7 +31,7 @@ static void keep_alive(void) * or "-e" to enable the card. */ -void term(int sig) +static void term(int sig) { close(fd); fprintf(stderr, "Stopping watchdog ticks...\n"); From 3e5531caffcc07b67452c4a8170ffb4c2bd1c9b7 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Tue, 7 Aug 2012 15:14:12 +0530 Subject: [PATCH 187/208] watchdog: da9052: Remove duplicate inclusion of delay.h delay.h header file was included twice. Signed-off-by: Sachin Kamat Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/da9052_wdt.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/watchdog/da9052_wdt.c b/drivers/watchdog/da9052_wdt.c index 3f75129eb0a9..f7abbaeebcaf 100644 --- a/drivers/watchdog/da9052_wdt.c +++ b/drivers/watchdog/da9052_wdt.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include From 305a3d204aae15eddf1988e50e33aee4119b710d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= Date: Wed, 22 Aug 2012 17:02:42 +0200 Subject: [PATCH 188/208] drm/radeon: fix reading CB_COLORn_MASK from the CS MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Marek Olšák Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/r600_cs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index ab74e6b149e7..7799e283811f 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -1416,7 +1416,7 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) case R_028118_CB_COLOR6_MASK: case R_02811C_CB_COLOR7_MASK: tmp = (reg - R_028100_CB_COLOR0_MASK) / 4; - track->cb_color_mask[tmp] = ib[idx]; + track->cb_color_mask[tmp] = radeon_get_ib_value(p, idx); if (G_0280A0_TILE_MODE(track->cb_color_info[tmp])) { track->cb_dirty = true; } From 3b5ef597ec40603c368f65d3eb6d9818ed6a7bae Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= Date: Wed, 22 Aug 2012 17:02:43 +0200 Subject: [PATCH 189/208] drm/radeon: initialize tracked CS state MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This should help catch uninitialized registers and reject commands because of that. Signed-off-by: Marek Olšák Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/r600_cs.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 7799e283811f..8866937bd0b4 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -315,7 +315,14 @@ static void r600_cs_track_init(struct r600_cs_track *track) track->cb_color_bo[i] = NULL; track->cb_color_bo_offset[i] = 0xFFFFFFFF; track->cb_color_bo_mc[i] = 0xFFFFFFFF; + track->cb_color_frag_bo[i] = NULL; + track->cb_color_frag_offset[i] = 0xFFFFFFFF; + track->cb_color_tile_bo[i] = NULL; + track->cb_color_tile_offset[i] = 0xFFFFFFFF; + track->cb_color_mask[i] = 0xFFFFFFFF; } + track->nsamples = 16; + track->log_nsamples = 4; track->cb_target_mask = 0xFFFFFFFF; track->cb_shader_mask = 0xFFFFFFFF; track->cb_dirty = true; From 523885dec109188b6bed53ec67362072f13b0d43 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marek=20Ol=C5=A1=C3=A1k?= Date: Fri, 24 Aug 2012 14:27:36 +0200 Subject: [PATCH 190/208] drm/radeon: add proper checking of RESOLVE_BOX command for r600-r700 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Checking of the second colorbuffer was skipped on r700, because CB_TARGET_MASK was 0xf. With r600, CB_TARGET_MASK is changed to 0xff, so we must set the number of samples of the second colorbuffer to 1 in order to pass the CS checker. The DRM version is bumped, because RESOLVE_BOX is always rejected without this fix on r600. Signed-off-by: Marek Olšák Reviewed-by: Jerome Glisse Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/r600_cs.c | 19 +++++++++++++++++-- drivers/gpu/drm/radeon/r600d.h | 8 ++++++++ drivers/gpu/drm/radeon/radeon_drv.c | 3 ++- drivers/gpu/drm/radeon/reg_srcs/r600 | 1 - 4 files changed, 27 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c index 8866937bd0b4..f37676d7f217 100644 --- a/drivers/gpu/drm/radeon/r600_cs.c +++ b/drivers/gpu/drm/radeon/r600_cs.c @@ -63,6 +63,7 @@ struct r600_cs_track { u32 cb_color_size_idx[8]; /* unused */ u32 cb_target_mask; u32 cb_shader_mask; /* unused */ + bool is_resolve; u32 cb_color_size[8]; u32 vgt_strmout_en; u32 vgt_strmout_buffer_en; @@ -321,6 +322,7 @@ static void r600_cs_track_init(struct r600_cs_track *track) track->cb_color_tile_offset[i] = 0xFFFFFFFF; track->cb_color_mask[i] = 0xFFFFFFFF; } + track->is_resolve = false; track->nsamples = 16; track->log_nsamples = 4; track->cb_target_mask = 0xFFFFFFFF; @@ -359,6 +361,8 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) volatile u32 *ib = p->ib.ptr; unsigned array_mode; u32 format; + /* When resolve is used, the second colorbuffer has always 1 sample. */ + unsigned nsamples = track->is_resolve && i == 1 ? 1 : track->nsamples; size = radeon_bo_size(track->cb_color_bo[i]) - track->cb_color_bo_offset[i]; format = G_0280A0_FORMAT(track->cb_color_info[i]); @@ -382,7 +386,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) array_check.group_size = track->group_size; array_check.nbanks = track->nbanks; array_check.npipes = track->npipes; - array_check.nsamples = track->nsamples; + array_check.nsamples = nsamples; array_check.blocksize = r600_fmt_get_blocksize(format); if (r600_get_array_mode_alignment(&array_check, &pitch_align, &height_align, &depth_align, &base_align)) { @@ -428,7 +432,7 @@ static int r600_cs_track_validate_cb(struct radeon_cs_parser *p, int i) /* check offset */ tmp = r600_fmt_get_nblocksy(format, height) * r600_fmt_get_nblocksx(format, pitch) * - r600_fmt_get_blocksize(format) * track->nsamples; + r600_fmt_get_blocksize(format) * nsamples; switch (array_mode) { default: case V_0280A0_ARRAY_LINEAR_GENERAL: @@ -799,6 +803,12 @@ static int r600_cs_track_check(struct radeon_cs_parser *p) */ if (track->cb_dirty) { tmp = track->cb_target_mask; + + /* We must check both colorbuffers for RESOLVE. */ + if (track->is_resolve) { + tmp |= 0xff; + } + for (i = 0; i < 8; i++) { if ((tmp >> (i * 4)) & 0xF) { /* at least one component is enabled */ @@ -1288,6 +1298,11 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx) track->nsamples = 1 << tmp; track->cb_dirty = true; break; + case R_028808_CB_COLOR_CONTROL: + tmp = G_028808_SPECIAL_OP(radeon_get_ib_value(p, idx)); + track->is_resolve = tmp == V_028808_SPECIAL_RESOLVE_BOX; + track->cb_dirty = true; + break; case R_0280A0_CB_COLOR0_INFO: case R_0280A4_CB_COLOR1_INFO: case R_0280A8_CB_COLOR2_INFO: diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h index bdb69a63062f..fa6f37099ba9 100644 --- a/drivers/gpu/drm/radeon/r600d.h +++ b/drivers/gpu/drm/radeon/r600d.h @@ -66,6 +66,14 @@ #define CC_RB_BACKEND_DISABLE 0x98F4 #define BACKEND_DISABLE(x) ((x) << 16) +#define R_028808_CB_COLOR_CONTROL 0x28808 +#define S_028808_SPECIAL_OP(x) (((x) & 0x7) << 4) +#define G_028808_SPECIAL_OP(x) (((x) >> 4) & 0x7) +#define C_028808_SPECIAL_OP 0xFFFFFF8F +#define V_028808_SPECIAL_NORMAL 0x00 +#define V_028808_SPECIAL_DISABLE 0x01 +#define V_028808_SPECIAL_RESOLVE_BOX 0x07 + #define CB_COLOR0_BASE 0x28040 #define CB_COLOR1_BASE 0x28044 #define CB_COLOR2_BASE 0x28048 diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 27d22d709c90..8c593ea82c41 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -63,9 +63,10 @@ * 2.19.0 - r600-eg: MSAA textures * 2.20.0 - r600-si: RADEON_INFO_TIMESTAMP query * 2.21.0 - r600-r700: FMASK and CMASK + * 2.22.0 - r600 only: RESOLVE_BOX allowed */ #define KMS_DRIVER_MAJOR 2 -#define KMS_DRIVER_MINOR 21 +#define KMS_DRIVER_MINOR 22 #define KMS_DRIVER_PATCHLEVEL 0 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags); int radeon_driver_unload_kms(struct drm_device *dev); diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600 index f93e45d869f4..20bfbda7b3f1 100644 --- a/drivers/gpu/drm/radeon/reg_srcs/r600 +++ b/drivers/gpu/drm/radeon/reg_srcs/r600 @@ -744,7 +744,6 @@ r600 0x9400 0x00028C38 CB_CLRCMP_DST 0x00028C3C CB_CLRCMP_MSK 0x00028C34 CB_CLRCMP_SRC -0x00028808 CB_COLOR_CONTROL 0x0002842C CB_FOG_BLUE 0x00028428 CB_FOG_GREEN 0x00028424 CB_FOG_RED From 4e58591c8961b3e31709313f75819f2eec06e322 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Tue, 21 Aug 2012 19:06:21 -0400 Subject: [PATCH 191/208] drm/radeon: don't disable plls that are in use by other crtcs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some plls are shared for DP. Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Reviewed-by: Michel Dänzer --- drivers/gpu/drm/radeon/atombios_crtc.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index f4d4505fe831..961d366f00eb 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -1682,9 +1682,22 @@ static void atombios_crtc_disable(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_atom_ss ss; + int i; atombios_crtc_dpms(crtc, DRM_MODE_DPMS_OFF); + for (i = 0; i < rdev->num_crtc; i++) { + if (rdev->mode_info.crtcs[i] && + rdev->mode_info.crtcs[i]->enabled && + i != radeon_crtc->crtc_id && + radeon_crtc->pll_id == rdev->mode_info.crtcs[i]->pll_id) { + /* one other crtc is using this pll don't turn + * off the pll + */ + goto done; + } + } + switch (radeon_crtc->pll_id) { case ATOM_PPLL1: case ATOM_PPLL2: @@ -1701,6 +1714,7 @@ static void atombios_crtc_disable(struct drm_crtc *crtc) default: break; } +done: radeon_crtc->pll_id = -1; } From 8d1af57ae3c4458ed0de93ef97f388dd1b3239c7 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 22 Aug 2012 09:54:56 -0400 Subject: [PATCH 192/208] drm/radeon/atom: rework DIG modesetting on DCE3+ The ordering is important and the current drm code wasn't cutting it for modern DIG encoders. We need to have information about crtc before setting up the encoders so I've shifted the ordering a bit. Probably we'll need a full rework akin to danvet's recent intel patchs. This patch fixes numerous issues with DP bridge chips and makes link training much more reliable. Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/atombios_encoders.c | 109 +++++++++------------ 1 file changed, 47 insertions(+), 62 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index f9bc27fe269a..4a7f95e5550d 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1379,6 +1379,8 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); + struct drm_encoder *ext_encoder = radeon_get_external_encoder(encoder); + struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); struct radeon_connector *radeon_connector = NULL; struct radeon_connector_atom_dig *radeon_dig_connector = NULL; @@ -1390,19 +1392,37 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) switch (mode) { case DRM_MODE_DPMS_ON: - /* some early dce3.2 boards have a bug in their transmitter control table */ - if ((rdev->family == CHIP_RV710) || (rdev->family == CHIP_RV730) || - ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) { - if (ASIC_IS_DCE6(rdev)) { - /* It seems we need to call ATOM_ENCODER_CMD_SETUP again - * before reenabling encoder on DPMS ON, otherwise we never - * get picture - */ - atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0); + if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) { + if (!connector) + dig->panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE; + else + dig->panel_mode = radeon_dp_get_panel_mode(encoder, connector); + + /* setup and enable the encoder */ + atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0); + atombios_dig_encoder_setup(encoder, + ATOM_ENCODER_CMD_SETUP_PANEL_MODE, + dig->panel_mode); + if (ext_encoder) { + if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev)) + atombios_external_encoder_setup(encoder, ext_encoder, + EXTERNAL_ENCODER_ACTION_V3_ENCODER_SETUP); } atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); - } else { + } else if (ASIC_IS_DCE4(rdev)) { + /* setup and enable the encoder */ + atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0); + /* enable the transmitter */ + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); + } else { + /* setup and enable the encoder and transmitter */ + atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0); + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0); + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); + /* some early dce3.2 boards have a bug in their transmitter control table */ + if ((rdev->family != CHIP_RV710) || (rdev->family != CHIP_RV730)) + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE_OUTPUT, 0, 0); } if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) { if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { @@ -1420,10 +1440,19 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode) case DRM_MODE_DPMS_STANDBY: case DRM_MODE_DPMS_SUSPEND: case DRM_MODE_DPMS_OFF: - if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) + if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) { + /* disable the transmitter */ atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); - else + } else if (ASIC_IS_DCE4(rdev)) { + /* disable the transmitter */ atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0); + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); + } else { + /* disable the encoder and transmitter */ + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE_OUTPUT, 0, 0); + atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); + atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0); + } if (ENCODER_MODE_IS_DP(atombios_get_encoder_mode(encoder)) && connector) { if (ASIC_IS_DCE4(rdev)) atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_OFF, 0); @@ -1848,10 +1877,12 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, struct drm_device *dev = encoder->dev; struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); - struct drm_encoder *ext_encoder = radeon_get_external_encoder(encoder); radeon_encoder->pixel_clock = adjusted_mode->clock; + /* need to call this here rather than in prepare() since we need some crtc info */ + radeon_atom_encoder_dpms(encoder, DRM_MODE_DPMS_OFF); + if (ASIC_IS_AVIVO(rdev) && !ASIC_IS_DCE4(rdev)) { if (radeon_encoder->active_device & (ATOM_DEVICE_CV_SUPPORT | ATOM_DEVICE_TV_SUPPORT)) atombios_yuv_setup(encoder, true); @@ -1870,38 +1901,7 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA: - if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE5(rdev)) { - struct drm_connector *connector = radeon_get_connector_for_encoder(encoder); - struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; - - if (!connector) - dig->panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE; - else - dig->panel_mode = radeon_dp_get_panel_mode(encoder, connector); - - /* setup and enable the encoder */ - atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0); - atombios_dig_encoder_setup(encoder, - ATOM_ENCODER_CMD_SETUP_PANEL_MODE, - dig->panel_mode); - } else if (ASIC_IS_DCE4(rdev)) { - /* disable the transmitter */ - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); - /* setup and enable the encoder */ - atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_SETUP, 0); - - /* enable the transmitter */ - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); - } else { - /* disable the encoder and transmitter */ - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); - atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0); - - /* setup and enable the encoder and transmitter */ - atombios_dig_encoder_setup(encoder, ATOM_ENABLE, 0); - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_SETUP, 0, 0); - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_ENABLE, 0, 0); - } + /* handled in dpms */ break; case ENCODER_OBJECT_ID_INTERNAL_DDI: case ENCODER_OBJECT_ID_INTERNAL_DVO1: @@ -1922,14 +1922,6 @@ radeon_atom_encoder_mode_set(struct drm_encoder *encoder, break; } - if (ext_encoder) { - if (ASIC_IS_DCE41(rdev) || ASIC_IS_DCE61(rdev)) - atombios_external_encoder_setup(encoder, ext_encoder, - EXTERNAL_ENCODER_ACTION_V3_ENCODER_SETUP); - else - atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE); - } - atombios_apply_encoder_quirks(encoder, adjusted_mode); if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_HDMI) { @@ -2116,7 +2108,6 @@ static void radeon_atom_encoder_prepare(struct drm_encoder *encoder) } radeon_atom_output_lock(encoder, true); - radeon_atom_encoder_dpms(encoder, DRM_MODE_DPMS_OFF); if (connector) { struct radeon_connector *radeon_connector = to_radeon_connector(connector); @@ -2137,6 +2128,7 @@ static void radeon_atom_encoder_prepare(struct drm_encoder *encoder) static void radeon_atom_encoder_commit(struct drm_encoder *encoder) { + /* need to call this here as we need the crtc set up */ radeon_atom_encoder_dpms(encoder, DRM_MODE_DPMS_ON); radeon_atom_output_lock(encoder, false); } @@ -2177,14 +2169,7 @@ static void radeon_atom_encoder_disable(struct drm_encoder *encoder) case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: case ENCODER_OBJECT_ID_INTERNAL_KLDSCP_LVTMA: - if (ASIC_IS_DCE4(rdev)) - /* disable the transmitter */ - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); - else { - /* disable the encoder and transmitter */ - atombios_dig_transmitter_setup(encoder, ATOM_TRANSMITTER_ACTION_DISABLE, 0, 0); - atombios_dig_encoder_setup(encoder, ATOM_DISABLE, 0); - } + /* handled in dpms */ break; case ENCODER_OBJECT_ID_INTERNAL_DDI: case ENCODER_OBJECT_ID_INTERNAL_DVO1: From c205b232a64fed6d26edd7e40985b396de99a27f Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 24 Aug 2012 18:21:21 -0400 Subject: [PATCH 193/208] drm/radeon/atom: powergating fixes for DCE6 Power gating is per crtc pair, but the powergating registers should be called individually. The hw handles power up/down properly. The pair is powered up if either crtc in the pair is powered up and the pair is not powered down until both crtcs in the pair are powered down. This simplifies programming and should save additional power as the previous code never actually power gated the crtc pair. Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/atombios_crtc.c | 22 ++-------------------- 1 file changed, 2 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index 961d366f00eb..2817101fb167 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -258,7 +258,6 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode) radeon_crtc->enabled = true; /* adjust pm to dpms changes BEFORE enabling crtcs */ radeon_pm_compute_clocks(rdev); - /* disable crtc pair power gating before programming */ if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set) atombios_powergate_crtc(crtc, ATOM_DISABLE); atombios_enable_crtc(crtc, ATOM_ENABLE); @@ -278,25 +277,8 @@ void atombios_crtc_dpms(struct drm_crtc *crtc, int mode) atombios_enable_crtc_memreq(crtc, ATOM_DISABLE); atombios_enable_crtc(crtc, ATOM_DISABLE); radeon_crtc->enabled = false; - /* power gating is per-pair */ - if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set) { - struct drm_crtc *other_crtc; - struct radeon_crtc *other_radeon_crtc; - list_for_each_entry(other_crtc, &rdev->ddev->mode_config.crtc_list, head) { - other_radeon_crtc = to_radeon_crtc(other_crtc); - if (((radeon_crtc->crtc_id == 0) && (other_radeon_crtc->crtc_id == 1)) || - ((radeon_crtc->crtc_id == 1) && (other_radeon_crtc->crtc_id == 0)) || - ((radeon_crtc->crtc_id == 2) && (other_radeon_crtc->crtc_id == 3)) || - ((radeon_crtc->crtc_id == 3) && (other_radeon_crtc->crtc_id == 2)) || - ((radeon_crtc->crtc_id == 4) && (other_radeon_crtc->crtc_id == 5)) || - ((radeon_crtc->crtc_id == 5) && (other_radeon_crtc->crtc_id == 4))) { - /* if both crtcs in the pair are off, enable power gating */ - if (other_radeon_crtc->enabled == false) - atombios_powergate_crtc(crtc, ATOM_ENABLE); - break; - } - } - } + if (ASIC_IS_DCE6(rdev) && !radeon_crtc->in_mode_set) + atombios_powergate_crtc(crtc, ATOM_ENABLE); /* adjust pm to dpms changes AFTER disabling crtcs */ radeon_pm_compute_clocks(rdev); break; From 0ceb996c9e729b056977a0f07692b38bbd57bc77 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Mon, 27 Aug 2012 17:48:18 -0400 Subject: [PATCH 194/208] drm/radeon: rework panel mode setup Adjust the panel mode setup to match the behavior of the vbios. Rather than checking for specific bridge chip ids, just check the eDP configuration register. This saves extra aux transactions and works across DP bridge chips without requiring additional per chip id checking. Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/atombios_dp.c | 29 ++++++++++++---------------- 1 file changed, 12 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c index 7712cf5ab33b..3623b98ed3fe 100644 --- a/drivers/gpu/drm/radeon/atombios_dp.c +++ b/drivers/gpu/drm/radeon/atombios_dp.c @@ -577,30 +577,25 @@ int radeon_dp_get_panel_mode(struct drm_encoder *encoder, struct radeon_device *rdev = dev->dev_private; struct radeon_connector *radeon_connector = to_radeon_connector(connector); int panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE; + u16 dp_bridge = radeon_connector_encoder_get_dp_bridge_encoder_id(connector); + u8 tmp; if (!ASIC_IS_DCE4(rdev)) return panel_mode; - if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) == - ENCODER_OBJECT_ID_NUTMEG) - panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE; - else if (radeon_connector_encoder_get_dp_bridge_encoder_id(connector) == - ENCODER_OBJECT_ID_TRAVIS) { - u8 id[6]; - int i; - for (i = 0; i < 6; i++) - id[i] = radeon_read_dpcd_reg(radeon_connector, 0x503 + i); - if (id[0] == 0x73 && - id[1] == 0x69 && - id[2] == 0x76 && - id[3] == 0x61 && - id[4] == 0x72 && - id[5] == 0x54) + if (dp_bridge != ENCODER_OBJECT_ID_NONE) { + /* DP bridge chips */ + tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP); + if (tmp & 1) + panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE; + else if ((dp_bridge == ENCODER_OBJECT_ID_NUTMEG) || + (dp_bridge == ENCODER_OBJECT_ID_TRAVIS)) panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE; else - panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE; + panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE; } else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) { - u8 tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP); + /* eDP */ + tmp = radeon_read_dpcd_reg(radeon_connector, DP_EDP_CONFIGURATION_CAP); if (tmp & 1) panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE; } From 4a2b6662c3632176b4fdf012243dd3751367bf1f Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Tue, 28 Aug 2012 16:50:22 -0400 Subject: [PATCH 195/208] drm/radeon: force dma32 to fix regression rs4xx,rs6xx,rs740 It seems some of those IGP dislike non dma32 page despite what documentation says. Fix regression since we allowed non dma32 pages. It seems it only affect some revision of those IGP chips as we don't know which one just force dma32 for all of them. https://bugzilla.redhat.com/show_bug.cgi?id=785375 Signed-off-by: Jerome Glisse Cc: Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index d2e243867ac6..33da8bff8942 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1051,7 +1051,7 @@ int radeon_device_init(struct radeon_device *rdev, if (rdev->flags & RADEON_IS_AGP) rdev->need_dma32 = true; if ((rdev->flags & RADEON_IS_PCI) && - (rdev->family < CHIP_RS400)) + (rdev->family <= CHIP_RS740)) rdev->need_dma32 = true; dma_bits = rdev->need_dma32 ? 32 : 40; From f54b350d89bf16d31593b935bafccf510ff4a708 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Wed, 29 Aug 2012 13:24:15 +0200 Subject: [PATCH 196/208] drm/radeon: fix double free in radeon_gpu_reset MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit radeon_ring_restore is freeing the memory for the saved ring data. We need to remember that, otherwise we try to restore the ring data again on the next try. Additional to that it shouldn't try the reset infinitely if we have saved ring data. Signed-off-by: Christian König Reviewed-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_device.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c index 33da8bff8942..7a3daebd732d 100644 --- a/drivers/gpu/drm/radeon/radeon_device.c +++ b/drivers/gpu/drm/radeon/radeon_device.c @@ -1346,12 +1346,15 @@ retry: for (i = 0; i < RADEON_NUM_RINGS; ++i) { radeon_ring_restore(rdev, &rdev->ring[i], ring_sizes[i], ring_data[i]); + ring_sizes[i] = 0; + ring_data[i] = NULL; } r = radeon_ib_ring_tests(rdev); if (r) { dev_err(rdev->dev, "ib ring test failed (%d).\n", r); if (saved) { + saved = false; radeon_suspend(rdev); goto retry; } From 51cd8e6ff265650e35e46b5bcbe2ee381a7a2877 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 28 Aug 2012 19:57:21 -0700 Subject: [PATCH 197/208] mm, slab: lock the correct nodelist after reenabling irqs cache_grow() can reenable irqs so the cpu (and node) can change, so ensure that we take list_lock on the correct nodelist. This fixes an issue with commit 072bb0aa5e06 ("mm: sl[au]b: add knowledge of PFMEMALLOC reserve pages") where list_lock for the wrong node was taken after growing the cache. Reported-and-tested-by: Haggai Eran Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- mm/slab.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/slab.c b/mm/slab.c index f8b0d539b482..811af03a14ef 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3260,6 +3260,7 @@ force_grow: /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); + node = numa_mem_id(); /* no objects in sight? abort */ if (!x && (ac->avail == 0 || force_refill)) From 41fa54377057ab38bc3e08ebb46168a7daf2e63b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 29 Aug 2012 19:48:26 -0400 Subject: [PATCH 198/208] drm/radeon: fix dig encoder selection on DCE61 Was using the DCE41 code which was wrong. Fixes blank displays on a number of Trinity systems. Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/atombios_encoders.c | 31 ++++++++++++++++++---- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c index 4a7f95e5550d..6e8803a1170c 100644 --- a/drivers/gpu/drm/radeon/atombios_encoders.c +++ b/drivers/gpu/drm/radeon/atombios_encoders.c @@ -1769,13 +1769,34 @@ static int radeon_atom_pick_dig_encoder(struct drm_encoder *encoder) struct radeon_crtc *radeon_crtc = to_radeon_crtc(encoder->crtc); struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct drm_encoder *test_encoder; - struct radeon_encoder_atom_dig *dig; + struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv; uint32_t dig_enc_in_use = 0; - /* DCE4/5 */ - if (ASIC_IS_DCE4(rdev)) { - dig = radeon_encoder->enc_priv; - if (ASIC_IS_DCE41(rdev)) { + if (ASIC_IS_DCE6(rdev)) { + /* DCE6 */ + switch (radeon_encoder->encoder_id) { + case ENCODER_OBJECT_ID_INTERNAL_UNIPHY: + if (dig->linkb) + return 1; + else + return 0; + break; + case ENCODER_OBJECT_ID_INTERNAL_UNIPHY1: + if (dig->linkb) + return 3; + else + return 2; + break; + case ENCODER_OBJECT_ID_INTERNAL_UNIPHY2: + if (dig->linkb) + return 5; + else + return 4; + break; + } + } else if (ASIC_IS_DCE4(rdev)) { + /* DCE4/5 */ + if (ASIC_IS_DCE41(rdev) && !ASIC_IS_DCE61(rdev)) { /* ontario follows DCE4 */ if (rdev->family == CHIP_PALM) { if (dig->linkb) From 4a68a74ba04e7ccf798d45988f4f2d2131fb5063 Mon Sep 17 00:00:00 2001 From: Forest Bond Date: Mon, 13 Aug 2012 16:31:24 +0000 Subject: [PATCH 199/208] gma500: Consider CRTC initially active. [this one ideally should make 3.6 - it fixes the very annoying mode setting bug] This causes the pipe to be forced off prior to initial mode set, which roughly mirrors the behavior of the i915 driver. It fixes initial mode setting on my Intel DN2800MT (Cedarview) board. Without it, mode setting triggers an out-of-range error from the monitor for most modes, but only on initial configuration (i.e. they can be configured successfully from userspace after that). Signed-off-by: Forest Bond Signed-off-by: Alan Cox Cc: stable Signed-off-by: Dave Airlie --- drivers/gpu/drm/gma500/psb_intel_display.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/gma500/psb_intel_display.c b/drivers/gpu/drm/gma500/psb_intel_display.c index 30dc22a7156c..8033526bb53b 100644 --- a/drivers/gpu/drm/gma500/psb_intel_display.c +++ b/drivers/gpu/drm/gma500/psb_intel_display.c @@ -1362,6 +1362,9 @@ void psb_intel_crtc_init(struct drm_device *dev, int pipe, (struct drm_connector **) (psb_intel_crtc + 1); psb_intel_crtc->mode_set.num_connectors = 0; psb_intel_cursor_init(dev, psb_intel_crtc); + + /* Set to true so that the pipe is forced off on initial config. */ + psb_intel_crtc->active = true; } int psb_intel_get_pipe_from_crtc_id(struct drm_device *dev, void *data, From 6f33814bd4d9cfe76033a31b1c0c76c960cd8e4b Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Wed, 8 Aug 2012 23:12:19 +0200 Subject: [PATCH 200/208] drm: Add EDID_QUIRK_FORCE_REDUCED_BLANKING for ASUS VW222S Connecting an ASUS VW222S [1] over VGA a garbled screen is shown with vertical stripes in the top half. In commit bc42aabc [2] commit bc42aabc6a01b92b0f961d65671564e0e1cd7592 Author: Adam Jackson Date: Wed May 23 16:26:54 2012 -0400 drm/edid/quirks: ViewSonic VA2026w Adam Jackson added the quirk `EDID_QUIRK_FORCE_REDUCED_BLANKING` which is also needed for this ASUS monitor. All log files and output from `xrandr` is included in the referenced Bugzilla report #17629. Please note that this monitor only has a VGA (D-Sub) connector [1]. [1] http://www.asus.com/Display/LCD_Monitors/VW222S/ [2] http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=commit;h=bc42aabc6a01b92b0f961d65671564e0e1cd7592 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=17629 Signed-off-by: Paul Menzel Cc: Cc: Adam Jackson Cc: Ian Pilcher Cc: Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_edid.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index a8743c399e83..b7ee230572b7 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -87,6 +87,9 @@ static struct edid_quirk { int product_id; u32 quirks; } edid_quirk_list[] = { + /* ASUS VW222S */ + { "ACI", 0x22a2, EDID_QUIRK_FORCE_REDUCED_BLANKING }, + /* Acer AL1706 */ { "ACR", 44358, EDID_QUIRK_PREFER_LARGE_60 }, /* Acer F51 */ From 768fd0737f4533635ea351566dff98fd4912b0d8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 28 Aug 2012 10:02:08 +0200 Subject: [PATCH 201/208] s390/32: Don't clobber personality flags on exec In native 32 bit mode the personality flags were not correctly inherited. This is the s390 version of 59e4c3a2 "powerpc/32: Don't clobber personality flags on exec". Reported-by: Mike Frysinger Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/elf.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index 32e8449640fa..9b94a160fe7f 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -180,7 +180,8 @@ extern char elf_platform[]; #define ELF_PLATFORM (elf_platform) #ifndef CONFIG_64BIT -#define SET_PERSONALITY(ex) set_personality(PER_LINUX) +#define SET_PERSONALITY(ex) \ + set_personality(PER_LINUX | (current->personality & (~PER_MASK))) #else /* CONFIG_64BIT */ #define SET_PERSONALITY(ex) \ do { \ From cee58483cf56e0ba355fdd97ff5e8925329aa936 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Fri, 31 Aug 2012 13:30:06 -0400 Subject: [PATCH 202/208] time: Move ktime_t overflow checking into timespec_valid_strict Andreas Bombe reported that the added ktime_t overflow checking added to timespec_valid in commit 4e8b14526ca7 ("time: Improve sanity checking of timekeeping inputs") was causing problems with X.org because it caused timeouts larger then KTIME_T to be invalid. Previously, these large timeouts would be clamped to KTIME_MAX and would never expire, which is valid. This patch splits the ktime_t overflow checking into a new timespec_valid_strict function, and converts the timekeeping codes internal checking to use this more strict function. Reported-and-tested-by: Andreas Bombe Cc: Zhouping Liu Cc: Ingo Molnar Cc: Prarit Bhargava Cc: Thomas Gleixner Cc: stable@vger.kernel.org Signed-off-by: John Stultz Signed-off-by: Linus Torvalds --- include/linux/time.h | 7 +++++++ kernel/time/timekeeping.c | 10 +++++----- 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/include/linux/time.h b/include/linux/time.h index b0bbd8f0130d..b51e664c83e7 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -125,6 +125,13 @@ static inline bool timespec_valid(const struct timespec *ts) /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; + return true; +} + +static inline bool timespec_valid_strict(const struct timespec *ts) +{ + if (!timespec_valid(ts)) + return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0c1485e42be6..34e5eac81424 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -428,7 +428,7 @@ int do_settimeofday(const struct timespec *tv) struct timespec ts_delta, xt; unsigned long flags; - if (!timespec_valid(tv)) + if (!timespec_valid_strict(tv)) return -EINVAL; write_seqlock_irqsave(&tk->lock, flags); @@ -476,7 +476,7 @@ int timekeeping_inject_offset(struct timespec *ts) /* Make sure the proposed value is valid */ tmp = timespec_add(tk_xtime(tk), *ts); - if (!timespec_valid(&tmp)) { + if (!timespec_valid_strict(&tmp)) { ret = -EINVAL; goto error; } @@ -659,7 +659,7 @@ void __init timekeeping_init(void) struct timespec now, boot, tmp; read_persistent_clock(&now); - if (!timespec_valid(&now)) { + if (!timespec_valid_strict(&now)) { pr_warn("WARNING: Persistent clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); now.tv_sec = 0; @@ -667,7 +667,7 @@ void __init timekeeping_init(void) } read_boot_clock(&boot); - if (!timespec_valid(&boot)) { + if (!timespec_valid_strict(&boot)) { pr_warn("WARNING: Boot clock returned invalid value!\n" " Check your CMOS/BIOS settings.\n"); boot.tv_sec = 0; @@ -713,7 +713,7 @@ static struct timespec timekeeping_suspend_time; static void __timekeeping_inject_sleeptime(struct timekeeper *tk, struct timespec *delta) { - if (!timespec_valid(delta)) { + if (!timespec_valid_strict(delta)) { printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; From 4cbe5a555fa58a79b6ecbb6c531b8bab0650778d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 1 Sep 2012 10:39:58 -0700 Subject: [PATCH 203/208] Linux 3.6-rc4 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 354026873b13..371ce8899f5c 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Saber-toothed Squirrel # *DOCUMENTATION* From 699c9d30bc3de2224b1d2fecec5303b7f754058d Mon Sep 17 00:00:00 2001 From: Chao Xie Date: Mon, 27 Aug 2012 10:53:59 +0800 Subject: [PATCH 204/208] arm: mmp: make private clock definition exclude from common clock the clock.c is mmp private implementation, make it excluded from common clock framework Signed-off-by: Chao Xie Signed-off-by: Haojian Zhuang --- arch/arm/mach-mmp/Makefile | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-mmp/Makefile b/arch/arm/mach-mmp/Makefile index b786f7e6cd1f..815c3e74c24a 100644 --- a/arch/arm/mach-mmp/Makefile +++ b/arch/arm/mach-mmp/Makefile @@ -2,13 +2,16 @@ # Makefile for Marvell's PXA168 processors line # -obj-y += common.o clock.o devices.o time.o irq.o +obj-y += common.o devices.o time.o irq.o # SoC support obj-$(CONFIG_CPU_PXA168) += pxa168.o obj-$(CONFIG_CPU_PXA910) += pxa910.o obj-$(CONFIG_CPU_MMP2) += mmp2.o sram.o +ifeq ($(CONFIG_COMMON_CLK), ) +obj-y += clock.o +endif ifeq ($(CONFIG_PM),y) obj-$(CONFIG_CPU_PXA910) += pm-pxa910.o obj-$(CONFIG_CPU_MMP2) += pm-mmp2.o From 50d0e24499787a39e5fa585a770591648a9760fd Mon Sep 17 00:00:00 2001 From: Chao Xie Date: Mon, 27 Aug 2012 10:54:00 +0800 Subject: [PATCH 205/208] arm: mmp: move pxa168 clock definition to separated file move pxa168 clock definition to another file. Then pxa168 can choose common clock framework or private clock framework. Signed-off-by: Chao Xie Signed-off-by: Haojian Zhuang --- arch/arm/mach-mmp/Makefile | 1 + arch/arm/mach-mmp/clock-pxa168.c | 91 ++++++++++++++++++++++++++++++++ arch/arm/mach-mmp/common.h | 1 + arch/arm/mach-mmp/pxa168.c | 58 ++------------------ 4 files changed, 98 insertions(+), 53 deletions(-) create mode 100644 arch/arm/mach-mmp/clock-pxa168.c diff --git a/arch/arm/mach-mmp/Makefile b/arch/arm/mach-mmp/Makefile index 815c3e74c24a..bb63f86185a9 100644 --- a/arch/arm/mach-mmp/Makefile +++ b/arch/arm/mach-mmp/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_CPU_MMP2) += mmp2.o sram.o ifeq ($(CONFIG_COMMON_CLK), ) obj-y += clock.o +obj-$(CONFIG_CPU_PXA168) += clock-pxa168.o endif ifeq ($(CONFIG_PM),y) obj-$(CONFIG_CPU_PXA910) += pm-pxa910.o diff --git a/arch/arm/mach-mmp/clock-pxa168.c b/arch/arm/mach-mmp/clock-pxa168.c new file mode 100644 index 000000000000..5e6c18ccebd4 --- /dev/null +++ b/arch/arm/mach-mmp/clock-pxa168.c @@ -0,0 +1,91 @@ +#include +#include +#include +#include +#include +#include + +#include + +#include "common.h" +#include "clock.h" + +/* + * APB clock register offsets for PXA168 + */ +#define APBC_UART1 APBC_REG(0x000) +#define APBC_UART2 APBC_REG(0x004) +#define APBC_GPIO APBC_REG(0x008) +#define APBC_PWM1 APBC_REG(0x00c) +#define APBC_PWM2 APBC_REG(0x010) +#define APBC_PWM3 APBC_REG(0x014) +#define APBC_PWM4 APBC_REG(0x018) +#define APBC_RTC APBC_REG(0x028) +#define APBC_TWSI0 APBC_REG(0x02c) +#define APBC_KPC APBC_REG(0x030) +#define APBC_TWSI1 APBC_REG(0x06c) +#define APBC_UART3 APBC_REG(0x070) +#define APBC_SSP1 APBC_REG(0x81c) +#define APBC_SSP2 APBC_REG(0x820) +#define APBC_SSP3 APBC_REG(0x84c) +#define APBC_SSP4 APBC_REG(0x858) +#define APBC_SSP5 APBC_REG(0x85c) + +#define APMU_NAND APMU_REG(0x060) +#define APMU_LCD APMU_REG(0x04c) +#define APMU_ETH APMU_REG(0x0fc) +#define APMU_USB APMU_REG(0x05c) + +/* APB peripheral clocks */ +static APBC_CLK(uart1, UART1, 1, 14745600); +static APBC_CLK(uart2, UART2, 1, 14745600); +static APBC_CLK(uart3, UART3, 1, 14745600); +static APBC_CLK(twsi0, TWSI0, 1, 33000000); +static APBC_CLK(twsi1, TWSI1, 1, 33000000); +static APBC_CLK(pwm1, PWM1, 1, 13000000); +static APBC_CLK(pwm2, PWM2, 1, 13000000); +static APBC_CLK(pwm3, PWM3, 1, 13000000); +static APBC_CLK(pwm4, PWM4, 1, 13000000); +static APBC_CLK(ssp1, SSP1, 4, 0); +static APBC_CLK(ssp2, SSP2, 4, 0); +static APBC_CLK(ssp3, SSP3, 4, 0); +static APBC_CLK(ssp4, SSP4, 4, 0); +static APBC_CLK(ssp5, SSP5, 4, 0); +static APBC_CLK(gpio, GPIO, 0, 13000000); +static APBC_CLK(keypad, KPC, 0, 32000); +static APBC_CLK(rtc, RTC, 8, 32768); + +static APMU_CLK(nand, NAND, 0x19b, 156000000); +static APMU_CLK(lcd, LCD, 0x7f, 312000000); +static APMU_CLK(eth, ETH, 0x09, 0); +static APMU_CLK(usb, USB, 0x12, 0); + +/* device and clock bindings */ +static struct clk_lookup pxa168_clkregs[] = { + INIT_CLKREG(&clk_uart1, "pxa2xx-uart.0", NULL), + INIT_CLKREG(&clk_uart2, "pxa2xx-uart.1", NULL), + INIT_CLKREG(&clk_uart3, "pxa2xx-uart.2", NULL), + INIT_CLKREG(&clk_twsi0, "pxa2xx-i2c.0", NULL), + INIT_CLKREG(&clk_twsi1, "pxa2xx-i2c.1", NULL), + INIT_CLKREG(&clk_pwm1, "pxa168-pwm.0", NULL), + INIT_CLKREG(&clk_pwm2, "pxa168-pwm.1", NULL), + INIT_CLKREG(&clk_pwm3, "pxa168-pwm.2", NULL), + INIT_CLKREG(&clk_pwm4, "pxa168-pwm.3", NULL), + INIT_CLKREG(&clk_ssp1, "pxa168-ssp.0", NULL), + INIT_CLKREG(&clk_ssp2, "pxa168-ssp.1", NULL), + INIT_CLKREG(&clk_ssp3, "pxa168-ssp.2", NULL), + INIT_CLKREG(&clk_ssp4, "pxa168-ssp.3", NULL), + INIT_CLKREG(&clk_ssp5, "pxa168-ssp.4", NULL), + INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), + INIT_CLKREG(&clk_lcd, "pxa168-fb", NULL), + INIT_CLKREG(&clk_gpio, "pxa-gpio", NULL), + INIT_CLKREG(&clk_keypad, "pxa27x-keypad", NULL), + INIT_CLKREG(&clk_eth, "pxa168-eth", "MFUCLK"), + INIT_CLKREG(&clk_usb, NULL, "PXA168-USBCLK"), + INIT_CLKREG(&clk_rtc, "sa1100-rtc", NULL), +}; + +void __init pxa168_clk_init(void) +{ + clkdev_add_table(ARRAY_AND_SIZE(pxa168_clkregs)); +} diff --git a/arch/arm/mach-mmp/common.h b/arch/arm/mach-mmp/common.h index 1c9d6c1ea97a..e47f73f55c45 100644 --- a/arch/arm/mach-mmp/common.h +++ b/arch/arm/mach-mmp/common.h @@ -7,3 +7,4 @@ extern void timer_init(int irq); extern void __init icu_init_irq(void); extern void __init mmp_map_io(void); extern void mmp_restart(char, const char *); +extern void __init pxa168_clk_init(void); diff --git a/arch/arm/mach-mmp/pxa168.c b/arch/arm/mach-mmp/pxa168.c index 62d787c34475..b7f074f15498 100644 --- a/arch/arm/mach-mmp/pxa168.c +++ b/arch/arm/mach-mmp/pxa168.c @@ -18,8 +18,8 @@ #include #include -#include #include +#include #include #include #include @@ -50,62 +50,13 @@ void __init pxa168_init_irq(void) icu_init_irq(); } -/* APB peripheral clocks */ -static APBC_CLK(uart1, PXA168_UART1, 1, 14745600); -static APBC_CLK(uart2, PXA168_UART2, 1, 14745600); -static APBC_CLK(uart3, PXA168_UART3, 1, 14745600); -static APBC_CLK(twsi0, PXA168_TWSI0, 1, 33000000); -static APBC_CLK(twsi1, PXA168_TWSI1, 1, 33000000); -static APBC_CLK(pwm1, PXA168_PWM1, 1, 13000000); -static APBC_CLK(pwm2, PXA168_PWM2, 1, 13000000); -static APBC_CLK(pwm3, PXA168_PWM3, 1, 13000000); -static APBC_CLK(pwm4, PXA168_PWM4, 1, 13000000); -static APBC_CLK(ssp1, PXA168_SSP1, 4, 0); -static APBC_CLK(ssp2, PXA168_SSP2, 4, 0); -static APBC_CLK(ssp3, PXA168_SSP3, 4, 0); -static APBC_CLK(ssp4, PXA168_SSP4, 4, 0); -static APBC_CLK(ssp5, PXA168_SSP5, 4, 0); -static APBC_CLK(gpio, PXA168_GPIO, 0, 13000000); -static APBC_CLK(keypad, PXA168_KPC, 0, 32000); -static APBC_CLK(rtc, PXA168_RTC, 8, 32768); - -static APMU_CLK(nand, NAND, 0x19b, 156000000); -static APMU_CLK(lcd, LCD, 0x7f, 312000000); -static APMU_CLK(eth, ETH, 0x09, 0); -static APMU_CLK(usb, USB, 0x12, 0); - -/* device and clock bindings */ -static struct clk_lookup pxa168_clkregs[] = { - INIT_CLKREG(&clk_uart1, "pxa2xx-uart.0", NULL), - INIT_CLKREG(&clk_uart2, "pxa2xx-uart.1", NULL), - INIT_CLKREG(&clk_uart3, "pxa2xx-uart.2", NULL), - INIT_CLKREG(&clk_twsi0, "pxa2xx-i2c.0", NULL), - INIT_CLKREG(&clk_twsi1, "pxa2xx-i2c.1", NULL), - INIT_CLKREG(&clk_pwm1, "pxa168-pwm.0", NULL), - INIT_CLKREG(&clk_pwm2, "pxa168-pwm.1", NULL), - INIT_CLKREG(&clk_pwm3, "pxa168-pwm.2", NULL), - INIT_CLKREG(&clk_pwm4, "pxa168-pwm.3", NULL), - INIT_CLKREG(&clk_ssp1, "pxa168-ssp.0", NULL), - INIT_CLKREG(&clk_ssp2, "pxa168-ssp.1", NULL), - INIT_CLKREG(&clk_ssp3, "pxa168-ssp.2", NULL), - INIT_CLKREG(&clk_ssp4, "pxa168-ssp.3", NULL), - INIT_CLKREG(&clk_ssp5, "pxa168-ssp.4", NULL), - INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), - INIT_CLKREG(&clk_lcd, "pxa168-fb", NULL), - INIT_CLKREG(&clk_gpio, "pxa-gpio", NULL), - INIT_CLKREG(&clk_keypad, "pxa27x-keypad", NULL), - INIT_CLKREG(&clk_eth, "pxa168-eth", "MFUCLK"), - INIT_CLKREG(&clk_usb, NULL, "PXA168-USBCLK"), - INIT_CLKREG(&clk_rtc, "sa1100-rtc", NULL), -}; - static int __init pxa168_init(void) { if (cpu_is_pxa168()) { mfp_init_base(MFPR_VIRT_BASE); mfp_init_addr(pxa168_mfp_addr_map); pxa_init_dma(IRQ_PXA168_DMA_INT0, 32); - clkdev_add_table(ARRAY_AND_SIZE(pxa168_clkregs)); + pxa168_clk_init(); } return 0; @@ -114,6 +65,7 @@ postcore_initcall(pxa168_init); /* system timer - clock enabled, 3.25MHz */ #define TIMER_CLK_RST (APBC_APBCLK | APBC_FNCLK | APBC_FNCLKSEL(3)) +#define APBC_TIMERS APBC_REG(0x34) static void __init pxa168_timer_init(void) { @@ -121,10 +73,10 @@ static void __init pxa168_timer_init(void) * ourselves instead of using clk_* API. Clock rate is defined * by APBC_TIMERS_CLK_RST (3.25MHz) and enabled free-running */ - __raw_writel(APBC_APBCLK | APBC_RST, APBC_PXA168_TIMERS); + __raw_writel(APBC_APBCLK | APBC_RST, APBC_TIMERS); /* 3.25MHz, bus/functional clock enabled, release reset */ - __raw_writel(TIMER_CLK_RST, APBC_PXA168_TIMERS); + __raw_writel(TIMER_CLK_RST, APBC_TIMERS); timer_init(IRQ_PXA168_TIMER1); } From 9e73d6982314a903beebb2e47e585a9804f237cf Mon Sep 17 00:00:00 2001 From: Chao Xie Date: Mon, 27 Aug 2012 10:54:01 +0800 Subject: [PATCH 206/208] arm: mmp: move pxa910 clock definition to separated file move pxa910 clock definition to another file. Then pxa910 can choose common clock framework or private clock framework. Signed-off-by: Chao Xie Signed-off-by: Haojian Zhuang --- arch/arm/mach-mmp/Makefile | 1 + arch/arm/mach-mmp/clock-pxa910.c | 67 ++++++++++++++++++++++++++++++++ arch/arm/mach-mmp/common.h | 1 + arch/arm/mach-mmp/pxa910.c | 40 ++----------------- 4 files changed, 73 insertions(+), 36 deletions(-) create mode 100644 arch/arm/mach-mmp/clock-pxa910.c diff --git a/arch/arm/mach-mmp/Makefile b/arch/arm/mach-mmp/Makefile index bb63f86185a9..ac0e8858c9d8 100644 --- a/arch/arm/mach-mmp/Makefile +++ b/arch/arm/mach-mmp/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_CPU_MMP2) += mmp2.o sram.o ifeq ($(CONFIG_COMMON_CLK), ) obj-y += clock.o obj-$(CONFIG_CPU_PXA168) += clock-pxa168.o +obj-$(CONFIG_CPU_PXA910) += clock-pxa910.o endif ifeq ($(CONFIG_PM),y) obj-$(CONFIG_CPU_PXA910) += pm-pxa910.o diff --git a/arch/arm/mach-mmp/clock-pxa910.c b/arch/arm/mach-mmp/clock-pxa910.c new file mode 100644 index 000000000000..933ea71d0b56 --- /dev/null +++ b/arch/arm/mach-mmp/clock-pxa910.c @@ -0,0 +1,67 @@ +#include +#include +#include +#include +#include +#include + +#include + +#include "common.h" +#include "clock.h" + +/* + * APB Clock register offsets for PXA910 + */ +#define APBC_UART0 APBC_REG(0x000) +#define APBC_UART1 APBC_REG(0x004) +#define APBC_GPIO APBC_REG(0x008) +#define APBC_PWM1 APBC_REG(0x00c) +#define APBC_PWM2 APBC_REG(0x010) +#define APBC_PWM3 APBC_REG(0x014) +#define APBC_PWM4 APBC_REG(0x018) +#define APBC_SSP1 APBC_REG(0x01c) +#define APBC_SSP2 APBC_REG(0x020) +#define APBC_RTC APBC_REG(0x028) +#define APBC_TWSI0 APBC_REG(0x02c) +#define APBC_KPC APBC_REG(0x030) +#define APBC_SSP3 APBC_REG(0x04c) +#define APBC_TWSI1 APBC_REG(0x06c) + +#define APMU_NAND APMU_REG(0x060) +#define APMU_USB APMU_REG(0x05c) + +static APBC_CLK(uart1, UART0, 1, 14745600); +static APBC_CLK(uart2, UART1, 1, 14745600); +static APBC_CLK(twsi0, TWSI0, 1, 33000000); +static APBC_CLK(twsi1, TWSI1, 1, 33000000); +static APBC_CLK(pwm1, PWM1, 1, 13000000); +static APBC_CLK(pwm2, PWM2, 1, 13000000); +static APBC_CLK(pwm3, PWM3, 1, 13000000); +static APBC_CLK(pwm4, PWM4, 1, 13000000); +static APBC_CLK(gpio, GPIO, 0, 13000000); +static APBC_CLK(rtc, RTC, 8, 32768); + +static APMU_CLK(nand, NAND, 0x19b, 156000000); +static APMU_CLK(u2o, USB, 0x1b, 480000000); + +/* device and clock bindings */ +static struct clk_lookup pxa910_clkregs[] = { + INIT_CLKREG(&clk_uart1, "pxa2xx-uart.0", NULL), + INIT_CLKREG(&clk_uart2, "pxa2xx-uart.1", NULL), + INIT_CLKREG(&clk_twsi0, "pxa2xx-i2c.0", NULL), + INIT_CLKREG(&clk_twsi1, "pxa2xx-i2c.1", NULL), + INIT_CLKREG(&clk_pwm1, "pxa910-pwm.0", NULL), + INIT_CLKREG(&clk_pwm2, "pxa910-pwm.1", NULL), + INIT_CLKREG(&clk_pwm3, "pxa910-pwm.2", NULL), + INIT_CLKREG(&clk_pwm4, "pxa910-pwm.3", NULL), + INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), + INIT_CLKREG(&clk_gpio, "pxa-gpio", NULL), + INIT_CLKREG(&clk_u2o, NULL, "U2OCLK"), + INIT_CLKREG(&clk_rtc, "sa1100-rtc", NULL), +}; + +void __init pxa910_clk_init(void) +{ + clkdev_add_table(ARRAY_AND_SIZE(pxa910_clkregs)); +} diff --git a/arch/arm/mach-mmp/common.h b/arch/arm/mach-mmp/common.h index e47f73f55c45..1cad41b41c51 100644 --- a/arch/arm/mach-mmp/common.h +++ b/arch/arm/mach-mmp/common.h @@ -8,3 +8,4 @@ extern void __init icu_init_irq(void); extern void __init mmp_map_io(void); extern void mmp_restart(char, const char *); extern void __init pxa168_clk_init(void); +extern void __init pxa910_clk_init(void); diff --git a/arch/arm/mach-mmp/pxa910.c b/arch/arm/mach-mmp/pxa910.c index 6da52e9f2bdc..7d84521bb715 100644 --- a/arch/arm/mach-mmp/pxa910.c +++ b/arch/arm/mach-mmp/pxa910.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -25,7 +24,6 @@ #include #include "common.h" -#include "clock.h" #define MFPR_VIRT_BASE (APB_VIRT_BASE + 0x1e000) @@ -82,44 +80,13 @@ void __init pxa910_init_irq(void) icu_init_irq(); } -/* APB peripheral clocks */ -static APBC_CLK(uart1, PXA910_UART0, 1, 14745600); -static APBC_CLK(uart2, PXA910_UART1, 1, 14745600); -static APBC_CLK(twsi0, PXA168_TWSI0, 1, 33000000); -static APBC_CLK(twsi1, PXA168_TWSI1, 1, 33000000); -static APBC_CLK(pwm1, PXA910_PWM1, 1, 13000000); -static APBC_CLK(pwm2, PXA910_PWM2, 1, 13000000); -static APBC_CLK(pwm3, PXA910_PWM3, 1, 13000000); -static APBC_CLK(pwm4, PXA910_PWM4, 1, 13000000); -static APBC_CLK(gpio, PXA910_GPIO, 0, 13000000); -static APBC_CLK(rtc, PXA910_RTC, 8, 32768); - -static APMU_CLK(nand, NAND, 0x19b, 156000000); -static APMU_CLK(u2o, USB, 0x1b, 480000000); - -/* device and clock bindings */ -static struct clk_lookup pxa910_clkregs[] = { - INIT_CLKREG(&clk_uart1, "pxa2xx-uart.0", NULL), - INIT_CLKREG(&clk_uart2, "pxa2xx-uart.1", NULL), - INIT_CLKREG(&clk_twsi0, "pxa2xx-i2c.0", NULL), - INIT_CLKREG(&clk_twsi1, "pxa2xx-i2c.1", NULL), - INIT_CLKREG(&clk_pwm1, "pxa910-pwm.0", NULL), - INIT_CLKREG(&clk_pwm2, "pxa910-pwm.1", NULL), - INIT_CLKREG(&clk_pwm3, "pxa910-pwm.2", NULL), - INIT_CLKREG(&clk_pwm4, "pxa910-pwm.3", NULL), - INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), - INIT_CLKREG(&clk_gpio, "pxa-gpio", NULL), - INIT_CLKREG(&clk_u2o, NULL, "U2OCLK"), - INIT_CLKREG(&clk_rtc, "sa1100-rtc", NULL), -}; - static int __init pxa910_init(void) { if (cpu_is_pxa910()) { mfp_init_base(MFPR_VIRT_BASE); mfp_init_addr(pxa910_mfp_addr_map); pxa_init_dma(IRQ_PXA910_DMA_INT0, 32); - clkdev_add_table(ARRAY_AND_SIZE(pxa910_clkregs)); + pxa910_clk_init(); } return 0; @@ -128,12 +95,13 @@ postcore_initcall(pxa910_init); /* system timer - clock enabled, 3.25MHz */ #define TIMER_CLK_RST (APBC_APBCLK | APBC_FNCLK | APBC_FNCLKSEL(3)) +#define APBC_TIMERS APBC_REG(0x34) static void __init pxa910_timer_init(void) { /* reset and configure */ - __raw_writel(APBC_APBCLK | APBC_RST, APBC_PXA910_TIMERS); - __raw_writel(TIMER_CLK_RST, APBC_PXA910_TIMERS); + __raw_writel(APBC_APBCLK | APBC_RST, APBC_TIMERS); + __raw_writel(TIMER_CLK_RST, APBC_TIMERS); timer_init(IRQ_PXA910_AP1_TIMER1); } From 8430305dc3f3a286a337f1b4419c04afe55a2583 Mon Sep 17 00:00:00 2001 From: Chao Xie Date: Mon, 27 Aug 2012 10:54:02 +0800 Subject: [PATCH 207/208] ARM: mmp: move mmp2 clock definition to separated file move mmp2 clock definition to another file. Then mmp2 can choose common clock framework or private clock framework. Signed-off-by: Chao Xie Signed-off-by: Haojian Zhuang --- arch/arm/mach-mmp/Makefile | 1 + arch/arm/mach-mmp/clock-mmp2.c | 111 +++++++++++++++++++++++++++++++++ arch/arm/mach-mmp/common.h | 1 + arch/arm/mach-mmp/mmp2.c | 71 ++------------------- 4 files changed, 118 insertions(+), 66 deletions(-) create mode 100644 arch/arm/mach-mmp/clock-mmp2.c diff --git a/arch/arm/mach-mmp/Makefile b/arch/arm/mach-mmp/Makefile index ac0e8858c9d8..095c155d6fb8 100644 --- a/arch/arm/mach-mmp/Makefile +++ b/arch/arm/mach-mmp/Makefile @@ -13,6 +13,7 @@ ifeq ($(CONFIG_COMMON_CLK), ) obj-y += clock.o obj-$(CONFIG_CPU_PXA168) += clock-pxa168.o obj-$(CONFIG_CPU_PXA910) += clock-pxa910.o +obj-$(CONFIG_CPU_MMP2) += clock-mmp2.o endif ifeq ($(CONFIG_PM),y) obj-$(CONFIG_CPU_PXA910) += pm-pxa910.o diff --git a/arch/arm/mach-mmp/clock-mmp2.c b/arch/arm/mach-mmp/clock-mmp2.c new file mode 100644 index 000000000000..21d22002cd19 --- /dev/null +++ b/arch/arm/mach-mmp/clock-mmp2.c @@ -0,0 +1,111 @@ +#include +#include +#include +#include +#include +#include + +#include + +#include "common.h" +#include "clock.h" + +/* + * APB Clock register offsets for MMP2 + */ +#define APBC_RTC APBC_REG(0x000) +#define APBC_TWSI1 APBC_REG(0x004) +#define APBC_TWSI2 APBC_REG(0x008) +#define APBC_TWSI3 APBC_REG(0x00c) +#define APBC_TWSI4 APBC_REG(0x010) +#define APBC_KPC APBC_REG(0x018) +#define APBC_UART1 APBC_REG(0x02c) +#define APBC_UART2 APBC_REG(0x030) +#define APBC_UART3 APBC_REG(0x034) +#define APBC_GPIO APBC_REG(0x038) +#define APBC_PWM0 APBC_REG(0x03c) +#define APBC_PWM1 APBC_REG(0x040) +#define APBC_PWM2 APBC_REG(0x044) +#define APBC_PWM3 APBC_REG(0x048) +#define APBC_SSP0 APBC_REG(0x04c) +#define APBC_SSP1 APBC_REG(0x050) +#define APBC_SSP2 APBC_REG(0x054) +#define APBC_SSP3 APBC_REG(0x058) +#define APBC_SSP4 APBC_REG(0x05c) +#define APBC_SSP5 APBC_REG(0x060) +#define APBC_TWSI5 APBC_REG(0x07c) +#define APBC_TWSI6 APBC_REG(0x080) +#define APBC_UART4 APBC_REG(0x088) + +#define APMU_USB APMU_REG(0x05c) +#define APMU_NAND APMU_REG(0x060) +#define APMU_SDH0 APMU_REG(0x054) +#define APMU_SDH1 APMU_REG(0x058) +#define APMU_SDH2 APMU_REG(0x0e8) +#define APMU_SDH3 APMU_REG(0x0ec) + +static void sdhc_clk_enable(struct clk *clk) +{ + uint32_t clk_rst; + + clk_rst = __raw_readl(clk->clk_rst); + clk_rst |= clk->enable_val; + __raw_writel(clk_rst, clk->clk_rst); +} + +static void sdhc_clk_disable(struct clk *clk) +{ + uint32_t clk_rst; + + clk_rst = __raw_readl(clk->clk_rst); + clk_rst &= ~clk->enable_val; + __raw_writel(clk_rst, clk->clk_rst); +} + +struct clkops sdhc_clk_ops = { + .enable = sdhc_clk_enable, + .disable = sdhc_clk_disable, +}; + +/* APB peripheral clocks */ +static APBC_CLK(uart1, UART1, 1, 26000000); +static APBC_CLK(uart2, UART2, 1, 26000000); +static APBC_CLK(uart3, UART3, 1, 26000000); +static APBC_CLK(uart4, UART4, 1, 26000000); +static APBC_CLK(twsi1, TWSI1, 0, 26000000); +static APBC_CLK(twsi2, TWSI2, 0, 26000000); +static APBC_CLK(twsi3, TWSI3, 0, 26000000); +static APBC_CLK(twsi4, TWSI4, 0, 26000000); +static APBC_CLK(twsi5, TWSI5, 0, 26000000); +static APBC_CLK(twsi6, TWSI6, 0, 26000000); +static APBC_CLK(gpio, GPIO, 0, 26000000); + +static APMU_CLK(nand, NAND, 0xbf, 100000000); +static APMU_CLK_OPS(sdh0, SDH0, 0x1b, 200000000, &sdhc_clk_ops); +static APMU_CLK_OPS(sdh1, SDH1, 0x1b, 200000000, &sdhc_clk_ops); +static APMU_CLK_OPS(sdh2, SDH2, 0x1b, 200000000, &sdhc_clk_ops); +static APMU_CLK_OPS(sdh3, SDH3, 0x1b, 200000000, &sdhc_clk_ops); + +static struct clk_lookup mmp2_clkregs[] = { + INIT_CLKREG(&clk_uart1, "pxa2xx-uart.0", NULL), + INIT_CLKREG(&clk_uart2, "pxa2xx-uart.1", NULL), + INIT_CLKREG(&clk_uart3, "pxa2xx-uart.2", NULL), + INIT_CLKREG(&clk_uart4, "pxa2xx-uart.3", NULL), + INIT_CLKREG(&clk_twsi1, "pxa2xx-i2c.0", NULL), + INIT_CLKREG(&clk_twsi2, "pxa2xx-i2c.1", NULL), + INIT_CLKREG(&clk_twsi3, "pxa2xx-i2c.2", NULL), + INIT_CLKREG(&clk_twsi4, "pxa2xx-i2c.3", NULL), + INIT_CLKREG(&clk_twsi5, "pxa2xx-i2c.4", NULL), + INIT_CLKREG(&clk_twsi6, "pxa2xx-i2c.5", NULL), + INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), + INIT_CLKREG(&clk_gpio, "pxa-gpio", NULL), + INIT_CLKREG(&clk_sdh0, "sdhci-pxav3.0", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh1, "sdhci-pxav3.1", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh2, "sdhci-pxav3.2", "PXA-SDHCLK"), + INIT_CLKREG(&clk_sdh3, "sdhci-pxav3.3", "PXA-SDHCLK"), +}; + +void __init mmp2_clk_init(void) +{ + clkdev_add_table(ARRAY_AND_SIZE(mmp2_clkregs)); +} diff --git a/arch/arm/mach-mmp/common.h b/arch/arm/mach-mmp/common.h index 1cad41b41c51..bd453274fca2 100644 --- a/arch/arm/mach-mmp/common.h +++ b/arch/arm/mach-mmp/common.h @@ -9,3 +9,4 @@ extern void __init mmp_map_io(void); extern void mmp_restart(char, const char *); extern void __init pxa168_clk_init(void); extern void __init pxa910_clk_init(void); +extern void __init mmp2_clk_init(void); diff --git a/arch/arm/mach-mmp/mmp2.c b/arch/arm/mach-mmp/mmp2.c index c709a24a9d25..c2ce3d05b044 100644 --- a/arch/arm/mach-mmp/mmp2.c +++ b/arch/arm/mach-mmp/mmp2.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -29,7 +28,6 @@ #include #include "common.h" -#include "clock.h" #define MFPR_VIRT_BASE (APB_VIRT_BASE + 0x1e000) @@ -98,67 +96,6 @@ void __init mmp2_init_irq(void) mmp2_init_icu(); } -static void sdhc_clk_enable(struct clk *clk) -{ - uint32_t clk_rst; - - clk_rst = __raw_readl(clk->clk_rst); - clk_rst |= clk->enable_val; - __raw_writel(clk_rst, clk->clk_rst); -} - -static void sdhc_clk_disable(struct clk *clk) -{ - uint32_t clk_rst; - - clk_rst = __raw_readl(clk->clk_rst); - clk_rst &= ~clk->enable_val; - __raw_writel(clk_rst, clk->clk_rst); -} - -struct clkops sdhc_clk_ops = { - .enable = sdhc_clk_enable, - .disable = sdhc_clk_disable, -}; - -/* APB peripheral clocks */ -static APBC_CLK(uart1, MMP2_UART1, 1, 26000000); -static APBC_CLK(uart2, MMP2_UART2, 1, 26000000); -static APBC_CLK(uart3, MMP2_UART3, 1, 26000000); -static APBC_CLK(uart4, MMP2_UART4, 1, 26000000); -static APBC_CLK(twsi1, MMP2_TWSI1, 0, 26000000); -static APBC_CLK(twsi2, MMP2_TWSI2, 0, 26000000); -static APBC_CLK(twsi3, MMP2_TWSI3, 0, 26000000); -static APBC_CLK(twsi4, MMP2_TWSI4, 0, 26000000); -static APBC_CLK(twsi5, MMP2_TWSI5, 0, 26000000); -static APBC_CLK(twsi6, MMP2_TWSI6, 0, 26000000); -static APBC_CLK(gpio, MMP2_GPIO, 0, 26000000); - -static APMU_CLK(nand, NAND, 0xbf, 100000000); -static APMU_CLK_OPS(sdh0, SDH0, 0x1b, 200000000, &sdhc_clk_ops); -static APMU_CLK_OPS(sdh1, SDH1, 0x1b, 200000000, &sdhc_clk_ops); -static APMU_CLK_OPS(sdh2, SDH2, 0x1b, 200000000, &sdhc_clk_ops); -static APMU_CLK_OPS(sdh3, SDH3, 0x1b, 200000000, &sdhc_clk_ops); - -static struct clk_lookup mmp2_clkregs[] = { - INIT_CLKREG(&clk_uart1, "pxa2xx-uart.0", NULL), - INIT_CLKREG(&clk_uart2, "pxa2xx-uart.1", NULL), - INIT_CLKREG(&clk_uart3, "pxa2xx-uart.2", NULL), - INIT_CLKREG(&clk_uart4, "pxa2xx-uart.3", NULL), - INIT_CLKREG(&clk_twsi1, "pxa2xx-i2c.0", NULL), - INIT_CLKREG(&clk_twsi2, "pxa2xx-i2c.1", NULL), - INIT_CLKREG(&clk_twsi3, "pxa2xx-i2c.2", NULL), - INIT_CLKREG(&clk_twsi4, "pxa2xx-i2c.3", NULL), - INIT_CLKREG(&clk_twsi5, "pxa2xx-i2c.4", NULL), - INIT_CLKREG(&clk_twsi6, "pxa2xx-i2c.5", NULL), - INIT_CLKREG(&clk_nand, "pxa3xx-nand", NULL), - INIT_CLKREG(&clk_gpio, "pxa-gpio", NULL), - INIT_CLKREG(&clk_sdh0, "sdhci-pxav3.0", "PXA-SDHCLK"), - INIT_CLKREG(&clk_sdh1, "sdhci-pxav3.1", "PXA-SDHCLK"), - INIT_CLKREG(&clk_sdh2, "sdhci-pxav3.2", "PXA-SDHCLK"), - INIT_CLKREG(&clk_sdh3, "sdhci-pxav3.3", "PXA-SDHCLK"), -}; - static int __init mmp2_init(void) { if (cpu_is_mmp2()) { @@ -168,25 +105,27 @@ static int __init mmp2_init(void) mfp_init_base(MFPR_VIRT_BASE); mfp_init_addr(mmp2_addr_map); pxa_init_dma(IRQ_MMP2_DMA_RIQ, 16); - clkdev_add_table(ARRAY_AND_SIZE(mmp2_clkregs)); + mmp2_clk_init(); } return 0; } postcore_initcall(mmp2_init); +#define APBC_TIMERS APBC_REG(0x024) + static void __init mmp2_timer_init(void) { unsigned long clk_rst; - __raw_writel(APBC_APBCLK | APBC_RST, APBC_MMP2_TIMERS); + __raw_writel(APBC_APBCLK | APBC_RST, APBC_TIMERS); /* * enable bus/functional clock, enable 6.5MHz (divider 4), * release reset */ clk_rst = APBC_APBCLK | APBC_FNCLK | APBC_FNCLKSEL(1); - __raw_writel(clk_rst, APBC_MMP2_TIMERS); + __raw_writel(clk_rst, APBC_TIMERS); timer_init(IRQ_MMP2_TIMER1); } From 7f744b17140af1a9c8804a1c81c9dae6bb52a7fb Mon Sep 17 00:00:00 2001 From: Chao Xie Date: Mon, 27 Aug 2012 10:54:03 +0800 Subject: [PATCH 208/208] ARM: mmp: remove unused definition in APBC and APMU Signed-off-by: Chao Xie Signed-off-by: Haojian Zhuang --- arch/arm/mach-mmp/include/mach/regs-apbc.h | 95 ---------------------- arch/arm/mach-mmp/include/mach/regs-apmu.h | 15 ---- 2 files changed, 110 deletions(-) diff --git a/arch/arm/mach-mmp/include/mach/regs-apbc.h b/arch/arm/mach-mmp/include/mach/regs-apbc.h index 68b0c93ec6a1..ddc812f40341 100644 --- a/arch/arm/mach-mmp/include/mach/regs-apbc.h +++ b/arch/arm/mach-mmp/include/mach/regs-apbc.h @@ -13,101 +13,6 @@ #include -/* - * APB clock register offsets for PXA168 - */ -#define APBC_PXA168_UART1 APBC_REG(0x000) -#define APBC_PXA168_UART2 APBC_REG(0x004) -#define APBC_PXA168_GPIO APBC_REG(0x008) -#define APBC_PXA168_PWM1 APBC_REG(0x00c) -#define APBC_PXA168_PWM2 APBC_REG(0x010) -#define APBC_PXA168_PWM3 APBC_REG(0x014) -#define APBC_PXA168_PWM4 APBC_REG(0x018) -#define APBC_PXA168_RTC APBC_REG(0x028) -#define APBC_PXA168_TWSI0 APBC_REG(0x02c) -#define APBC_PXA168_KPC APBC_REG(0x030) -#define APBC_PXA168_TIMERS APBC_REG(0x034) -#define APBC_PXA168_AIB APBC_REG(0x03c) -#define APBC_PXA168_SW_JTAG APBC_REG(0x040) -#define APBC_PXA168_ONEWIRE APBC_REG(0x048) -#define APBC_PXA168_ASFAR APBC_REG(0x050) -#define APBC_PXA168_ASSAR APBC_REG(0x054) -#define APBC_PXA168_TWSI1 APBC_REG(0x06c) -#define APBC_PXA168_UART3 APBC_REG(0x070) -#define APBC_PXA168_AC97 APBC_REG(0x084) -#define APBC_PXA168_SSP1 APBC_REG(0x81c) -#define APBC_PXA168_SSP2 APBC_REG(0x820) -#define APBC_PXA168_SSP3 APBC_REG(0x84c) -#define APBC_PXA168_SSP4 APBC_REG(0x858) -#define APBC_PXA168_SSP5 APBC_REG(0x85c) - -/* - * APB Clock register offsets for PXA910 - */ -#define APBC_PXA910_UART0 APBC_REG(0x000) -#define APBC_PXA910_UART1 APBC_REG(0x004) -#define APBC_PXA910_GPIO APBC_REG(0x008) -#define APBC_PXA910_PWM1 APBC_REG(0x00c) -#define APBC_PXA910_PWM2 APBC_REG(0x010) -#define APBC_PXA910_PWM3 APBC_REG(0x014) -#define APBC_PXA910_PWM4 APBC_REG(0x018) -#define APBC_PXA910_SSP1 APBC_REG(0x01c) -#define APBC_PXA910_SSP2 APBC_REG(0x020) -#define APBC_PXA910_IPC APBC_REG(0x024) -#define APBC_PXA910_RTC APBC_REG(0x028) -#define APBC_PXA910_TWSI0 APBC_REG(0x02c) -#define APBC_PXA910_KPC APBC_REG(0x030) -#define APBC_PXA910_TIMERS APBC_REG(0x034) -#define APBC_PXA910_TBROT APBC_REG(0x038) -#define APBC_PXA910_AIB APBC_REG(0x03c) -#define APBC_PXA910_SW_JTAG APBC_REG(0x040) -#define APBC_PXA910_TIMERS1 APBC_REG(0x044) -#define APBC_PXA910_ONEWIRE APBC_REG(0x048) -#define APBC_PXA910_SSP3 APBC_REG(0x04c) -#define APBC_PXA910_ASFAR APBC_REG(0x050) -#define APBC_PXA910_ASSAR APBC_REG(0x054) - -/* - * APB Clock register offsets for MMP2 - */ -#define APBC_MMP2_RTC APBC_REG(0x000) -#define APBC_MMP2_TWSI1 APBC_REG(0x004) -#define APBC_MMP2_TWSI2 APBC_REG(0x008) -#define APBC_MMP2_TWSI3 APBC_REG(0x00c) -#define APBC_MMP2_TWSI4 APBC_REG(0x010) -#define APBC_MMP2_ONEWIRE APBC_REG(0x014) -#define APBC_MMP2_KPC APBC_REG(0x018) -#define APBC_MMP2_TB_ROTARY APBC_REG(0x01c) -#define APBC_MMP2_SW_JTAG APBC_REG(0x020) -#define APBC_MMP2_TIMERS APBC_REG(0x024) -#define APBC_MMP2_UART1 APBC_REG(0x02c) -#define APBC_MMP2_UART2 APBC_REG(0x030) -#define APBC_MMP2_UART3 APBC_REG(0x034) -#define APBC_MMP2_GPIO APBC_REG(0x038) -#define APBC_MMP2_PWM0 APBC_REG(0x03c) -#define APBC_MMP2_PWM1 APBC_REG(0x040) -#define APBC_MMP2_PWM2 APBC_REG(0x044) -#define APBC_MMP2_PWM3 APBC_REG(0x048) -#define APBC_MMP2_SSP0 APBC_REG(0x04c) -#define APBC_MMP2_SSP1 APBC_REG(0x050) -#define APBC_MMP2_SSP2 APBC_REG(0x054) -#define APBC_MMP2_SSP3 APBC_REG(0x058) -#define APBC_MMP2_SSP4 APBC_REG(0x05c) -#define APBC_MMP2_SSP5 APBC_REG(0x060) -#define APBC_MMP2_AIB APBC_REG(0x064) -#define APBC_MMP2_ASFAR APBC_REG(0x068) -#define APBC_MMP2_ASSAR APBC_REG(0x06c) -#define APBC_MMP2_USIM APBC_REG(0x070) -#define APBC_MMP2_MPMU APBC_REG(0x074) -#define APBC_MMP2_IPC APBC_REG(0x078) -#define APBC_MMP2_TWSI5 APBC_REG(0x07c) -#define APBC_MMP2_TWSI6 APBC_REG(0x080) -#define APBC_MMP2_TWSI_INTSTS APBC_REG(0x084) -#define APBC_MMP2_UART4 APBC_REG(0x088) -#define APBC_MMP2_RIPC APBC_REG(0x08c) -#define APBC_MMP2_THSENS1 APBC_REG(0x090) /* Thermal Sensor */ -#define APBC_MMP2_THSENS_INTSTS APBC_REG(0x0a4) - /* Common APB clock register bit definitions */ #define APBC_APBCLK (1 << 0) /* APB Bus Clock Enable */ #define APBC_FNCLK (1 << 1) /* Functional Clock Enable */ diff --git a/arch/arm/mach-mmp/include/mach/regs-apmu.h b/arch/arm/mach-mmp/include/mach/regs-apmu.h index 7af8deb63e83..93c8d0e29bb9 100644 --- a/arch/arm/mach-mmp/include/mach/regs-apmu.h +++ b/arch/arm/mach-mmp/include/mach/regs-apmu.h @@ -13,21 +13,6 @@ #include -/* Clock Reset Control */ -#define APMU_IRE APMU_REG(0x048) -#define APMU_LCD APMU_REG(0x04c) -#define APMU_CCIC APMU_REG(0x050) -#define APMU_SDH0 APMU_REG(0x054) -#define APMU_SDH1 APMU_REG(0x058) -#define APMU_USB APMU_REG(0x05c) -#define APMU_NAND APMU_REG(0x060) -#define APMU_DMA APMU_REG(0x064) -#define APMU_GEU APMU_REG(0x068) -#define APMU_BUS APMU_REG(0x06c) -#define APMU_SDH2 APMU_REG(0x0e8) -#define APMU_SDH3 APMU_REG(0x0ec) -#define APMU_ETH APMU_REG(0x0fc) - #define APMU_FNCLK_EN (1 << 4) #define APMU_AXICLK_EN (1 << 3) #define APMU_FNRST_DIS (1 << 1)